Energy transition is a major structural change in the whole social system, and the energy system must be changed globally to replace fossil fuels. Hydropower is one of the largest renewable energy in the world. However the involuntary resettlees due to the construction of hydropower projects are suffering from being far away from their native land, losing the land cultivated for generations and the houses they live in, and losing the social relationship network based on geography and blood ties. Based on the system evaluation theory of reservoir resettlement and referring to relevant research findings, this paper constructs a comprehensive evaluation index framework for assessing the implementation effect of the PostRelocation Support (PReS) policy. The research region is located in Zhijin County, Bijie City, Guizhou Province, China. Accordingly, a combined method of a structural equation model and a fuzzy comprehensive evaluationary model is used in this paper to analyze the implementation of the PReS policy. The results show that the total score of implementing effects of the PReS policy is 4.4, with dramatic significance. The subindex scores of the resettlers’ family income, living conditions, and production conditions; the local economy; and social stability are 4.3, 4.6, 4.4, 4.6, and 4.3, respectively, with dramatic significance. This paper has analyzed and summarized the successful practices of implementing the PReS policy for reservoir resettlers in three dimensions: poverty alleviation, beautiful home construction and accelerating rural revitalization. Research shows that China's rural reservoir resettlers' PReS policy has been more effective in restoring the livelihoods of reservoir resettlers.

Panoramic and periapical radiograph tools help dentists diagnose the most common dental diseases. Generally, dentists identify dental caries manually by inspecting X-ray images. However, due to their heavy workload, or poor image quality, dentists may sometimes overlook some unnoticeable dental caries, which may ultimately hinder the patient treatment. The purpose of this study was to develop an algorithm that classifies the teeth X-Ray images into three categories of “Normal”, “Caries”, and “Filled”. Our study used a dataset of 116 patients and 3712 single teeth images for training, validation and testing. Images were pre-processed using a sharpening filter and an intensity color map. We used a pre-trained transfer learning model, the NASNetMobile, which served as the feature extractor and the Convolutional Neural Network (CNN) model served as the classifier. The training dataset had a “Recall” of 0.92, 0.90 and 0.91 for “Normal”, “Caries” and “Filled” respectively and the test dataset had a “Recall” of 0.86, 0.81 and 0.85 for “Normal”, “Caries” and “Filled” respectively. The classification of the teeth X-Rays was successful and can be valuable for dentist as the artificial intelligence algorithm can serve as a decision support tool to aid dentists when they need to diagnose dental treatment.

1) Background: Genomic medicine harbors the real potential to improve the health and healthcare jour-ney of patients, care provider experiences, and improve health system efficiency – even reducing health care costs. There is expected to be an exponential growth in medically necessary new genome- based tests and test approaches in coming years. Testing can also create scientific research and commercial opportu-nities beyond healthcare decision-making. The purpose of this research is to generate a better under-standing of Canada’s state of readiness for genomic medicine, and to provide some insights for other healthcare systems; (2) Methods: a mixed-methodsapproach of literature review and key informant in-terviews with a purposive sample of experts was used. Health system readiness was assessed using a pre-viously published set of conditions. (3) Results: Canada has created some of the established conditions but more needs to be done to improve the state of readiness for genome-based medicine. Important gaps are the need for linked information systems and data integration; evaluative processes that are timely, and transparent; navigational tools for care providers; dedicated funding to facilitate rapid onboarding and supports test development and proficiency testing; and broader engagement with a broader set of inno-vation stakeholders. These findings highlight the known role of organizational context, social influence, and other factors that are known to affect the diffusion of innovation within health systems

Obstructive Sleep Apnea (OSA) is nowadays one of the respiratory pathologies with a higher in-cidence globally in developed countries. This situation led to an increase in the demand for medical appointments and diagnostic studies related to that condition, especially those based on poly-somnographies and cardiorespiratory polygraphies. These studies are limited in resources, causing long waiting lists with the subsequent impact on the patients’ health. Furthermore, it is necessary to mention that OSA’s symptomatology is not very specific, and it is typically present in the general population (excessive sleepiness, snore, etc.). In this regard, this paper proposes a novel intelligent clinical decision support system for the diagnosis of OSA which could be used to help medical teams, both in primary care settings and in units specialized in respiratory pathologies. The aim of the proposed system is to help discriminate the patients suspected of suffering from the pathology from those who are not. To this end, two types of information sets of heterogeneous nature are consid-ered. The first one encompasses objective data, related to the patient's health profile with infor-mation usually available in electronic health records. The second type comprises subjective data, referred to the symptomatology reported by the patient in a previous interview. To process the first group of information, a Machine Learning classification algorithm is used, Bagged Trees in this case. For processing the second information set, related with the symptomatology of the patient, a col-lection of expert systems based on fuzzy inferential systems arranged in cascade are employed. As a result, the system is able to determine two risk indicators related to the patient's risk of suffering from OSA: the Statistical Risk and the Symbolic Risk respectively. Subsequently, by interpreting both risk indicators mentioned it will be possible to determine the severity of the patients’ health, proposing a preliminary evaluation on their condition. For the initial tests of the system, a software artifact has been built using a dataset with 4,978 selected patients, suspected of suffering from OSA, from the Álvaro Cunqueiro Hospital in Vigo. The results obtained are promising, demonstrating the potential usefulness of this type of tools in medical diagnosis. Once the system has been validated with new data from clinical environments, it is considered as possible to obtain a relevant improvement in the quality of the healthcare services, and a reduction in the associated costs.

The objective of this study was to identify the key elements used by prehospital emergency physicians (EP) to decide whether or not to attempt advanced life support (ALS) in asystolic out-of-hospital cardiac arrest (OHCA). From 01.01.2009 to 01.01.2017, all adult victims of asystolic OHCA in Geneva, Switzerland, were retrospectively included. Patients with signs of "obvious death" or with a Do-Not-Attempt-Resuscitation order were excluded. Patients were categorized as having received ALS if this was mentioned in the medical record, or, failing that, if at least one dose of adrenaline had been administered during cardio-pulmonary resuscitation (CPR). Prognostic factors known at the time of EP's decision were included in a multivariable logistic regression model. 784 patients were included. Factors favourably influencing the decision to provide ALS were witnessed OHCA (OR=2.14, 95%CI1.43–3.20) and bystander CPR (OR=4.10, 95%CI2.28–7.39). Traumatic aetiology (OR=0.04, 95%CI0.02–0.08), age >80 years (OR=0.14, 95%CI0.09–0.24) and a Charlson comorbidity index greater than 5 (OR=0.12, 95%CI0.06–0.27) were the factors most strongly associated with the decision not to attempt ALS. Factors influencing the EP’s decision to attempt ALS in asystolic OHCA are the relatively young age of the patients, few comorbidities, presumed medical aetiology, witnessed OHCA and bystander CPR.

Background: In 2014 the World Health Organization (WHO) warned of an emerging world-wide crisis of antibiotic resistant microorganisms. In response, government and professional organizations recommended that health care systems adopt antimicrobial stewardship programs (ASPs). In the United States, the Centers for Medicare Services (CMS) mandated antimicrobial stewardship in the hospital inpatient setting. Effective January 1, 2020, the Joint Commission required ambulatory centers that prescribe antibiotics, such as wound centers, to institute an ASP. Chronic wounds often remain open for months, during which time patients may receive multiple courses of antibiotics and numerous antimicrobial topical treatments. The wound clinician plays an integral role in reducing antimicrobial resistance in the outpatient setting: antibiotics prescribed for skin and soft tissue infections are among the most common in an outpatient setting. One of the most challenging aspects of antimicrobial stewardship in treating chronic wounds is the inaccuracy of bacterial and infection diagnosis. Methods: Joint Commission lists five elements of performance (EP): (1) Identifying an antimicrobial stewardship leader, (2) establishing an annual antimicrobial stewardship goal, (3) implementing evidence-based practice guidelines related to the antimicrobial stewardship goal, (4) providing clinical staff with educational resources related to the antimicrobial stewardship goal, and (5) collecting, analyzing, and reporting data related to the antimicrobial stewardship goal. This article focuses on choosing and implementing an evidence-based ASP goal for 2020. Discussion: Clinical trials have demonstrated the ability of fluorescence imaging (MLiX) to detect clinically significant levels of bacteria in chronic wounds. Combined with clinical examination of signs and symptoms of infection, the MLiX procedure improves the clinician’s ability to diagnose infection and can guide antimicrobial use. In order to satisfy the elements of performance, the MLiX procedure was incorporated into the annual ASP goal for several wound care centers. Clinicians were educated on the fluorescence imaging device and guidelines were instituted. Collection of antimicrobial utilization data is underway.

Air passenger traffic prediction is crucial for the effective operation of civil aviation airports. Despite some progress in this field, the prediction accuracy and methods need further improvement. This paper proposes an integrated approach to the prediction of air passenger index as follows. Firstly, the air passenger index is defined and classified by the K-means clustering method. Based on the mutual information (MI) principle, the information entropy is used to analyze and select the key influencing factors of air passenger travel. By incorporating the MI principle into the support vector regression (SVR) framework, this paper presents an innovative MI-SVR machine learning model used to predict the air passenger index. Finally, the proposed model is validated by passenger throughput data of the Shanghai Pudong International Airport, China. The experimental results prove the model feasibility and effectiveness by comparing them with conventional methods, such as ARIMA, LSTM, and other machine learning models, outperformed by the MI-SVR model. Besides, it is shown that the prediction effect of each model could be improved by introducing influencing factors based on mutual information. The main findings are considered instrumental to the airport operation and air traffic optimization.

Air passenger traffic prediction is crucial for the effective operation of civil aviation airports. Despite some progress in this field, the prediction accuracy and methods need further improvement. This paper proposes an integrated approach to the prediction of air passenger index as follows. Firstly, the air passenger index is defined and classified by the K-means clustering method. Based on the mutual information (MI) principle, the information entropy is used to analyze and select the key influencing factors of air passenger travel. By incorporating the MI principle into the support vector regression (SVR) framework, this paper presents an innovative MI-SVR machine learning model used to predict the air passenger index. Finally, the proposed model is validated by passenger throughput data of the Shanghai Pudong International Airport, China. The experimental results prove the model feasibility and effectiveness by comparing them with conventional methods, such as ARIMA, LSTM, and other machine learning models, outperformed by the MI-SVR model. Besides, it is shown that the prediction effect of each model could be improved by introducing influencing factors based on mutual information. The main findings are considered instrumental to the airport operation and air traffic optimization.

Social responsibility is imperative for its important function in the growth of societies and organizations. However, the research on corporate social responsibility (OSR) has predominantly focused on the actions of organizations. Not much has been discussed regarding the employee's behaviours in promoting the development of social responsibility within organizations. CI is known for its significant role in the organization's various outcomes, Although a conceptualization and some empirical support have been provided for its relationship with the behaviour of employees, However, the effect of CI on employee socially responsible behaviours has not yet been investigated. In this article, following OC and OI theories, we improve the research model which can describe mechanisms underpinning through which CI, OI and POS support actions for employees' social responsibility. Data was collected from members of service professionals in Saudi Arabia and examined using Structural Equation Modeling- Partial Least Squares. The findings indicated that CI actions and activities develop the skills that motivate employees to support social responsibility inside and outside the organization. Moreover, our research paper explained the mechanism under which CI activities reshape employees' socially responsible manners. The current study is among the first to look at how to modify the socially responsible behaviour of employees across organizations, which can be a starting point for transforming those employees into a sustainable society.

This study addresses the influence of working conditions on Work-Related Quality of Life (WRQOL) among Spanish healthcare professionals. The research seeks to elucidate the mediating roles of job engagement and burnout, and the moderating effects of resilience and self-efficacy, in this relationship. Methods: The study included 374 healthcare workers from Spain, encompassing physicians, nurses, and nursing assistants. It employed a methodological approach using validated instruments to assess psychosocial risks, work-life quality, job engagement, burnout, and resilience. Data were gathered through self-reported questionnaires. Results: Key findings indicate a negative association between working conditions and WRQOL. Job engagement and burnout significantly mediated this relationship, accounting for 19% to 33% of the variance in WRQOL. Notably, lack of support emerged as a strong negative factor for work-related quality of life. Additionally, resilience moderated the relationship between lack of support and burnout. Conclusions: The study concludes that improving working conditions could increase WRQOL. Interventions aimed at enhancing engagement and addressing burnout may be effective. The moderating role of resilience suggests that strategies to enhance resilience could also be beneficial. These findings hold significant implications for policy formulation and human resources planning in healthcare, emphasizing the need for enhanced workplace support and the development of resilience among health workers.

In the dynamic and complex environment of industrial control rooms, operators are often inundated with a multitude of tasks and alerts, which can lead to an overwhelming situation known as task overload. This state can precipitate decision fatigue and a heavier reliance on cognitive biases, potentially compromising the decision-making process. To mitigate such risks, the implementation of decision support systems becomes crucial. These systems are designed to assist operators in making swift and well-informed decisions, particularly when they sense their own judgment may be faltering. Our research introduces an AI-based framework that leverages dynamic influence diagrams and reinforcement learning to construct an effective decision support system. The cornerstone of this framework is the creation of a robust, interpretable, and efficient tool that supports control room operators during critical process disturbances. By integrating expert knowledge, the dynamic influence diagram forms a comprehensive model that captures the uncertainties inherent in complex industrial processes. It is adept at anomaly detection and recommending optimal actions. Moreover, this model is enhanced through a strategic partnership with reinforcement learning algorithms, which fine-tune the recommendations to be more context-specific and precise. The ultimate goal of our framework is to provide operators with a live, reliable decision support system that can significantly improve their response during process upsets. This paper outlines the development of our AI framework and its application within a simulated control room environment. Our findings indicate that the use of decision support systems can lead to improved operator performance and reduced cognitive workload. However, it also reveals a trade-off with situation awareness, which tends to diminish as operators may become overly reliant on the system’s guidance. Trust emerges as a critical factor in the adoption and effectiveness of decision support systems. Our research underscores the importance of balancing the benefits of decision support with the need for maintaining operator engagement and comprehension during process operations.

Human-to-human communication via the computer is mainly done using a keyboard or microphone. In the field of Virtual Reality (VR), where the most immersive experience possible is desired, the use of a keyboard contradicts this goal, while the use of a microphone is not always desirable (e.g. silent commands during task force training) or simply not possible (e.g. if the user has a hearing loss). Data gloves help to increase immersion within the VR as they correspond to our natural interaction. At the same time, they offer the possibility to accurately capture hand shapes, such as those used in non-verbal communication (e.g. thumbs up, okay gesture, ...) and in sign language. In this paper, we present a hand shape recognition system using Manus Prime X data gloves, including data acquisition, data preprocessing, and data classification to enable nonverbal communication within VR. We investigate the impact on accuracy and classification time of using an Outlier Detection and a Feature Selection approach in our data preprocessing. To obtain a more generalized approach, we also studied the impact of artificial Data Augmentation, i.e., we create new artificial data from the recorded and filtered data to augment the training dataset. With our approach, 56 different hand shapes could be distinguished with an accuracy of up to 93.28%. With a reduced number of 27 hand shapes, an accuracy of up to 95.55% could be achieved. Voting Meta-Classifier (VL2) has proven to be the most accurate, albeit slowest, classifier. A good alternative is Random Forest (RF), which was even able to achieve better accuracy values in a few cases and was generally somewhat faster. Outlier Detection has proven to be a effective approach, especially in improving classification time. Overall, we have shown that our hand shape recognition system using data gloves is suitable for communication within VR.

This paper presents a method of fusion of identification (attribute) information provided by two types of sensors: combined primary and secondary (IFF) surveillance radars and ESM (Electronic Support Measures). In the first section, the basic taxonomy of attribute identification is adopted in accordance with the standards of STANAG 1241 ed. 5 and STANAG 1241 ed. 6 (draft). These standards provide the following basic values of the attribute identifications: FRIEND, HOSTILE, NEUTRAL, UNKNOWN and additional values: ASSUMED FRIEND and SUSPECT. The basis of theoretical considerations is Dezert-Smarandache theory (DSmT) of inference. The paper presents and practically uses for combining identification information from different ESM sensors and radars six information fusion rules proposed by DSmT - the Proportional Conflict Redistribution rules (PCR1, PCR2, PCR3, PCR4, PCR5 and PCR6). In the paper, rules of determining attribute information by ESM sensor equipped with the data base of radar emitters are presented. It was proposed that each signal vector sent by the ESM sensor contained an extension specifying a randomized identification declaration (hypothesis) - basic belief assignment (BBA). The paper also presents a model for determining the basic belief assignment for a combined primary and secondary radar. Results of the PCR rules of sensor information combining for different scenarios of radio-electronic situation (deterministic and Monte Carlo) are presented in the final part of the paper. They confirm the legitimacy of the use of Dezert-Smarandache theory into information fusion for primary radars, secondary radars and ESM sensors.

Swift and diligent resilience response is mandatory in sustainable geo-distributed ecosystems. The real-time geo-spatial resilience requires agility in millions of parallel and distributed data processing tasks on data acquired from regional condition monitoring(RCM) systems. These tasks include expiditous resolution of complex sustainability conflict sets, promptly anomalies characterization in chaos sets, and resilience response uniqueness. This work is an archetype of a paragon geo-resilience support system(GRSS) for regional sustainability using a novel melioration in DADO production machine. The proposed expert system capitalized the synergic strengths of RETE, TREAT, LEAPS and GATOR networks was designed and implemented as a synthetic DADO machine(SDM). The generic architecture of DADO machine was improved in this work by enrichment in rule set conditions and solution set for regional scale resilience rule set conditions. The condition left-hand side(LHS) X equal to the solution set 2X for right-hand side (RHS) was the goal achieved by working memory(WM) optimization and conflict resolution strategy(CRS) in alpha and beta networks rules. A round-trip time of 80.2 seconds for first event response set using 1492 segment size and sequence number 360,000 with maximum packets at a single geospatial structure was 21 packets/sec was a noticeable landmark in this work. LEAPS and Concurrent-read algorithm for GATOR cluster networks in the proposed synthetic DADO machine architecture was the overall implementation that enabled urban scale resilient system practically possible on physical SHM deployment.

In Data Science we are concerned with the integration of relevant sciences in observed and empirical contexts. This results in the unification of analytical methodologies, and of observed and empirical data contexts. Given the dynamic nature of convergence, described are the origins and many evolutions of the Data Science theme. The following are covered in this article: the rapidly growing post-graduate university course provisioning for Data Science; a preliminary study of employability requirements, and how past eminent work in the social sciences and other areas, certainly mathematics, can be of immediate and direct relevance and benefit for innovative methodology, and for facing and addressing the ethical aspect of Big Data analytics, relating to data aggregation and scale effects. Associated also with Data Science is how direct and indirect outcomes and consequences of Data Science include decision support and policy making, and both qualitative as well as quantitative outcomes. For such reasons, the importance is noted of how Data Science builds collaboratively on other domains, potentially with innovative methodologies and practice. Further sections point towards some of the most major current research issues.

Estimating Forest growing stock volume (GSV) is crucial for forest growth and resource management, as it reflects forest productivity. National measurements are laborious and costly, however integrating satellite data such as optical, Synthetic Aperture Radar (SAR), and Airborne Laser Scanning (ALS) with National Forest Inventory (NFI) data and machine learning (ML) methods has transformed forest management. In this study, Random Forest (RF), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost) were used to predict GSV using Estonian NFI data, Sentinel-2 imagery, and ALS point cloud data. Four variable combinations were tested: CO1 (vegetation indices and LiDAR), CO2 (vegetation indices and individual band reflectance), CO3 (LiDAR and individual band reflectance), and CO4 (a combination of vegetation indices, individual band reflectance, and LiDAR). Across Estonia's geographical regions, RF consistently delivered the best performance. In the northwest (NW), RF achieved an R² of 0.63 and an RMSE of 125.39 m³/plot. In the southwest (SW), it achieved an R² of 0.73 and an RMSE of 128.86 m³/plot. In the northeast (NE), RF achieved an R² of 0.64 and an RMSE of 133.77 m³/plot, and an R² of 0.70 and an RMSE of 120.72 m³/plot was achieved in the southeast (SE). These results underscore RF's precision in predicting GSV across diverse environments, though refining variable selection and improving tree species data could further enhance accuracy.

This article compares the predictive capabilities of six models namely the Linear Discriminant Analysis (LDA), Logistic Regression (LR), Support Vector Machine (SVM), XGBoost, Random Forest (RF) and Deep Neural Network (DNN) to predict the default behaviour of credit card holders in Taiwan using data from the UCI machine learning database. Python programming language was used for data analysis. Statistical methods were compared with machine learning algorithms using the confusion matrix measured in metric terms of prediction accuracy, sensitivity, specificity, precision, G-mean, F1 score, ROC and AUC. The dataset contains 30,000 credit card user’s information with 6636 default observations and 23,364 non-default cases. The study results found that modern machine learning methods outperformed traditional statistical methods in terms of predictive performance measured by F1 score, G-mean and AUC. Traditional methods like logistic regression were marginally better than linear discriminant analysis and support vector machines in terms of predictive performance measured by area under the receiver operating characteristic curve. In the modern machine learning methods, deep neural networks were better in most of the predictive performance metrics than XGBoost and Random Forest methods.

Livestock management is challenging for resource-poor (R-P) farmers due to unavailability of quality feed, limited professional advice and rumor-spreading about animal health condition in a herd. This research seeks to improve animal health in southern Africa by promoting sericea lespedeza (Lespedeza cuneata), a nutraceutical fodder legume. An automated geospatial model for precision agriculture (PA) can identify suitable locations for its cultivation. Additionally, a novel approach of radio frequency identifier (RFID) supported telemetry technology can track animal movement, and the analyses of data using artificial intelligence can determine sickness of small ruminants. This RFID-based system is being connected to a smartphone app (under construction) to alert farmers of potential livestock health issues in real-time so they can take immediate corrective measures. An accompanying Decision Support System (DSS) site is being developed for R-P farmers to obtain all possible support on livestock production, including the designed PA and RFID-based DSS.

Satellite-based data classification performance remains a challenge for research community in the field of land use/land cover mapping. Here we investigated supervised per-pixel classifications performance under different scenarios, based on single and seasonal multispectral data combina-tions of different sensors (Landsat-8 OLI and Sentinel-2 MSI). In case of Landsat, seasonal spectral indices (EVI and NDMI) were included. A typical Mediterranean watershed with a complex landscape comprised of various forest and wetland ecosystems, crops, artificial surfaces, and lake water was selected to test our approach. All available geospatial data from national databases (Forest Map, LPIS, Natura2000 habitats, cadastral parcels, etc.) are used as ancillary data for clas-sification training and validation. We examined and compared the performance of ML, RF, KNN and SVM classifiers under different scenarios for land use/land cover mapping, according to Co-pernicus Land Cover nomenclature. In total, eight land use/land cover classes were identified in Landsat-8 OLI and nine in Sentinel-2 MSI for an acceptable overall accuracy over 85%. A com-parison of the overall classification accuracies shows that Sentinel-2 overall accuracy was slightly higher than Landsat-8 (96.68% vs. 93.02%). Respectively, the best-performed algorithm was ML in Sentinel-2 while in Landsat-8 was KNN. However, machine-learning algorithms have similar results regardless the type of sensor. We concluded that best classification performances achieved using seasonal multispectral data. Future research should be oriented towards integrating time-series multispectral data of different sensors and geospatial ancillary data for land use/land cover mapping.

On April 17, 2019, a coach with tourists from Germany crashed in Madeira requiring repatriation by the German Air Force. The Advance Trauma Life Support (ATLS) concept was the central component of patient care. Data in Madeira were collected through a structured interview. The analysis of the Aeromedical Evacuation was based on intensive care transport records. In Germany all available were reviewed for data collection. Quality of life (HRQoL) was evaluated by the 12-item Short-Form Health Survey (SF-12). Twenty-eight prehospital patients were transported to the Level III Trauma Center in Funchal (Madeira). Five operative procedures were performed. Fifteen patients were eligible for Aeromedical Evacuation (AE). In the second hospital phase in Germany in total 82 radiological images and nine operations were performed. Hospital stay lasted 11 days (median, IQR 10–18). Median Follow-up (14 of 15 patients) was 16 months (IQR 16–21). 80% (8 out of 10) showed an increased risk for post-traumatic stress disorder (PTSD). Six key findings were identified in this study: divergent injury classification, impact of AE mission on health status, lack of communication, need of PTSD prophylaxis, patient identification, media coverage. Those findings may improve AE missions in the future e.g. required after armed conflicts.

Online digital mental health communities can contribute to users’ mental health positively and negatively. Yet the measurement of outcomes and impact relating to digital mental health communities is difficult to capture. In this paper we demonstrate the development of an online experience measure for a specific children and young people’s community inside a digital mental health service. The development is informed by three phases: (i) item reduction through Estimate-Talk-Estimate modified Delphi methods, (ii) user testing with participatory action research and (iii) a pilot within the digital service community to explore its use. Rounds of experts talks help to reduce the items. User experience workshops helped to inform the usability and appearance, wording, and purpose of the measure. Finally, the pilot results highlight completion rates, difference in scores for age and community roles and a preference to ‘relate to others’; as a mechanism of support. Outcomes frequently selected in the measure show the importance of certain aspects of the community, such as safety, connection, and non-judgment previously highlighted in the literature. Self-reported helpfulness scales like this one could be used as indicators of meaningful engagement within the community and its content but further research is required to ascertain its acceptability and validity. Phased approaches involving stakeholders and participatory action research enhances the development of digitally enabled measurement tools.

While current studies have focused on adoption and the relevant content of the app to become a decision support system, very few studies have focused on the farmer's intention and initial decision to adopt. Based on a survey of 394 smallholder farmers this study investigated Mexican farmers’ willingness to adopt an agricultural advice app. A Structural Equation Modelling approach, based on the Unified Theory of Acceptance and Use of Technology (UTAUT) was applied. To understand farmers’ adoption decision, extended constructs were studied (e.g. mastery-approach goals) along with farmers’ age and participation in an innovation hub. Results showed that the intention to adopt the app is predicted by how farmers believe that technical infrastructure exists and by the expectation of the farmers using the app to acquire new knowledge. The multi-group analysis revealed that performance expectancy is a relevant predictor of the intention to adopt, whereas the mastery-approach goal is relevant only for younger and farmers not connected to the innovation hub. The results may well be a baseline to research further suitable non-financial incentives for different farmers’ groups, then encourage initial adoption and enhance uptake. The findings are useful for practitioners and app developers designing digital decision support tools.

In the current industrial landscape, increasingly pervaded by technological innovations, the adoption of optimized strategies for asset management is becoming a critical key success factor. Among the various strategies available, the “Prognostics and Health Management” strategy is able to support maintenance management decisions more accurately, through continuous monitoring of equipment health and “Remaining Useful Life” forecasting. In the present study, Convolutional Neural Network-based Deep Neural Network techniques are investigated for the Remaining Useful Life prediction of a punch tool, whose degradation is caused by working surface deformations during the machining process. Surface deformation is determined using a 3D scanning sensor capable of returning point clouds with micrometric accuracy during the operation of the punching machine, avoiding both downtime and human intervention. The 3D point clouds thus obtained are transformed into bidimensional image-type maps, i.e., maps of depths and normal vectors, to fully exploit the potential of convolutional neural networks for extracting features. Such maps are then processed by comparing 15 genetically optimized architectures with the transfer learning of 19 pre-trained models, using a classic machine learning approach, i.e., Support Vector Regression, as a benchmark. The achieved results clearly show that, in this specific case, optimized architectures provide performance far superior (MAPE=0.058) to that of transfer learning which, instead, remains at a lower or slightly higher level (MAPE=0.416) than Support Vector Regression (MAPE=0.857).

Artificial Intelligence (AI) is revolutionizing decision-making procedures in healthcare information systems (HIS), increasing the efficacy, accuracy, and personalization of healthcare. Notwithstanding remarkable progresses, yet there remain gaps in the holistic comprehension and implication of AI-driven technologies across various HIS scenarios. These gaps, consisting limited integration of AI across a variety of HIS parts and inadequate emphasize on interpretability and privacy, motivate our study to conduct a structured evaluation of recent AI applications in this domain. In this study, we present a novel taxonomy for the AI implication in medical decision-making. We analyzed 30 articles and categorized them into six groups including: Clinical Decision Support Systems (CDSS), Predictive Analytics, Natural Language Processing (NLP), Computer-Aided Diagnostics (CAD), Robotic-Assisted Surgery, and Virtual Health Assistants (VHAs/chatbots). Our study aims to propose a holistic perspective of the fast evolving perspective of AI in HIS. The majority of the investigated studies were published from 2023 and 2022, with Springer as the leading publisher (33%). Python and MATLAB were the most well-known simulation languages, applied in 48% and 20% of the papers, respectively, reflecting the technical trends in the area. By emphasizing on pivotal criteria like interpretability, accuracy, and privacy, this research aims to elucidate the crucial issues and development driving AI-driven decision-making in HIS.

Fixed offshore wind turbines continue to be developed for high latitude areas where not only wind and wave loads need to be considered, but also moving sea ice. Current rules and regulations for the design of fixed offshore structures in ice-covered waters do not adequately consider effects of ice loading and its stochastic nature on fatigue life of the structure. Ice crushing on such structures results in ice-induced vibrations, which can be represented by loading the structure using a variable-amplitude loading (VAL) sequence. Typical offshore load spectra are developed for wave and wind loading. Thus, a combined VAL spectrum is developed for wind, wave, and ice action. To this goal, numerical models are used to simulate the dynamic ice-, wind-, and wave-structure interaction. The stress time-history at an exemplarily selected critical point in an offshore wind energy monopile support structure is extracted from the model and translated into a VAL sequence, which can then be used as a loading sequence for the fatigue assessment or fatigue testing of welded joints of offshore wind turbine support structures. This study presents the approach to determine combined load spectra and standardized time series for wind, wave, and ice action.

Solar energy is a renewable resource of energy that is broadly utilized and has the least emissions among the renewable energies. In this study, machine learning methods of artificial neural networks (ANNs), least squares support vector machines (LSSVM), and neuro-fuzzy are used for advancing prediction models for thermal performance of a photovoltaic-thermal solar collector (PV/T). In the proposed models, the inlet temperature, flow rate, heat, solar radiation, and the sun heat have been considered as the inputs variables. Data set has been extracted through experimental measurements from a novel solar collector system. Different analyses are performed to examine the credibility of the introduced approaches and evaluate their performance. The proposed LSSVM model outperformed ANFIS and ANNs models. LSSVM model is reported suitable when the laboratory measurements are costly and time-consuming, or achieving such values requires sophisticated interpretations.

Background: Physical and mental health of corporate employees is equally important, especially in international salespeople in the in vitro diagnostic (IVD) medical device industry. The rapid growth of the IVD market is driven by the increasing prevalence of chronic and infectious diseases. This study aims to identify the association of socio-demographic, occupational, organizational, and psychosocial factors with mental health outcomes for depression, anxiety, and somatic symptoms in Chinese IVD international salespeople. Methods: The study was a cross-sectional survey of ISs in IVD companies officially registered in China. An online survey was designed to collect data through email contact with IVD companies and social media between August 2022 and March 2023. Measured factors included effort-reward imbalance (ERI), health-promoting leadership (HPL), health climate (HC), inner strength (IS), and perceived social support (PSS). Mental health outcomes assessed using the Core Symptom Index (CSI) were depression, anxiety, and somatic symptoms. Results: A total of 244 salespeople responded to the survey. CSI scores indicated that 18.4% (n = 45) and 10.2% (n = 25) of the respondents had symptoms of major depression and anxiety, respectively. ERI was positively correlated, while the IS and PSS were negatively correlated with major depression, anxiety, and somatic symptoms (p < .01). Health climate was negatively correlated with major depression (p < .05). Education background was associated with somatic symptoms (p < .05). ERI, IS, and gender were significant predictors of major depression, anxiety, and somatic symptoms (p < .05). Conclusion: The prevalence of depression and anxiety in China’s IVD international salespeople was considered low compared with prevalence in Chinese populations during COVID-19, but higher than those before the pandemic. Effort–reward imbalance, inner strength, and gender were significant factors in major depression, anxiety, and somatic symptoms among IVD international salespeople.

There is growing recognition in research and policy of a mental health crisis among Canada’s paramedics but despite this, epidemiological surveillance of the problem is in its infancy. Just weeks before the emergence of the COVID-19 pandemic, we surveyed paramedics from a single, large, urban paramedic service in Ontario, Canada to assess for symptom clusters consistent with Post-Traumatic Stress Disorder (PTSD), major depressive disorder, and generalized anxiety disorder and to identify potential risk factors for each. In total, we received 589 completed surveys (a 97% completion rate) and found that 11% screened positive for PTSD, 15% for depression, and 15% for anxiety, with 1 in 4 active-duty paramedics screening positive for any of the three as recently as February 2020. In adjusted analyses, the risk of a positive screen varied as a function of employment classification, gender, self-reported resilience, and previous experience as a member of the service’s peer support team. Our findings support the position that paramedics screen positive for mental disorders at high rates – a problem likely to have worsened since the onset of the COVID-19 pandemic. We echo the calls of researchers and policymakers for urgent action to support paramedic mental health in Canada.

Heat metres are used to calculate the consumed energy in central heating systems. The subject of this article is to prepare a method of predicting a failure of a heat meter in the next settlement period. Predicting failures is essential to coordinate the process of exchanging the heat metres and to avoid inaccurate readings, incorrect billing and additional costs. The reliability analysis of heat metres was based on historical data collected over many years. Three independent models of machine learning were proposed, and they were applied to predict failures of metres. The efficiency of the models was confirmed and compared using the selected metrics. The optimisation of hyperparameters characteristics for each of models was successfully applied. The article shows that the diagnostics of devices does not have to rely only on newly collected information, but it is also possible to use the existing big data sets.

Forecasting streamflow accurately is essential to achieve an efficient integrated water resources management strategy and provide consistent support to water decision-makers. We present a simple, low-cost and robust approach for forecasting monthly and yearly streamflow during the hydrological year in course, applicable to headwater catchments. It combines the use of regression analysis techniques, the two-parameter Gamma continuous cumulative probability distribution function and the Monte Carlo method. It is based on a probabilistic comparison of the progression of the current hydrological year with the historic observed series. The methodology has been successfully applied to two headwater reservoirs within the Guadalquivir River Basin in southern Spain. The root-mean-square error and correlation coefficient were used to measure the accuracy of the model and the results showed good levels of reliability. The outputs are the probabilistic monthly and yearly streamflow and 80% confidence interval. Further reductions in prediction errors may be achieved from increasing the number of observed years. These risk-based predictions are of great value, especially, before the intensive irrigation campaign starts (usually in April), when Water Authorities are to take responsible management decisions about the best allocation of the available water volume between the different water users and environmental needs.

DNA repair helps in maintaining the proper and healthy functioning for the cells in the human body. Failure in DNA repair process can lead to aberrations as well as tumorous stages. There are various types of damages that a DNA can go through, one of which is the DNA double strand breaks (DSB) that can be repaired via homologous recombination (HR). RAD51 plays a central role in HR and has been implicated as a negative/poor prognostic marker for colorectal adenocarcinoma, with high expression in colorectal cancer. Mechanistically, RAD51AP1 facilitates RAD51 during the repairing process by binding with RAD51 via two DNA binding sites, thus helping in the D-loop formation in the HR process. Often, in biology, we are faced with the problem of exploring relevant unknown biological hypotheses in the form of myriads of combination of factors that might be affecting the pathway under certain conditions. For example, RAD51AP1-XRCC2 is one such 2^nd order combination whose relation needs to be tested under the influence recently developed Porcupine-WNT inhibitor ETC-1922159. The x-ray repair cross complementing XRCC family is known to work as a mediator or stabilizer for RAD51 during the HR process. The inhibitor is known to suppress Porcupine and thus inhibit a range of oncogenes known to be directly or indirectly affected by the Wnts. In a recent unpublished work in bioRxiv, we had the opportunity to rank these unknown biological hypotheses for down regulated genes at 2^nd order level after the drug was administered. The in silico observations showed that the combination of RAD51AP1-XRCC2 was assigned a relatively lower rank, thus validating the pipeline's efficacy with the confirmed wet lab experiment that indicate that both RAD51AP1 and XRCC2 were down regulated after treatment in cancer cells. Here, we take one step further by in silico analysis of the 3^rd order combinations of RAD51-X-X & RAD51AP1-X-X (X can be known or unknown factor), from a range of 100 randomly picked down regulated genes after ETC-1922159 treatment. The pipeline uses the density based HSIC (Hibert Schmidth Information Criterion) sensitivity index with an rbf (radial basis function) kernel, which is known to be highly effective in sensitivity analysis. Various unknown/unexplored/untested RAD51/RAD51AP1 related 3^rd order biological hypotheses emerge some of which are confirmed in wet lab, while others need to be tested.

We introduce the Concept-Model-Graph-View Cycle (CMGVC). The CMGVC facilitates coherent architecture analysis, reasoning, insight, and decision-making based on conceptual models that are transformed into a generic, robust graph data structure (GDS). The GDS is then transformed into multiple views of the model, which inform stakeholders in various ways. This GDS-based approach decouples the view from the model and constitutes a powerful enhancement of model-based systems engineering (MBSE). The CMGVC applies the rigorous foundations of Category Theory, a mathematical framework of representations and transformations. We show that modeling languages are categories, drawing an analogy to programming languages. The CMGVC architecture is superior to direct transformations and language-coupled common representations. We demonstrate the CMGVC to transform a conceptual system architecture model built with the Object Process Modeling Language (OPM) into dual graphs and a stakeholder-informing matrix that stimulates system architecture insight.

The need to increase the energy efficiency of buildings as well as the use of local renewable heat sources has caused that heat meters are used not only to calculate the consumed energy but also for the active management of central heating systems. Increasing the reading frequency and the use of measurement data to control the heating system expands the requirements for the reliability of heat meters. The aim of the research is to analyse a large set of meters in the real network and predict their faults to avoid inaccurate readings, incorrect billing, heating system disruption and unnecessary maintenance. The reliability analysis of heat metres, based on historical data collected over several years, shows some regularities which cannot be easily described by physics-based models. The failure rate is almost constant and does depend on the past but is a non-linear combination of state variables. To predict meters' failures in the next settlement period, three independent machine learning models are implemented and compared with selected metrics because even the high performance of a single model (87\% True Positive for Neural Network) may be insufficient to make a maintenance decision. Additionally, performing hyperparameters optimisation boosts models' performance by a few percent. Finally, three improved models are used to build an ensemble classifier which outperforms the individual models. The proposed procedure ensures the high efficiency of fault detection (>95\%), while maintaining overfitting at the minimum level. The methodology is universal and can be utilised to study the reliability and predict faults of other types of meters and different objects with the constant failure rate.

Often, in biology, we are faced with the problem of exploring relevant unknown biological hypotheses in the form of myriads of combination of factors that might be affecting the pathway under certain conditions. For example, Brancati et al.1 observe that mutations in poliovirus receptor related protein 4 (PVRL4), encoding cell adhesion molecule nectin-4, causes Ectodermal dysplasia-syndactyly syndrome. Interaction with cad- herins also implies an influence of nectin-4 on Wnt signaling, which plays a relevant role in limb development (Brancati et al.1). However, not much work has been done to explore the relation of Wnts and PVR family. In CRC cells treated with ETC-1922159, both were found up regulated. In a recent unpublished work in Open Science Framework, Sinha2, we had the opportunity to rank these unknown biological hypotheses for both up and down regulated genes at 2nd order level after drug administration. The search engine alloted high nu- merical valued rankings to some combinations of PVR-WNT, thus indicating a possibility of high combinatorial synergy also. The in-silico derived influences can be represented graphically as - PVR w.r.t WNT with PVR <- WNT9A; and WNT w.r.t PVR with WNT-7B/9A <- PVR and WNT4 <- PVRL2; In the light of the recent findings of PVR with IFN (interferon) and the known interactions between IFN and Wnts, there might be a possibilty to explore the bridge of PVR, IFN and WNTs. The 3 fold (PVR - IFN; IFN - WNT; WNT - PVR), 2 way cross family analysis might shed light on the possible combinations that might be of import. Here, we present a 2-way cross family analysis of multiple, such in-silico ranked 2nd order synergistic combinations, after ETC-1922159 treatment of CRC cells. Via this 2-way cross family analysis, we are able to discover through majority voting, the combinations that might of interest to biologists and also derive plausible influences of components of combinations among themselves. Note that these form biological hypotheses which indicate whether a particular combination and the direction of influence within the combination, exist synergistically in CRC cells. Wet lab tests will indicate the veracity of these combinations and if proven true, will lead to further study of mechanism between the components.

Predicting change from multivariate time series has relevant applications ranging from medical to engineering fields. Multisensory stimulation therapy in patients with dementia aims to change the patient’s behavioral state. For example, patients who exhibit a baseline of agitation may be paced to change their behavioral state to relaxed. This study aims to predict changes in behavioral state from the analysis of the physiological and neurovegetative parameters to support the therapist during the stimulation session. In order to extract valuable indicators for predicting changes, both handcrafted and learned features were evaluated and compared. The handcrafted features were defined starting from the CATCH22 feature collection, while the learned ones were extracted using a Temporal Convolutional Network, and the behavioral state was predicted through Bidirectional Long Short-Term Memory Auto-Encoder, operating jointly. From the comparison with the state-of-the-art, the learned features-based approach exhibits superior performance with accuracy rates of up to 99.42% with a time window of 70 seconds and up to 98.44% with a time window of 10 seconds.

Remaining service life (RSL) of pavement, as a sign of future pavement performance, has always received growing attention from pavement engineers. The RSL describes the time from the moment of pavement inspection until such a time when a major repair or reconstruction is required. The conventional approach to determining RSL involves using non-destructive tests. These tests, in addition to being costly, interfere with traffic flow and compromise users' safety. In this paper, surface distresses of pavement have been used to estimate the pavement’s RSL in order to eliminate the aforementioned problems and challenges. To implement the proposed theory, 105 flexible pavement segments were taken from Shahrood-Damghan Highway (Highway 44) in Iran. For each pavement segment, the type, severity, and extent of surface damage and pavement condition index (PCI) were determined. The pavement RSL was then estimated using non-destructive tests include Falling Weight Deflectometer (FWD) and Ground Penetrating Radar (GPR). After completing the dataset, the modeling was conducted to predict RSL using three techniques include Support Vector Regression (SVR), Support Vector Regression Optimized by Fruit Fly Optimization Algorithm (SVR-FOA), and Gene Expression Programming (GEP). All three techniques estimated the RSL of the pavement by selecting the PCI as input. The Correlation Coefficient (CC), Nash-Sutcliffe efficiency (NSE), Scattered Index (SI), and Willmott’s Index of agreement (WI) criteria were used to examine the performance of the three techniques adopted in this study. In the end, it was found that GEP with values of 0.874, 0.598, 0.601, and 0.807 for CC, SI, NSE, and WI criteria, respectively, had the highest accuracy in predicting the RSL of pavement.

Urban areas are centres of business and innovation. Freight transport is indispensable for the proper functioning of any modern urban society. Urban areas can’t function without an appropriate freight transport system, due to the need to replenish stocks of food and other goods in retail shops. The complexity of the decisions concerning implementation of measures to improve the movement of goods in the city requires tools designed to support this process. The purpose of this article is to introduce the possibility of applying the Analytic Hierarchy Process (AHP) as well as the Decision Making Trial and Evaluation Laboratory Method (DEMATEL) in choosing a set of measures and in analysing in the field of distribution logistics, which will help to solve the delivery problems and streamline the cargo flows in Szczecin, in the context of sustainable development.

This paper explores the challenges faced by blue-collared international migrants in adapting to new and unfamiliar climates while pursuing job opportunities, with a focus on poverty alleviation. Drawing on existing research and empirical evidence, the study investigates the trials encountered by these migrants as they navigate climate shocks and assesses the potential impacts on poverty reduction efforts. The findings underscore the significant difficulties blue-collared migrants experience when confronted with abrupt changes in climate conditions, adversely affecting their physical and mental well-being, as well as their employment prospects. The process of adjustment involves not only acclimating to new climate patterns but also navigating cultural nuances and social dynamics, exacerbating stress and feelings of isolation. Consequently, these challenges can perpetuate poverty by disrupting employment stability and limiting opportunities for career advancement. To address these issues, the paper proposes comprehensive support measures, including targeted pre-departure training programs, access to retraining opportunities, and assistance in securing sustainable livelihoods. By prioritizing climate resilience and empowering blue-collared migrants to adapt effectively to new climates, it becomes possible to enhance their livelihood prospects, reduce poverty levels, and foster sustainable development. The paper concludes by highlighting the significance of integrating climate adaptation strategies with poverty alleviation efforts to create a more inclusive and resilient future for blue-collared migrants in their pursuit of sustainable livelihoods.

Stroke constitutes a significant public health concern due to its impact on mortality and morbidity. This study investigates the utility of machine learning algorithms in predicting stroke and identifying key risk factors using data from the Suita study, comprising 7,389 participants and 53 variables. Initially, unsupervised K-prototype clustering categorized participants into risk clusters, while five supervised models including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosted Machine (Light-GBM) were employed to predict stroke outcomes. Stroke incidence disparities among identified risk clusters using the unsupervised K-prototype clustering method are substantial, according to the findings. Supervised learning, particularly RF was a preferable option because of the higher levels of performance metrics. The Shapley Additive Explanations (SHAP) method identified age, systolic blood pressure, hypertension, estimated glomerular filtration rate, metabolic syndrome, and blood glucose level as key predictors of stroke, aligning with findings from the unsupervised clustering approach in high-risk groups. Additionally, previously unidentified risk factors such as elbow joint thickness, fructosamine, hemoglobin, and calcium level demonstrate potential for stroke prediction. In conclusion, machine learning facilitated accurate stroke risk predictions and highlighted potential biomarkers, offering a data-driven framework for risk assessment and biomarker discovery.

The domain of construction engineering and management is evolving rapidly. Optimizing resource positioning is crucial for meeting the challenges of efficiency and productivity. This research presents a novel methodology that incorporates Agent-Based Modeling (ABM), Building Information Modeling (BIM), and Bluetooth Low Energy (BLE) technologies, augmented with a Client Early Warning System (CEWS) and a Decision Support System (DSS). What makes this study unique is that it provides a real-time methodology for resource allocation and project management, tailored to address the complexities of modern construction projects. The application of this integrated technological framework marks a significant leap in construction management, empowering data-driven decision-making and significantly improving project efficiency. Empirically validated through a case study at Helwan University's College of Engineering and substantiated by expert surveys, this research showcases a transformative model for resource management. The findings not only underscore the practical applicability of this approach but also open new horizons for its adoption in global construction practices, offering insights for future research endeavors focused on expanding these methodologies to a wider range of resources.

\textsc{Background} Often, in biology, we are faced with the problem of exploring relevant unknown biological hypotheses in the form of myriads of combination of factors that might be affecting the pathway under certain conditions. Currently, a major problem in biology is to cherry pick the combinations based on expert advice, literature survey or guesses for investigation. The search and wet lab testing of these combinations costs a lot in terms of time, investment and energy. In a recent development of the PORCN-WNT inhibitor ETC-1922159 for colorectal cancer, a list of down-regulated genes were recorded in a time buffer after the administration of the drug. The regulation of the genes were recorded individually but for a majority, it is still not known which higher ($\geq 2$) order combinations might be playing a greater role in the pathway. \textsc{Results} The pipeline provides a prioritised list of important $2^{nd}$ order combinations of a range of family of genes involved in the Wnt pathway. More specifically, it reveals the various unexplored FZD-WNT combinations that have been untested till now in the pathway. In relation to ETC-1922159 affected combinations, the down-regulation of LGR-RNF family after the drug treatment is evident in these rankings as it takes bottom priorities for LGR5-RNF43 combination. The LGR6-RNF43 takes higher ranking than LGR5-RNF43, indicating that it might not be playing a greater role as LGR5 during the Wnt enhancing signals. These rankings confirm the efficacy of the proposed search engine design. \textsc{Conclusion} A pipeline has been developed to prioritise an $n^{th}$ order combination of factors that affect a signaling pathway. It takes into account the sensitivity indices computed from variance based (SOBOL) and density-kernel based (HSIC) methods to estimate the influence of each factor or combination of factors. These are then fed as feature vectors into a powerful support vector ranking algorithm that produces a ranked list of the interactions/combinations.

Keywords: Electrical power systems, Support vector machines, Random Forest, Machine learning, Wavelet transform, Transmission lines fault, Electrical power quality, Short circuit, Classification of faults, Localization of faults, Decision trees, Ensemble learning, K-nearest neighbors.

Digital technologies have changed the way supply chain operations are structured. In this article, we conduct systematic syntheses of literature on the impact of new technologies on supply chains and the related cyber risks. A taxonomic/cladistic approach is used for the evaluations of progress in the area of supply chain integration in the Industrial Internet of Things and Industry 4.0, with a specific focus on the mitigation of cyber risks. An analytical framework is presented, based on a critical assessment with respect to issues related to new types of cyber risk and the integration of supply chains with new technologies. This paper identifies a dynamic and self-adapting supply chain system supported with Artificial Intelligence and Machine Learning (AI/ML) and real-time intelligence for predictive cyber risk analytics. The system is integrated into a cognition engine that enables predictive cyber risk analytics with real-time intelligence from IoT networks at the edge. This enhances capacities and assist in the creation of a comprehensive understanding of the opportunities and threats that arise when edge computing nodes are deployed, and when AI/ML technologies are migrated to the periphery of IoT networks.

In the present work, a novel and the robust computational investigation is carried out to estimate solubility of different acids in supercritical carbon dioxide. Four different algorithms such as radial basis function artificial neural network, Multi-layer Perceptron (MLP) artificial neural network (ANN), Least squares support vector machine (LSSVM) and adaptive neuro-fuzzy inference system (ANFIS) are developed to predict the solubility of different acids in carbon dioxide based on the temperature, pressure, hydrogen number, carbon number, molecular weight, and acid dissociation constant of acid. In the purpose of best evaluation of proposed models, different graphical and statistical analyses and also a novel sensitivity analysis are carried out. The present study proposed the great manners for best acid solubility estimation in supercritical carbon dioxide, which can be helpful for engineers and chemists to predict operational conditions in industries.

Solar energy is a renewable resources of energy which is broadly utilized and have the least pollution impact between the available alternatives of fossil fuels. In this investigation, machine leaening approaches of neural networks (NN), neuro-fuzzy and least squares support vector machine (LSSVM) are used to build the models for prediction of the thermal performance of a photovoltaic-thermal solar collector (PV/T) by estimating its efficiency as an output of the model while inlet temperature, flow rate, heat, solar radiation, and heat of sun are input of the designed model. Experimental measurements was prepared by designing a solar collector system and 100 data extracted. Different analyses are also performed to examine the credibility of the introduced approaches revealing great performance. The suggested LSSVM model represented the best performance regarding the mean squared error (MSE) of 0.003 and correlation coefficient (R²) value of 0.99, respectively.

This paper discusses the computer-aided (CAD) classification between Hepatocellular Carcinoma (HCC), i.e., the most common type of liver cancer, and Liver Abscess, based on ultrasound image texture features and Support Vector Machine (SVM) classifier. Among 79 cases of liver diseases, with 44 cases of HCC and 35 cases of liver abscess, this research extracts 96 features of Gray-Level Co-occurrence Matrix (GLCM) and Gray-Level Run-Length Matrix (GLRLM) from the region of interests (ROIs) in ultrasound images. Three feature selection models, i) Sequential Forward Selection, ii) Sequential Backward Selection, and iii) F-score, are adopted to determine the identification of these liver diseases. Finally, the developed system can classify HCC and liver abscess by SVM with the accuracy of 88.875%. The proposed methods can provide diagnostic assistance while distinguishing two kinds of liver diseases by using a CAD system.

This comprehensive study delves into the implementation and effectiveness of the flipped classroom model in engineering EMI (English as a Medium of Instruction) courses in Taiwan. Situated within the strategic framework of Taiwan's Bilingual Nation 2023 policy, this research aims to enhance the global competitiveness of Taiwan's semiconducting manufacturing engineering sector. The study’s primary focus is on understanding the perceptions and learning outcomes of EFL (English as a Foreign Language) students in engineering courses. Through a methodical approach using descriptive statistics and chi-square tests, the study analyzes data from 33 junior engineering students specializing in mechanical and mechatronic fields. The findings highlight a significant positive influence of the flipped classroom model on various aspects of student learning, including increased engagement, heightened creativity, and enhanced problem-solving skills. Additionally, the study emphasizes the critical role of timely L1 support in facilitating effective learning in EMI settings. These outcomes not only demonstrate the flipped classroom's viability as a sustainable educational approach but also provide crucial insights for educators and policymakers. By aligning cutting-edge teaching methods with the evolving needs of engineering education, this study contributes to the discourse on educational innovation. It ultimately guides the development of future engineering programs that cater to diverse student needs and fosters the cultivation of skilled engineering professionals.

Electricity demand prediction is vital for energy production management and proper exploitation of the present resources. Recently, several novel machine learning (ML) models have been employed for electricity demand prediction to estimate the future prospects of the energy requirements. The main objective of this study is to review the various ML models applied for electricity demand prediction. Through a novel search and taxonomy, the most relevant original research articles in the field are identified and further classified according to the ML modeling technique, perdition type, and the application area. A comprehensive review of the literature identifies the major ML models, their applications and a discussion on the evaluation of their performance. This paper further makes a discussion on the trend and the performance of the ML models. As the result, this research reports an outstanding rise in the accuracy, robustness, precision and the generalization ability of the prediction models using the hybrid and ensemble ML algorithms.