Background: Over the past few years there has been immense evolution in various areas particularly in the areas of digital technologies wherein the pace of change is very high. Industrial areas such as operations and supply chain management together with advanced technologies such as machine learning, big data analytics, artificial intelligence, as well as the Internet of Things, create completely different forms of operational models for various industries. In the area of healthcare too, these emerging computational sophistication is introduced to revolutionise the approaches to prevent, diagnose and treat diverse diseases and illnesses. Objective: The objective of this study is to provide an extensive review of the contemporary approaches utilizing data to cope with significant mental disorders. From over 60 relevant scholarly articles published between 2011 and 2023, it discusses how tools such as predictive modelling, social media analysis, data from smartphones, and chatbots help with issues such as early detection, telemonitoring, provision of psychological support, and individualised prevention. Method: An initial literature review to analyse over 60 research articles, which include empirical studies that were conducted between 2011 and 2023. The research assessed implemented novel digital approaches to mental health interventions including big data analytics for predicting condition status, machine learning for examining social media content, behaviour monitoring through smartphone sensors, and using conversational agents or chatbots. The following is an overview of general conclusions from experimental and descriptive secondary research studies published in professional outlets concerning possible advantages and disadvantages of data science applied to important concerns in mental health. Results: Research reveals that integrating subtle e-health tools in tandem with typical treatment approaches holds the potential to expand mental health services to more or less integrate them into clients’ day-to-day lives, and practically individualize effective treatments accordingly. Technological solutions for instance allow remote risk assessment, symptom monitoring and determination of treatment compliance. New lines of virtualized paradigm solve social challenges that interfere with the conventional provision and consumption of care. However, questions of privacy and the long-term effects as well as clinical adoption are yet to be solved in a analytically distinct manner.

The aim of Predictive Maintenance, within the field of Prognostics and Health Management (PHM), is to identify and anticipate potential issues in the equipment before these become critical. The main challenge to be addressed is to assess the amount of time a piece of equipment will function effectively before it fails, which is known as Remaining Useful Life (RUL). Deep Learning (DL) models, such as Deep Convolutional Neural Networks (DCNN) and Long Short-Term Memory (LSTM) networks, have been widely adopted to address the task, with great success. However, it is well known that this kind of black box models are opaque decision systems, and it may be hard to explain its outputs to stakeholders (experts in the industrial equipment). Due to the large number of parameters that determine the behavior of these complex models, understanding the reasoning behind the predictions is challenging. This work presents a critical and comparative revision on a number of XAI methods applied on time series regression model for PM. The aim is to explore XAI methods within time series regression, which have been less studied than those for time series classification. The model used during the experimentation is a DCNN trained to predict the RUL of an aircraft engine. The methods are reviewed and compared using a set of metrics that quantifies a number of desirable properties that any XAI method should fulfill. The results show that GRAD-CAM is the most robust method, and that the best layer is not the bottom one, as is commonly seen within the context of Image Processing.

The research presented in this review highlights the critical importance of integrating Artificial Intelligence (AI) in aquaculture to enhance efficiency, sustainability, and fish health management. Current aquaculture practices face significant challenges, such as data quality issues, incomplete and noisy data, and the complexity of managing diverse environmental and biological factors affecting fish health. To address these challenges, the review explores advanced AI methodologies, including deep learning, the Internet of Things (IoT), and data fusion techniques, to develop robust predictive and health management (PHM) systems in aquaculture. The study summarizes various AI-based approaches for real-time monitoring, disease detection, and optimized feeding strategies, which improve the overall management of aquaculture operations. These methods involve the use of high-precision sensors, automated image and acoustic data acquisition, and sophisticated data preprocessing and integration techniques. Collectively, these techniques aim to ensure accurate, real-time monitoring and predictive analysis of fish health and environmental conditions. The research findings demonstrate the successful application of AI techniques in achieving significant improvements in fish growth rates, reducing environmental impact, and enhancing operational efficiency. For example, AI-driven PHM systems have shown high detection accuracy and efficient management of feed and water quality parameters, leading to better fish health outcomes and lower mortality rates. In conclusion, the integration of AI in aquaculture presents a transformative approach, offering valuable insights and practical solutions for sustainable and intelligent fish farming. The study underscores the value of AI in enhancing predictive capabilities, optimizing resource use, and ensuring the ecological sustainability of aquaculture practices, thereby contributing to the growing global demand for efficient and sustainable fish production systems.

The abstract of the study on the challenges and opportunities of supply chain digitalization encapsulates the primary findings and their implications from the perspectives of industry leaders. This qualitative research investigated how senior executives across diverse sectors perceive and manage the transition to digital supply chains. Interviews with twenty industry leaders revealed key challenges such as data integration, cybersecurity, organizational resistance, and financial constraints. Data integration issues were particularly pronounced, as participants struggled with unifying disparate data sources from legacy and modern systems, creating barriers to achieving cohesive digital frameworks. Cybersecurity emerged as a critical concern due to the increased vulnerability of digital supply chains to cyber threats, necessitating robust and proactive security measures. Organizational resistance, driven by employee apprehensions about job displacement and technological unfamiliarity, highlighted the need for effective change management practices, including clear communication and training. Financial constraints, especially for small and medium-sized enterprises (SMEs), underscored the difficulty of justifying the substantial investments required for advanced digital technologies. Despite these challenges, the study identified significant opportunities associated with digitalization, including enhanced operational efficiency, improved visibility, predictive analytics, and better customer satisfaction. Digital tools were found to streamline processes, reduce manual intervention, and provide real-time insights into supply chain performance, thus facilitating more informed decision-making and swift responses to disruptions. The accelerated adoption of digital technologies during the COVID-19 pandemic demonstrated their essential role in enhancing supply chain resilience and agility. Additionally, the integration of sustainability goals through digitalization supported resource optimization and waste reduction, aligning with broader corporate social responsibility objectives. The findings suggest that while the path to digital transformation is complex, the benefits of improved efficiency, decision-making, customer satisfaction, and sustainability present compelling incentives for organizations to invest in and embrace digital supply chain solutions.

This qualitative research investigates how supply chain innovations drive marketing differentiation in consumer goods companies. In a competitive global marketplace, firms are increasingly leveraging advanced supply chain management (SCM) practices to enhance operational efficiency and create distinctive market positions. The study explores five key supply chain innovations—digitalization, sustainability practices, predictive analytics, agile supply chain models, and collaborative partnerships—and their impact on marketing differentiation strategies. Data were collected through semi-structured interviews with 20 executives and managers from leading consumer goods companies, analyzing themes related to innovation adoption, challenges, and outcomes. Findings indicate that digital technologies such as IoT, AI, and blockchain are pivotal in improving supply chain visibility, optimizing inventory management, and enabling real-time decision-making, thereby supporting personalized customer experiences and agile responses to market dynamics. Sustainability practices, including sustainable sourcing and green logistics, emerge as critical drivers of brand reputation and consumer trust, aligning with growing consumer preferences for eco-friendly products. Predictive analytics facilitate better demand forecasting and pricing strategies, while agile supply chain models enhance flexibility and responsiveness in delivering products faster to market. Despite benefits, challenges include integrating innovations with legacy systems, managing resistance to change, and addressing data security concerns. Strategies for overcoming these barriers include leadership commitment, cross-functional collaboration, talent development, and strategic partnerships. By embracing these strategies and innovations, consumer goods companies can strengthen their competitive positioning, enhance customer satisfaction, and achieve sustainable growth in a rapidly evolving marketplace.

This qualitative research explores the transformative role of Artificial Intelligence (AI) in Supplier Relationship Management (SRM) within the e-commerce sector. SRM is critical for e-commerce platforms to maintain efficient supply chains, optimize supplier interactions, and ensure competitive advantage in a dynamic marketplace. AI technologies offer advanced capabilities such as predictive analytics, machine learning algorithms, and natural language processing, which revolutionize traditional SRM practices by enhancing decision-making accuracy, mitigating supply chain risks, and fostering personalized supplier relationships. Through semi-structured interviews with 20 e-commerce professionals and industry experts, this study investigates AI's impact on supplier selection, operational efficiencies, and strategic supplier relationships. Findings highlight AI's ability to streamline supplier evaluation processes, improve demand forecasting accuracy, and optimize inventory management strategies. AI also facilitates personalized supplier engagement through sentiment analysis and real-time insights, promoting collaboration and trust. Ethical considerations, including algorithmic bias and data privacy, emerge as significant concerns in AI adoption for SRM. Addressing these challenges is crucial to maintaining stakeholder trust and ensuring responsible AI deployment. Furthermore, technological integration barriers and organizational readiness are identified as critical factors influencing successful AI implementation. Looking forward, the study underscores the potential of AI to drive innovation and competitiveness in e-commerce SRM, emphasizing the importance of ethical AI practices, technological infrastructure investments, and organizational preparedness for sustainable growth.

Background: Early risk stratification tools for COVID-19 patients were indicated but little is known about their ability to effectively detect clinical deterioration among COVID-19 patients. Objectives: To assess the prognostic accuracy of NEWS2 in predicting severe morbidity and mortality in hospitalization for COVID-19 patients. Methods: A prospective cohort study was performed among adult patients with a confirmed diagnosis of COVID-19 who were admitted to the inpatient units at COVID-19 Martyrs Medical Military Complex and Palestinian Red Crescent Society Hospital, located at Nablus, Palestinian Authority. NEWS2 scores were measured at admission, on 6, 12, 24, and 48 hours after their admission to the hospital using Receiver Operating Characteristic Curves (ROC). Results: Overall, 192 adult COVID-19 patients aged 25-94 years (mean=62.1, SD=13.9) were enrolled. Of those, 49.0% were males, 47.4% were vaccinated, and 53.6% were with diabetes. The mean NEWS scores during the patient’s hospital stay were excellent predictors of mechanical ventilation, admission to the ICU, and mortality, as indicated by an AUROC of 0.94 (95% CI: 0.88-1.00, P<0.001), 0.91 (95% CI: 0.87-0.96, P<0.001) and 0.96 (95% CI: 0.92-1.00, P<0.001), respectively. The classification of 192 patients into NEWS score categories indicated that 12.5% were classified as high-risk at admission. Conclusion: The NEWS2 had moderate sensitivity and specificity in predicting the deterioration of patients with COVID-19. Our findings support the utility of NEWS2 monitoring as a sensitive approach for initially assessing COVID-19 patients. It could be helpful to improve predictive performance by supplementing the score parameters with additional measures besides the clinical judgment.

Background/Purpose: Multimorbidity of malaria, anaemia, and malnutrition (MAMM) is a condition in which an individual cohabits with two or more of these health outcomes and is becoming an emergent public health concern in sub-Saharan African countries. The independent associations of a child’s demographic variables and socioeconomic disparities with a child’s health outcomes have been established in literature. However, the effects of the intersection of these factors on MAMM, while accounting for other covariates have not been studied. Therefore, this study aimed to determine how children’s sex, age and socioeconomic status interact to explain the variations in MAMM among children aged 6-59 months in Nigeria. Methods: Data from the 2018 Nigeria Demographic and Health Survey and the 2018 National Human Development Report (NHDR) were used. The study includes weighted samples of 10,184 children aged 6-59 months in Nigeria. A three-level multilevel mixed effect ordinal logistic regression model such that individual characteristics at level 1 are nested in communities at level 2 and nested in states at level 3 was used. Subsequently, predictive probability charts and average adjusted probability tables were used to interpret the intersectional effects. Five models were created in this scenario. Model 1 is the interaction between the child's sex and wealth status; model 2, child's sex and age; model 3 is between child's age and wealth status; model 4 has the three 2-way interactions of child's sex, age, and household wealth status, and model 5 includes model 4 and the 3-way interactions between a child's sex, age, and wealth quintiles. Results: The prevalence of children with ‘none of the three diseases’ outcomes was 17.3% (1767/10,184), while, 34.4% (3499/10,184) had ‘only one of the diseases’, and 48.3% (4,918/10,184) cohabit with ‘two or more’ of MAMM. However, in the multivariate analyses, model 3 was the best fit compared with other models, so, that the two-way interaction effects of a child's age and wealth status are significant predictors in the model. Children aged 36-47 months living in the poorest households have the probability of 0.11, 0.18, and 0.32 of contracting MAMM above the probability of children of the same age and live in the middle, more prosperous and richest households, respectively, while all other covariates are held constant. Thus, the variation in MAMM over a child's age differs depending on the household wealth quintile. In other words, as the children grow older, variations in MAMM become more evident between the rich and the poor household. Conclusion: Therefore, it is recommended that policies that are geared toward economic redistribution will help bridged the disparities observed in multiple diseases among children aged 6-59 months in Nigeria

Lipidomics provides comprehensive study of all lipid components in cells, serum, plasma or tissues of organisms, aiming to the discovery of diagnostic, prognostic and predictive biomarkers of diseases such as malignancies. This systematic review evaluates studies, where lipidomics applies to the diagnosis, prognosis, prediction of ovarian cancer (OC) and the discrimination between malignant and benign ovarian masses. Literature search was conducted in PubMed, Science Direct and SciFinder. Only publications written in English language after 2012 were included. From the reference lists of primary included studies, relevant citations were identified and were also added in our list. All studies included referred to the application of lipidomics in serum/plasma samples of human cases with OC, whereby few of them included also tumor tissue samples. In some of the included studies metabolomic analysis was also involved where other metabolites besides lipids were identified. Qualitative data were assessed and risk of bias was determined using the ROBINS-I tool. In total, 29 studies were included, 15 of which applied non-targeted, 7 targeted lipidomics and 7 were reviews relevant to our aim. Most studies concerned the possible application of lipidomics in OC diagnosis, exhibiting phospholipids and sphingolipids as the most significantly altered during development of the disease. In conclusion, this systematic review highlights the potential contribution of lipids as biomarkers in OC management.

This study investigates the emerging applications of Artificial Intelligence (AI) in strategic management and its impact on organizational decision-making processes. As AI technology rapidly advances, it has become a crucial component in redefining organizational strategies. According to a global survey by the Boston Consulting Group, over 60% of executives believe that AI can significantly improve key performance indicators and enhance opportunities for strategic differentiation and sustainable competitive advantages. Using a descriptive-survey methodology and questionnaire-based data collection, this research examines the influence of AI on strategic decision-making in large organizations. The statistical population comprises senior managers across various industries, with sampling conducted through convenience sampling. Data analysis was performed using SMART-PLS software, revealing significant improvements in strategic decision-making processes through AI implementation. The study demonstrates that AI, by analyzing complex data sets and identifying hidden patterns, assists managers in making more optimal decisions. Furthermore, AI's predictive analytics capabilities contribute to enhanced strategic planning and risk mitigation in decision-making processes. The research findings indicate a statistically significant positive correlation (r = 0.72, p < 0.001) between AI adoption and the quality of strategic decisions. This paper concludes by proposing that organizations should leverage AI as a tool to strengthen their organizational strategies, while emphasizing the importance of ethical considerations and human oversight. The implications of this research extend to both academic and practical domains, offering insights into the integration of AI in strategic management processes and its potential to revolutionize organizational decision-making paradigms.

This qualitative research explores the impact of Artificial Intelligence (AI) on Customer Relationship Management (CRM), providing a comprehensive analysis of how AI technologies are transforming CRM practices. AI integration in CRM has revolutionized customer interactions, enabling enhanced personalization, efficiency, and customer engagement. By leveraging machine learning, natural language processing, and predictive analytics, organizations can create highly tailored customer experiences, automate routine tasks, and anticipate future customer needs with precision. The study identifies the significant benefits of AI, including improved customer insights, faster response times, and proactive engagement strategies. However, it also highlights the challenges associated with AI adoption in CRM, such as data privacy and security concerns, algorithmic bias, high implementation costs, and resistance to change. The findings emphasize the need for robust data protection measures, strategies to mitigate biases, significant investments in technology and training, and effective change management to overcome these challenges. The thematic analysis reveals key areas where AI is making an impact, including customer service, customer segmentation, and personalized marketing strategies. Additionally, the study discusses the organizational implications of AI adoption, such as enhanced decision-making, increased productivity, and the necessity for staff reskilling. Future directions for AI in CRM suggest further advancements in AI algorithms, greater integration with other business systems, enhanced customer experiences, and a focus on ethical AI practices. This research underscores the transformative potential of AI in CRM and provides insights for organizations aiming to leverage AI for improved customer relationship management.

Predictive maintenance technologies have emerged as a transformative force in retail supply chain management, offering the potential to significantly enhance operational efficiency, reduce costs, and improve customer satisfaction. This study explores the implementation and impact of predictive maintenance within the retail sector, focusing on its benefits, challenges, technological tools, and future directions. The findings indicate that predictive maintenance enables a proactive approach to equipment management, leading to substantial reductions in downtime and maintenance costs, extended equipment lifespan, and enhanced sustainability through reduced energy consumption and waste. However, the adoption of these technologies is not without challenges. High initial costs, the need for specialized skills in data analytics and IoT, issues with data quality and reliability, organizational resistance, and cybersecurity concerns present significant barriers to successful implementation. Technological tools such as IoT sensors, data analytics platforms, machine learning algorithms, and digital twins are crucial for the effective functioning of predictive maintenance systems, providing real-time data monitoring and analysis that improve decision-making and maintenance planning. The study also highlights promising future trends, including advancements in AI, machine learning, IoT, and blockchain technologies, which are expected to further enhance predictive maintenance capabilities. To fully realize the potential of predictive maintenance, companies must address the identified challenges, invest in workforce development, and implement robust data security measures. Future research should focus on exploring these advancements, understanding the broader environmental impacts, and conducting cross-industry analyses to identify best practices. Overall, while predictive maintenance offers substantial benefits, its successful integration requires a nuanced approach that balances technological innovation with strategic and operational considerations.

Patients who survived critical COVID-19 frequently reported post-acute sequelae of COVID-19 (PASC) such as psychosomatic and neurocognitive health problems. The goal of this study was to identify clinical risk factors and other predictors for such long-term consequences in severely ill COVID-19 patients. Adult COVID-19 intensive care unit (ICU) survivors from August 2020 to May 2021 were enrolled. A broad range of clinical, laboratory and chest computed tomography (CT) data was collected during ICU stay. The association between ICU predictors and psychosomatic, respiratory and neurocognitive assessments 12 months after ICU discharge was analyzed using univariate regression analysis. In 17 patients (mean age 58.9 ± 11.4 years), laboratory markers (CRP, lymphocytes, hemoglobin), ICU severity (SOFA, SAPS II, need for mechanical ventilation), complications (ARDS), and lung CT data (ground-glass opacity) were promising predictors of depressive and anxiety symptoms, fatigue, and sleep problems. Recovery of psychosomatic health such as fatigue, depression and anxiety correlated with lower levels of inflammation and high hemoglobin levels. ARDS, mechanical ventilation and worse SOFA and SAPS II scores were further risk factors for depressive and anxiety symptoms. Our study identified novel associations such as pulmonary ground-glass opacity being positively associated with depression, anxiety, fatigue, and insomnia levels.

Accurate sentiment prediction on digital platforms while ensuring user anonymity and privacy presents substantial challenges. Predominantly, existing methodologies are centralized, impeding the achievement of both robust analysis with strong privacy protections and model accuracy. This paper investigates federated learning (FL), augmented with a novel Data Obfuscation (DO) technique and Bidirectional Encoder Representations from Transformers (BERT), to develop a new framework addressing this issue. The proposed framework enables continuous supervision of mental states by autonomously learning from aggregated global data on federated servers. The use of the emotion data set for prediction demonstrated a considerable improvement in accuracy (82.74%), precision (83.30%) and recall (82.74%) and F-1 score (82.80%) over baseline results of precision (16.73%), precision (23.29%), recall (16.73%) and F-1 score (18.18%). In addition, two privacy attack scenarios were executed to evaluate system resilience. Membership Inference Attacks, which determine whether a specific data point was part of the training set, and Linkage Attacks, which attempt to associate data samples with a specific client. However, the system preserves its privacy guarantees despite these adversities. The proposed approach skillfully balances privacy and accuracy, establishing a foundation for scalable and secure mental health support systems. This research exemplifies a model for leveraging FL and Data Obfuscation to enhance both the privacy and effectiveness of predictive analytics in critical applications, offering transformative advantages for digital platforms by enabling deep emotional analysis of users while safeguarding their privacy.

BACKGROUND AND AIMS: Cardiovascular disease and colorectal cancer (CRC) are significant health problems and share some risk factors. The aim of our study was to develop and validate a predictive score for advanced colorectal neoplasia (CRN) based on risk factors for cardiovascular disease and CRC. MATERIALS AND METHODS: A cross-sectional study comprising a derivation cohort and an external validation cohort of 1049 and 308 patients respectively. A prediction score for advanced CRN (CRNAS: Colorectal Neoplasia Advanced Score) was developed from a logistic regression model, comprising sex, age, first-degree family history for CRC, systolic and diastolic blood pressure, total cholesterol, HDL-cholesterol, body mass index, diabetes, smoking, and antihypertensive treatment. Other cardiovascular risk scores (Framingham-Wilson, REGICOR, SCORE and FRESCO) were also used to predict the risk of advanced CRN. The discriminatory capacity of each score was evaluated using the area under the curve (AUC). RESULTS: CRN were found in 379 subjects from the derivation cohort (36%) including 228 patients (22%) with an advanced CRN. Male sex, age, diabetes, and smoking were identified as independent risk factors for advanced CRN. The newly created score (CRNAS), showed an AUC of 0.68 (95% CI: 0.64-0.73) for advanced CRN, which was better than cardiovascular risk scores (p

This study focuses on predicting PM2.5 levels at the University of Petroșani by employing advanced machine learning techniques to analyze a dataset that encapsulates a wide array of air pollutants and meteorological factors. Utilizing data from IoT sensors and established environmental monitoring stations, the research leverages Random Forest, Gradient Boosting Machines, and Support Vector Regression models to forecast air quality, emphasizing the complex interplay between various pollutants. The models demonstrate varying degrees of accuracy, with the Random Forest model achieving the highest predictive power, indicated by an R2 score of 0.82764. Our findings highlight the significant impact of specific pollutants such as NO, NO2, and CO on PM2.5 levels, suggesting targeted mitigation strategies could enhance local air quality. Additionally, the study explores the role of temporal dynamics in pollution trends, employing time-series analysis to further refine the predictive accuracy. This research contributes to the field of environmental science by providing a nuanced understanding of air quality fluctuations in a university setting and offering a replicable model for similar environments seeking to reduce airborne pollutants and protect public health.

Introduction: The escalating morbidity, mortality, and healthcare costs associated with invasive candidiasis pose significant challenges in pediatric intensive care units (PICUs). Conventional diagnostic methods fall short in effectiveness, while various risk factors exacerbate the prevalence of these infections. This study introduces a novel model that amalgamates the Candida Score with key predictors to enhance the specificity and applicability of mortality risk assessments for pediatric patients with fungemia. Methods: This retrospective cohort study aimed to develop an integrated model for estimating mortality risk in children with fungemia in PICUs. We constructed and evaluated multiple predictive models using the Candida Score and other relevant clinical and laboratory variables. The discriminative abilities of the models were assessed using the area under the receiver operating characteristic curve (AUC). Results: The study cohort comprised 85 pediatric patients admitted between 2016 and 2020, with a median age of 6 months and a male predominance of 62.4%. The mortality rate was 45.9%. Candida albicans was the most prevalent causative agent, accounting for 37.55% of fungemia cases. Multivariable Logistic regression revealed the duration of mechanical ventilation, and the Candida Score were significant predictors of mortality. Each additional day of ventilation increased mortality odds by 11.5% (OR = 1.115, 95% CI: 1.025-1.212, p = 0.011), while a higher Candida Score more than doubled the odds (OR = 2.205, 95% CI: 1.359-3.578, p = 0.001).The Random Forest predictive model demonstrated superior discriminative performance, with an AUC of 0.838 (95% CI: 0.738-0.917), outperforming Gradient Boosting and Logistic Regression models, which had AUCs of 0.7759 (95% CI: 0.667-0.877) and 0.7085 (95% CI: 0.589-0.813), respectively. Although the internal validation yielded satisfactory results, external validation is warranted. Conclusion: This study presents an innovative approach for accurately assessing the risk of mortality due to fungemia in PICU patients by integrating the Candida Score with critical predictors. The Random Forest model emerged as the most effective predictive tool due to its exceptional discriminative ability.

This study explores the transformative impact of machine learning on predictive analytics within supply chain management. As supply chains become increasingly complex and dynamic, traditional methods of forecasting and management are proving inadequate. Machine learning offers advanced algorithms capable of analyzing vast datasets to uncover patterns and trends that enhance decision-making processes. This research investigates how machine learning improves demand forecasting accuracy, optimizes inventory management, strengthens supplier relationships, and enhances risk management. The study employs a qualitative approach, analyzing data from industry case studies and expert interviews to identify key themes and challenges associated with the adoption of machine learning. Findings reveal that machine learning significantly improves forecasting precision, reduces inventory costs, and enables proactive supplier and risk management. However, challenges such as ensuring data quality, acquiring specialized skills, integrating new technologies with existing systems, and addressing ethical considerations are critical. The study also highlights the potential of emerging technologies like blockchain, IoT, and 5G to further enhance machine learning applications in supply chain management. This research contributes to a deeper understanding of how machine learning can drive innovation and efficiency in supply chains, while also addressing the hurdles that organizations must overcome. The results underscore the need for a balanced approach that incorporates technological advancements and ethical practices to fully leverage the benefits of machine learning.

A Digital Twin (DT) refers to a virtual representation or digital replica of a physical object, system, process, or entity. This concept involves creating a detailed, real-time digital counterpart that mimics the behavior, characteristics, and attributes of its physical counterpart. DTs have the potential to improve efficiency, reduce costs, and enhance decision-making by providing a detailed, real-time understanding of the physical systems they represent. While this technology is finding application in numerous fields, such as energy, healthcare, transportation, it appears to be a key component of the digital transformation of industries. In this paper, we present the research results achieved by IoTwins, a European research project aimed at investigating opportunities and issues of adopting DTs in the fields of industrial manufacturing and facility management. Particularly, we discuss a DT model and a reference architecture for use by the research community to implement a platform for the development and deployment of industrial DTs in the cloud continuum. Guided by the devised architectures’ principles, we implemented an open platform and a development methodology to help companies build DT-based industrial applications and deploy them in the so-called Edge/Cloud continuum. To prove the research value and the usability of the implemented platform, we discuss a simple yet practical development use case.

The rapid progress in renewable energy sources and the increasing complexity of energy distribution networks have highlighted the need for efficient and intelligent energy management systems. This paper presents a comparative analysis of two optimisation algorithms, P and M70, used for the optimal control of the operation of microgrids in islanded mode. The main objective is to minimise production costs while ensuring a reliable energy supply. Algorithm P prioritises the use of photovoltaic (PV) and battery storage and operates the diesel generator at minimum capacity to reduce fuel consumption and maximise the use of renewable energy sources. Algorithm M70, on the other hand, uses a heuristic approach to adaptively manage energy resources in real time. In this study, the performance of both algorithms is evaluated through simulation in different operating scenarios. The results show that both algorithms significantly improve the efficiency of the microgrid, with the M70 algorithm showing better adaptability and cost efficiency in dynamic environments. This research contributes to ongoing efforts to develop robust and scalable energy management systems for future smart grids.

Most of the management in retail and sports facilities about tennis balls is subjective and leads to early disposal, further contributing to environmental waste. This paper discusses a machine learning-based framework to optimize tennis ball usage by providing an accurate forecast of their lifetime, using data-driven insights. We develop and test several predictive models using Random Forest, Support Vector Machines, and Neural Networks based on holistic datasets that include data on bounce dynamics, material composition, usage frequency, and environmental conditions. The framework also allows real-time monitoring and decision-making for the replacement of the tennis balls, in addition to identification of the key factors that influence performance degradation. Our results show that this could significantly extend the life of tennis balls, which again can help reduce the overall waste and support sports industry sustainability efforts. The proposed open-access framework is scaling up a solution for tennis clubs/stores in order to improve operational efficiency with a low environmental impact while contributing to the circular economy at the same time.

Predictive biomarkers for immune checkpoint inhibitors (ICI), such as PD-L1 expression (TPS), remain limited in clinical applications. Improved novel ICI predictive biomarkers are urgently needed. We evaluated a live single-cell functional liquid biopsy cytokine profiling platform to track immunotherapy treatment response and outcomes. Peripheral blood mononuclear cell samples of healthy donors and NSCLC patients undergoing ICI-based therapies were collected longitudinally pre-/post-treatment under IRB-approved protocols. Samples were enriched for CD4+ and CD8+ T-lymphocytes and analyzed on the IsoLight platform. The single T-cells were captured in microchambers on IsoCode chips for cytokines profiling. Functional polyfunctionality data from 55,775 single cells were analyzed using the IsoSpeak software, kappa coefficient, and Kaplan-Meier survival plots. We found a significant difference between responders and non-responders in CD8+ T-cells’ changes in overall polyfunctionality and polyfunctional strength index (ΔPSI). ΔPSI score in CD8+ T-cells performed better than PD-L1 TPS and, when combined with PD-L1 TPS, strongly correlated with early ICI treatment response with a kappa coefficient of 1.0 (p=0.003). High CD4+ T-cells ΔPSI predicted a strong trend of improved PFS (3.9-fold) and OS (3-fold). In conclusion, single peripheral T-cell polyfunctionality dynamics analysis is a promising liquid biopsy profiling platform as NSCLC ICI predictive biomarker regardless of oncogene-addiction status.

Switched model predictive control (S-MPC) and recurrent neural network with long short-term memory (RNN-LSTM) are powerful control methods that have been extensively studied for energy management in microgrids (MGs). These methods are complementary in terms of constraint satisfaction, computational demand, adaptability, and comprehensibility, but typically one method is chosen over the other. The S-MPC method selects optimal models and control strategies dynamically based on the system’s operating mode and performance objectives. On the other hand, integration of auto-regressive (AR) with these powerful control methods improves prediction accuracy and system conditions’ adaptability. This paper compares the two approaches to control and proposes a novel algorithm called Switched Auto-regressive Neural Control (S-ANC) that combines their respective strengths. Using a control formulation equivalent to S-MPC and the same controller model for learning, the results indicate that pure RNN-LSTM cannot provide constraint satisfaction. The novel S-ANC algorithm can satisfy constraints and deliver comparable performance to MPC while enabling continuous learning. Results indicate that S-MPC optimization increases power flows within the MG, resulting in efficient utilization of energy resources. By merging the AR and LSTM, the model’s computational time decreased by nearly 47.2%. Also, this study evaluated our predictive model’s accuracy: (i) R-squared error is 0.951, indicating strong predictive ability, and (ii) mean absolute error (MAE) and mean square error (MSE) values of 0.571 indicate accurate predictions with minimal deviations from actual values.

Background: Studies have tried to identify predictors of functional markers of keratoconus progression, whereas structural outcomes of collagen cross-linking have not been properly investigated. Objective: find and set up a combination of diagnostic modalities and measurements to reliably reflect CXL efficiency. Material and methods: We retrospectively reviewed the medical histories of 107 KC patients (131 eyes) who underwent CXL in a medical center from January 2018 to December 2022. The dataset included preoperative examinations and follow-up results, which provided a total of 796 observations. The cases of other corneal diseases, repeated CXL, pregnancy, and observations without follow-up examinations were excluded. Results: The study findings revealed a significant drop in the central and corneal thickness during 14.01±9.98 months of observations. Linear and polynomial equations suggested different trends in pachymetry change after CXL. The linear model showed corneal thinning, and according to the polynomials, pachymetry findings return to baseline values two years after CXL. Conclusion: The most reliable prognosis of postoperative corneal thickness is achieved with the models trained on keratometry readings and topography indices. BAD indices are also reliable predictors of the corneal thickness after CXL. A combination of the aforementioned structural parameters and their derivatives can reliably predict CXL efficiency.

Abstract: Safety issues related to the electrification of more electric aircraft (MEA) need to be addressed because of the increasing complexity of aircraft electrical power systems and the growing number of safety-critical sub-systems that need to be powered. Managing the energy storage systems and the flexibility in the load-side plays an important role in preserving the system’s safety when facing an energy shortage. This paper presents a system-level centralized operation management strategy based on model predictive control (MPC) for MEA to schedule battery systems and exploit flexibility in the demand-side while satisfying time-varying operational requirements. The proposed online control strategy aims to maintain energy storage (ES) and prolong the battery life cycle, while minimizing load shedding, with fewer switching activities to improve devices lifetime and to avoid unnecessary transients. Using a mixed-integer linear programming (MILP) formulation, different objective functions are proposed to realize the control targets, with soft constraints improving the robustness of the model. Besides, an evaluation framework is proposed to analyze the effects of various objective functions and the prediction horizon on system performance, which provides the designers and users of MEA and other complex systems with new insights into operation management problem formulation.

The construction of different roads, such as freeways, highways, major roads or minor roads must be accompanied by constant monitoring and evaluation of service delivery. Pavements are generally assessed by engineers in terms of the smoothness, surface condition, structural condition and surface safety. Pavement assessment is often conducted using the qualitative indices such as international roughness index (IRI), pavement condition index (PCI), structural condition index (SCI) and skid resistance value (SRV), which are used for smoothness assessment, surface condition assessment, structural condition assessment, and surface safety assessment, respectively. In this paper, Tehran-Qom Freeway in Iran has been selected as the case study and its smoothness and pavement surface conditions are assessed. At 2-km intervals, a 100-meter sample unit is selected in the slow-speed lane (totally, 118 sample units). In these sample units, the PCI is calculated after a visual inspection of the pavement and the recording of distresses. Then, in each sample unit, the average IRI is computed. The purpose of this study is to provide a method for estimating PCI based on IRI. The proposed theory was developed by Random Forest (RF), and Random Forest optimized by Genetic Algorithm (RF-GA) methods and these methods were validated using correlation coefficient (CC), scattered index (SI), and Willmott’s index of agreement (WI) criteria. The proposed method reduces costs, saves time and eliminates the safety risks.

Predictive maintenance (PM) algorithms are widely applied for detecting operational anomalies on industrial processes to trigger maintenance before a possible breakdown; however, much less focus has been devoted to the use of such PM predictions as feedback in automated process control mechanisms. They usually integrate preventive solutions to protect the machines, usually causing downtimes. The premise of this study is to develop a holistic adaptive process scheduling mechanism that incorporates PM analysis as a safety component to optimize the operation mode of an industrial process toward preventing breakdowns while maintaining its availability and operational state, thereby reducing downtimes. As PM is largely a data-driven approach; hence, relies on the setup, we first compare different PM approaches and identify a one-class support vector machine (OCSVM) as the best performing option for the anomaly detection on our setup. Then, we propose a novel pipeline to integrate maintenance predictions into a real-time adaptive process scheduling mechanism. It schedules for the most suitable operation, i.e., optimizing for machine health and process efficiency, according to the abnormal readings. To demonstrate the pipeline on action, we implement our approach on a small-scale conveyor belt system utilizing our Internet of Things (IoT) framework. The results show that our PM-based adaptive process control provides an efficient process with less or no downtime. We also conclude that a PM approach does not provide sufficient efficiency without its integration into an autonomous planning process.

In this paper, we present an approach which examines whether there are persistent abnormal returns around the periods of index rebalancing, using a factor-based framework. By employing this methodology, we observe the yield of normal returns around these events, although the detected abnormal returns may not usually be statistically significant. Therefore, we conclude the study by addressing how one such supposed strategy for rebalance trading is systematic constructive by supervision of some predictive model for the candidates based on all available in the TSX universe for inclusion into the S&P Capped TSX Composite Index in about a month. Trade signals were constructed using a logistic binary classifier based on the same factors used by the index committee to determine the qualifications for inclusion in the index. The problem of a very low probability of out of context security selection for addition to the index is solved at the expense of random over-sampling. In the end, these trade signals were then used to create a hypothetical trading strategy that outperformed the back-test period.

Zinc, an essential trace mineral, plays a crucial role in over 300 enzymes that are vital for major metabolic pathways. Zinc deficiency can cause various symptoms and sometimes lead to serious conditions, especially after surgery. Therefore, recognising the prevalence and predictors of zinc deficiency before surgery is essential for preventing associated symptoms. Although zinc deficiency is linked to several diseases, its association with orthopaedic disorders remains unclear. This retrospective study aimed to explore the prevalence and predictors of zinc deficiency in orthopaedic inpatients prior to surgery. This retrospective case-control study aimed to investigate the prevalence and predictors of zinc deficiency in orthopaedic inpatients. Patients admitted to the Department of Orthopaedic Surgery at Teikyo University Chiba Medical Center between 15 February 2022 and 31 August 2022 were included. The case-control design categorised patients into zinc deficiency (case) and non-deficiency (control) groups based on serum zinc concentrations (< 60 µg/dL). The data retrieved from the centre’s database included demographics, comorbidities, reasons for hospitalisation, fracture details, medication use, and laboratory values. Statistical tests included Fisher’s exact test for categorical variables and a two-sample t-test for continuous vari-ables. To identify factors associated with zinc deficiency, multivariate analysis ( backward stepwise regression model) was performed for items that were significantly different from the univariate analysis. A total of 156 orthopaedic patients were included in this study. Forty-seven patients (30.1%) had a zinc deficiency. The fracture rate was significantly higher in the case group than in the control group (68.1 % vs. 33.9 %; p < 0.001); spinal disease was significantly less common in the case group than in the control group (2.1 % vs. 31.2 %; p < 0.001); and OA was significantly less common in the case group than in the control group (8.5 % vs. 22.9 %; p = 0.04). The case group had signif-icantly higher rates of fragility and hip and pelvic fractures than did the control group. Spinal disease was less common in the case group than in the control group. Laboratory findings revealed significantly lower mean serum zinc (46.2 µg/dL) in the case group than in the control group (76.3 µg/dL), accompanied by lower albumin and haemoglobin concentrations. Hypoalbuminemia and anaemia were more prevalent in the case group than in the control group. Multivariate logistic regression identified age ≥ 60, anaemia, hip fracture, and hypoalbuminaemia as independent predictive factors for zinc deficiency, while spinal disease was associated with decreased risk. This study identified zinc deficiency in 30.1% of orthopaedic inpatients based on serum zinc concen-trations. Furthermore, age ≥ 60, anaemia, hip fracture, and hypoalbuminaemia were determined as independent predictive factors for zinc deficiency.

Aims: To date, precision medicine plays a pivotal role in the clinical administration of solid tumor patients. In this scenario, a rapidly increasing number of predictive biomarkers have been approved in diagnostic practice or are currently investigated in clinical trials. A pitfall in the molecular tests is the diagnostic routine sample available to analyze predictive biomarkers; scant tissue sample often represents the only diagnostical source of nucleic acids to assess molecular analysis. At the sight of these critical issues, Next Generation Sequencing (NGS) platforms emerged as referral testing strategy for molecular analysis of predictive biomarkers in routine practice but high-skilled personnel, extensive working-time drastically impact on the widespread diffusion of this technology in diagnostic setting. Here, we technically validate a fully integrated NGS platform on diagnostic routine tissue samples previously tested with NGS based diagnostic workflow by a referral institution. Methods: A retrospective series of n=64 samples (n=32 DNA, n=32 RNA samples), previously tested using a customized NGS assay (SiRe™ and SiRe fusion) were retrieved from internal archive of University of Naples Federico II. Each sample was tested by adopting Oncomine Precision Assay (OPA), able to detect 2769 molecular actionable alterations [hot spot mutations, copy number variations (CNV) and gene fusions on fully integrated NGS platform (Genexus, Thermofisher Scientifics. (26,27) Concordance rate between these technical approaches was carried out. Results: Genexus system successfully carried out molecular analysis in all instances. A concordance rate of 96.9% (31 out of 32) was observed between OPA and SiRe™ panel both for DNA and RNA based analysis. A negative predictive value of 100% and a positive predictive value of 96.9% (62 out of 64) was assessed. Conclusions: Fully automatized Genexus system combined with OPA (Thermofisher Scientifics) may be considered a technically valuable, saving time sequencing platform to test predictive biomarkers in diagnostic routine practice.

Artificial intelligence (AI) is transforming many healthcare fields including pediatric urology. This in-depth review explores recent advances in AI tools for pediatric urology, emphasizing how state-of-the-art technologies can be used to enhance patient treatment. An initial overview of pediatric urology is given to provide context for this interdisciplinary field and the wide spectrum of problems this entails, before discussing potential uses of AI to improve diagnostic accuracy, treatment planning, and surgical results. AI-powered predictive models are already changing pediatric clinical practice by guiding interpretation of medical images and supporting decision making. In addition to outlining the aims, methods, and conclusions of previous studies on AI applications in pediatric urology, this review also highlights knowledge gaps and priority areas for future study. Particular focus is given to specialized surgeries such pyeloplasty, where AI-guided treatment may help overcome specific technical challenges of this complex procedure. Also highlighted are practical, ethical, and legal aspects of integrating AI into pediatric urology, which will be crucial for responsible innovation in patient-centered treatment. Overall, this article aims to enlighten and inspire clinicians, researchers, and other healthcare stakeholders by offering insight into the future of AI in pediatric urology.

An Oscillating Water Column device, specifically a Savonius turbine, underwent comprehensive testing within an air duct to evaluate its performance under varying rotational speeds, flow directions, and the presence of power augmenters positioned both in front of and behind the device. The experimental setup involved the utilization of load cells and pressure transducers, with their data utilized to calculate pressure differentials across the turbine and torque. Subsequently, a predictive model based on decision trees was developed using Machine Learning. This model was then used to analyze the influence of various features on predicting the pressure difference, considered as the output. The results of the validation (10-fold cross-validation) and test phases were thoroughly investigated. Moreover, obtaining a predictive model allows for the exploration of different scenarios without relying solely on physical experimentation, thereby broadening the scope for further testing.

Over the last 20 years, begomoviruses have emerged as devastating pathogens, limiting the production of different crops worldwide. Weather conditions increase vector populations, with negative effects on crop production. In this work we evaluated the relationship between the in-cidence of begomovirus and climatic conditions before and during the crop cycle. Soybean and bean fields from the northwest (NW) of Argentina were monitored for 14 years and classified as moderate (≤50%) and severe (> 50%) according to the relative incidence. Two hundred bio-meteorological variables were constructed, summarizing meteorological data in 10-day peri-ods from June to March of each crop year. The studied variables included temperature, precipi-tation, relative humidity, wind (speed and direction), pressure, cloudiness and visibility. For bean, high maximum winter temperatures, low spring humidity and precipitation 10 days before planting correlated with severe incidence. In soybeans, high late winter and pre-planting tem-peratures, and low spring precipitations were found to be good predictors of high incidence of begomovirus presence. The results suggest that temperature and pre-sowing precipitations can be used to predict incidence status [predictive accuracy: 82% (bean) and 75% (soybean)]. Thus, these variables can be incorporated in early warning systems for crop management deci-sion-making to reduce the virus impact on bean and soybean crops.

The integration of Artificial Intelligence (AI) and the Internet of Things (IoT) in healthcare is transforming chronic disease management and pandemic response, particularly for vulnerable populations such as the elderly and those with multiple chronic conditions. This review systematically examines the current applications of AI and IoT technologies in managing chronic diseases like diabetes, cardiovascular disease, and chronic obstructive pulmonary disease (COPD), alongside their role in enhancing healthcare response during the COVID-19 pandemic. Key findings demonstrate significant improvements in patient outcomes, including enhanced glycemic control in diabetes management, early detection of cardiovascular anomalies, and a reduction in hospital admissions for chronic disease patients through AI-enabled remote monitoring. Despite these advancements, challenges remain, including data security, algorithmic bias, and the high cost of implementing AI and IoT systems. This review explores future directions for overcoming these obstacles, emphasizing the potential of multi-dimensional data integration, real-time predictive analytics, and personalized AI models to further revolutionize healthcare. Additionally, the accompanying Graphic Abstract visually illustrates how AI-driven insights, generated from IoT-enabled devices, are transforming healthcare delivery by facilitating real-time monitoring, personalized interventions, and proactive patient care. The article concludes with recommendations for addressing the technological, ethical, and regulatory challenges that must be overcome to fully realize the potential of AI and IoT in healthcare.

Based on an in-depth analysis of the factors influencing the compressive strength of ultra-high performance concrete (UHPC), this study examined the impact of both single factors and combined factors on UHPC performance using experimental data. The correlation analysis indicates that cement content, water content, steel fiber, and fly ash significantly affect the strength of UHPC, whereas silica fume, superplasticizers, and slag powder have a relatively smaller influence. This analysis provides a scientific basis for model development. Furthermore, the support vector regression (SVR) model was optimized using the arithmetic optimization algorithm (AOA). The superior performance and computational efficiency of the AOA-SVR model in predicting UHPC compressive strength were validated. Compared to SVR, support vector machine（SVM）, and other single models, the AOA-SVR model achieves the highest R2 value and the lowest error rates. The results demonstrate that the optimized AOA-SVR model possesses excellent generalization ability and can more accurately predict the compressive strength of UHPC.

Major depressive disorder (MDD) is a highly prevalent, debilitating disorder with a high rate of treatment resistance. One strategy to improve treatment outcomes is to identify patient-specific, pre-intervention factors that can predict treatment success. Neurophysiological measures such as electroencephalography (EEG), which measures the brain’s electrical activity from sensors on the scalp, offer one promising approach for predicting treatment response for psychiatric illnesses, including MDD. In this study, a secondary data analysis was conducted on the publicly available Two Decades-Brainclinics Research Archive for Insights in Neurophysiology (TDBRAIN) database. Specifically, hierarchical regression modeling was used to predict treatment response from baseline demographics, symptom severity, and resting-state EEG features in 119 MDD patients receiving repetitive transcranial magnetic stimulation (rTMS). Across models, both age and baseline symptom severity, assessed by the Beck’s Depression Inventory, were significant predictors of rTMS treatment response, with older individuals and more severe depression scores associated with decreased odds of a positive treatment response. EEG measures contributed predictive power to these models; however, these improvements in outcome predictability only trended towards statistical significance (p~0.07 in multiple models). These findings provide confirmation of previous demographic and clinical predictors, while pointing to EEG metrics that may provide predictive information in future studies.

Precision medicine approaches often relies on complex and integrative analysis of multiple biomarkers from “omics” data to generate insights that can help either diagnostics, prognostics or therapeutical decisions. Such insights are often made using Machine learning (ML) models that make sample classification for a particular phenotype (yes/no). Building such models is a challenge and time-consuming, requiring advanced coding skills and mathematical modelling expertise. Artificial intelligence (AI) is a methodological solution that has the potential to facilitate, optimize and scale model development. In this work, we developed an AI-based, user-friendly and code-free platform (https://digitalphenomics.com) that fully automates the development of predictive models from quantitative “omics” data. Here, we show the application of this tool with the development of cancer survival prognostics models using real-life data from breast, lung and renal cancer transcriptomes. We report and compare their sensitivity, specificity, accuracy and Receiver Operating Characteristic (ROC) curve Area Under the Curve (AUC). Further, we report the associated sets of genes (biomarkers) and their expression pattern that are predictive of cancer survival. Moreover, we made our models available as online tools to generate prognostic predictions based on the gene expression of the biomarkers. In conclusion, we demonstrated that our tool is a robust user-friendly solution to develop bespoke predictive tools from “omics” data which facilitate precision medicine introduction to the point-of-care.

With the disruption of digital technologies, customers have emerged as co-producers in order to reduce costs and enhance productivity. Customer-driven business logic recognizes customer capabilities and sustainable innovation as key factors in the performance of customized manufacturing enterprises. The potential relationship between customers and producers has become a new area of inquiry. Existing research rarely delves into the impact of customer predictive ability on the process of customized production activities, particularly in relation to sustainable innovation, which remains inadequately characterized. Ships serve as a typical representation of customized enterprises. This study explores the underlying drivers of sustainable innovation through customer demand orientation by examining 20-year historical patterns in the global shipping and shipbuilding markets, considering the environmental dependency and temporal correlation characteristics of the shipbuilding market (producers) and the shipping market (consumers). By employing time series and panel data in a machine learning algorithm, specifically the random forest model, the study reveals a strong and statistically significant correlation between new ship deliveries and the Baltic Dry Index (BDI), with larger value ships having a more pronounced impact on the consumer market. The correlation analysis confirms that these two variables, in combination, can comprehensively reflect customer predictive ability and serve as crucial decision criteria for customer investment in new ship production. Furthermore, based on principal component analysis of customer predictive ability and ship innovation levels, as well as Granger causality tests, the study demonstrates that customer predictive ability is a Granger cause of sustainable innovation in customized production. Customer predictive ability influences sustainable innovation in customized enterprises to varying degrees. This research provides valuable insights for shipbuilding companies in terms of engaging in sustainable innovation in international markets and understanding the value of international market customers.

The purpose of this paper is to develop a theoretical predictive model for LNG shipping routes selection process. Strategic decisions about shipping costs could be improved if a deeper knowledge about products economic value is provided. Developments made on the extraction and industrial processes related to this fossil fuel are driving the natural gas sector towards a unique globalised market. Moreover, data analytics applications as well as machine learning are topics presented as perfect catalysers for achieving an unprecedented natural gas globalised market. Additionally, this paper aims at showing the state of the art of new techniques used in transportation engineering that might have synergies with other industries (eg. commodities cost reduction, energy supply…). Finally, this paper aims to provide foundation for further research and development using more sophisticated data and algorithms that will help to close the gap between theoretical and practical scope of this techniques.

Using data-driven models to solve predictive maintenance problems has been prevalent for original equipment manufacturers (OEMs). However, such models fail to solve two tasks that OEMs are interested in: (1) Making the well-built failure prediction models working on existing scenarios (vehicles, working conditions) adaptive to target scenarios. (2) Finding out the failure causes, furthermore, determining whether a model generates failure predictions based on reasonable causes. This paper investigates a comprehensive architecture towards making the predictive maintenance system adaptive and interpretable by proposing (1) an ensemble model dealing with time-series data consisting of a long short-term memory (LSTM) neural network and Gaussian threshold to achieve failure prediction one week in advance and (2) an online transfer learning algorithm and a meta learning algorithm, which render existing models adaptive to new vehicles with limited data volumes. (3) Furthermore, the Local Interpretable Model-agnostic Explanations (LIME) interpretation tool and super-feature methods are applied to interpret individual and general failure causes. Vehicle data from Isuzu Motors, Ltd., are adopted to validate our method, which include time-series data and histogram data. The proposed ensemble model yields predictions with 100% accuracy for our test data on engine stalling problem and is more rapidly adaptive to new vehicles with smaller error following application of either online transfer learning or the meta learning method. The interpretation methods help elucidate the global and individual failure causes, confirming the model credibility.

A series of experiments were conducted to measure and quantify the yield, dry matter content, sugars content and nitrates content of grass intended for ensilement. These experiments took place in the East Midlands of Ireland during the Spring, Summer and Autumn of 2019. A bespoke sensor rig was constructed; included in this rig was a hyperspectral radiometer that measured a broad spectrum of reflected natural light from a circular spot approximately 1.2 metres in area. Grass inside a 50cm square quadrat was manually collected from the centre of the circular spot for ground truth estimation of the grass qualities. Up to 25 spots were recorded and sampled each day. The radiometer readings for each spot were automatically recorded onto a laptop that controlled the sensor rig, and ground truth measurements were made either on site or within 24 hours in a wet chemistry laboratory. The collected data was used to build Partial Least Squares Regression (PLSR) predictive models of grass qualities from the hyperspectral dataset and it was found that substantial relationships exist between the spectral reflectance from the grass and yield (r2 = 0.62), dry matter % (r2 = 0.54), sugar content (r2 = 0.54) and nitrates (r2 = 0.50). This shows that hyperspectral reflectance data contains substantial information about key grass qualities and can form part of a broader holistic data driven approach to provide accurate and rapid predictions to farmers, agronomists and agricultural contractors.

U.S. Navy Surface Ship depot-level maintenance periods of performance were studied to develop a method for predicting maintenance durations. The need for the method has been highlighted by Navy leadership in recent media posts describing unacceptable maintenance delays and this research provides practitioners and decisionmakers with a reliable estimating tool. This study helps by putting forth a method that defines the rate of work accomplishment based on relevant variables. Using ordinary least squares models, this research revealed that the size of the contract obligation and the amount of shipyard work occurring simultaneously in the market are key variables in determining depot maintenance durations. With the knowledge found here, the next logical step is an optimization model for each U.S. Navy surface ship homeport.

Pancreatic ductal adenocarcinoma (PDAC) is expected to be the second cause of cancer death by 2022. For nearly 80% of patients, diagnosis occurs at an advanced, non-surgical stage, making such patients incurable. Gemcitabine is still an important component in PDAC treatment and is most often used as a backbone to test new targeted therapies and there is, to date, no routine biomarker to predict its efficacy. Samples from a phase III randomized trial were used to develop trough a large approach based on blood-based liquid biopsy, transcriptome profiling, and machine learning, a 9 gene predictive signature for gemcitabine sensitivity. Patients with a positive test (41.6%) had a significantly longer progression free survival (PFS) (3.8 months vs. 1.9 months p=0.03) and a longer overall survival (OS) (14.5 months vs. 5.1 p<0.0001). In multivariate analyses, this signature was independently associated with PFS (HR=0.5 (0.28-0.9) p=0.025) and OS (HR=0.39 (0.21-0.7) p=0.002).

Machine learning (ML) has emerged as a critical tool for making sense of the growing amount of genetic and genomic data available because of its ability to find complex patterns in high dimensional and heterogeneous data. While the complexity of ML models is what makes them powerful, it also makes them difficult to interpret. Fortunately, recent efforts to develop approaches that make the inner workings of ML models understandable to humans have improved our ability to make novel biological insights using ML. Here we discuss the importance of interpretable ML, different strategies for interpreting ML models, and examples of how these strategies have been applied. Finally, we identify challenges and promising future directions for interpretable ML in genetics and genomics.

The goal of this contribution is an application of the Linear General Model Predictive Control (LGMPC). In this paper, stability of the LGMPC is proven by means of a demonstration of a Theorem stating a sufficient and constructive condition. This condition can be applied for calculating the weight matrices of the cost function in the optimisation problem in LGMPC. Lower bounds conditions are found for one of these matrices and then a system with saturation is taken into consideration. The conditions could be interpreted and discussions through physical aspects. The obtained results were tested by means of computer simulations and an example with a recover water process is considered.

GNSS receivers are nowadays commonly used in monitoring applications, e.g., in estimating crustal and infrastructure deformations. This is basically due to the recent improvements in GNSS instruments and methodologies that allow high precision positioning, 24 h availability and semiautomatic data processing. In this paper, GNSS estimated deformations on a dam structure have been analyzed and compared with pendulum data. This study has been carried out for the Eleonora D’Arborea (Cantoniera) dam, which is in the Sardinia Island. Time series of pendulum and GNSS over a time span of 2.5 years have been aligned so to be comparable. Analytical models fitting these time series have been estimated and compared. Those models were able to properly fit pendulum data and GNSS data, with standard deviation of residuals smaller than one millimeter. This encouraging results led to the conclusion that GNSS technique can be profitably applied to dam monitoring allowing a denser description, both in space and time, of the dam displacements than the one based on pendulum observations.

This article provides a detailed analysis of non-invasive techniques for prediction and diagnosis of faults in internal combustion engines, focusing on the application of the Proknow-C and Methodi Ordinatio systematic review methods. Initially, the relevance of these techniques in promoting energy sustainability and mitigating greenhouse gas emissions is discussed, aligning with the Sustainable Development Goals (SDGs) of Agenda 2030 and the Paris Agreement. The systematic review conducted in the subsequent sections offers a comprehensive mapping of the state-of-the-art, highlighting the effectiveness of combining these methods in categorizing and systematizing relevant scientific literature. The results reveal significant advancements in the use of artificial intelligence (AI) and digital signal processors (DSP) to enhance fault diagnosis, as well as underscore the crucial role of non-invasive techniques in minimizing interference in monitored systems. Finally, concluding remarks point towards future research directions, emphasizing the need to develop digital twins for internal combustion engines and identify gaps for further improvements in fault diagnosis and prediction techniques.

In this report, we present a study demonstrating how machine learning methods can reveal the interaction of different risk factors of post-transplant leukemic relapse and obtain robust predictions even with a modest clinical dataset. Using a cohort of 63 pediatric patients with acute lymphocytic leukemia (ALL) and 46 patients with acute myeloid leukemia (AML) who underwent stem cell transplant at a single institution, we built predictive models of leukemic relapse with both pretransplant and posttransplant patient variables (specifically lineage-specific chimerism) using the random forest classifier. The random forest classifier revealed different important predictive factors between ALL and AML in our relapse models consistent with previous knowledge. Furthermore, it also distinguished donor CD34 chimerism as most impactful in relapse prediction compare to donor chimerism of other cellular lineages in our dataset for ALL but CD3 for AML. Our models greatly improved sensitivity and specificity at predicting relapses in cross validation compared to a reference model based on our own institutional incidence of relapse and inferential statistical principles. Local Interpretable Model-Agnostic Explanations, an interpretable machine learning tool, confirmed our Random Forest Classification result and provided an intuitive explanation of how our machine learning models made the relapse prediction for each individual patient.

Heart failure is a leading cause of death among people worldwide. The cost of treatment can be prohibitive, and early prediction of heart failure would reduce treatment costs to patients and hospitals. Improved prediction of readmission would also be of great help hospital, allowing them to better manage their treatment programs and budgets. This systematic review aims to summarize recent studies of predictive analytics models that have been constructed to predict heart failure and readmission. Some of these models use a statistical approach and others a machine learning approach. Electronic patient health records, including demography, physical and clinical values, and laboratory findings are used to design and build predictive models. Predictive analytics with good performance have become essential for clinicians and specialists. Choosing a suitable machine learning algorithm and data preprocessing technique will improve predictive model performance, including data imputation and class imbalance.

Climate change is affecting the planet, compromising survival and altering forest ecosystems. Investigating climatic variations in all regions is important. The aim of this research was to assess such variations in the W and Pendjari Biosphere Reserves in Benin from 1985 to 2015 and predict climate up to 2045. Drought frequency was assessed by using the Standardized Precipitation and Evapotranspiration Index (SPEI) and correlation was performed between climatic variables. Then a predictive analysis was computed. From 1985 to 2015, there was change in the climate with few severe dry and wet years while no extreme climatic condition was noticed. Most of the years showed nearly normal climatic conditions. The predicted climate indicates an absence of extreme conditions up to 2045 but an increase in the annual humidity is expected. A low decrease in annual mean temperature with high confidence is expected. Decision-makers can better organize adaptation programs and sensitize people in the reserves on their role in environmental conservation and mitigation of climate change using these outputs.

All kinds of vessels consist of dozens of complex machineries with rotating parts and electric motors that operate continuously in a harsh environment with excess temperature and humidity, vibration, fatigue and load. A breakdown or malfunction in one of these machineries can significantly impact the vessel’s operation and safety and consequently, the safety of the crew and the environment. To maintain operational efficiency and seaworthiness, the shipping industry invests substantial resources in preventive maintenance and repairs. This research presents the economic and technical benefits of predictive maintenance over to traditional preventive maintenance, and repair by replacement approaches in the maritime domain. By leveraging modern technology and Artificial Intelligence, we can analyze real-time operating conditions of machinery, enabling early detection of potential damages and allowing for effective planning of future maintenance and repair activities. In this paper, we propose and develop a Convolutional Neural Network that is fed with raw vibration measurements acquired in a laboratory environment from the ball bearings of a motor. Then, we investigate whether the proposed network can accurately detect the functional state of ball bearings and categorize any possible failures present, contributing to improved maintenance practices in the shipping industry.

Cybersecurity plays a relevant role in the new digital age in aerospace industry. Predictive algorithms are necessary to interconnect complex systems within the cyberspace. In this context, where security protocols do not apply, challenges to maintain data privacy and security arise for the organizations. Thus, the need of cybersecurity is required. The four main categories to classify threats are interruption, fabrication, modification and interception. They all share a common thing, soften the three pillars which cybersecurity needs to guarantee. These pillars are confidentiality, availability and integrity of data (CIA). Data injection can contribute to this event by creation of false indicators which can lead to errors creation during the manufacturing engineering process. In this paper, the impact of data injection on existing dataset used on manufacturing process is shown. The design model synchronizes the following mechanisms developed within machine learning techniques which are, the risk matrix indicator to assess the probability of producing an error, the dendrogram to clusters the dataset in groups with similarities, the logistic regression to predict the potential outcomes and the confusion matrix to analyze the performance of the algorithm. The results presented in this study, which was carried out using a real dataset related to the electrical harnesses installed in a C295 military aircraft, estimate that injection of false data indicators increase the probability of errors creation in 24.22 % on the predicted outcomes required for the generation of the manufacturing process. Overall, implementing cybersecurity measures and advanced methodologies to detect and prevent cyberattacks are necessary.

The present study aimed to develop a mathematical model to estimate the performance of an indoor rowing event of 6000m through an 500 m all out test in junior athletes. We selected141 subjects from the Brazilian rowing confederation database (15.9 ± 1.0 years), subsequently randomised the sample to the development (~70%) and cross-validation (~30%) groups of the mathematical model. Performance data for 500m and 6000m were collected (there was a 48h washout between one test and anoth-er).Subsequently, the mathematical model: Time(min) 6000m = { [( Time(s) 500-m * 6) * 2] / 60} + 1.3, was developed by arithmetic modeling using machine learning and Regression analysis, being tested by intraclass correlation coefficient (ICC), Concordance correlation coefficient (CCC), Validity (Cb ), preci-sion (ρ) and bland-Altman plotting. The prediction of the result of 6000m through the mathematical model utilizando apenas o desempenho de 500m “all-out” test showed a significant reliability in de-velopment group (r2 = 0.730, ICC = 0.753; CCC = 0.895, Cb = 0.879, ρ: 0.957, pure error: 0.2 secounds (1.0% estimative error)); and in cross-validation group (r2 = 0.710, ICC = 0.747; CCC = 0.888, Cb = 0.875, ρ: 0.903, pure error: 0.3 secounds (1.4% estimative error)). When comparing the estimated re-sults of the 6000m performance by the mathematical model with the real performance of 6000m per-formed in indoor rowing, no statistical differences were observed. In addition, the mathematical model did not present a significant proportion bias in relation to the 6000 m performance in both groups. The mathematical model for predicting 6000m performance through a 500m fast test was significant for national level junior rowing athletes.

The territory of Serbia is vulnerable to various types of natural and man-made disasters. The risk is not equal across the entire territory, depending on the type of hazard and the expected potential for damage. So far, the level of community disaster resilience has not been determined in Serbia. There are no scientific preconditions for its improvement to reduce the future material and intangible consequences of disasters. Regarding that, the project’s main objective is to develop and validate a predictive model of community disaster resilience based on social identity influences through an investigation impact of social identity indicators on the level of community disaster resilience in Serbia. The project is based on the upcoming research on whether the level of community disaster resilience can be predicted based on social identity indicators, how social identity indicators affect different dimensions of community disaster resilience, and how disasters shape social identity. The project is based on multimethod research in which quantitative (face-to-face interviews in 40 of the 191 municipalities), and qualitative (semi-structured interviews) research methodology will be applied. A developed predictive model with an index of community disaster resilience in Serbia will empower the creation of preconditions for designing public policies, strategies and procedures for improving resilience and reducing the consequences of disasters on people and their property and enhancing citizens’ security. The project will encourage the prediction of community disaster resilience based on social identity indicators, improving disaster foresight and preparing to limit disaster losses. Based on the development of analytical frameworks for understanding community disaster resilience and social identity in disasters, essential preconditions for designing innovative information systems will be created to enable local communities to increase their level of resilience.

Fuel consumption, subsequent emissions and safe operation of class 8 vehicles are of prime importance in recent days. It is imperative that the vehicle operates in its true optimal operating region given a variety of constraints such as road grade, load, gear shifts, Battery State of charge (for hybrid vehicles), etc. In this paper a research study is conducted to evaluate the fuel economy and subsequent emission benefits when applying predictive control to a mild hybrid line haul truck. The problem is solved using a combination of dynamic programming with back tracking and model predictive control. The specific fuel saving features that are studied in this work are dynamic cruise control, gear shifts, vehicle coasting and torque management. These features are evaluated predictively as compared to a reactive behavior. The predictive behavior of these features are a function of road grade. The result and analysis shows significant improvement in fuel savings along with NOx benefits. Out of the control features dynamic cruise (predictive) control and dynamic coasting showed the most benefits while predictive gear shifts and torque management (by power splitting between battery and engine) for this architecture did not show fuel benefits but provided other benefits in terms of powertrain efficiency.

One of the most dangerous diseases that threaten people is Cancer. Cancer if diagnosed in earlier stages can be eradicated with its life threatening consequences. In addition, accuracy in prediction plays a major role. Hence, developing a reliable model that contributes much towards the medical community in early diagnosis of Biopsy images with perfect accuracy come to the scenario. The article aims towards development of better predictive models using multi-variate data and high-resolution diagnostic tools in clinical cancer research. This paper proposes the social spider optimization (SSO) algorithm tuned neural network to classify microscopic biopsy images of cancer. The significance of the proposed model relies on the effective tuning of the weights of the NN classifier by the SSO algorithm. The performance of the proposed strategy is analysed with the performance metrics, such as accuracy, sensitivity, specificity, and MCC measures, and are attained to be 95.9181%, 94.2515%, 97.125%, and 97.68% respectively, which shows the effectiveness of the proposed method in effective cancer disease diagnosis.

Significant challenges exist globally regarding literacy teaching and learning, particularly in poor socio-economic settings in countries of the Global South. In this paper we argue that to address these challenges, major features of how the brain works that are currently ignored in the educational literature should be taken into account. First, perception is an active process based in detection of errors in hierarchical predictions of sensory data and action outcomes. Reading is a particular case. Second, emotions play a key role in underlying cognitive functioning. Innate affective systems underlie and shape all brain functioning, including oral and written forms of language and sign. Third, there is not the fundamental difference between listening/speaking and reading/writing often alleged on the basis of evolutionary arguments. Both are socio-cultural practices driven and learnt by the communication imperative of the social brain. Fourth, like listening, reading is not a linear, bottom-up process. Both are non-linear contextually shaped psycho-social processes of understanding, shaped by current knowledge and cultural contexts and practices. Reductionist neuroscience studies which focus on decontextualized parts of reading cannot access all the relevant processes. An integrated view of brain function reflecting this non-linear nature implies that an ongoing focus on personal meaning and understanding provides positive conditions for all aspects of literacy learning. Assessment of literacy teaching at all its stages should include indicators that take into account these foundational features relating reading and writing to neuroscience.

Globally, there is massive uptake and explosion of data and challenge is to address issues like scale, pace, velocity, variety, volume and complexity of this big data. Considering the recent epidemic in China, modeling of COVID-19 epidemic for cumulative number of infected cases using data available in early phase was big challenge. Being COVID-19 pandemic during very short time span, it is very important to analyze the trend of these spread and infected cases. This chapter presents medical perspective of COVID-19 towards epidemiological triad and the study of state-of-the-art. The main aim this chapter is to present different predictive analytics techniques available for trend analysis, different models and algorithms and their comparison. Finally, this chapter concludes with the prediction of COVID-19 using Prophet algorithm indicating more faster spread in short term. These predictions will be useful to government and healthcare communities to initiate appropriate measures to control this outbreak in time.

Background: Malignant pleural mesothelioma (MPM) is an atypical, belligerent tumor that matures into cancer in the pleura, a stratum of tissue bordering the lungs. Pleural mesothelioma is a common type of mesothelioma that accounts for about 75 percent of all mesothelioma diagnosed yearly in the United States. Diagnosis of mesothelioma takes several months and is expensive. Given the difficulty of diagnosing MPM, early identification is crucial for patient survival. Our study implements artificial intelligence and recommends the best fit model for early diagnosis and prognosis of MPM. Method: We retrospectively retrieved patient’s medical reports generated by Dicle University, Turkey and implemented multi-layered perceptron (MLP), voted perceptron (VP), Clojure classifier (CC), kernel logistic regression (KLR), stochastic gradient decent SGD), adaptive boosting (AdaBoost), Hoeffding tree (VFDT), and primal estimated sub-gradient solver for support vector machine (s-Pegasos). We evaluated the models, compared and tested using paired T-test (corrected) at 0.05 significance based on their respective classification accuracy, f-measure, precision, recall, root mean squared error, receivers characteristic curve (ROC), and precision-recall curve (PRC). Results: In phase-1 SGD, AdaBoost.M1, KLR, MLP, VFDT generates optimal results with the highest possible performance measures. In phase-2, AdaBoost with a classification accuracy of 71.29% outperformed all other algorithms. C-reactive protein, platelet count, duration of symptoms, gender, and pleural protein were found to be the most relevant predictors that can prognosticate mesothelioma. Conclusion: This study confirms that data obtained from biopsy and imagining tests are strong predictors of mesothelioma but are associated with high cost, however, can identify mesothelioma with optimal accuracy. Predictive analytics without using biopsy results can diagnose mesothelioma with acceptable accuracy. Implementation of phase-2 followed by phase-1 can address diagnosis expenses and maximize disease prognosis. Additionally, results indicate improved MPM diagnosis using AI methods dependent upon the specific application.

Imatinib 400 mg is the standard of care for medical treatment of advanced GISTs. In the majority of cases, however, GISTs eventually develop resistance to imatinib. The optimal second line treatment has not been established yet and imatinib dose escalation (800 mg) or sunitinib represent two feasible options. The objective of this retrospective, multi-institutional, study is to analyze the validity of several parameters as possible predictive factors of response to sunitinib after imatinib failure. We reviewed 128 metastatic GISTs treated with sunitinib between January 2007 to June 2017. Primary tumour site, metastatic site, c-KIT/PDGFR-α mutational status, PET-FDG status and type of disease progression to sunitinib were assessed as possible predictive factors of response. This study identifies the gastric site of primary tumor as a predictive factor to sunitinib efficacy in second line setting. The mutational status (GIST WT), the site of metastasis (peritoneum) and the FDG-PET status (negative), although not statistically significant, seem to be elements of increased activity for sunitinib treatment. These results provide the rationale to drive physician for sunitinib choice in second line setting for metastatic GISTs, to improve patients selection and to maximize the benefit from the treatment, on the basis of possible predictive factors of response.

The paper presents a case study and a model for condition monitoring of Diesel engines’ oil of urban buses, through the accompaniment of the evolution of its degradation, with the objective to implement a predictive maintenance policy. Along time, because the usage, there is some decay in the lubricant properties. However, in normal functioning conditions, the lubricants properties, at the time the manufacturers recommend its changing, regardless of they are within the safety limits. Then, based on the accompaniment of the lubricants’ oil condition, the intervals of oil replacement can be enlarged what implies the availability increasing and the corresponding production increasing of the equipment. The model presented in this paper shows its potential to be spread to other types of equipment and organisations that want can implement similar maintenance policies, to achieve the best availability based on the real equipment health conditioning conditions

Microgrid (MG) control is essential for efficient, reliable, and sustainable energy management in distributed energy systems. Genetic Algorithm-based energy management systems (GA-EMS) can optimally control a MG by finding global optima and handling complex, non-linear, and non-convex problems, but they can be computationally intensive, making real-time control challenging. Model Predictive Control (MPC)-based EMS predicts future behaviour over a defined horizon, ensuring optimal performance and constraint satisfaction but typically relies on linear models. This paper proposes a novel Genetic Predictive Control (GPC) method, combining GA and MPC to enhance resource allocation, balance multiple objectives, and adapt dynamically to changing conditions. Integrating GA with MPC significantly improves the handling of non-linearities and non-convexity in the system model, leading to more accurate and effective control. Comparative analysis shows that GPC significantly reduces excess power production—surplus power generated beyond load demand—improving resource allocation efficiency. For instance, in the Mutation–Random Selection scenario, GPC reduced excess power to 76.0W compared to 87.0W with GA. Additionally, GPC balances cost, emissions, and power efficiency. In the Crossover-Elitism scenario, GPC achieved a daily cost of $113.94 compared to GA's $127.80, and carbon emissions of 52.83 kg CO2e compared to GA's 69.71 kg CO2e, demonstrating GPC's cost efficiency and environmental benefits. While MPC optimizes a weighted sum of objectives, designing appropriate weights can be challenging and may result in non-convex problems. GA handles multiple, conflicting objectives through multi-objective optimization, providing Pareto-optimal solutions. GPC's dynamic adaptability maintains optimal performance by forecasting future load demands and adjusting control actions. GPC consistently achieves lower emissions than GA across various scenarios and, although it sometimes incurs higher costs, such as $113.94 compared to $131.90 in the Crossover–Random Selection scenario, its holistic approach balances these costs with other metrics, making it cost-effective in the long run. By reducing excess power production and emissions, GPC contributes to economic savings and promotes sustainable practices. These findings underscore GPC's potential as a versatile, efficient, and environmentally beneficial optimization tool for power generation systems.

Background/Objectives: Vascular invasion, especially extramural vascular invasion (EMVI) has emerged as prognostic parameter for rectal cancer (RC) in recent years. Prediction of reccurence and metastases development poses a significant challenge for oncologists, needing markers for prediction of adverse outcome. The aim of this study was to examine the prognostic significance of pathohistologically detected EMVI in untreated rectal cancer and its implications in separate reporting. Methods: We examined 100 untreated RC patients who underwent curative resection from January 2016 to June 2018 with follow up of 5 years. Patients were divided in equal EMVI- and EMVI+ groups based on histological re-examination of H&E stained postoperative surgical samples. Results: The presence of EMVI within the selected cohort was significantly associated with female gender, T3/T4 and N1/N2 post-operative stages, positive lymph nodes, lymph node ratio LNR2 and LNR3 groups, abundant tumor-infiltrating lymphocytes, positive lympho-vascular invasion (LVI), perineural (PNI), and circumferential resection margin (CRM) (p<0.05 in all tests). Within EMVI+ patients, local recurrences and/or metastases, and death outcomes were more frequent events (p=0.029 and p=0.035, respectively), while survival analyses revealed that EMVI+ patients had significantly shorter overall survival (OS, p=0.040) and disease-free survival (DFS, p=0.028). Concerning LVI, differences in OS between LVI+ and LVI- patients were not statistically significant (p=0.068), while LVI+ patients had significantly shorter DFS (p=0.024). Moreover, univariate COX regression analysis demonstrated the negative impact of EMVI on OS (HR: 2.053, 95% CI: 1.015-4.152; p=0.045) and DFS (HR: 2.106, 95% CI: 1.066-4.870; p=0.038), which was not the case for LVI+ RC patients. Conclusions: Obtained results strongly suggest significance of separate reporting of EMVI from lympho-vascular invasion, as it is potentially a surogate marker for adverse prognosis and outcome.

The ever-increasing industrialization of certain areas of the planet combined with the simultaneous degradation of the natural environment are alarming phenomena, especially in the field of human health. The concentration of Particulate Matter with an aerodynamic diameter of 2.5μm (PM2.5) and 10μm (PM10), nitrogen oxides (NOx), carbon monoxide (CO), sulfur dioxide (SO2), and ozone (O3) needs constant monitoring, as they consist the main cause for many diseases. Based on the existence of statutory limits, by the World Health Organization (WHO), for the concentration of each of the aforementioned air pollutants, it is considered necessary to develop forecasting systems that will have the ability to correlate the current meteorological data with the concentrations of the above pollutants. In this work, the attempt to predict the air pollutants concentrations in the wider area of Beijing, China, is successfully carried out using artificial neural networks (ANNs) models. In the frame of the specific work, a significant number of ANNs was developed. For this purpose, an open-access meteorological and air pollution database was used. Finally, a statistical evaluation of the developed prognostic models was carried out. Results showed that ANNs present a re-markable prognostic ability in order to forecast the air pollution levels in an urban environment.

Developments in artificial intelligence techniques allow for an improvement in sustainable mobility strategies with particular reference to energy consumption estimates of electric vehicles (EVs). This research proposes a vehicle energy model developed on the basis of Deep Neural Network (DNN) technology. The study also explores the potential application of the model developed for the movement data of new vehicles in the province of Enna, Sicily, Italy. which is characterized by numerous attractors and the increasing number of hybrid and electric cars circulating. The energy model for electric vehicles shows high accuracy and versatility, requiring vehicle velocity and acceleration as input data to predict energy consumption. The research article also provides recommendations for the energy modeling of electric vehicles and outlines additional steps for model development. The implemented methodological approach and its results can be used by transport decision makers to plan new transport policies in Italian cities aimed at optimizing vehicle charging infrastructure. They can also help vehicle users accurately estimate energy consumption, generate maps, and identify locations with the highest energy consumption.

Enhancing the management and monitoring of oil and gas processes demands developing precise predictive analytics techniques. Over the past two years, oil and its prediction have advanced significantly using conventional and modern Machine Learning techniques. Several review articles detail the developments in predictive maintenance and technical and non-technical aspects of influencing the uptake of big data. The absence of references for machine learning techniques impacts the effective optimization of predictive analytics in the oil and gas sector. This review paper offers readers thorough information on the latest machine learning methods utilized in this industry's predictive analytical modelling. The review covers forms of Machine Learning techniques used in predictive analytic modelling from 2021 to 2023 (91 articles). It provides an overview of the details of the papers that were reviewed, comprising of the model’s categories, the data's temporality, field, and name, the dataset's type, predictive analytics (classification or clustering or prediction), the models' input and output parameters, performance metrics, optimal model, and benefits and its drawbacks. Additionally, suggestions for future research directions are provided to raise the potential of the associated knowledge and increase the accuracy of oil and gas predictive analytics models.

Longitudinal cutting is a most common process in steel structure manufacturing, and the man-hours of the process provide an important basis for enterprises to generate production schedules.However, currently the man-hours in factories are mainly estimated by experts, and the accuracy of this method is relatively low.In this study,we propose a system that predicts man-hours with history data in the manufacturing process and that can be applied in practical structural steel fabrication.The system addresses the data inconsistency problem by one-hot encoding and data normalization techniques,Pearson correlation coefficient for feature selection,and the Random Forest Regression(RFR) for prediction.Compared with the other three Machine Learning(ML) algorithms, the Random Forest algorithm has the best performance.The results demonstrate that the proposed system outperforms the conventional approach and has better forecast accuracy, so that it is suitable for man-hours prediction.

Recent technological advancements such as IoT and Big Data have granted industries extensive access to data, opening up new opportunities for integrating Artificial Intelligence (AI) across various applications to enhance production processes. We can cite two critical areas where AI can play a key role in industry such as product quality control and predictive maintenance. This paper presents a survey of AI applications in the domain of Industry 4.0, with a specific focus on product quality control and predictive maintenance. Experiments were conducted using two datasets, incorporating different machine learning and deep learning models from the literature. Furthermore, this paper provides an overview of the AI solution development approach for product quality control and predictive maintenance. This approach includes several key steps, such as data collection, data analysis, model development, model explanation, and model deployment.

This study addressed algorithmic bias in predictive policing, focusing on the Chicago Police Department's Strategic Subject List (SSL) dataset. We specifically focused on identifying and mitigating age-related biases, a notably underexplored area in prior research. Our research introduced Conditional Score Recalibration as a bias mitigation strategy alongside the well-established Class Balancing technique. Conditional Score Recalibration involved reassessing and adjusting risk scores for individuals initially assigned moderately high-risk scores in the dataset. This recalibration marked such individuals as low risk if they met three conditions, namely: no prior arrests for violent offenses, no previous arrests for narcotic offenses, and having never been involved in shooting incidents. These fairness strategies were implemented on the Random Forest model, and the fairness metrics employed included Equality of Opportunity Difference, Average Odds Difference, and Demographic Parity. The results showed a significant improvement in model fairness, particularly for age biases, without compromising the model's accuracy. These findings challenged the often-assumed trade-off between fairness and accuracy, underscoring the feasibility of achieving fairness without compromising accuracy.

Intelligent transportation systems (ITS) are at the forefront of advancements in transportation, offering enhanced efficiency, safety, and environmental friendliness. To enable ITS, autonomous systems play a pivotal role, leveraging breakthroughs in autonomous driving, data-driven modeling, and multiagent control strategies to establish sustainable and coordinated traffic management. The integration of connected and automated vehicles has garnered significant attention as a potential solution for alleviating traffic congestion and improving fuel economy, achieved through global route optimization and cooperative driving. This study focuses on a predictive control perspective to address the cooperative cruise control problem. Online decision-making is employed during the driving process, utilizing information gathered from the network. By employing bargaining games to establish an operating agreement among vehicles, we formalize a synchronization approach based on predictive control theory. Ultimately, these findings are put to the test in an emulation environment within a hardware-in-the-loop system.

The GPA is a universally recognised and utilised metric of academic performance that is considered to also measure a student’s potential for academic performance in the future. In this short communication we examine to what extent the GPA of the first grade of high school predicts performance in the later grades of high school, either generally (as classified in excellent student, strong student, weak student or very weak student) or more accurately (as indicated by the exact GPA in the next grade). We also put to the test the widely held notion that it might be best if core courses such as language and mathematics contributed more to the calculation of the GPA compared to secondary courses such as physical education or music. Our findings confirm the predictive properties of the GPA but strongly rebut the notion that a weighted GPA might achieve a better reflection of students’ potential. The study is based on the academic records of every student in Greece that progressed from first to third grade of high school in the 2016-2019 period. This data set contains records of more than 85,000 students, making it one of the most extensive studies ever conducted on the topic of the properties of the GPA.

The objective of this study is to design an optimal model predictive control (MPC) strategy using manipulated variables to control the production of a sufficient amount of hydrogen through low temperature autothermal reforming of dimethyl ether (DME), a reforming reaction performed using PdO/ZnO/γ-Al2O3 catalysts coated on honeycomb cordierite ceramics. Experiments and simulation have verified that the optimal activity temperature of the catalyst is 400 °C, and the hydrogen volume fraction in syngas is over 43%. In the implementation of the hydrogen production system, the MPC controller can precisely determine the feed rates of DME, high-purity air, and water based on the space state equation of the reformer, to achieve the anti-disturbance of the reformer temperature. Thus, the reduction of hydrogen yield and sintering of the catalyst as a result of overheating are prevented. As the static and dynamic performance of hydrogen production exhibits excellent tracking of the setpoints, an autonomous, automated, and reliable continuous system was designed to meet the desired hydrogen demand situation. This study shows that an autonomous, automated, and reliable continuous hydrogen production reforming system can be designed to actively respond to the on-board hydrogen usage situation.

(1) Background: Ventilator-associated pneumonia (VAP) causes high mortality among patients with respiratory disease and imposes major burdens on healthcare infrastructure. Models that use electronic health record data to predict the onset of VAP may spur earlier treatment and improve patient outcomes. We developed and studied the performance of interpretable machine learning (ML) models that predict the onset of VAP from electronic health records (EHRs); (2) Methods: We trained Logistic Regression (LR), full feature Explainable Boosting Machine (fEBM), and eXtreme Gradient Boosting (XGBoost) ML models on data from the MIMIC- III (v1.3) database. Model performance was measured by area under the receiver operating characteristic curves (AUCs). We trained a minimal-feature EBM model (mEBM) with features derived from white blood cell (WBC) counts, duration of ventilation, and Glasgow Coma Scale (GCS). Finally, model robustness was evaluated on randomly sparsified EHR datasets; (3) Results: The fEBM model outperformed the XGBoost and LR models at 24 hours post-intubation. The mEBM model maintained an AUC of 0.893. The fEBM model performance remained robust on sparsified datasets; (4) Conclusions: Our novel interpretable ML algorithm reliably predicts the onset of VAP in intubated patients. Integration of this EBM-based model into clinical practice may enable clinicians to better anticipate and prevent VAP.

Purpose: To investigate trabeculopuncture (TP) for predicting the outcome of ab interno trabeculectomy (AIT). AIT is an effective, low-risk procedure for open angle glaucoma. Despite widespread utilization, it fails in patients with an unidentified distal outflow resistance. Methods: We bisected 81 enucleated porcine eyes and perfused them for 72 hours. They were assigned to two groups: trial (n=42) and control (n=39). Intraocular pressure (IOP) was measured continuously. At 24 hours, four YAG-laser trabeculopunctures on the nasal trabecular meshwork were performed, followed by a 180° AIT at the same site at 48 hours. Eyes were divided into TP and AIT responders and non-responders; the proportion of TP responders between both AIT groups was compared. Results: Both post-TP and post-AIT IOPs were lower than baseline IOP (p=0.015 and p<0.01, respectively). The success rates of TP and AIT were 69% and 85.7%, respectively. The proportion of TP responders among AIT responders was greater than that of AIT non-responders (p<0.01). Sensitivity and specificity values of TP as predictive test for AIT success were 77.7% and 83.3%, respectively. The positive and negative predictive values were 96.6% and 38.5%, respectively. Conclusion: A 10% reduction in IOP after TP can be used as predictor for the success (>20% IOP decrease) of 180° AIT in porcine eyes.

This paper presents the results of quantitative research regarding the predictive model of citizens' attitudes about the risks of introducing the death penalty in the Republic of Serbia legal system. The research was conducted with the use of a questionnaire that was requested and then collected online from 427 people in June 2021. A multivariate regression analysis was used, identifying the extent to total scores of the main dependent variables (introducing the death penalty; trust in the legal system; advantages of introduction; disadvantages of introduction scores) were associated with five demographic and socio-economic variables: gender, marital, education, income, and age. We tested the central hypothesis of which gender is predicting variables citizens' attitudes about the risks of introducing the death penalty in the legal system of Serbia. The findings revealed that gender and educational level were the most effective predictors of the research variables under question. The majority of respondents support the introduction of the death penalty and the most important predictor of disadvantages of introducing the death penalty in the legal system is age. Based on the findings that there are major differences in the citizens' attitudes about the risks of introducing the death penalty in the legal system, policies, strategies, and regulations must take into account these very important findings.

XGBoost is recognized as an algorithm with exceptional predictive capacity. Models for a binary response indicating the existence of accident claims vs. no claims can be used to identify the determinants of traffic accidents. We compare the relative performances of logistic regression and XGBoost approaches for predicting the existence of accident claims using telematics data. The dataset contains information from an insurance company about individuals’ driving patterns – including total annual distance driven and percentage of total distance driven in urban areas. Our findings show that logistic regression is a suitable model given its interpretability and good predictive capacity. XGBoost requires numerous model-tuning procedures to match the predictive performance of the logistic regression model and greater effort as regards interpretation.

The following paper describes an economical, multiple model predictive control (EMMPC) for an air conditioning system of a confectionery manufacturer in Germany. The application consists of a packaging hall for chocolate bars, in which a new local conveyor belt air conditioning system is used and thus the temperature and humidity limits in the hall can be significantly extended. The EMMPC calculates the optimum energy or cost humidity and temperature set points in the hall. For this purpose, time-discrete state space models and an economic objective function with which it is possible to react to flexible electricity prices in a cost-optimised manner are created. A possible future electricity price model for Germany with a flexible EEG levy was used as a flexible electricity price. The flexibility potential is determined by variable temperature and humidity limits in the hall, which are oriented towards the comfort field for easily working persons, and the building mass. The building mass of the created room model is used as a thermal energy store. Considering electricity price and weather forecasts as well as internal, production plan-dependent load forecasts, the model predictive controller directly controls the heating and cooling register and the humidifier of the air conditioning system.

Chatter, a self-excited vibration phenomenon, is a critical challenge in high-speed machining operations, affecting tool life, surface quality, and overall process efficiency. While ML models trained on simulated data have shown promise in detecting chatter, their real-world applicability remains uncertain due to discrepancies between simulated and actual machining environments. This study bridges the gap by validating a ML-based chatter detection system using both simulated and real-world data. We apply a Random Forest classification model trained on over 140,000 simulated machining datasets, incorporating techniques like Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL) to adapt the model for real-world operational data. The model is validated against 1,600 real-world machining datasets, achieving an accuracy of 86.1%, with strong precision and recall scores. Our results demonstrate the model’s robustness and potential for practical implementation in industrial settings, highlighting challenges such as sensor noise and variability in machining conditions. This work advances the use of predictive analytics in machining processes, offering a data-driven solution to improve manufacturing efficiency through more reliable chatter detection.

Thermal comfort indices are risk indicators for environmental conditions in livestock production. Predictive models based on these indices of heat stress, respiratory frequency, and presence of heat waves for lactating cows, comparing the prediction and correlation between these factors, generate responses that can improve animal management regarding physiological responses to heat stress during the incidence of heat waves. Therefore, the objective was to develop predictive models for heat wave risk alerts based on thermal stress indices, physiological responses, and surface temperature of lactating cows. The region's climatic conditions were evaluated based on data on temperature, air humidity, wind speed, black globe temperature, solar radiation, dew point temperature, and precipitation compiled from a meteorological station. In the processing phase, a data set was discretized into classes to apply machine learning techniques to generate a classification model with cross-validation of the data. The performance of the classifiers was evaluated based on the metrics: accuracy, precision, sensitivity (recall), and Kappa statistics. Predicting the risk of heat waves for lactating cows can meet the need to predict the frequency of heat waves for decision-making in environmental, nutritional, and health management to minimize adverse impacts on production. The accuracy of Decision Tree models (J48), Naive Bayes, and Logistic Regression was equal to 96.72%, 96.72%, and 98.36%, respectively. The performance in the evaluation metrics of the Logistic Regression prediction model was better than that of the decision tree and Naive Bayes models.

The article evaluates the use of machine learning methods to predict valve plate failures in hydraulic pumps. To conduct this assessment, a laboratory setup was developed that allowed the creation of a training dataset containing both the normal operating state of the pump and the operating state with three different valve plate damages. Five different predictive models were evaluated, including three composite models based on decision trees: Random Forest, Gradient-Boosted Trees, and Rotation Forest, as well as the kNN algorithm and a neural network. The analysis showed that neural networks achieved the highest prediction accuracy, enabling a prediction accuracy level of 89%. The kNN algorithm ranked second, and tree-based algorithms performed 4% worse than the neural network. Additionally, the attribute importance analysis revealed that leak flow, pressure output together with output flow, are the most important parameters for accurate prediction.

The implementation of systems condition monitoring is of utmost importance in ensuring effective maintenance, optimal efficiency, and adherence to established design criteria. This research presents a novel and economically efficient Digital Twin Model (DTM) designed for the purpose of Live Condition Monitoring (LCM) and Predictive Lifecycles. This study discusses the enhancement of DTs modelling by decreasing the number of dimensions from five to three: Physical, Digital, and Connection entities. The resulting model exhibits a notable improvement in accuracy and efficiency. The suggested Dynamic Time Model (DTM) enhances the empirical pre-set average load for both simulation and experimentation by 35.7%, which is equivalent to a 1.6-fold increase. The DTM demonstrates a significant enhancement in the empirical predefined average lifecycles of the system, as shown in the real-life case study. Specifically, the DTM achieves a 12-fold improvement compared to the simulated results and a nine-fold improvement compared to the experimental findings. The suggested Dynamic Time Management (DTM) demonstrates a significant enhancement in the average lifecycles of the system, with a 19.7% improvement (equivalent to 1.2 times greater) compared to the wireless DTM results obtained through the application of the real system load. The suggested Dynamic Time Warping (DTW) method's accuracy and efficiency are shown via a practical case study using the suspension system of a Peugeot 3008 vehicle.

This paper addresses challenges and solutions in urban development and infrastructure resilience, particularly in the context of Japan's rapidly urbanizing landscape. It explores the integration of smart city concepts to combat land subsidence and liquefaction, phenomena highlighted by the 2011 Great East Japan Earthquake. Using advanced technologies such as smart sensing and predictive analytics through kriging and ensemble learning, the study aims to improve the accuracy of geotechnical investigations and urban planning. By analyzing data from 433 geotechnical surveys in Setagaya, Tokyo, it develops predictive models to accurately determine the depth of bearing layers critical to urban infrastructure. The results demonstrate the superiority of ensemble learning in predicting the depth of bearing layers, with significant implications for smart city development and the sustainability of urban environments. This interdisciplinary approach not only seeks to mitigate risks associated with geological disturbances, but also promotes sustainable urban growth that prioritizes safety and prosperity. Through advanced technology and comprehensive research, the study underscores the potential of smart cities to address urban complexities and ensure a resilient, sustainable future.

In some applications of microgrid and distributed generation, it is required to feed islanded or stand-alone loads with high-quality voltage to provide low total harmonic distortion (THD). To fulfil these demands, an LC filter is connected to the output terminals of power electronics converters. A cascaded voltage and current control loop with pulse-width modulation schemes are used to regulate the voltage and current in these systems. However, these strategies have some drawbacks, particularly when multiple-input multiple-output plants (MIMO) are controlled using single-input single-output (SISO) design methods. This methodology usually produces a sluggish transient response and cross-coupling between different control loops. In this paper, a model predictive control (MPC) strategy based on the concept of optimal switching sequences (OSS) is designed to control voltage and current in an LC filter connected to a three-level neutral-point clamped converter. The strategy solves two well-formulated optimisation problems to achieve control of the LC filter variables and the voltages of the DC-link capacitors. Hardware-in-the-Loop (HIL) results are obtained to validate the feasibility of the proposed strategy, using a PLECS-RT HIL platform and a DSP Microlab Box controller. In addition to the good dynamic performance of the proposed OSS-MPC, it is demonstrated by the HIL results that the control algorithm is capable of obtaining low total harmonic distortion (THD) in the output voltage for different conditions.

The aims of this paper can be traced back to goals number seven, twelve and thirteen introduced by Agenda 2030, namely "affordable and clean energy", “responsible consumption and production” and "climate action”, respectively. This is due to the fact that the present work supports decarbonization processes acting in a direct way on the electricity consumption achieved by plants pertaining to the waste industry; in fact, this study aims at the realization of a machine learning model for predicting the energy consumption achieved by a mechanical biological treatment (MBT) waste plant located in central Italy, given the distribution of the entering waste. This model is implemented in MATLAB. The model can be used to tune the distribution of the entering waste in order to adapt the plant energy consumption to the capability of the energy sources and can serve as a play-ground model for other energy transformation plants. The results of the study, which feed the literature on the application of artificial intelligence to real industrial plants, could be used to determine energy efficiency actions that could be incorporated into Property’s strategic planning.

The prevalence of chronic diseases is dramatically increasing demand for emergency healthcare. Existing systems rely on patients self-identifying symptoms, causing dangerous delays. This study develops an AI and IoT-powered “digital twin” solution to enable continuous real-time monitoring and timely prediction of diverse medical emergencies. A digital twin is a virtual representation of an individual, modeled using multidimensional physiological data from wearable sensors. Machine learning techniques analyze patterns in this data to identify anomalies and predict emergencies like heart attacks or falls. A key contribution is an optimized ensemble algorithm combining gradient boosted trees, neural networks, and other techniques to accurately detect emergency events. Evaluation on a dataset of 9158 samples shows the digital twin identifies key emergencies with over 90% recall, enabling prevention and rapid response. It allows risk stratification and personalized interventions based on early warnings, circumventing over 2 million avoidable emergency room visits annually. This study demonstrates the feasibility of an integrated, predictive, patient-centric emergency response system enabled by digital twin technology.

Aim: This study was to evaluate the predictive value of tumor marker (TM) score in patients with hepatocellular carcinoma (HCC) treated with Atezolizumab plus Bevacizumab (Atez/Bev) as a first-line chemotherapy. Materials/Methods: From September 2020 to December 2022, 371 HCC patients treated with Atez/Bev, in whom alpha-fetoprotein (AFP), fucosylated AFP (AFP-L3) and des gamma-carboxy prothrombin (DCP) were measured at introducing Atez/Bev. Elevations of AFP (≥100 ng/ml), AFP-L3 (≥10%), and DCP (≥100 mAU/ml) were treated as positive, and the number of positive tumor marker was summed up and used as the previously proposed TM score. Hepatic reserve function was assessed with modified albumin-bilirubin grade (mALBI). Predictive values for prognosis were evaluated, retrospectively. Results: TM score 0 was in 81 (21.8%), score 1 in 110 (29.6%), score 2 in 112 (29.9%), and score 3 in 68 (18.3%), respectively. Median overall survival (OS) was not applicable [NA] (95% CI NA-NA), 24.0 months (95% CI 17.8-NA), 16.7 months (95% CI 17.8-NA) and NA (95%CI 8.3-NA) for TM scores 0, 1, 2 and 3, respectively (p<0.001). Median progression free survival (PFS) was also 16.5 months (95% CI 8.0-not applicable [NA]), 13.8 months (95% CI 10.6-21.3) and 7.7 months (95% CI 5.3-8.9), 5.8 months (95%CI 3.0-7.6), respectively (p<0.001). OS was stratified well in mALBI 1/2a as well as in mALBI 2a/2b. Whereas, PFS was well stratified in mALBI 2a/2b, while not in mALBI 1/2a. Conclusion: The TM score was a simple and useful prognostic marker in HCC patients treated with Atez/Bev.

The use of mathematical models of physiological systems in medicine has allowed the development of diagnostic, treatment, and medical educational tools, but their application for predictive, preventive, and personalized purposes is restricted by their complexity. Although there are strategies that reduce the complexity of applying models by fitting techniques, they focus on a single instant of time, neglecting the effect of the system's temporal evolution. The aim of this work is to propose a dynamic fitting strategy of physiological models with large number of parameters and a constrained amount of experimental data, focused on obtaining better predictions based on the system's temporal trend and useful to predict future states. It was applied in a cardiorespiratory model as a case study. Experimental data from a longitudinal study of healthy adult subjects under aerobic exercise were used for fitting and validation. The model predictions obtained at steady-state using the proposed strategy and the nominal values of the parameters were compared. The best results corresponded mostly to the proposed strategy, mainly regarding the overall prediction error. The results evidenced the usefulness of the dynamic fitting strategy, highlighting its use for predictive, preventive, and personalized applications.

In recent years, metabolomics has been used as a powerful tool to better understand the physiology of neurodegenerative diseases and identify potential biomarkers for progression. We used targeted and untargeted aqueous, and lipidomic profiles of the metabolome from human cerebrospinal fluid to build multivariate predictive models distinguishing patients with Alzheimer’s disease (AD), Parkinson’s disease (PD), and healthy age-matched controls. We emphasize several statistical challenges associated with metabolomic studies where the number of measured metabolites far exceeds sample size. We found strong separation in the metabolome between PD and controls, as well as between PD and AD, with weaker separation between AD and controls. Consistent with existing literature, we found alanine, kynurenine, tryptophan, and serine to be associated with PD classification against controls, while alanine, creatine, and long chain ceramides were associated with AD classification against controls. We conducted a univariate pathway analysis of untargeted and targeted metabolite profiles and find that vitamin E and urea cycle metabolism pathways are associated with PD, while the aspartate/asparagine and c21-steroid hormone biosynthesis pathways are associated with AD. We also found that the amount of metabolite missingness varied by phenotype, highlighting the importance of examining missing data in future metabolomic studies.

Background: CoronaVirus Disease 2019 (COVID-19) is the main discussed topic world-wide in 2020 and at the beginning of the Italian epidemic, scientists tried to understand the virus diffusion and the epidemic curve of positive cases with controversial findings and numbers. Objectives: In this paper, a data analytics study on the diffusion of COVID-19 in Lombardy Region and Campania Region is developed in order to identify the driver that sparked the second wave in Italy Methods: Starting from all the available official data collected about the diffusion of COVID-19, we analyzed google mobility data, school data and infection data for two big regions in Italy: Lombardy Region and Campania Region, which adopted two different approaches in opening and closing schools. To reinforce our findings, we also extended the analysis to the Emilia Romagna Region. Results: The paper aims at showing how different policies adopted in school opening / closing may have on the impact on the COVID-19 spread. Conclusions: The paper shows that a clear correlation exists between the school contagion and the subsequent temporal overall contagion in a geographical area.

Abstract:Global ship demolition is mostly concentrated in south Asian countries, namely Bangladesh, India, Pakistan and China, since 1990’s, having competitive advantage for their high natural tide, and low environmental and social costs. Due to high social and environmental externalities, stakeholders increase monitoring of the externalities and continue to prescribe improvement towards sustainability, which put pressures on profitability and competitiveness. As a consequence, also seen in the past, a leakage effect may emerge, leading to shift of this activity to a region, with relatively less monitored and less stricter on social and environmental impacts. Unfortunately, the leakage effect is never predicted in shipbreaking in order to understand the level of push compatible in the given socio-economic contexts. In this study, we have attempted to predict the future ship demolition landscape, applying machine learning technique to 34,531 in-service vessels worldwide, larger than 500 gross tonnage (GT), which is run against a learning model based on 3500 demolished vessels from 2014. This study shows that redistribution may occur among the top recycling nations: India may emerge out to be a dominant player in shipbreaking, surpassing Bangladesh by a margin of two-fold, while Pakistan and China are in decreasing trend. In addition, the leakage effect is observed, in that Vietnam is predicted to be the fourth largest ship demolition country, while China and Pakistan recede from the third and fourth place to 6th and 8th. Turkey is predicted to advance from fifth position to third position by vessel count but stays same in term of total GT dismantled. Although it is not clear if any leakage is to be observed in the near future, this study may be a model for future predictive analytics and help stakeholders take evidence-based business decisions.

In this paper, a capacitor microphone system is presented to improve the conversion of mechanical energy to electrical energy using a nonlinear auto regressive moving average-L2 (NARMA-L2) and model predictive control (MPC) controllers for the analysis of the open loop and closed loop system. The open loop system response shows that the output voltage signal need to be improved. The comparison of the closed loop system with the proposed controllers have been analyzed and a promising result have been obtained using Matlab/Simulink.

Modularity is arguably one of the most influential theses guiding research on brain and cognitive function since phrenology. This paper considers the following question: is modularity entailed by recent Bayesian models of brain and cognitive function, especially the predictive processing framework? It starts by considering three of the most well-articulated arguments for the view that modularity and predictive processing work well together. It argues that all three kinds of arguments for modularity come up short, albeit for different reasons. The analysis in this paper, although formulated in the context of predictive processing, speaks to broader issues with how to understand the relationship between functional segregation and integration and the reciprocal architecture of the predictive brain. These conclusions have implications for how to study brain and cognitive function. Specifically, when cognitive neuroscience works within an acyclic Markov decision scheme, adopted by most Bayesian models of brain and cognitive function, it may very well be methodologically misguided. This speaks to an increasing tendency within the cognitive neurosciences to emphasise recurrent and reciprocal neuronal processing captured within newly emerging dynamical causal modelling frameworks. The conclusions also suggest that functional integration is an organising principle of brain and cognitive function.

Multiobjective optimization plays an increasingly important role in modern applications, where several criteria are often of equal importance. The task in multiobjective optimization and multiobjective optimal control is therefore to compute the set of optimal compromises (the Pareto set) between the conflicting objectives. The advances in algorithms and the increasing interest in Pareto optimal solutions have led to a wide range of new applications related to optimal and feedback control which results in new challenges such as expensive models or real-time applicability. Since the Pareto set generally consists of an infinite number of solutions, the computational effort can quickly become challenging which is particularly problematic when the objectives are costly to evaluate or when a solution has to be presented very quickly. This article gives an overview over recent developments in accelerating multiobjective optimal control for complex problems where either PDE constraints are present or where a feedback behavior has to be achieved. In the first case, surrogate models yield significant speed-ups. Besides classical meta-modeling techniques for multiobjective optimization, a promising alternative for control problems is to introduce a surrogate model for the system dynamics. In the case of real-time requirements, various promising model predictive control approaches have been proposed, using either fast online solvers or offline-online decomposition. We also briefly comment on dimension reduction in many-objective optimization problems as another technique for reducing the numerical effort.

This paper explores developing and deploying a fog computing platform tailored for industrial environments, focusing on predictive maintenance and advanced data management. The research investigates the integration of custom sensors and algorithms to meet specific industrial requirements, emphasizing the application of Long Short-Term Memory (LSTM) models for predicting equipment failures. The study enhances proactive maintenance strategies and real-time decision-making by applying machine learning techniques within a fog computing architecture. The findings underscore the platform’s potential to advance industrial data processing, edge intelligence, and maintenance practices, contributing to improved efficiency and reduced downtime in industrial operations.

Background: Cancer remains a leading cause of death worldwide. The progress in effective treatment has been hampered by challenges in personalized therapy, particularly in patients with comorbid conditions. The integration of artificial intelligence (AI) into patient profiling offers a promising approach to enhancing individualized anticancer therapy. Objective: This narrative review explores the role of AI in refining anticancer therapy through personalized profiling, with a specific focus on cancer patients with co-morbid migraine. Methods: A comprehensive literature search was conducted across multiple databases, including PubMed, Scopus, and Google Scholar. Studies were selected based on their relevance to AI applications in oncology and migraine management, with a focus on personalized medicine and predictive modeling. Key themes were synthesized to provide an overview of recent developments, challenges, and emerging directions. Results: AI technologies such as machine learning (ML), deep learning (DL), and natural language processing (NLP) have become instrumental in discovery of genetic and molecular biomarkers to cancer and migraine. These technologies also enable predictive analytics for assessing the impact of migraine on cancer therapy in co-morbid cases, predicting outcomes and provide clinical decision support systems (CDSS) for real-time treatment adjustments. Conclusion: AI holds significant potential to improve the precision and effectiveness of cancer management and therapy, particularly for cancer patients with co-morbid migraine. Nevertheless, challenges remain over data integration, clinical validation, and ethical consideration, which must be addressed to appreciate the full potential for outlines approach.

This study explores the synergistic integration of Artificial Intelligence (AI) in information technology with photochemical methods to optimize nanoparticle synthesis. By leveraging machine learning algorithms and predictive modeling, we demonstrate significant enhancements in the precision, efficiency, and scalability of nanoparticle production. AI-driven analysis of reaction parameters, optical properties, and structural characteristics enables real-time monitoring and adaptive optimization of photochemical reactions.The developed framework utilizes deep learning techniques to correlate reaction conditions with nanoparticle size, shape, and composition, facilitating the synthesis of tailored nanoparticles for various applications. Results show improved monodispersity, increased yield, and reduced synthesis time compared to traditional methods.This innovative approach paves the way for the rapid development of high-performance nanoparticles in fields such as biomedical imaging, energy storage, and catalysis. By harnessing the power of AI in information technology, this research unlocks new possibilities for the precise and efficient synthesis of nanoparticles via photochemical methods.

Endometrial cancer (EC) poses a significant global health challenge, with increasing prevalence in 26 of 43 countries and over 13,000 deaths projected in the United States by 2024. This rise correlates with aging populations, the obesity epidemic, and changing reproductive patterns, including delayed childbearing. Despite the early diagnosis in 67% of cases, approximately 30% of cases present with regional or distant spread, leading to nearly 20% mortality rates. Unlike many cancers, EC mortality rates are escalating, outpacing therapeutic advancements until recently. One of the reasons for this was the lack of effective therapeutic options for advanced disease until recently. The introduction of immunotherapy has marked a turning point in EC treatment, particularly benefiting patients with defects in mismatch repair proteins (dMMRs). However, dMMR status alone does not ensure a favorable response, underscoring the need for precise patient selection. This review explores the pivotal role of mismatch repair proteins in EC, emphasizing their heterogeneity, the challenges in their assessment, and their potential as predictive biomarkers.

Differentiated thyroid cancer (DTC), comprising of papillary and follicular thyroid cancers, is the most prevalent type of thyroid malignancy. Accurate prediction of DTC is crucial for improving patient outcomes. Machine learning (ML) offers a promising approach to analyze risk factors and predict cancer recurrence. In this study, we aimed to develop predictive models to identify patients at an elevated risk of DTC recurrence based on 16 risk factors. We developed six ML models and applied them to a DTC dataset. We evaluated the ML models using Synthetic Minority Over-Sampling Technique (SMOTE) and with hyperparameter tuning. We measured the models’ performance using precision, recall, F1 score, and accuracy. Results showed that Random Forest consistently outperformed the other investigated models (KNN, SVM, Decision Tree, AdaBoost, and XGBoost) across all scenarios, demonstrating high accuracy and balanced precision and recall. The application of SMOTE improved model performance and hyperparameter tuning enhanced overall model effectiveness.

In a V2V communication environment, the control of electric vehicle platoons faces issues such as random communication delays, packet loss, and external disturbances, which affect sustainable transportation systems. In order to solve these problems and promote the development of sustainable transportation, a longitudinal control algorithm for the platoon based on robust Unscented Kalman Filter (UKF) and Model Predictive Control (MPC) is designed. First, a longitudinal kinematic model of the vehicle platoon is constructed, and discrete state-space equations are established. The robust UKF algorithm is derived by enhancing the UKF algorithm with Huber-M estimation. This enhanced algorithm is then used to estimate the state information of the leading vehicle. Based on the vehicle state information obtained from the robust UKF estimation, feedback correction and compensation are added to the MPC algorithm to design the robust UKF-MPC longitudinal controller. Finally, the effectiveness of the proposed controller is verified through CarSim/Simulink joint simulation. The simulation results show that in the presence of communication delay and data loss, the robust UKF-MPC controller outperforms the MPC and UKF-MPC controllers in terms of MSE and IAE metrics for vehicle spacing error and acceleration tracking error, and exhibits stronger robustness and stability.

The two combined technologies WPT and AI still have huge prospects for several industries such as consumer electronics and industry. This paper looks at the recent developments in WPT, particularly concerning AI-improved efficiency, range, and reliability. AI-driven also works to control power, manage device alignment, and test when maintenance is necessary, this makes powering smarter and more efficient. Accuracy is given by deploying machine learning and computer vision, and on the other hand, the maintenance procedure is done through predictions. Furthermore, the ability of the management system to include the use of AI in power regulation enables the control of consumption based on the load. In this study, the positive future effect of AI is discussed concerning improvements in WPT technologies, which is paramount in subsequent applications. Based on the results, it is essential to continue the investigation of the topic within this interdisciplinary science to advance existing problems and discover novel possibilities for evolution. Data based on experiments shows a significant improvement in the efficiency of information transfer where AI is used with rates up to 25% higher than those using the traditional ways. Additionally, advanced maintenance forecasting algorithms improve system availability by cutting down on 30% of the downtimes when applied in real-life applications of AI technology. The study also looks at the possibilities of the outlook to the future including emergence of the distributed artificial intelligence for autonomous WPT network, and additional potential of quantum computing for the use to improve the algorithm. This indicates that there is a new era for the convergence of WPT and AI to enhance the progress of power transfer system in conditions of elegant, efficient, and robust.