Additive manufacturing (AM) is an attractive technology for manufacturing industry due to flexibility in design and functionality, but inconsistency in quality is one of the major limitations that does not allow utilizing this technology for production of end-use parts. Prediction of mechanical properties can be one of the possible ways to improve the repeatability of the results. The part placement, part orientation, and STL model properties (number of mesh triangles, surface, and volume) are used to predict tensile modulus, nominal stress and elongation at break for polyamide 2200 (also known as PA12). EOS P395 polymer powder bed fusion system was used to fabricate 217 specimens in two identical builds (434 specimens in total). Prediction is performed for XYZ, XZY, ZYX, and Angle orientations separately, and all orientations together. The different non-linear models based on machine learning methods have higher prediction accuracy compared with linear regression models. Linear regression models have prediction accuracy higher than 80% only for Tensile Modulus and Elongation at break in Angle orientation. Since orientation-based modeling has low prediction accuracy due to a small number of data points and lack of information about material properties, these models need to be improved in the future based on additional experimental work.

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.

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 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.

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.

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.

Individual differences in the responsiveness of the brain to transcranial electrical stimulation (tES) is increasingly demonstrated in large variability in the tES effects. Anatomically detailed computational brain models have been developed to address this variability; however, static brain models are not ‘realistic’ in accounting for the dynamic state of the brain. Therefore, human-in-the-loop optimization is proposed in this perspective article based on an extensive systems analysis of the tES neurovascular effects. First, modal analysis was conducted using a physiologically detailed neurovascular model that found stable modes in the 0 Hz to 0.05 Hz range for the pathway for vessel response through the smooth muscle cells, measured with functional near-infrared spectroscopy (fNIRS). tES effects in the 0 Hz to 0.05 Hz range can also be measured with functional magnetic resonance imaging (fMRI)-tDCS data with a maximum TR=10sec. Therefore, we investigated an open-source fMRI-tDCS dataset that used a TR=3.36sec. We found that both the anodal tDCS condition and sham tDCS condition had similar Finite Impulse Response at the region of interest underlying the anode and a remote location, which indicated a global hemodynamic effect of sham tDCS beyond the intended transient sensations. Here, transient sensations can have arousal effects on the hemodynamics so we conducted a healthy case series for black box modeling of fNIRS-pupillometry of short-duration tDCS effects. The block exogeneity test rejected the claim that tDCS is not a 1-step Granger-cause of the fNIRS total hemoglobin changes (HbT) and pupil dilation changes (p<0.05). Also, grey-box modeling using fNIRS of the tDCS effects in chronic stroke showed HbT response to be significantly different (paired-sample t-test, p<0.05) between the ipsilesional and the contralesional hemisphere for primary motor cortex tDCS and cerebellar tDCS which was subserved by the smooth muscle cells. Here, our perspective is that various physiological pathways subserving tES effects can lead to state-trait variability that can be challenging for clinical translation. Therefore, we conducted a case study on human-in-the-loop optimization using our reduced dimension model and a stochastic, derivative-free Covariance Matrix Adaptation Evolution Strategy. Future studies need to investigate human-in-the-loop optimization of tES for reducing inter-subject and intra-subject variability in tES effects.

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.

The behavioral variant of frontotemporal dementia (bvFTD) has a devastating effect on multiple domains of daily living. The purpose of this PRISMA-compliant systematic review is to summarize the most important factors associated with functional impairment in this clinical group by critically analyzing the existing literature spanning the period from 2000 to 2023. To be included in the review, the study had to investigate any kind of correlates of functional status in bvFTD patients, using a previously validated instrument of functional assessment. Out of 40 articles assessed for eligibility, 18 met the inclusion criteria. The anatomical pattern of cerebral atrophy at baseline appeared to be the strongest predictor of the rate of functional decline over time, with the frontal-dominant anatomical subtype being associated with a faster rate of functional impairment. Additionally, executive dysfunction as well as apathy appeared to contribute significantly to functional disability in bvFTD patients. A comparative examination of bvFTD in relation to other clinical subtypes of FTD and other types of dementia in general suggests that it’s the predominant atrophy of the frontal lobes along with the subsequent unique combination of cognitive and neuropsychiatric manifestations that account for the pronounced functional limitations observed in these individuals, even from the early stages of the disease.

The use of artificial intelligence (AI) applications in education has the potential to revolutionize the learning experience for international students, who face unique challenges when studying in a foreign country. This paper explores various examples of AI applications in education and their potential impact on international students. AI applications such as personalized learning experiences, adaptive testing, predictive analytics, and chatbots for learning and research are examined for their potential to improve learning efficiency and provide customized education support. It also explores the significant risks and limitations associated with AI technologies, such as privacy, cultural differences, language proficiency, and ethical implications. To maximize the potential benefits of AI applications in higher education, it is crucial to implement appropriate safeguards and regulations. This paper provides a starting point for research on the potential impact of artificial intelligence on international students’ educational experiences and how AI may be integrated into educational administration and learning processes.

Tissue programmed death ligand-1 (PD-L1) protein expression is predictive of immune checkpoint inhibitor (ICI) benefit. However, tissue PD-L1 can be fraught with tissue acquisition and heterogeneity limitations. Plasma testing can overcome these limitations. However, the overall survival (OS) predictive benefit of plasma PD-L1 assays have not been well characterized. Patients with stage IV non-small cell lung cancer (NSCLC) and plasma cfRNA PD-L1 by PCR expression were identified and assessed for OS. 16 patients treated with front-line ICI-based regimens were assessed and represented a real-world patient population with over half with a performance status of 2 or greater. 10 contemporaneous patients at the same institution treated with chemotherapy alone were also identified and assessed. With a median follow-up of 33 months, median OS was 13 months with a 30% 3-year OS for the ICI treated patients compared to a median OS of 3 months and a 10% 3-year OS for those treated with chemotherapy alone. Comparative log-rank test p-value = 0.014 and a hazard ratio 0.376 (95%-CI 0.134-1.057). Plasma cfRNA PD-L1 was associated with a statistically significant survival benefit from ICI-based treatment compared to chemotherapy in the first line treatment of a real-world patient population of advanced NSCLC.

Non-small-cell lung cancer (NSCLC) is the second most common cancer worldwide, resulting in 1.8 million deaths/year. Most of the patients are diagnosed with a metastatic disease. Central Nervous System is one of the major metastatic sites. Brain metastases are associated with severe neurological symptoms, shorter survival and worst clinical outcomes. Brain radiotherapy and systemic oncological therapies are currently used for controlling both cancer progression and neurological symptoms. Brain radiotherapy includes stereotactic brain ablative radiotherapy (SBRT) or whole brain radiotherapy (WBRT). SBRT is applied for single or multiple (≤ 4) small lesions (&lt; 3 cm), while WBRT represents the best treatment choice in case of multiple and large brain metastases. In both cases radiotherapy application can represent an overtreatment causing severe toxicities without achieving a significant clinical benefit. So far, some scores have been proposed to define the potential clinical benefits derived from brain radiotherapy. However, most of them are not well validated into clinical practice. In this article, by presenting a clinical case of a patient with advanced NSCLC carrying a BRAFV600E mutation and brain metastases, we review the variables as well as the potential applicable scores to be considered in order to predict clinical outcomes and benefits from brain radiotherapy in patients with NSCLC and brain metastases.

BACKGROUND Epidemiological sciences have been evolving at an exponential rate paralleled only by the comparable growth within the discipline of data science. Digital epidemiological studies are playing a vital role in medical science analytics for the past few decades. To date, there are no published attempts at deploying the use of real-time analytics in connection with the disciplines of Dentistry or Medicine. AIMS AND OBJECTIVES We deployed a real-time statistical analysis in connection with topics in Dental Anatomy and Dental Pathology represented by the maxillary sinus, posterior maxillary teeth, related oral pathology. The purpose is to infer the digital epidemiology based on a continuous stream of raw data retrieved from Google Trends database. MATERIALS AND METHODS Statistical analysis was carried out via Microsoft Excel 2016 and SPSS version 24. Google Trends database was used to retrieve data for digital epidemiology. Real-time analytics and the statistical inference were based on encoding a programming script using Python high-level programming language. A systematic review of the literature was carried out via PubMed-NCBI, the Cochrane Library, and Elsevier databases. RESULTS The comprehensive review of databases of the literature, based on specific keywords search, yielded 491813 published studies. These were distributed as 488884 (PubMed-NCBI), 1611 (the Cochrane Library), and 1318 (Elsevier). However, there was no single study attempting real-time analytics. Nevertheless, we succeeded in achieving an automated real-time stream of data accompanied by a statistical inference based on data extrapolated from Google Trends. CONCLUSION Real-time analytics are of considerable impact when implemented in biological and life sciences as they will tremendously reduce the required resources for research. Predictive analytics, based on artificial neural networks and machine learning algorithms, can be the next step to be deployed in continuation of the real-time systems to prognosticate changes in the temporal trends and the digital epidemiology of phenomena of interest.

Non-small-cell lung cancer (NSCLC) is the second most common cancer worldwide, resulting in 1.8 million deaths/year. Most of the patients are diagnosed with a metastatic disease. Central Nervous System is one of the major metastatic sites. Brain metastases are associated with severe neurological symptoms, shorter survival and worst clinical outcomes. Brain radiotherapy and systemic oncological therapies are currently used for controlling both cancer progression and neurological symptoms. Brain radiotherapy includes stereotactic brain ablative radiotherapy (SBRT) or whole brain radiotherapy (WBRT). SBRT is applied for single or multiple (≤ 4) small lesions (&lt; 3 cm), while WBRT represents the best treatment choice in case of multiple and large brain metastases. In both cases radiotherapy application can represent an overtreatment causing severe toxicities without achieving a significant clinical benefit. So far, some scores have been proposed to define the potential clinical benefits derived from brain radiotherapy. However, most of them are not well validated into clinical practice. In this article, by presenting a clinical case of a patient with advanced NSCLC carrying a BRAFV600E mutation and brain metastases, we review the variables as well as the potential applicable scores to be considered in order to predict clinical outcomes and benefits from brain radiotherapy in patients with NSCLC and brain metastases.

The study is based on the notion that big data predictive analytics is important for developing strategic alliances performance of companies. this study investigates the relationship between big data predictive analytics, big data culture, and competitive strategies 'techniques were adopted, such as descriptive statistics, correlation,regression, etc. using SPSS and SmartPLS statistical software. Hypotheses were tested with bootstrapped analysis using SEM (through SmartPLS). The study developed a structural equation model by using the SEM analysis. The results of the SEM analysis suggested the hypothesized model of the study was valid. The results supported all the hypotheses of the study.Through empirical analysis, demonstrated the conclusion is that the big data predictive analytics has a positive and significant relationship with strategic alliance performance

This research explores the transformative impact of artificial intelligence (AI) on personalizing marketing campaigns, highlighting how AI technologies are reshaping modern marketing practices. AI tools such as machine learning, natural language processing (NLP), predictive analytics, deep learning, and computer vision are integral to enhancing customer engagement and optimizing marketing strategies. Machine learning algorithms enable precise customer segmentation and personalized recommendations, leading to more targeted and effective marketing messages. NLP facilitates the analysis of customer sentiment and enhances communication through advanced language processing and AI-powered chatbots. Predictive analytics and deep learning provide businesses with the capability to forecast customer behaviors and recognize complex data patterns, further refining marketing efforts. Computer vision technology contributes to personalization through innovations like visual search and augmented reality, creating immersive customer experiences. Despite the numerous benefits, the adoption of AI in marketing presents several challenges. Data privacy and security concerns, integration complexities, and the potential for algorithmic bias are critical issues that need to be addressed. Ethical considerations, including transparency and fairness in data usage, are also paramount to maintaining customer trust and ensuring responsible AI application. The future of AI in marketing promises continued advancements, with trends such as hyper-personalization and enhanced integration with technologies like the Internet of Things and voice search expected to drive further innovation. Overall, AI significantly enhances marketing effectiveness by offering tailored solutions and strategic insights while necessitating a thoughtful approach to ethical and practical challenges.

The Ames/quantitative structure-activity relationship (QSAR) International Challenge Projects held during 2014–2017 and 2020–2022, evaluated the performance of various predictive models. Despite the significant insights gained, the rules allowing participants to select prediction targets introduced ambiguity in model performance evaluation. This reanalysis identified the highest-performing prediction model, assuming a 100% coverage rate (COV) for all prediction target compounds and an estimated performance variation due to changes in COV. All models from both projects were evaluated using balance accuracy (BA), Matthews correlation coefficient (MCC), F1 Score (F1), and the first principal component (PC1). After normalizing the COV, a correlation analysis with these indicators was conducted, and the evaluation index for all prediction models in terms of the COV was estimated. In total, 109 models, the highest estimated BA (76.9) at 100% COV was MMI-VOTE1, reported by Meiji Pharmaceutical University (MPU). The best models for MCC, F1, and PC1 were all MMI-STK1, also reported by MPU. All models reported by MPU ranked in the top four. MMI-STK1 was estimated to have F1 scores of 59.2, 61.5, and 63.1 at COV levels of 90%, 60%, and 30%, respectively. These findings highlight the current state and potential of the Ames prediction technology.

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.

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.

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.

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 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.

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.

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.

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.

Immune checkpoint blockade (ICB) has revolutionized the prognosis of several advanced-stage solid tumors. However, its success has been far more limited in hematological malignancies and is mostly restricted to classical Hodgkin lymphoma (cHL) and primary mediastinal B cell lymphoma (PMBCL). In patients with non-Hodgkin lymphoma (NHL), response to PD-1/PD-L1 ICB monotherapy has been relatively limited, although some subtypes are more sensitive than others. Numerous predictive biomarkers have been investigated in solid malignancies, such as PD-L1 expression, tumor mutational burden (TMB) and microsatellite instability (MSI), among others. This case-illustrated review aims to appraise the current knowledge on PD-1/PD-L1 ICB efficacy in lymphoid malignancies, when used either as monotherapy or combined with other agents, and describes potential biomarkers of response in this specific setting.

Monitoring volatile organic compounds (VOCs) places a crucial role in environmental pollutants control and indoor air quality. In this study, a metal-oxide (MOx) sensor detector (used in a commercially available monitor) was employed to delineate the composition of air containing three common VOCs (ethanol, acetone and hexane) under various concentrations. Experiments with a single component and double components were conducted to investigate how the solvents interact with the metal oxide sensor. The experimental results revealed that the affinity between VOC and sensor was in the following order: acetone > ethanol > n-hexane. A mathematical model was developed, based on the experimental findings and data analysis, to convert the output resistance value of the sensor into concentration values, which in turn can be used to calculate a VOC-based air quality index. Empirical equations were established based on inferences of vapor composition versus resistance trends, and on an approach of using original and diluted air samples to generate two sets of resistance data per sample. The calibration of numerous model parameters allowed matching simulated curves to measured data. As such, the predictive mathematical model enabled quantifying not only the total concentration of sensed VOCs, but also estimating the VOC composition. This first attempt to obtain semi-quantitative data from a single MOx sensor, despite remaining selectivity challenges, is aimed at expanding the capability of mobile air pollutants monitoring devices.

Although decision making strategy based on clinico-histopathological criteria is well established, renal cell carcinoma (RCC) represents a spectrum of biological ecosystems characterized by distinct genetic and molecular alterations, diverse clinical courses and potential specific therapeutic vulnerabilities. Given the plethora of drugs available, the subtype-tailored treatment to RCC subtype holds the potential to improve patient outcome, shrinking treatment-related morbidity and cost. The emerging knowledge of the molecular taxonomy of RCC is evolving, whilst the antiangiogenic and immunotherapy landscape maintained and reinforced their potential. Although several prognostic factors of survival in patients with RCC have been described, no reliable predictive biomarkers of treatment individual sensitivity or resistance have been identified. In this review, we summarize the available evidence able to prompt more precise and individualized patient selection in well-designed clinical trials, covering the unmet need of medical choices in the era of next-generation anti-angiogenesis and immunotherapy.

Machine learning (ML) techniques can help predict survival among cancer patients and might help with a timely integration in palliative care. We aim to explore the importance of subjective variables self-reported and collected via electronic patient reported outcome measure (ePROM) for survival prediction. A total of 256 advanced cancer patients met the eligible criteria. We analyzed objective variables collected from electronic health records, subjective variables collected via ePROM and all clinical variables combined. We used logistic regression (LR), decision trees, and random forests to predict 1-year mortality. Receiver operating characteristic (ROC) curve - area under the curve (AUC) and the ML models feature importance were analyzed. The performance of all variables for predictions (LR reaches 0.80 [ROC AUC] and 0.72 [F1 Score]) does not improve over the performance of only clinical non-patient reported outcome (non-PRO) variables (LR reaches 0.81 [ROC AUC] and 0.72 [F1 Score]). Our study indicates that patient-reported outcome (PRO) variables, which measure subjective burden, cannot be reliably used to predict survival. Further research in this area is needed to clarify the role of self-reported patient's burden and mortality prediction via ML.

In this study, a novel two-layer control scheme aimed at enhancing the dynamic performance of a nonlinear vehicle through the utilization of an optimal control approach grounded in predictive control principles is presented. The first layer of our control system focuses on the computation of an optimized rotational torque that ensures lateral dynamic stability. This torque is subsequently translated into differential forces acting on the wheels, employing the inverse tire model to derive the desired longitudinal slips. These slip values are then transmitted to the second layer of our control system. In the second layer, the electric motors associated with the vehicle's wheels dynamically adjust the input torque to accurately track the desired slip, thereby ensuring the overall stability of the electric vehicle. In view of the paramount importance of energy consumption in electric vehicles, we adopt optimal control strategies to substantially minimize battery utilization. To this end, careful selection of appropriate weighting coefficients in the control laws enables us to maintain the electric motors within their permissible operational range while simultaneously minimizing battery energy consumption for desired slip tracking. Extensive simulation results validate the effectiveness of our proposed control system in proficiently managing nonlinear effects and safeguarding the vehicle's stability.

In the realm of modern drug discovery, the integration of chemoinformatics and quantitative structure-activity relationship (QSAR) modeling has emerged as a formidable alliance, enabling researchers to harness the vast potential of machine learning (ML) techniques for predictive molecular design and analysis. This review delves into the fundamental aspects of chemoinformatics, elucidating the intricate nature of chemical data and the crucial role of molecular descriptors in unveiling the underlying molecular properties. Molecular descriptors, including 2D fingerprints and topological indices, in conjunction with the structural-activity relationships (SARs), play a pivotal role in unlocking the pathway to small-molecule drug discovery. Technical intricacies of developing robust ML-QSAR models, including feature selection, model validation, and performance evaluation, are discussed herewith. Various ML algorithms, such as regression analysis and support vector machines, are showcased in the text for their ability to predict and comprehend the relationships between molecular structures and biological activities. This review serves as a comprehensive guide for researchers, providing an understanding of the synergy between chemoinformatics, QSAR, and ML. By embracing these cutting-edge technologies, predictive molecular analysis holds promise for expediting the discovery of novel therapeutic agents in the pharmaceutical sciences.

In response to increasing urbanization and the need for infrastructure resilient to natural hazards, this study introduces an AI-driven predictive model designed to assess the risk of soil liquefaction. Utilizing advanced ensemble machine learning techniques, the model integrates geotechnical and geographical data to accurately predict the potential for soil liquefaction in urban areas, with a specific focus on Yokohama, Japan. This methodology leverages comprehensive datasets from geological surveys and seismic activity to enhance urban planning and infrastructure development in smart cities. The primary outputs include detailed soil liquefaction risk maps that are essential for effective urban risk management. These maps support urban planners and engineers in making informed decisions, prioritizing safety, and promoting sustainability. The model employs a robust combination of neural networks and gradient boosting decision trees to analyze and predict data points, assessing soil susceptibility to liquefaction during seismic events. Notably, the model achieves high accuracy in predicting soil classifications and N-values, which are critical for evaluating soil liquefaction risk. Validation against an extensive dataset from geotechnical surveys confirms the model’s practical effectiveness. Moreover, the results highlight the transformative potential of AI in enhancing geotechnical risk assessments and improving the resilience of urban areas against natural hazards.

Carbon Capture and Storage (CCS) stands as a pivotal technological stride toward a sustainable future, with the practice of injecting supercritical CO2 into subsurface formations having already been an established practice for enhanced oil recovery operations. The overarching objective of CCS is to protract the operational viability and sustainability of platforms and oilfields, thereby facilitating a seamless transition towards sustainable practices. This study introduces a comprehensive framework for optimizing well placements in CCS operations, employing a derivative-free method known as Bayesian optimization. The development plan is tailored for scenarios featuring aquifers devoid of flow boundaries, incorporating production wells tasked with controlling pressure buildup and injection wells dedicated to CO2 sequestration. Notably, the wells operate under group control, signifying predefined injection and production targets and constraints that must be adhered to throughout the project’s lifespan. As a result, the objective function remains invariant under specific permutations of the well locations. Our investigation delves into the efficacy of Bayesian optimization under the introduced permutation invariance. The results reveal that it demonstrates critical efficiency in handling the optimization task extremely fast. In essence, this study advocates for the efficacy of Bayesian optimization in the context of optimizing well placements for CCS operations, emphasizing its potential as a preferred methodology for enhancing sustainability in the energy sector.

Internet of Things (IoT) technologies can greatly benefit from machine learning techniques and Artificial Neural Networks for data mining and vice versa. In the agricultural field, this convergence could result in the development of smart farming systems suitable for use as decision support systems by peasant farmers. This work presents the design of a smart farming system for crop production, which is based on low-cost IoT sensors and popular data storage services and data analytics services on the Cloud. Moreover, a new data mining method exploiting climate data along with crop production data is proposed for the prediction of production volume from heterogeneous data sources. This method was initially validated using traditional machine learning techniques and open historical data of the northeast region of the state of Puebla, Mexico, which were collected from data sources from the National Water Commission and the Agri-food Information Service of the Mexican Government.

Background/aims: Prior research identified a significant association between heart disease and metabolic dysfunction-associated liver steatohepatitis (MASLD), but the mechanisms are unclear. This study aims to search predictive biomarkers for grade I left ventricular diastolic dysfunction (LVDD), an early stage of heart failure (HF), in type 2 diabetes mellitus (T2DM) patients. Methods: This single-center, prospective observational study screened 73 T2DM patients for grade 1 LVDD and MASLD using 2D echocardiography, tissue analysis, spectral color Doppler, and Fibromax. Results: The study analyzed 50 patients (mean age 58±11.3 years) with a median diabetes duration of 7 years, abdominal obesity (mean BMI 34.4±5.9 kg/m2), and a mean HbA1c of 7.9±1.5%. The prevalence of grade I LVDD, fibrosis, mild steatosis, moderate to severe liver steatosis, mild MASLD, and moderate MASLD was 54%, 44%, 14%, 80%, 43%, and 34%, respectively. Regression analysis revealed that grade 1 LVDD was positively associated with age, Fibrotest, ɑ2-macroglobulin, epicardiac adipose tissue (EAT), and negatively associated with lateral s`, E wave, E/e`, E/A, medium E`, and septal e` (p&lt; 0.05 for all). ɑ2-macroglobulin &gt; 1.92 g/L (AUROC= 0.782, sensitivity 70.4%, specificity 81.2%) and fibrotest score &gt; 0.11 (AUROC 0.766, sensitivity 92.6%, specificity 56.2%) were significant predictors of grade I LVDD. Conclusion: HF is a multifaceted disorder associated with multisystem organ damage, including nonalcoholic MASLD. Although the underlying mechanisms remain unclear, innovative non-invasive biomarkers, such as ɑ2-macroglobulin or fibrotest, could concurrently indicate liver stiffness and the likelihood of grade I LVDD, an early, asymptomatic HF stage in T2DM patients.

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.

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.

Heart failure is associated with a significant mortality rate, and an elevated prevalence of this condition has been noted among hypertensive patients. The identification of predictive factors for heart failure progression in hypertensive individuals is crucial for early intervention and improved patient outcomes. In this study, we aimed to identify these predictive factors utilizing medical history data for hypertension patients. Specifically, we focused solely on utilizing medical data preceding the diagnosis of hypertension to enable patients to anticipate the onset of potential heart failure at the time of hypertension diagnosis. Age-specific and ICD system-specific predictive factors were identified utilizing the MIMIC-IV database through the application of two analytical approaches: chi-square tests and XGBoost modeling. Our findings reveal 21 overall predictive factors, encompassing conditions such as atrial fibrillation, the use of anticoagulants, kidney failure, obstructive pulmonary disease, and anemia. These factors were assessed through a comprehensive review of the existing literature. We anticipate that the results will offer valuable insights for the risk assessment of heart failure in hypertensive patients.

The Mining Industry has changed significantly in recent decades with the introduction of advanced technologies such as Artificial Intelligence (AI) and Machine Learning (ML). These innovations contribute to the creation of expert systems that help in optimizing processes, increasing the safety and sustainability of operations. This article is a literature review of modern AI and ML methods and technologies used in the Mining Industry. Discusses various intelligent and expert systems used to improve productivity, reduce operating costs, improve occupational safety, environmental sustainability, machine automation, predictive analytics, quality monitoring and control, and inventory and logistics management. The advantages and disadvantages of different approaches are analyzed, as well as their potential impact on the future of the Mining Industry. The review highlights the importance of integrating AI and ML into mining processes to achieve more efficient and safer solutions.

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. To address these issues, a robust UKF-MPC-based longitudinal control algorithm for the platoon 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 compensation is 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. Simulation results show that the robust UKF-MPC longitudinal controller performs better compared to the MPC and UKF-MPC longitudinal controllers. When facing the communication delay and packet loss problems, the robust UKF-MPC longitudinal controller has higher control accuracy and less performance degradation. It has strong robustness and stability.

The life cycle of a microgrid covers all the stages from idea to implementation, exploitation until its end of life, but with a lifespan of around 25 years. Covering them usually requires several software tools, which can make integration of results from different stages very difficult and may imply costs hard to estimate from the beginning of a project. This paper proposes a single platform of four modules developed in Matlab to assist all the processes a microgrid passes during its lifetime. The authors detail the architecture, functions and the development of the platform, either by using existing tools available in Matlab, or by developing new ones and designing new user interfaces linked with scripts based on its complex mathematical libraries. A proof-of-concept for this platform was presented by applying the life-cycle assessment process on a real-case study, a microgrid consisting in a photovoltaic plant, an office building as consumer and energy storage units.

COVID-19 has substantially influenced healthcare systems, requiring early prognosis for innovative therapies and optimal results, especially in individuals with comorbidities. Healthcare practitioners have used AI systems for investigating, anticipating, and predicting diseases, through means including medication development, clinical trial analysis, and pandemic forecasting. This study proposes the use of AI to predict disease severity in terms of hospital mortality among COVID-19 patients. Methodology: A cross-sectional study was conducted the approval from the Research Ethics Committee of King Abdulaziz University (KAU), Saudi Arabia. The study used sequential sampling approaches to include 50 Real-Time Polymerase Chain Reaction (RT-PCR) positive COVID-19 patients from KAU's coronavirus isolation wards. A pre-designed form was used to collect each patient's demographic information, including age and gender, signs and symptoms, illness severity (mild, moderate, severe), and laboratory findings. Furthermore, the length of the hospital stay and the result, whether the patient recovered or died, were reported. Results: The study involved 50 patients with varying degrees of disease severity, most of whom suffered from fever, fatigue, cough, sore throat, and diarrhoea. Laboratory analysis of COVID-19 patients showed increased white blood cell and platelet counts, with C-reactive protein levels above normal. Elevated LDH levels indicated possible tissue damage, while ferritin levels were elevated. Other enzymes were in the normal range, but bilirubin levels were slightly elevated. Overall, the patient's lab results indicated inflammation and possible blood clot formation. The study evaluated the predictive accuracy for outcomes and mortality of COVID-19 patients based on factors such as CRP, LDH, Ferritin, ALP, Bilirubin, D-dimers, and hospital stay (p-value ≤0.05). The predictive accuracy mortality of patients with COVID-19 using AI showed Hospital stay, D-Dimers ALP, Bilirubin, LDH, CRP, and Ferritin significantly affected hospital mortality. (p ≤ 0.0001). Conclusion: Artificial Intelligence is crucial for identifying early coronavirus infections and monitoring patient conditions. It improves treatment consistency and decision-making via the development of algorithms. AI can track the crisis at various scales, facilitate research, and aid in developing treatment regimens, prevention strategies, and drugs and vaccines. It also aids in monitoring health and facilitating research on the virus.

This research article aims to examine the factors that influence behavioral intentions using the traffic accident claim system in Indonesia. This research uses the Theory of Planned Behavior, the Model of Technology Acceptance, and the Integrated Theory of Technology Acceptance and Use, as well as using the Structural Equation Modeling-Partial Least Squares. The questionnaire was distributed to 580 respondents from three institutions – police, hospitals, and state-owned insurance companies – using quota sampling techniques. The results showed that TPB, TAM, and UTAUT had a significant influence in encouraging behavioral intentions using the traffic accident claim system. Further, the study found that 21st-century digital skills have a moderate role in the impact of acceptance models, planned behavior, and technology use on behavioral intent. Although the study was conducted in Indonesia and is limited to three institutions, it provides strategic guidance for policymakers to improve the use of traffic accident claim systems and reduce Road Traffic Accidents. Further research is recommended to explore from different angles and focus on service providers/operators of traffic accident claim systems to refine the findings of this study. This study contributes to the literature by investigating the factors that influence behavioral intentions using traffic accident claim systems and has a high degree of accuracy of answers from the point of view of traffic safety officers.

Background: Machine learning can analyze vast amounts of data and make predictions for events in the future. Our group created machine learning models for vital sign predictions. To transport the information of these predictions without numbers and numerical values and make them easily usable for human caregivers, we aimed to integrate them into the Philips Visual-Patient-avatar, an avatar-based visualization of patient monitoring. Methods: We conducted a computer-based simulation study with 70 participants in three European university hospitals. We validated the vital sign prediction visualizations by testing their identification by anesthesiologists and intensivists. Each prediction visualization consisted of a condition (e.g., blood pressure low) and an urgency (a visual indication of the timespan in which the condition is expected to occur). To obtain qualitative user feedback, we also conducted standardised interviews and derived statements that participants later rated in an online survey. Results: The mixed logistic regression model showed 77.9% (95%CI 73.2-82.0%) correct identification of prediction visualizations (i.e. condition and urgency both correctly identified) and 93.8% (95%CI 93.7-93.8%) for conditions only (i.e. without considering urgencies). Forty-nine of 70 participants completed the online survey. The online survey participants agreed that the prediction visualizations were fun to use (32/49, 65.3%), and that they could imagine working with them in the future (30/49, 61.2%). They also agreed that identifying the urgencies was difficult (32/49, 65.3%). Conclusions: This study found that care providers correctly identified >90% of the conditions (i.e. without considering urgencies). The accuracy of identification decreased when considering urgencies in addition to conditions. Therefore, in future development of the technology, we will focus on either only displaying conditions (without urgencies) or improve the visualizations of urgency to enhance usability for human users.

The motion of Unmanned Surface Vehicles (USVs) is frequently disturbed by the ocean wind, wave and current. A poorly designed controller will lead to failures and even safety problems during actual navigation. In order to obtain satisfied control performance of the motion for the USVs, a Model Predictive Control (MPC) based on improved Nonlinear Disturbance Observer (NDO) is proposed. Firstly, the USV model is approximately linearized and MPC is designed for the multivariable system with constraints. In order to compensate the influence of disturbances, an improved NDO is designed, with which the calculation time for the MPC saved a lot. Finally, comparison experiments are conducted between the MPC with NDO and the MPC with improved NDO, and the results show that they have similar performance to the USVs. However, the proposed method has less parameter to be tuned and it is much more time-saving compared to the MPC with traditional NDO.

A self-protective metal/ liquid microcapsule composite plating coating has been prepared in our previous research. The release speed of liquid core material from microcapsules is crucial for the coating surface properties. The aim of this paper is to study the permeability rule of liquid microcapsules within composite coatings. According to permeability experimental data’s linear characteristics, multiple linear regression is firstly used to set up permeability model of liquid microcapsules. The results show that a reliable mathematical model about membrane porosity, viscosity of core material and membrane thickness is established under ambient temperature and moisture. Meanwhile, the predictive capacity and reliability of this model are analyzed carefully.

Precision Agriculture is the ability to handle variations in productivity within a field and maximize financial return, optimize resource utilization and minimize impact of the environment. It is also the process of automated data collection, cloud storage and utilization to build robust decision support system. In case of Ethiopia, due to poor communication infrastructure coverage and absence of the state-of-the-art technology in the agriculture sector, implementing precision farming system is a challenging tasks in the domain area. In this work, we proposed a fusion of multiple sensors using IOT and IIOT infrastructure to collect critical data from farming fields to develop precision farming facility for decision makers. The main purpose was to monitor weather variability, automate irrigation process, extract critical soil properties. In addition, we have used time series data collected from sensor devices to build forecasting model. Fusion of multiple IoT device provide a mechanism in the agriculture area to deal with real-time monitoring of crops. It is cost-effective technology and required low-energy with edge computing sensor device. We employed the Message Queuing Telemetry Transport (MQTT) protocol to connect the Industrial/Internet of Things (I/IoT) to the cloud server. The communication between system user and sensor device has been done via cloud using Node-RED platform, web android APIs. The cloud-based Eco-system allows us to aggregate, visualize, and analyze live streams output from each sensor in real-time manner. Finally, we have built time series forecasting model using records collected by each sensor device. Using the multi-variate time series data-set, we have obtained about 99 forecasting accuracy on some important variables. Finally, we have developed mobile and web-based application for the end-user to monitor the proposed system remotely.

There is immense variability in the postharvest quality of Hass avocados. However, there is a lack of knowledge to guaranteeing the robustness of fruit with consistent quality. The aims of this work were to develop a multivariate methodology for evaluating the postharvest quality of avocado and to determine predictive quality markers to manage fruit quality. Fruit samples produced under different nutrient management, elevation, date-to-harvest, and growing-cycle conditions were analyzed. The results highlighted soil and weather differences among orchards. Nutrient management practices based on index balancing in some samples increased both productivity and the fruit size. High variability was observed in the dry matter related to the age of the fruit at harvest. Ripening heterogeneity was very large in low-elevation orchards where the fruit was picked relatively early. High flesh mineral contents delayed fruit ripening. At low growing temperatures, more oleic and linoleic acids were present in fruits. The sensory texture and taste descriptors were affected by the fruit age and related to the flesh composition. Logistic, PLS-DA, and biplot models effectively represented the variabilities in the ripening pattern, composition, and sensory profile of avocado fruits and allowed the samples to be grouped according to the internal fruit quality.

Background Content marketing is increasingly important for online branding. Brand popularity can be more easily determined online than sales-based measures but is not yet well-explained from a content marketing perspective. Promising predictors are open data syndication policies, connectivity to e-commerce platforms, product reviews, data health, and the depth and width of a brands product portfolio. A predictive content marketing model can help brand owners to understand their e-commerce potential. Methods We used brand popularity (Brand Popularity Rank) and catalog data in combination with product reviews from an independent content aggregator. For all datasets, we selected the overlapping dataset for brand popularity and brand reviews based on a period of 90 days from June 10, 2022, till September 24, 2022 (n = 333 brands). Backward stepwise multiple linear regression was used to develop a predictive content marketing model of the Brand Popularity Rank. Results Through stepwise backward multiple linear regression five highly significant (p < 0.01) predictive factors for brand rank are selected in our content marketing model: the brand’s data syndication policy, the number of connected e-commerce platforms, a brand’s number of products, its number of products per category, and the number of product categories in which it is active. Our model explains 78% of the variance of Brand Popularity Rank and has a good and highly significant fit: F (5, 327) = 233.5, p < 0.00001. Conclusions We conclude that a content marketing model can adequately predict a Brand Popularity Rank based on online popularity. In this model an open content syndication policy, more connected e-commerce platforms, and catalog size, i.e., presence in more categories and more products per category are each related to a better (lower) Brand Popularity Rank score.

Osteosarcoma (OSA) is the most common primary malignant bone tumor. More than 40% of patients with OSA have poor prognoses. We aimed to discover a biomarker for patient stratification and therapeutic targets for these high-risk patients. Using Single Sample Gene Set Enrichment Analysis (ssGSEA) and univariate Cox analysis, six hallmarks were identified as significant prognostic factors for overall survival (OS). Three were selected to construct a multivariate Cox model. Then, WGCNA, univariate Cox regression, Kaplan-Meier (KM) survival analyses, and multivariate Cox analyses were combined to filter promising candidates and establish a seven-gene signature to predict OS, whose prognostic value was validated internally and externally. Subsequently, Differential Expression Analysis was conducted between high- and low-risk patients, and the Robust Rank Aggregation algorithm was used to determine the robust DEGs. Metascape was used to perform pathway and process enrichment analyses as well as construct protein-protein interaction (PPI) networks. Finally, RPS28 was identified as an independent risk factor by using univariate and multivariate Cox regression, which was preliminarily validated as a promising therapeutic target by using RNA interference. In conclusion, we might contribute to optimizing risk stratification and an excellent therapeutic target for high-risk patients with OSA.

The efficacy of weed management depends on the correct control timing according to the seedling emergence dynamics. Since soil temperature and soil moisture are two main factors that determine weed germination, the hydrothermal time model can be used to predict their emergence. The aim of this study was to estimate the base temperature (Tb) and base water potential (Ψb) for germination of Chenopodium album, Amaranthus retroflexus, Setaria pumila and Panicum capillare collected from fields in continental Croatia and then to compare these values with those of Italian populations embedded in the AlertInf model. Germination tests were performed at seven constant temperatures (ranging from 4 to 27°C) and eight water potentials (0.00 to - 1.00 MPa). Estimated Tb and Ψb were 3.4°C, -1.38 MPa for C. album, 13.9°C, -0.36 MPa for A. retroflexus, 6.6°C, -0.71 MPa for S. pumila and 11.0°C, -0.87 MPa for P. capillare, respectively. According to the criterion of overlap of the 95% confidence intervals, only Tb of C. album, and Ψb of A. retroflexus were similar between Croatian and Italian populations. Further field experiments should be conducted in the Croatian field to monitor weed emergence patterns of C. album and to calibrate the AlerInf equation parameters.

Driving simulators are widely used for understanding human-machine interaction, driver behavior and in driver training. The effectiveness of simulators in these process depends largely on their ability to generate realistic motion cues. Though the conventional filter-based motion cueing strategies have provided reasonable results, these methods suffer from poor workspace management. To address this issue, linear MPC-based strategies have been applied in the past. However, since the kinematics of the motion platform itself is non-linear and the required motion varies with the driving conditions, this approach tends to produce sub-optimal results. This paper presents a nonlinear MPC-based algorithm which incorporates the nonlinear kinematics of the Stewart platform within the MPC algorithm in order to increase the cueing fidelity and utilize maximum workspace. Further, adaptive weights-based tuning is used to smoothen the movement of the platform towards its physical limits. Full-track simulations were carried out and performance indicators were defined to objectively compare the response of the proposed algorithm with classical washout filter and linear MPC-based algorithms. The results indicate a better reference tracking with lower root mean square error and higher shape correlation for the proposed algorithm. Lastly, the effect of the adaptive weights-based tuning was also observed in the form of smoother actuator movements and better workspace utilization.

Breast Cancer diagnosis is one of the most studied problems in the medical domain. In the medical domain, cancer diagnosis has been studied extensively which instantiates the need of early prediction of cancer disease. For obtaining advance prediction, health records are exploited and given as input to an automated system. This paper focuses on constructing an automated system by employing deep learning based recurrent neural network models. A stacked GRU-LSTM-BRNN is proposed in this paper that accepts health records of a patient for determining possibility of being affected by breast cancer. Proposed model is compared against other baseline classifiers such as stacked Simple-RNN model, stacked LSTM-RNN model, stacked GRU-RNN model. Comparative results obtained in this study indicate that stacked GRU-LSTM-BRNN yield better classification performance for predictions related to breast cancer disease.

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.

This paper is an attempt to forecast the potential application of Digital Twin in an industrial environment by adopting scenario analysis as part of technology monitoring. In recent years Digital Twin has become one of the most emerging topics in both the tech industry and academia. This field is the latest addition to industry 4.0. It has paved a great growth opportunity in the fields of Healthcare, manufacturing, and smart city areas. The Digital twin can be defined as mirroring the physical entities into a virtual environment where the status, health, and control of these entities can be monitored and controlled. It is a field where Artificial intelligence and the Internet of Things play a major role in the handshake between the two environments. In this paper we have done a thorough analysis to find out the possible future outcome of this technology in the manufacturing industry from the perspective of our fictious company. These scenarios expose various challenges and opportunities our organization may face in our future endeavour.

Neutrophil to lymphocyte ratio (NLR) is a promising predictive and prognostic factor in breast cancer. We investigated its ability to predict disease-free survival (DFS) and overall survival (OS) in patients with luminal A or luminal B-HER2-negative breast cancer who received neoadjuvant chemotherapy (NACT). Pre-treatment complete blood cell counts from 168 consecutive patients with luminal breast cancer were evaluated to assess NLR. The study population was stratified into NLRlow or NLRhigh according to a cut-off value established by receiving operator curve (ROC) analysis. Data on additional pre- and post-treatment clinical-pathological characteristics were also collected. Kaplan-Meier curves, log-rank tests, and Cox proportional hazards models were used for statistical analyses. Patients with pre-treatment NLRlow showed a significantly shorter DFS (HR 6.97, 95% CI 1.65-10.55, p= 0.002) and OS (HR 7.79, 95% CI 1.25-15.07, p= 0.021) compared to those with NLRhigh. Non-ductal histology, luminal B subtype, and post-treatment Ki67≥ 14% were also associated with worse DFS (p= 0.016, p= 0.002, and p= 0.001, respectively). In multivariate analysis, luminal B subtype, post-treatment Ki67≥ 14%, and NLRlow remained independent prognostic factors for DFS, while only post-treatment Ki67≥ 14% and NLRlow affected OS. The present study provides evidence that pre-treatment NLRlow helps identify women at higher risk of recurrence and death among patients affected by luminal breast cancer treated with NACT.

The adoption of the Internet of Things (IoT) in supply chain operations has emerged as a pivotal advancement, offering the potential to significantly enhance operational efficiency, visibility, and responsiveness. This study explores the multifaceted impact of IoT integration in supply chains, emphasizing both the opportunities and challenges associated with its implementation. Through a combination of semi-structured interviews, case studies, and a comprehensive literature review, the research uncovers how IoT technologies contribute to improved asset tracking, real-time inventory management, and optimized logistics. Key benefits include enhanced operational efficiency, predictive maintenance capabilities, and better supply chain collaboration, which collectively lead to increased customer satisfaction and cost savings. However, the study also identifies several challenges, including the high costs of IoT infrastructure, difficulties in integrating new technologies with existing systems, and concerns over data security and privacy. These challenges pose significant barriers to adoption, particularly for smaller organizations. Despite these obstacles, the study highlights the substantial opportunities presented by IoT, such as fostering innovation, developing new business models, and enhancing supply chain resilience. The findings suggest that while the path to successful IoT adoption may be complex and resource-intensive, the potential benefits make it a valuable investment for organizations seeking to remain competitive in a rapidly evolving market. Addressing the identified challenges while leveraging the advantages of IoT will be crucial for companies aiming to optimize their supply chain operations and achieve long-term success.

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.

Novel drugs profoundly changed the outcomes in CLL patients and traditional prognostic/predictive factors that were delineated in the era of chemo-immunotherapy need to be validated in the contest of these new targeted therapies. Currently, the most important prognostic genetic biomarkers are immunoglobulin heavy chain variable (IGHV) mutational status, genetic aberrations including del(17p)/TP53 abnormalities and the complex karyotype. In this review we discuss the prognostic/predictive role of these genetic markers in relation to novel treatments. Moreover, we present and discuss the new score systems that were elaborated and validated in the era of new drugs. Given the deeper responses obtained with small molecules, new prognostic/predictive markers, including measurable residual disease, and validated prognostic scores could possibly be incorporated into routine prognostic scores, to better identify “very-high” CLL patients, who will need more effective treatments.

The most important prognostic factors in curatively treated prostate cancer at the initial diagnosis are T and N stage, histological subtype, Gleason score, initial PSA, PSA density and percentage of core biopsy positivity. Newer, but non-standard prognostic factors are urine PCA3 and genetic markers of prostate cancer. A simple, but seemingly underestimated standard test is serum Calcium (Ca) level, which has been shown by a previous study group to be a good predictor of lethal prostate cancer, but there is scarce evidence regarding the prognostic value of calcium levels at diagnosis. We aimed to determine whether a Ca level in the upper part of normal values has a prognostic value in curatively treated prostate cancer. We have retrospectively included 84 consecutive patients with prostate cancer, who underwent curative radiotherapy (primary or adjuvant; external beam RT with or without brachytherapy). We have performed statistical analysis of available prognostic factors. Ca level at diagnosis was found to be a statistically significant predictor of disease-free survival.

Here, we propose a prescriptive simulation model of a process operator’s decision-making assisted by artificial intelligence (AI) algorithm in a technical system control loop. We analyze situations fraught with a catastrophic threat that may cause unacceptable damage. Operators’ decision-making is interpreted in terms of a subjectively admissible probability of disaster and subjectively necessary reliability of its assessment. We distinguish four extreme decision-making strategies corresponding to different ratios between the above variables. An experiment simulating a process facility, an AI algorithm and operator's decision-making strategy was held. It showed that depending on the properties of a controlled process (the speed of hazard onset) and the AI algorithm characteristics (Type I and II error rate), each of such strategies or some intermediate strategy may prove to be more beneficial than others. The same approach is applicable to the identification and analysis of sustainability of strategies applied in real-life operating conditions, as well as to the development of a computer simulator to train operators to control hazardous technological processes using AI-generated advice.

Predictive maintenance (PdM) represents a transformative approach to ensuring the security and reliability of critical infrastructure systems. This proactive maintenance strategy leverages advanced data analytics, machine learning, and sensor technology to anticipate and address potential failures before they occur. By continuously monitoring the health of infrastructure components and analyzing performance data, predictive maintenance enables timely interventions, minimizes unplanned downtimes, and enhances overall system resilience. This paper explores the application of predictive maintenance in safeguarding critical infrastructure, focusing on its impact on security, operational efficiency, and cost-effectiveness. Case studies demonstrate how PdM has been successfully implemented across various sectors, including transportation, energy, and utilities, highlighting its role in mitigating risks and extending the lifespan of essential assets. The findings underscore the importance of integrating predictive maintenance into security strategies to protect vital infrastructure from emerging threats and ensure uninterrupted service delivery.

The traditional understanding of brain function has predominantly focused on chemical and electrical processes. However, new research in fruit fly (Drosophila) binocular vision reveals ultrafast photomechanical photoreceptor movements significantly enhance information processing, thereby impacting a fly's perception of its environment and behaviour. The coding advantages resulting from these mechanical processes suggest that similar physical motion-based coding strategies may affect neural communication ubiquitously. The theory of neural morphodynamics proposes that rapid biomechanical movements and microstructural changes at the level of neurons and synapses enhance the speed and efficiency of sensory information processing, intrinsic thoughts, and actions by regulating neural information in a phasic manner. We propose that morphodynamic information processing evolved to drive predictive coding, synchronising cognitive processes across neural networks to match the behavioural demands at hand effectively.

The development of Artificial Intelligence-based tools is having a big impact on industry. In this context, the maintenance operations of important assets and industrial resources are deeply changing both from a theoretical and a practical perspective, even in the field of ship propulsion systems. Namely, conventional preventive maintenance schedules audits and checks at fixed times by using statistics on component failures, but it can be improved by a predictive maintenance based on the real component health status, which is inspected by proper sensors. In this way, time and costs are saved. More in details, data-driven models, through Machine Learning (ML) algorithms, generate the expected values of monitored variables for comparison with real measurements coming from the asset, hence for a diagnosis based on the difference between expectations and observations. Then, a ML-based fault detection starts with the choice of the ML algorithm. This process is often not the consequence of an in-depth deep analysis of the different algorithms available in the literature. For that reason, the authors propose a simple procedure to support a first implementation stage of the so-called Condition Based Maintenance (CBM): a quick benchmarking of the most suitable ML algorithms useful for fault detection. The algorithms are compared by taking into account not only the algorithm output error, shown by the Mean Squared Error between predictions and data, but also the response time, which is a crucial variable for maintenance purpose.

This work presents a Fault-Tolerant Model Predictive Control (FTMPC) algorithm applied to a simulation model for sewer networks. The control system will aim to prevent contaminated water from escaping the network, especially during periods of heavy rainfall, that can cause combined sewer overflows (CSO), while maintaining the flow of water towards the wastewater treatment plant (WWTP) as close as possible to its nominal value. The main purpose of the work is to preserve the operation of the predictive controller as much as possible, in accordance with its operational objectives, when there may be anomalies affecting the elements of the control system, mainly sensors and actuators. Comparing the results obtained considering various types of faults, with situations of normal controlled operation and with the behavior of the sewer network when no control is applied, will allow some conclusions to be drawn at the end.

Throughout the Covid19 period, families were forced to stay indoors, adapting to online school-ing, remote work, and virtual social engagements, inevitably altering the dynamics within households. There is a notable increase in mental health challenges in terms of anxiety and de-pression in children and adolescents. This study intends to explore the psychosocial effects of the Covid-19 pandemic in Italian families adopting self- and proxy-report questionnaires on anxiety, anger, and health-related quality of life. The results showed that approximately 20% obtained a clinical anxiety score and only 10% obtained a clinical anger score. There was found a difference in the perception of the quality of life reported by the child and that perceived by the parent. The stepwise regression model showed that total anxiety scores were predicted by sex, quality of life scores from the parents' self-report version and total anger score. Another stepwise regression model identified physiological and social anxiety as the best predictors that impact the quality of life. Parental well-being actively influences the well-being of children, so it is fundamental to implement preventive programmes and promote child well-being providing parents the most adequate support possible.

The main challenges in oil platforms are how to define optimal setpoints and decision-making for controlling variables due to many existing dynamical production uncertainties while conceding safe operation and minimizing discharge to sea and atmosphere without killing plantwide inventory. A novel scheduling model to optimize the whole essential units of an oil platform production gathering topside and subsea variables is disclosed. A proper topside and subsea scheduling model enables and creates harmony between optimal production, supply chain, costs, and market dynamics, satisfying demands, environmental and operations constraints leading to stability. The interest of the present research lies in determining the optimal topside and subsea operational settings and decision-making, establishing maximum E&P performance and production control setpoints while predicting and manipulating reservoir lifespan and its revitalization. This objective is attained through a novel multiperiod large-scale model for the planning and operational production scheduling and model predictive control (MPC) in oil platforms complying with sustainability, profitability, platform design capacities, and offloading of oil and gas to supply chains or to pipeline exportation. The present model details heat and mass transfer, PVT, flow profiles along a planning horizon and can be used to any oil platform since comprises all the essential unit operations for oil, gas, CO₂, H₂S and water. The model maximizes the total oil production over any planning horizon. The model is versatile, and decision-making can be either linear or nonlinear but rather a MILP or LP as best choice on optimizing large-scale systems. If the model is applied with auto rescheduling on site within variable hours or minutes, it becomes a real-time optimization schedule approach. Due to its high-velocity performance and robustness, a novel multi-objective function strategy, acting as an LP generic plantwide MPC with industrial scope to maximize production while controlling the process is presented, and as an example is here used to control slug flow to avoid equipment trips and inventory instability, at the same time production is maximized. The output from the decision-making was compared to actual plant data, and the results proved compliance to the design capacity with process safety and sustainability. Comparing to official Brazil's government data for oil, the case study showed superiority to the same size platforms, like FPSOs P-75 and MV32, e.g., more than 101.5% more capacity to produce oil in beginning of campaign after first oil, and 10.5% during campaign. The present work indicates that: 1) the production of millions of barrels is being delayed or left aside; 2) not scheduling production harms the environment and diminish process safety; 3) not scheduling production can create stochastic supply chain deliveries instead of organizing it by deterministic offloading days; 4) scheduling is essential to manipulate, revitalize and monitor reservoir's pressure and content under uncertainty; 5) the oil platform can be automatic optimized by a plantwide MPC reducing human activity/dependency; 6) scheduling gives more transparency to stakeholders and contractors by forecasting business data and capability, and can design, develop or enable new businesses.

Lysophosphatidic acid (LPA) is a promising biomarker candidate to screen for ovarian cancer (OC) and potentially stratify and treat patients according to disease stage. LPA is known to target actin-binding protein gelsolin that is a key regulator of actin filament assembly. Previous studies have shown that the phosphate headgroup of LPA alone is inadequate to bind to the short chain of amino acids in gelsolin known as the PIP2-binding domain. Thus, the molecular-level detail of the mechanism of LPA binding is poorly understood. Here, we model LPA binding to the PIP2-binding domain of gelsolin in the gelsolin-actin complex through extensive ten microsecond atomistic molecular dynamics (MD) simulations. We predict that LPA binding causes a local conformational rearrangement due to LPA interactions with both gelsolin and actin residues. These conformational changes are a result of the amphipathic nature of LPA, where the anionic phosphate, polar glycerol and ester groups, and lipophilic aliphatic tail mediate LPA binding via charged electrostatic, hydrogen bonding, and van der Waals interactions. The negatively-charged LPA headgroup binds to the PIP2-binding domain of gelsolin-actin while its hydrophobic tail is inserted into actin, creating a strong LPA-insertion pocket that weakens the gelsolin–actin interface. The computed structure, dynamics, and energetics of the ternary gelsolin–LPA–actin complex confirms that a quantitative OC assay is possible based on LPA-triggered actin release from the gelsolin-actin complex.

Effective marketing decision-making benefits from a rigorous, data-driven process that systematically evaluates alternatives based on insights and analysis. This study develops and evaluates a 5-stage decision-making process model integrating marketing engineering principles aimed to optimize marketing decisions. An experiment randomized 150 participants into groups following either the proposed model or an unaided approach. Results indicate the model-following group achieved significantly higher ROI from marketing decisions (19.3% vs 16.4%) and employed key elements like customer segmentation, experimentation, and optimization to a greater extent. However, limitations including the experiment's scenario, self-report measures, and cross-sectional design constrain implications. Future research employing probability sampling, multiple decision contexts, longitudinal designs, manipulation checks, and objective metrics can further validate the proposed model. Overall, the study advances the understanding of how structured decision processes based on marketing engineering principles may optimize marketing decisions and outcomes.

The reactive nature of traditional frequency stability methods can lead to delayed corrective actions and unnecessary loss-of-load. This work presents a distributed model predictive control method for proactive power system frequency stability. Dynamic state estimation model is derived through a particle filter. By being able to estimate the future state of frequency, corrective actions can be taken before the system reaches a critical condition. Proactive approach makes it possible to optimize the response to a disturbance, which results in a decrease of the amount of compensation utilized. The method is tested via Matlab simulations based on Kundur's Two-Area System, and the IEEE 14-Bus system. Performance metrics are provided and evaluated against other contemporary solutions found in literature. Easy-to-derive model, without hard-to-design parameters, indicate potential towards real-life applications.

For a decade, the studies of dynamic control for unmanned aerial vehicles took a large interest, where drones as a useful technology in different areas were always suffering from several issues like instability-high energy consumption of batteries - inaccuracy of tracking targets. Different approaches are proposed for dealing with the non-linearity issues which present the most important features of this system. This paper describes our focus on the most common control strategies, known as model predictive control MPC, by developing a model based on the sensors embedded in our Tello quadrotor used for indoor purposes. The original controller of Tello quadrotor is supposed to be a slave, where the designed model predictive controller is created in MATLAB and imported to another embedded system, considered as a master; the objective of this model is to track the reference trajectory, almost keeping the stability of the system and ensure the low energy consumption. In the first part, a profound description of the modelling process of a dynamic model for drones is presented, explaining the design of MPC controller with both linear and non-linear strategies built in MATLAB. In the final part, simulation and results are discussed regarding its behaviour and performance, highlighting the MPC model's important role on drones' energy consumption profile.

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 dof delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data is available. Due to the sequential nature of the data, non-linearity of the system, and correlations between parameter time series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method is capable of calculating RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

High-performance motor drives that operate in harsh conditions require an accurate and robust angular position measurement to correctly estimate the speed and reduce the torque ripple produced by angular estimation error. For that reason, a resolver is used in motor drives as a position sensor due to its robustness. A resolver-to-digital converter (RDC) is an observer used to get the angular position from the resolver signals. Most RDCs are based on angle tracking observers (ATOs). On the other hand, generalized predictive control (GPC) has become a powerful tool in developing controllers and observers for industrial applications. However, no GPC-based RDC with zero steady-state error during constant speed operation was proposed. This paper proposes an RDC based on a second-order difference GPC (SOD-GPC). In SOD-GPC, the second-order difference operator is applied to design a GPC model with two embedded integrators. Thus, the SOD-GPC is used to design a type-II ATO whose steady-state angle estimation error tends to zero during constant speed operation. Simulation and experimental results prove that the proposed RDC system has better performance than other literature approaches.

Soy leghemoglobin (LegH) has been gaining interest over the last years as an efficient flavor and aroma compound in plant-based meat substitutes. Hence, in the following article we demonstrate the methods for LegH production using a recombinant Komagataella phaffii strain. Multiple fed-batch fermentation with an alternative to BSM medium, where glucose was used as the main carbon source, were implemented and the growth kinetics, e.g., maximal specific biomass growth - 0.239 g·g−1·h−1, biomass yield from substrate - 0.298 g·g−1 and maximal specific substrate consumption rate - 0.81 g·g−1·h−1, were identified. Leghemoglobin production resulted in a yield of 0.513 mg·gDCW 1, while the highest biomass density achieved in the study was 121.80 gDCW·L 1. The applied medium showed potential for additional optimization studies, as in contrast to BSM, made it possible to separate pH control from nitrogen supply, does not affect medium turbidity measurements and does not induce metabolite synthesis during yeast biomass growth.

Insulin-like growth factor binding proteins (IGFBPs) are critical modulators of the metabolism. In adults, IGFBPs are associated with obesity and insulin resistance but the association of IGFBPs with metabolic homeostasis in children and adolescents is not fully characterized. In this study we investigated the association of plasma IGFBPs (IGFBP-1, 3 and 7) with weight status, central adiposity and cardiovascular disease markers Hs-CRP and Ox-LDL. A total of 420 adolescents (age 11-14 years) were randomly recruited from public middle schools in Kuwait. IGFBPs were measured using bead-based multiplexing while Hs-CRP and Ox-LDL were measured using ELISA. IGFBP-1 levels were significantly lower in obese and overweight participants compared to normal weight children. Only IGFBP-1 was negatively associated with waist circumference to height (WC/Ht) ratio. IGFBP-1 was negatively correlated with Hs-CRP while IGFBP-3 and IGFBP-7 were negatively correlated with Ox-LDL. These data demonstrate a robust negative association of IGFBP-1, but not IGFBP-3 or -7, with overweight and obesity, and the inflammation marker Hs-CRP. Central adiposity (WC/Ht ratio) was a stronger predictor of IGFBP-1 than BMI-for-age z-score. IGFBP-1 could thus be used as a sensitive predictive diagnostic tool for obesity and its subsequent effects in screening and monitoring of obesity-related metabolic complications in adolescents.

This work is located in a growing sector within the field of renewable energies, wave energy converters (WECs). Specifically, it focuses on one of the point absorbers wave (PAWs) of the hybrid platform W2POWER. With the aim of maximising the mechanical power extracted from the waves by these WECs and reduce their mechanical fatigue, the design of five different model predictive controllers (MPCs) with hard and soft constraints has been carried out. As contribution of this paper, two of the MPCs have been designed with the addition of an embedded integrator. In order to validate the MPCs, an exhaustive study on performance and robustness is realized through simulations carried out in which uncertainties in the WEC dynamics are considered. Furthermore, looking for realistic in these simulations, an identification methodology for PAWs is proposed and validated by means of real time series of a scale prototype.

Deep learning neural networks require an immense amount of computation, especially in the training phase of the network when networks with multiple layers of intermediate neurons need to be built. In this paper, we will focus on the PSO algorithm with the aim of significantly accelerating the DLNN training phase by taking advantage of the GPGPU architecture and the Apache Spark analytics engine for large-scale data processing tasks. PSO is a bio-inspired stochastic optimization method whose goal is to iteratively improve the solution to a (usually complex) problem by attempting to approximate a given objective. However, parallelizing an efficient PSO is not a straightforward process due to the complexity of the computations performed on the swarm of particles and the iterative execution of the algorithm until a solution close to the objective with minimal error is achieved. In the present work, two parallelizations of the PSO algorithm have been implemented , both designed for a distributed execution environment. The synchronous parallel PSO implementation ensures consistency at the cost of potential idle time due to global synchronization, while the asynchronous parallel PSO approach improves execution time by reducing the need for global synchronization, making it more suitable for large datasets and distributed environments such as Apache Spark. Both variants of PSO have been implemented to distribute the computational load supported by this algorithm –due to the costly fitness evaluation and updating of particle positions– across the different Spark cluster executor nodes to effectively achieve coarse-grained parallelism, resulting in a significant performance increase over current sequential variants of PSO.

Dynamic virtual testing by Hardware in the Loop (HIL) real time simulation systems is common to minimize physical tests to validate and verify control algorithms, logics and software, under normal and emergency conditions. The accurate but costly HIL models setup activities could have an extended use to simulate faulty conditions that are seldom observable in the real system, yet they must be detected in advance and recognized. Data driven diagnostic methods have reached a mature development, in various sectors, proving effective in early detecting slowly varying deviations from nominal patterns of signals, even without a priori knowledge of their nature and behavior. These methods rely on vast amount of data logged from real systems that are ever and ever richer of monitoring telemetries that are worth being exploited. However, due to the usually reliable and safe systems being managed, it is often difficult to collect enough data on anomalous situations to validate fault detection and isolation and limit false positives. HIL model-based simulations allow generating and observing operational domains or transients rarely observed in real operations. This allows identifying the signals that are most correlated to faults and that could be selected to setup data-based diagnostic models of parts or subsystems, which are more suitable than the whole HIL model for online diagnostics, as well as to identify the features and trends that are most symptomatic of anomalous conditions.

In the evolving landscape of vibration analysis, the integration of machine learning technologies for semi-automated analytical processes presents challenges in establishing clear cause-and-effect relationships in decision-making formulas. This research addresses this gap by exploring analytical diagnosis through residual signals, enabling the identification of anomalies and underperformance in machinery. Vibration signature analysis, focusing on distinctive vibration patterns, proves instrumental in detecting bearing defects and optimizing maintenance for enhanced operational efficiency and safety. Mathematical modeling, particularly worst-case analysis, provides a structured framework for decision-making under uncertainty. The research employs descriptive methods to analyze bearing wear data, transforming it into quantitative data for multiple regression equations. The derived equations reveal the dominance of harmonics in determining bearing wear stages, with PeakVue and overall vibration further indicating damage progression. The findings emphasize the significance of harmonic detection and high-frequency vibration analysis in predicting bearing health, offering a comprehensive approach to enhance machinery reliability. The study concludes with practical recommendations for bearing damage diagnosis based on the developed mathematical models, providing valuable insights for predictive maintenance strategies.

Grasping the spatial and temporal patterns of forest fires, along with the key factors that drive them and the ability to forecast such events accurately, is essential for the successful management of forests. In China's southern region, forest fires significantly endanger the ecological system, public safety, and economic well-being. Through the application of Geographic Information Systems (GIS) and LightGBM (Light Gradient Boosting Machine) model, this study investigates the determinants of fire incidents and formulates a predictive model for forest fire occurrences, alongside a zoning strategy, within the Central-South area. The results indicate: (i) Spatially, fire points exhibit significant clustering and autocorrelation characteristics; (ii) The Central-South Forest Fire Prediction Model shows exceptional accuracy, reliability, and predictive power, with high performance metrics across training and validation sets, including over 85% accuracy, precision, recall, and F1 scores, along with AUC values above 89%, underscoring its efficacy in forecasting forest fires and distinguishing between fire events; (iii) Throughout the year, forest fire risks in the Central-South region of China vary by region and season, with risk spikes from March to May in Guangdong, Guangxi, Hunan, Hubei, and Hainan. From June to August, localized risks are observed in Heyuan and Huangshi, while from September to November, an increase in risk is noted in Guangdong (Meizhou, Heyuan, Shaoguan), Guangxi (Nanning, Hezhou, Yulin), and Hunan (Binzhou, Yongzhou, Hengyang) due to cooler, drier conditions and leaf litter accumulation. From December to February, the risk continues in specific areas across Guangdong, Guangxi, Hunan, and Hubei.

In the context of constructing new power systems, distribution networks are increasingly incorporating distributed resources such as distributed photovoltaic (PV) systems, decentralized wind turbines (WT), and new types of energy storage system (ESS), which may lead to prominent issues such as voltage overruns and reverse heavy overloads in the distribution network. While distributed resources are valuable for voltage regulation, their regulation characteristics vary with their operation means, and the randomness and volatility of renewable power generation will also influence the optimization and regulation of voltage in the distribution network. This paper proposes a multi-time scale reactive power optimization and regulation method for distribution networks in a multi-source interactive environment. Firstly, the voltage regulation characteristics of distributed PV systems, decentralized ES, and distributed WT are analyzed. Based on this analysis, then a multi-time scale voltage optimization scheme for distribution networks using MPC method is proposed, which optimizes the voltage regulation strategies for each distributed resource in a rolling manner. Furthermore, an event-triggered real-time voltage zoning control strategy based on voltage sensitivity is proposed to address the real-time sudden voltage overlimit problems. The modified IEEE 33-node system is used to verify the performance of proposed method, simulation results indicate that the issue of voltage overruns at distribution network nodes has been improved, and the intraday rolling optimization yields results that are more realistic compared to the day-ahead optimization method.

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 work (in two parts) will review the recently developed predictive modeling methodology called “4th-BERRU-PM” and its applicability to energy systems as exemplified by an illustrative application to the Polyethylene-Reflected Plutonium (acronym: PERP) OECD/NEA reactor physics benchmark. The acronym 4th-BERRU-PM designates the “Fourth-Order Best-Estimate Results with Reduced Uncertainties Predictive Modeling” methodology, which yields best-estimate results with reduced uncertainties for the first fourth-order moments (mean values, covariance, skewness, and kurtosis) of the optimally predicted posterior distribution of model results and calibrated model parameters. The 4th-BERRU-PM uses the Maximum Entropy (MaxEnt) principle to incorporate fourth-order experimental and computational information, including fourth (and higher) order sensitivities of computed model responses to model parameters, thus incorporating, as particular cases, the results previously predicted by the second-order predictive modeling methodology 2nd-BERRU-PM, and vastly generalizing the results produced by extant data assimilation and data adjustment procedures. The 4th-BERRU-PM methodology encompasses the scopes of high-order sensitivity analysis (SA), uncertainty quantification (UQ), data assimilation (DA) and model calibration (MC). The application of the 4th-BERRU-PM methodology to energy systems is illustrated by means of the above-mentioned OECD/NEA reactor physics benchmark, which is modeled using the neutron transport Boltzmann equation involving 21976 imprecisely known parameters, the solution of which is representative of “large-scale computations.” The model result (“response”) of interest is the leakage of neutrons through the outer surface of this spherical benchmark, which can be computed numerically and measured experimentally. Part 1 of this work illustrates the impact of high-order sensitivities, in conjunction with parameter standard deviations of various magnitudes, on the determination of the expected value and variance of the computed response in terms of the first four moments of the distribution of the uncertain model parameters. Part 2 of this work will illustrate the capabilities of the 4th-BERRU-PM methodology for combining computational and experimental information, up to and including forth-order sensitivities and distributional moments, for producing best-estimate values for the predicted responses and model parameters while reducing their accompanying uncertainties.

Lodging is a common problem in maize production that seriously impacts yield, quality, and the capacity for mechanical harvesting. Evaluation of site-specific lodging risks requires establishment of a method for multi-year monitoring. In this study, spectral images collected by the Sentinel-2 satellite were processed to obtain three types of data: gray-level co-occurrence matrix texture (GLCM), vegetation indices (VIs), and spectral reflectance (SR). Lodging classification models were then established with Random Forest (RF) using each of the three data types separately (the GLCM, VI, and SR models) and in combination (SR+VI model, SR+GLCM model, VI+GLCM mod-el, and SR+VI+GLCM model). By gradually removing features with low importance scores from the SR+VI+GLCM model and analyzing the changes in the overall accuracy (OA), the optimal set of predictive variables was identified and used to construct the optimal model. A model built us-ing data from a single timepoint in 2021 was tested on data collected at a similar timepoint in 2019 and vice versa to assess interannual model generalizability. The results of this study demon-strate that for monitoring maize lodging, models constructed with a single feature type, the GLCM model had significantly lower accuracy compared to the VI and SR models. During certain growth stages, the model constructed with combined features had significantly higher accuracy in monitoring maize lodging compared to models constructed with a single feature. During the pro-cess of selecting the optimal predictive variables, it was found that the accuracy of the model did not increase as the number of predictive variables increased. The results show that the positive and negative validation models had an accuracy of 96.55% and 95.18%, with kappa values of 0.93 and 0.83, respectively. This indicates that the model has strong generality for the same repro-ductive stage between years. This study provides a detailed method for large-scale maize lodging monitoring, allowing for identification of optimal planting practices to reduce the probability of lodging and ultimately improving regional maize yield and quality.

This paper presents a cascade predictive control structure based on the field-oriented control (FOC) in the dq rotor reference frame for the synchronous reluctance machine (SynRM). The constant d-axis current control strategy was used and thus, the electromagnetic torque was directly controlled by the q-axis current. Because the model of the two axes currents from the inner loop is a coupled non-linear multivariable one, to non-interaction linear control the two currents, their decoupling was achieved through feedforward components. Following the decoupling, two independent monovariable linear systems resulted for the two currents dynamics that were controlled using model predictive control (MPC) algorithms, considering their ability to automatically handle the state bounds. The most important bounds for SynRM are the limits imposed on currents and voltages, which in the dq plane correspond to a circular limit. To avoid computational effort, linear limitations were adopted through polygonal approximations, resulting in rectangular regions in the dq plane. For the outer loop that controls the angular speed with a constrained MPC algorithm, as plant was considered the q-axis current closed loop dynamics and the torque linear equation. To evaluate the performances of the proposed cascade predictive control structure, a simulation study using MPC controllers versus PI ones was conducted.

We present a generalized state-space model formulation particularly motivated by an online scheduling perspective. Through these proposed generalizations, we enable a natural way to handle routinely encountered disturbances and a rich set of corresponding counter-decisions. Thereby, greatly simplifying and extending the possible application of mathematical programming based online scheduling solutions to diverse application settings.

The main functions of the automated systems rely on the advanced sensors for detection and perception of the environment around the vehicle. Radars and cameras are commonly utilized to detect the potential obstacles and vehicles ahead on the road. Nevertheless, cameras can generate spurious detections in the extreme weather conditions such as fog, rain, dust, snow, dark, and heavy sunlight in the sky. Due to limitations in vertical field view of the radars, single radars are not reliable to detect the height of the targets precisely. In this paper, a triple radar arrangement (long-range, medium-range, and short-range radars) based on sensor fusion technique is proposed to detect objects with different size in level 2 Advanced Driver-Assistance (ADAS) system. The typical objects including truck, pedestrians, and animals are detected in different scenarios. The developed model considered ISO 26262 and ISO/PAS 21448 to reasonably address insufficient robustness and inability of the sensors. The models of sensor and level 2 ADAS systems are developed using MATLAB toolbox and Simulink. Sensor detection performance is determined by running simulations with triple radar setup. Obtained results demonstrate that the proposed approach generates accurate detections of targets in all tested scenarios.

The variability of the material properties of steel from different suppliers causes problems in achieving the required surface quality after turning. Therefore, the manufacturer needs to be able to estimate the resulting quality before starting production, especially if it is an expensive, small-batch production from stainless steel. Predictive models will make it possible to estimate the surface roughness from the mechanical properties of steel in the Mill Test Certificate (MTC) and thus support decision-making about the supplier selection or the acceptance of a material supply. Multivariate second-order polynomial model and feedforward back-propagation Artificial Neural Network (ANN) model were used to enhance the methodological robustness in formulating the decision if the predicted surface roughness is outside the required range, even before accepting the delivery. Both models can accurately predict surface roughness, while the ANN model is more accurate than the polynomial model; however, the predictive model is sensitive to the accuracy of the input data, and the model’s prediction is valid only under precisely defined conditions. The prediction model is used in a step-by-step decision-making procedure, which enables the trained staff to make a quick decision.

Anomaly detection is an active area of research with numerous methods and applications. This survey reviews the state-of-the-art of data-driven anomaly detection techniques and their application to the the aviation domain. After a brief introduction to the main traditional data-driven methods for anomaly detection, we review the recent advances in the area of neural networks, deep learning and temporal-logic based learning. We cover especially unsupervised techniques applicable to time series data because of their relevance to the aviation domain, where the lack of labeled data is the most usual case, and the nature of flight trajectories and sensor data is sequential, or temporal. The advantages and disadvantages of each method are presented in terms of computational efficiency and detection efficacy. The second part of the survey explores the application of anomaly detection techniques to aviation and their contributions to the improvement of the safety and performance of flight operations and aviation systems. As far as we know, some of the presented methods have not yet found an application in the aviation domain. We review applications ranging from the identification of significant operational events in air traffic operations to the prediction of potential aviation system failures for predictive maintenance.

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.

As the use of AI in medical imaging has increased, so has the need to explain a model’s results. Segmentation models are one technique used to produce explainable results. Due to larger size and sophistication, segmentation models which operate on 2D data can often produce better results than models operating on 3D data. In the real world, imaging is combined with clinical factors for diagnosis. To replicate this, multimodal models are used which combine image and text modalities. I propose a multimodal arrangement that converts 3D scans to 2D and uses a 2D segmentation model (DeepLabV3) to analyze the images. This is combined with clinical biomarkers to achieve a complete confidence score. Using the Medical Segmentation Decathlon Lung (MSDL) dataset and the LUng CAncer Screening dataset (LUCAS), I achieved a testing Dice coefficient of 0.91 on segmentation with a receiver operating characteristic (ROC), average precision (AP), and F-Score of 0.89, 0.91, and 0.85 respectively on the final multimodal results. This approach raises the F-score from the previously achieved value of 0.508 to 0.85, creating a new baseline of what is achievable with multimodal lung cancer diagnostics and possible methods to achieve these accuracies.

Condition monitoring is a crucial process for ensuring industrial assets' reliability and operational efficiency. In the age of the digital industry, AI-based data-driven condition monitoring is proving extremely effective in detecting potential issues before they escalate into major problems, thereby reducing downtime, minimizing maintenance costs, and extending the lifespan of the equipment. The availability of tools that can enable the operationalization of these data-driven solutions is, therefore, critical. In this direction, this work proposes a comprehensive, modular, and scalable pipeline covering all the steps from the data acquisition to the AI model training and inference phases. The tool integrates the data acquisition and processing steps with a configurable feature extraction phase. Moreover, the system also integrates deep learning algorithms for diagnosis and prognosis, including a domain adaptation stage to permit transfer learning and increase generalizability. In addition, it features a communication system using MQTT, which allows for an online data stream to enable real-time monitoring and maintenance. The overall infrastructure was deployed in actual industrial settings and tested in a real-time experiment, demonstrating the proposed approach's validity.

The study delves into the critical examination of the Size of Loss distribution patterns in the context of auto insurance during pre- and post-pandemics, emphasizing their profound influence on insurance pricing and regulatory frameworks. Through a comprehensive analysis of the historical Size of Loss data, insurers and regulators gain essential insights into the probabilities and magnitudes of insurance claims, informing the determination of precise insurance premiums and the management of case reserving. This approach aids in fostering fair competition, ensuring equitable premium rates, and preventing discriminatory pricing practices, thereby promoting a balanced insurance landscape. The research further investigates the transformative impact of the COVID-19 pandemic on these Size of Loss patterns, given the substantial shifts in driving behaviors and risk landscapes. Also, the research contributes to the literature by addressing the need for more studies focusing on the implications of the COVID-19 pandemic on pre- and post-pandemic auto insurance loss patterns, thus offering a holistic perspective encompassing both insurance pricing and regulatory dimensions.

Infertility affects millions worldwide, posing a significant global health challenge. The proteomic analysis of follicular fluid provides a comprehensive view of the complex molecular landscape within ovarian follicles, offering valuable information on the factors influencing oocyte development and on the overall reproductive health. The follicular fluid is derived from the plasma and contains various proteins that can have different roles in oocyte health and infertility and this fluid is a critical microenvironment for the developing oocytes as well. Using HPLC/MS method we investigated the protein composition of the follicular fluid and after classification we did relative quantification of the identified proteins in the pregnant (P) and non-pregnant (NP) groups. Based on the protein-protein interaction analysis ALB and ApoA1 was found to be hub proteins and the quantitative comparison of the P and NP groups resulted significantly lower concentration of ApoA1 and HDL-cholesterol in the P group. As both molecules are involved in the cholesterol transport, we also investigated their role in the development of oocytes and in the prediction of fertility.

This work focuses on addressing the dynamic positioning and trajectory tracking problem for a 4 degree-of-freedom (DOF) unmanned underwater vehicle (UUV) in the presence of nonlinear dynamics, parametric uncertainties, system constraints, and time-varying external disturbances. To tackle this problem, a disturbance observer-based control (DOBC) scheme is proposed. The scheme is structured around the model predictive control (MPC) method integrated with an extended active observer (EAOB). Compared to the conventional disturbance observer, the EAOB has the unique ability to handle both external disturbances and system/measurement noises simultaneously. The EAOB leverages a combination of sensor measurements and a system dynamic model to estimate disturbances in real-time, which allows continuous estimation and compensation of time-varying disturbances back to the controller. The proposed disturbance observer-based MPC (DOBMPC) is implemented by feeding the estimated disturbances back into the MPC’s prediction model, which forms a robust adaptive controller with a parameter-varying model. The proposed control strategy is validated through simulations in a Gazebo and Robot Operating System (ROS) environment. The results show that it can effectively reject unpredictable disturbances and improve the UUV’s control performance.