Key Metrics Research Articles

The Impact of Big Data and Artificial Intelligence on Influencer Marketing

Influencer marketing has rapidly emerged as a cornerstone of digital advertising strategies, enabling brands to connect authentically with target audiences through trusted voices on social media platforms. However, measuring the effectiveness of these campaigns has long been a challenge due to the complexity of digital ecosystems and the sheer volume of data generated by user interactions. Big Data and Artificial Intelligence (AI) are revolutionizing the way brands evaluate influencer marketing campaigns, offering unprecedented insights into key performance metrics such as engagement, audience sentiment, and conversion rates. This paper explores how data analytics and AI tools are transforming the identification of influencers, the optimization of campaign performance, and the prediction of future trends. Furthermore, we address the ethical considerations surrounding data privacy and the transparency of AI-driven decisions in influencer marketing. Ultimately, this study highlights how Big Data and AI are not only enhancing the efficiency of influencer marketing but also reshaping the future of digital advertising as a whole.

Perioperative risk scores: prediction, pitfalls, and progress

Purpose of review Perioperative risk scores aim to risk-stratify patients to guide their evaluation and management. Several scores are established in clinical practice, but often do not generalize well to new data and require ongoing updates to improve their reliability. Recent advances in machine learning have the potential to handle multidimensional data and associated interactions, however their clinical utility has yet to be consistently demonstrated. In this review, we introduce key model performance metrics, highlight pitfalls in model development, and examine current perioperative risk scores, their limitations, and future directions in risk modelling. Recent findings Newer perioperative risk scores developed in larger cohorts appear to outperform older tools. Recent updates have further improved their performance. Machine learning techniques show promise in leveraging multidimensional data, but integrating these complex tools into clinical practice requires further validation, and a focus on implementation principles to ensure these tools are trusted and usable. Summary All perioperative risk scores have some limitations, highlighting the need for robust model development and validation. Advancements in machine learning present promising opportunities to enhance this field, particularly through the integration of diverse data sources that may improve predictive performance. Future work should focus on improving model interpretability and incorporating continuous learning mechanisms to increase their clinical utility.

Streamlining Smart Grids Reliability Assessment: An Innovative Mapping Approach

Assessing smart grid reliability, considering both cyber and physical components, typically involves a mapping step, escalating complexity and computational overhead. This paper presents a pioneering mapping approach that redefines the fundamental paradigm of smart grid reliability assessment. By leveraging a defined interconnection matrix, the method optimizes computational efficiency, curtailing the array of potential system states. Evaluation employing key performance metrics - Loss of Load Probability (LOLP) and Expected Energy Not Supplied (EENS) - quantitatively demonstrates the superiority of our approach. Also, we explore the ramifications of integrating a dynamic thermal rating (DTR) in the process of reliability assessment, augmenting component safety through permissible enhancements in their ratings. Results underscore a notable reduction in total system states, from 221 to 214 for the bus topology and from 222 to 216 for the ring topology. Moreover, the analysis reveal substantial enhancements (Up to 43.58% ) in reliability indices upon consideration of the DTR system.

Ultra Enhancement of the Resolution of the Divergence Beam-Based SPR Sensor Using a Wavelet Filter

Surface Plasmon Resonance (SPR) sensors are highly sensitive to refractive index variations, making them ideal for biosensing and chemical detection applications. However, their performance can be constrained by noise, resolution limits, and signal distortions, particularly in divergence beam-based configurations. This research presents an ultra-enhancement of the performance of divergence beam-based SPR sensors by employing advanced wavelet filtering techniques. Wavelets, with their multi-resolution analysis capability, are applied to denoise and refine the sensor signal, significantly improving key performance metrics, including resolution, mean square error (MSE), root mean square error (RMSE), signal-to-noise ratio (SNR), sensitivity matrix (SM), and combined sensitivity factor (CSF).The wavelet filter effectively decomposes the SPR signal into distinct frequency bands, separating noise while retaining high-frequency components required for accurate sensing. This results in a significant reduction in MSE and RMSE of 30 and 92.26%, respectively, while simultaneously improving SNR by 54.08%, maintaining signal quality. The wavelet filter significantly improved the resolution of the SPR sensor by 99.95% (1.3772×10-7 RIU), allowing for more precise detection of refractive index changes and boosting diverge beam-based SPR sensor performance. In addition, a sensitivity matrix (SM) and combined sensitivity factor (CSF) were improved by 42 and 41.94%, respectively, allowing for a more thorough evaluation of the sensor's performance across multiple operational parameters. Simulation and experimentation show that wavelet filtering surpasses standard filtering approaches in terms of noise suppression and signal clarity. This technology has considerable potential for improving the accuracy and reliability of SPR sensors in high-sensitivity applications

Bridging the gap: A comparative analysis of indoor and outdoor performance for photovoltaic-thermal-thermoelectric hybrid systems

This research evaluates the performance of a hybrid thermal-thermoelectric photovoltaic air collector system (PV/T-TE) through experimental investigations. By integrating photovoltaic (PV) panels with thermoelectric (TE) modules, the system aims to enhance efficiency and energy output by converting waste heat into additional electricity. The study examines the impact of radiation intensity, ranging from 455.65 to 795.18 W/m2, on the system's performance, utilizing output temperature (To) and plate temperature (Tp) as key metrics. Managing waste heat in PV technology remains a challenge, impacting efficiency. Traditional PV/T systems generate both electricity and thermal energy but suffer efficiency losses due to inadequate heat management. Integrating TE modules into PV/T systems offers a promising solution, but optimal configurations and performance impacts under varying conditions are underexplored. Limited research focuses on PV/T-TE hybrid systems, with most studies addressing PV-TE systems. The objectives of this research are to experimentally assess the impact of integrating TE modules on the thermal and electrical efficiency of PV/T systems under varying radiation intensities and air mass flow rates. The methodology involves setting up a PV/T-TE hybrid system, conducting experiments under controlled conditions, and analyzing key performance metrics. The study explores optimal TE module configurations and installation techniques to maximize heat transfer and electricity generation. Comparative analysis with conventional PV/T systems establishes the superiority of the hybrid system. Findings indicate significant benefits from incorporating TE modules, enhancing energy output and efficiency by maintaining optimal PV panel temperatures.

Effects of amide proton transfer imaging in diagnosis, grading and prognosis prediction of cervical cancer: a systematic review and meta-analysis

PurposeTo assess the effectiveness of Amide Proton Transfer (APT) imaging in predicting the histopathological characteristics of cervical cancer. MethodsA comprehensive literature search was conducted across multiple databases, covering studies until December 27, 2023. The meta-analysis was performed using Stata 15 and Review Manager 5.4 software. Key metrics analyzed included pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and summary receiver operating characteristic (sROC) curves. The analysis focused on differentiating cervical cancer types, squamous carcinoma differentiation, and lymph node involvement. Meta-regression was employed to investigate heterogeneity. ResultsThirteen studies involving 868 patients were included in the meta-analysis. For differentiating adenocarcinoma from squamous carcinoma, the pooled sensitivity was 0.82 (95%CI: 0.71-0.90), specificity was 0.65 (95%CI: 0.48-0.79), and DOR was 9 (95%CI: 1.6-3.5). When distinguishing poorly differentiated from moderately/well-differentiated squamous carcinoma, the sensitivity was 0.74 (95%CI: 0.66-0.81), specificity was 0.83 (95%CI: 0.75-0.89), and DOR was 14 (95%CI: 8-23). For identifying lymph node involvement, the sensitivity was 0.87 (95%CI: 0.78-0.92), specificity was 0.66 (95%CI: 0.59-0.73), and DOR was 13 (95%CI: 7-26). No publication bias was detected. ConclusionsAPT imaging demonstrates high sensitivity and specificity in distinguishing between cervical cancer types, grading squamous carcinoma, and detecting lymph node involvement. It can be considered a reliable technique for predicting the pathological features of cervical cancer in clinical practice.

An approach based on data mining and genetic algorithm to optimizing time series clustering for efficient segmentation of customer behavior

In today's highly competitive market, organizations face significant challenges in accurately understanding and segmenting customer behavior due to the inherently dynamic and evolving nature of customer interactions over time. Traditional customer segmentation methods often neglect these temporal variations, leading to ineffective business strategies and missed opportunities. This research addresses this critical gap by introducing an innovative time series-based approach for customer behavior segmentation. By modeling each customer's behavior as a time series capturing key metrics such as purchase frequency, transaction amounts, and customer lifecycle costs the proposed method dynamically adapts to behavioral changes over time. To enhance segmentation precision, a genetic algorithm is employed to optimize feature weights, ensuring that the most relevant factors are emphasized. These optimized features are then clustered using spectral clustering to identify distinct and meaningful customer segments. The effectiveness of the proposed method is validated using 30 months of transactional data from a payment services company. The results demonstrate that the proposed approach, particularly when combined with spectral clustering and optimally weighted features, significantly surpassing the performance of traditional static segmentation techniques. This research not only provides a more accurate framework for uncovering hidden patterns in customer behavior but also delivers actionable insights for targeted marketing and personalized customer strategies.

A bibliometric analysis of research on physical activity and fitness among preschool children in Asia (2020-2024)

Background: Physical activity (PA) and physical fitness (PF) are essential for preschool children's development. However, rising childhood obesity and sedentary lifestyles are concerning. A comprehensive analysis of the research landscape is necessary to inform better interventions and policies. Research Objectives: This study aims to conduct a bibliometric analysis of research on physical activity and physical fitness among preschool children in Asia from 2020 to 2024. Methods: The analysis was based on publications from Scopus and Web of Science, focussing on keyword co-occurrence, citation analysis, and co-authorship networks. We used tools like ScientoPy and VOSviewer to assess key metrics such as the number of publications, citations, and influential contributors. Findings/Results: The study reveals significant trends, with a peak in research productivity in 2022, reflecting heightened global attention on early physical health. China, Japan, and Iran led contributions, with China dominating in publication volume. Notable researchers included Saeed Ghorbani and emerging contributors Ahmad Chaeroni and Amir Dana. Leading journals, such as the International Journal of Environmental Research and Public Health and Frontiers in Public Health, were prominent sources. Conclusion: Despite a decline in productivity post-2022, PA and PF research for preschoolers remains important. These shifting trends provide opportunities for researchers to explore new areas or innovate approaches. Significant contributions from Asian researchers also indicate a geographic shift in the global research focus. This study also highlights the importance of physical activity in preschoolers and how trends in scientific publications can help policymakers formulate more effective interventions to improve children's fitness.

The STAP-Net: A new health perception and prediction framework for bearing-rotor systems under special working conditions

The health perception of bearing-rotor systems and their remaining useful life prediction has been a critical and challenging theme in the field of Prognostic and Health Management (PHM). Deep learning has become a prominent area of PHM research. However, current models have difficulty in adequately extracting the deep degradation characteristics of bearings and effectively capturing time-series information during the failure process. Also, most remaining useful life (RUL) prediction methods focus on point estimation, limiting their ability to quantify prediction uncertainty. To address these shortcomings, this study proposes a novel health perception and prediction framework, the Spatiotemporal Self-Attention Mechanism Probabilistic model (STAP-Net). The framework embodies the principles of lightweight design, focusing, and probabilistic approaches, and is tailored for bearing rotor systems operating under unique conditions. The key innovation of STAP-Net is the integration of a modified gate recurrent unit, known as the Weight Diminish Recurrent Unit (WDRU). It greatly reduces the training parameters of the proposed STAP-Net framework and improves the convergence speed of the framework while ensuring the prediction accuracy. Through analyzing the bearing-rotor system degradation data, the efficacy of STAP-Net is validated under special operating conditions such as misalignment and abrasive wear. The superior performance of the proposed framework is evaluated and confirmed based on 3 key metrics: high-precision point prediction, suitable prediction intervals, and reliable probabilistic prediction results.

Enhancing the performance of Ga2O3 FinFETs through double fin channels and buried oxide

In this study, double fin channels and buried oxide has been implemented on Ga2O3 FinFET. Exhaustive simulations have been performed to study the performance of the proposed device and its comparison has been drawn with the device with only double fin channels without buried oxide, and the conventional FinFET. Various device characteristics such as output and transfer characteristics etc., have been studied and several figure of merits (FoMs) such as transconductance, parasitic capacitances, gain bandwidth product, intrinsic delay etc., have also been obtained. Further, the inverter has been designed using all the devices under consideration. It has been demonstrated that the inverter using the proposed device exhibits excellent characteristics in terms of significant improvement in key metrics such as noise margin, transient response etc., as compared to the inverter using conventional devices. The current study also lays the groundwork for designing various high-performance circuits for ultra-high frequency applications.

УРОВЕНЬ Р-СЕЛЕКТИНА, ИНТЕГРИНА-Β3 В ПЛАЗМЕ КРОВИ У ПАЦИЕНТОВ С ИШЕМИЧЕСКОЙ БОЛЕЗНЬЮ СЕРДЦА ПОСЛЕ ЧРЕСКОЖНОГО КОРОНАРНОГО ВМЕШАТЕЛЬСТВА

Background. Coronary artery disease (CAD) is a leading cause of mortality and disability worldwide. Modern treatment methods, such as percutaneous coronary intervention (PCI), have significantly improved patients’ outcomes. However, the risk of stent restenosis remains a significant problem. Objective. To determine the levels of biochemical markers (P-selectin and integrin-β3) in the plasma of patients with coronary artery disease (CAD) after percutaneous coronary intervention (PCI), and to evaluate the effectiveness of various models for predicting in-stent restenosis. Material and methods. The study included 209 CAD patients divided into four groups: healthy individuals, patients with chronic CAD without indications for invasive coronary angiography, patients with CAD who underwent elective PCI, and patients with in-stent restenosis. Plasma levels of P-selectin and integrin-β3 were measured using enzymelinked immunosorbent assay (ELISA). Results. In-stent restenosis occurred in 12 patients (8.05%) after elective PCI. Analysis showed that P-selectin and integrin-β3 levels did not have statistically significant differences between patient groups. The predictive model including BMI, ventricular extrasystole, number of stents, diabetes mellitus, and multifocal atherosclerotic coronary artery disease showed the best key metrics efficiency. Conclusion. P-selectin and integrin-β3 levels did not show significant differences in patients with in-stent restenosis. The model including BMI, VE, number of stents, DM, and MFCAD is the most effective for predicting restenosis recurrence.

Translating primary care to telehealth: analysis of in-person paediatric consultations and role of the carers.

The usage of telehealth in general practice (GP) has risen substantially ever since the COVID-19 pandemic. Over this timeframe, telehealth has provided care for all patient demographics, including the paediatric population (aged<18). However, the translatability of telehealth (ie, whether in-person tasks can be supported remotely via telehealth) rarely considers the paediatric population or their carers. To examine the degree of translatability to telehealth for in-person GP consultations on paediatric patients with consideration of the carers' roles. This study screened 281 videos of in-person GP consultations set within UK general practices, and 20 of them were eligible for analysis. Secondary analysis of in-person GP consultations to examine tasks, physical artefacts, examinations and the interaction between carer, patient and GP. A novel scoring method revolving around two key metrics, taking into consideration the carer, was designed to analyse whether the tasks performed can be supported via telehealth. Analysis of 20 eligible consultations revealed 13 distinct physical examinations, 19 physical artefacts and 17 clinical tasks. Of these 17 clinical tasks, 41% were deemed 'definitely or easily translatable to telehealth,' ' 29% 'somewhat translatable with patient-provided equipment,' 12% 'potentially translatable,' and 18% 'currently untranslatable.' The average telehealth translatability score was 6.1/10, which suggests possible challenges with telehealth support. Regarding carer involvement, 90% of consultations involved collecting patient history, 70% placation of child, and 40% had physical support during examinations. Tasks performed during paediatric in-person GP consultations may not be easily translatable to telehealth and caution should be exercised when considering its translatability to telehealth.

A comprehensive analysis of wind power integrated with solar and hydrogen storage systems: Case study of Java's Southern coast

Wind and solar energy are vital to the global transition toward sustainable energy systems, driven by the need to reduce fossil fuel dependence, mitigate climate change, and enhance energy security. This study aims to optimize system performance by integrating hydrogen technology and addressing capacity shortages and excess energy. First, a comprehensive analysis of wind characteristics in a strategically important area to meet unaccomplished Indonesia's 2023 wind energy targets, focusing on Java's southern coast using wind speed data from the System Advisor Model (SAM), was conducted. Four scenarios are then evaluated: wind turbine (WT)-battery energy storage system (BESS), WT-photovoltaic (PV)-BESS, WT-fuel cell (FC)-electrolyzer (EL)-hydrogen tank (H2T), and WT-PV–FC–EL-H2T. Key metrics analyzed include excess energy, Levelized Cost of Electricity (LCOE), Net Present Cost (NPC), capacity shortage (CS), and electrolyzer full-load hours (EFH). Results show that average wind speeds reach 4.2 m/s in Pandeglang, with the WT–FC–EL-H2T system being the most reliable, exhibiting a 5% capacity shortage and 68.5% excess electricity. The WT-PV–FC–EL scenario is the most cost-effective, with a COE of $0.508/kWh and an NPC of $2.6 million. These findings provide valuable insights for improving sustainable energy infrastructure in the region.

Efficient Thermal Integration Model based on a Biogas-fired Gas Turbine Cycle (GTC) for Electricity and Desalination Applications; Thermo-Economic and GA-based Optimization

As the global energy demand continues to rise, there is an urgent need to improve the efficiency and sustainability of power generation systems. This study integrated a modified supercritical carbon dioxide (S-CO2) and multi-effect desalination (MED) units to recover residual heat from a gas turbine cycle (GTC) in two stages, significantly enhancing electricity production while reducing the environmental footprint of the GTC. The significance of this study lies in its comprehensive approach, combining thermodynamic, environmental, and thermoeconomic analyses alongside thorough sensitivity evaluations. A triple optimization framework was implemented to optimize the system's performance, focusing on key metrics such as exergy efficiency, CO2 reduction rates, and levelized energy cost, utilizing the NSGA-II and the TOPSIS decision-making method in MATLAB software. Economic viability was assessed through a net present value (NPV) analysis, demonstrating substantial profitability. Finally, a comparison study of the devised system CO2 emissions rate was performed for different renewable energy sources. A specific application of the devised system is its capacity to generate 1.415 m³/h of distilled water while generating 1441 kW of electricity. Sensitivity analysis identified the combustion chamber temperature as the most critical design parameter, with a sensitivity index of 0.328. The optimum economic indicators showed marked improvement, with the NPV increasing from 2.371 M$ to 10.75 M$ and the payback period decreasing from 13.28 years to 7.18 years.

Assessment of noise pollution-prone areas using an explainable geospatial artificial intelligence approach

This research aims to use the power of geospatial artificial intelligence (GeoAI), employing the categorical boosting (CatBoost) machine learning model in conjunction with two metaheuristic algorithms, the firefly algorithm (CatBoost-FA) and the fruit fly optimization algorithm (CatBoost-FOA), to spatially assess and map noise pollution prone areas in Tehran city, Iran. To spatially model areas susceptible to noise pollution, we established a comprehensive spatial database encompassing data for the annual average Leq (equivalent continuous sound level) from 2019 to 2022. This database was enriched with critical spatial criteria influencing noise pollution, including urban land use, traffic volume, population density, and normalized difference vegetation index (NDVI). Our study evaluated the predictive accuracy of these models using key performance metrics, including root mean square error (RMSE), mean absolute error (MAE), and receiver operating characteristic (ROC) indices. The results demonstrated the superior performance of the CatBoost-FA algorithm, with RMSE and MAE values of 0.159 and 0.114 for the training data and 0.437 and 0.371 for the test data, outperforming both the CatBoost-FOA and CatBoost models. ROC analysis further confirmed the efficacy of the models, achieving an accuracy of 0.897, CatBoost-FOA with an accuracy of 0.871, and CatBoost with an accuracy of 0.846, highlighting their robust modeling capabilities.Additionally, we employed an explainable artificial intelligence (XAI) approach, utilizing the SHAP (Shapley Additive Explanations) method to interpret the underlying mechanisms of our models. The SHAP results revealed the significant influence of various factors on noise-pollution-prone areas, with airport, commercial, and administrative zones emerging as pivotal contributors.

Low-Temperature Oxidation Pathways are Critical to Thermal Incineration of PFAS-Laden Materials

With growing desire to destroy per- and poly-fluoroalkyl substances (PFAS) now known to be detrimental to human health, a sound understanding of fluorocarbon combustion chemistry is important to efficient thermal destruction within incinerators. While most fluorocarbon combustion models and the sets of reactions contained within them were originally developed for the high temperatures encountered in flame suppression applications, they have often been used to assess PFAS destruction in incinerators, which emphasize a lower range of temperatures. We present results that demonstrate that low-temperature fluorocarbon oxidation pathways—not yet known to play a role in fluorocarbon combustion—impact key incinerator performance metrics, including: PFAS surrogate mole fractions, products of incomplete destruction, and waste destruction efficiencies. The results further point to the utility of NO as a potential additive. The present results show the influence of these pathways for CF3O2, for which some data are available, but analogous pathways would also occur for other fluoroalkylperoxy radicals, for which little is known. The results demonstrate the need for future work to identify and characterize low-temperature pathways more generally, consider such pathways in kinetic model development, and experimentally probe intermediate temperature conditions to better understand, design, and control thermal destruction technologies for improved PFAS management.

Test Methodology for Short-Circuit Assessment and Safe Operation Identification for Power SiC MOSFETs

The short-circuit (SC) immunity of power silicon carbide (SiC) MOSFETs is critical for high-reliability applications, where robust monitoring and protection strategies are essential to ensure system safety. Despite their superior voltage blocking capabilities and high energy efficiency, SiC MOSFETs exhibit greater sensitivity to SC-induced degradation compared to their silicon counterparts. This increased vulnerability necessitates the precise assessment of the key SC performance metrics, such as short-circuit withstand time (TSCWT), as well as a deeper understanding of the failure mechanisms. In this study, a comprehensive experimental methodology for evaluating the SC behavior of SiC MOSFETs is presented and validated using industrial references. The investigation further explores the concept of a Safe Operating Area (SOA) under SC conditions, highlighting the significant impact of quasi-simultaneous SC events on device lifetime. Additionally, an application case study demonstrates how these events can drastically reduce the device’s lifespan.

Analyzing component failures in series-parallel systems with dependent components

This paper investigates a series-parallel system comprising N independent subsystems with interchangeable dependent components, a prevalent reliability structure in engineering and network design. The primary aim of this research is to derive the joint probability distribution of the number of failed components within these configurations, considering component dependence and varying distributions across subsystems. This approach reflects a more realistic scenario than previously explored in the literature. Initially, the analysis is conducted for systems with two subsystems and subsequently extended to encompass configurations with N subsystems. The study also evaluates key reliability metrics including the average number of failed components and the mean time to failure (MTTF) of the entire system, theoretically proving that the system’s MTTF increases with the number of components under certain sufficient conditions. In addition to probabilistic analysis, an optimization problem is addressed to determine the optimal allocation of components within each subsystem. The objective is to minimize the average cost associated with corrective maintenance, thereby enhancing the cost-effectiveness of system operation.

Blood pressure abnormality detection and Interpretation utilizing Explainable Artificial Intelligence

ObjectiveHypertension is a pressing medical dysfunction that increases the risks of many fatal diseases. Early detection of hypertension can be crucial to lead a healthy life. Machine learning (ML) can be useful for the early prediction of a patient's likelihood of having a blood pressure abnormality and preventing it. Explainable artificial intelligence (XAI) is a state-of-the-art ML toolset that helps us understand and explain the prediction of an ML model. This research aims to build an automatic blood pressure anomaly detection system with maximum accuracy using the fewest features and learn why a model arrived at a particular result using XAI. MethodsThis research utilized the "Blood Pressure Data for Disease Prediction" dataset from Kaggle. Data were collected from medical reports of random participants in 2019 based on the presence of blood pressure abnormality, chronic kidney disease, and adrenal and thyroid disorders. We have used several ML algorithms (extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), decision tree (DT), and Logistic regression (LR)) to predict blood pressure abnormality based on patient's data. Principal component analysis (PCA) and recursive feature elimination (RFE) algorithms are used as feature optimizers. The receiver operating characteristic (ROC) curve analysis and accuracy were the key outcome metrics. Through the experiment, we have also calculated various performance measurement techniques like precision, recall, specificity, F1 score, and kappa to pin down the model with the best performance. Moreover, we have implemented several XAI methods namely permutation feature importance (PFI), partial dependence plots (PDP), Shapley additive explanations (SHAP), and local interpretable model-agnostic explanations (LIME) for additional exploration of our best model. ResultsThe combination of RFE and XGBoost provides the most significant results. The results of the study show that the algorithm has an AUC of 0.95, indicating good discriminatory power in detecting abnormal BP. The accuracy, precision, recall, specificity, F1-score, and kappa gained are 91.50%, 88.64%, 92.65%, 92.27%, 90.83%, and 0.8 respectively. According to the results of the XAI experiment, the genetic pedigree coefficient and hemoglobin level in a patient contribute the most to blood pressure abnormality prediction. Adrenal and thyroid diseases, as well as chronic kidney illness, have an impact on the projections. Existing research backs up this conclusion. ConclusionWhile comparing to previous works on this dataset, the results of our research are superior and the use of XAI shed new light on our model's prediction. This study would provide new insight into blood pressure detection in the medical profession.

Advancing police-researcher collaboration and evidence-based policing: an evaluation of the applied criminology and data management course

ABSTRACT While the demand for evidence-based policing (EBP) has increased and researchers continue to generate important research findings, few targeted educational efforts have been made to nurture effective police-researcher collaboration and integrate EBP into police practice. The current study evaluates a 16-month-long Applied Criminology and Data Management Course (ACDC), which aimed to train police executives and early-career researchers to work together, produce EBP research, and disseminate their findings. Survey and observational data assess participant progress on four key Kirkpatrick evaluation model metrics: reaction, learning, behavior, and results. ACDC participants demonstrated satisfaction with the program and knowledge of skills required for effective collaboration and research. Most notably, they demonstrated application of skills through applied research and dissemination of results. Participants proved committed to advancing EBP via trainings to police executives and community stakeholders, publications, presentations, promotions to various relevant positions, and secured grant funding. Overall, these preliminary results suggest that ACDC can serve as a successful and feasible model for advancing EBP.