Analytics

The Holy Bible is the most read book in the world, originally written in Aramaic, Hebrew, and Greek over a time span in the order of centuries by many people, and formed by a combination of various literary styles, such as stories, prophecies, poetry, instructions, and others. As such, the Bible is a complex text to be analyzed by humans and machines. This paper provides a systematic survey of the application of Artificial Intelligence (AI) and some of its subareas to the analysis of the Biblical scriptures. Emphasis is given to what types of tasks are being solved, what are the main AI algorithms used, and their limitations. The findings deliver a general perspective on how this field is being developed, along with its limitations and gaps. This research follows a procedure based on three steps: planning (defining the review protocol), conducting (performing the survey), and reporting (formatting the report). The results obtained show there are seven main tasks solved by AI in the Bible analysis: machine translation, authorship identification, part of speech tagging (PoS tagging), semantic annotation, clustering, categorization, and Biblical interpretation. Also, the classes of AI techniques with better performance when applied to Biblical text research are machine learning, neural networks, and deep learning. The main challenges in the field involve the nature and style of the language used in the Bible, among others. Full article

Traffic prediction, as a core task to alleviate urban congestion and optimize the transport system, has limitations in the integration of multimodal data, making it difficult to comprehensively capture the complex spatio-temporal characteristics of the transport system. Although some studies have attempted to introduce multimodal data, they mostly rely on resource-intensive deep neural network architectures, which have difficultly meeting the demands of practical applications. To this end, we propose a traffic prediction framework based on simple machine learning techniques that effectively integrates property features, amenity features, and emotion features (PAE features). Validated with large-scale real datasets, the method demonstrates excellent prediction performance while significantly reducing computational complexity and deployment costs. This study demonstrates the great potential of simple machine learning techniques in multimodal data fusion, provides an efficient and practical solution for traffic prediction, and offers an effective alternative to resource-intensive deep learning methods, opening up new paths for building scalable traffic prediction systems. Full article

Deoxyribonucleic acid, more commonly known as DNA, is a fundamental genetic material in all living organisms, containing thousands of genes, but only a subset exhibit differential expression and play a crucial role in diseases. Microarray technology has revolutionized the study of gene expression, with two primary types available for expression analysis: spotted cDNA arrays and oligonucleotide arrays. This research focuses on the statistical analysis of data from spotted cDNA microarrays. Numerous models have been developed to identify differentially expressed genes based on the red and green fluorescence intensities measured using these arrays. We propose a novel approach using a Gaussian copula model to characterize the joint distribution of red and green intensities, effectively capturing their dependence structure. Given the right-skewed nature of the intensity distributions, we model the marginal distributions using gamma distributions. Differentially expressed genes are identified using the Bayes estimate under our proposed copula framework. To evaluate the performance of our model, we conduct simulation studies to assess parameter estimation accuracy. Our results demonstrate that the proposed approach outperforms existing methods reported in the literature. Finally, we apply our model to Escherichia coli microarray data, illustrating its practical utility in gene expression analysis. Full article

Graduate salaries are a significant concern for graduates, employers, and policymakers, as various factors influence them. This study investigates determinants of graduate salaries in the UK, utilising survey data from HESA (Higher Education Statistical Agency) and integrating advanced machine learning (ML) explanatory techniques with statistical analytical methodologies. By employing multi-stage analyses alongside machine learning models such as decision trees, random forests and the explainability with SHAP stands for (Shapley Additive exPanations), this study investigates the influence of 21 socioeconomic and demographic variables on graduate salary outcomes. Key variables, including institutional reputation, age at graduation, socioeconomic classification, job qualification requirements, and domicile, emerged as critical determinants, with institutional reputation proving the most significant. Among ML methods, the decision tree achieved a standout with the highest accuracy through rigorous optimisation techniques, including oversampling and undersampling. SHAP highlighted the top 12 influential variables, providing actionable insights into the interplay between individual and systemic factors. Furthermore, the statistical analysis using ANOVA (Analysis of Variance) validated the significance of these variables, revealing intricate interactions that shape graduate salary dynamics. Additionally, domain experts’ opinions are also analysed to authenticate the findings. This research makes a unique contribution by combining qualitative contextual analysis with quantitative methodologies, machine learning explainability and domain experts’ views on addressing gaps in the existing identification of graduate salary predicting components. Additionally, the findings inform policy and educational interventions to reduce wage inequalities and promote equitable career opportunities. Despite limitations, such as the UK-specific dataset and the focus on socioeconomic and demographic variables, this study lays a robust foundation for future research in predictive modelling and graduate outcomes. Full article

This study explores the role of cognitive performance in the general health of older Europeans aged 50 and over, focusing on gender differences, using data from 336,500 respondents in the sixth wave of the Survey of Health, Aging, and Retirement in Europe (SHARE). Cognitive functioning was assessed through self-rated reading and writing skills, orientation in time, numeracy, memory, verbal fluency, and word-list learning. General health status was estimated by constructing a composite index of physical and mental health-related measures, including chronic diseases, mobility limitations, depressive symptoms, self-perceived health, and the Global Activity Limitation Indicator. Participants were classified into good or poor health status, and logistic regression models assessed the predictive significance of cognitive variables on general health, supplemented by a relative importance analysis to estimate relative effect sizes. The results indicated that males had a 51.1% lower risk of reporting poor health than females, and older age was associated with a 4.0% increase in the odds of reporting worse health for both genders. Memory was the strongest predictor of health status (26% of the model $R^2$), with a greater relative contribution than the other cognitive variables. No significant gender differences were found. While this study estimates the odds of reporting poorer health in relation to gender and various cognitive characteristics, adopting a lifespan approach could provide valuable insights into the longitudinal associations between cognitive functioning and health outcomes. Full article

As the levels of automation and reliance on modern artificial intelligence (AI) approaches increase across multiple industries, the importance of the human-centered perspective becomes more evident. Various actors in such industrial applications, including equipment operators and decision makers, have their needs and preferences that often do not align with the decisions produced by black-box models, potentially leading to mistrust and wasted productivity gain opportunities. In this paper, we examine these issues through the lenses of visual analytics and, more broadly, interactive visualization, and we argue that the methods and techniques from these fields can lead to advances in both academic research and industrial innovations concerning the explainability of AI models. To address the existing gap within and across the research and application fields, we propose a conceptual framework for visual analytics design and evaluation for such scenarios, followed by a preliminary roadmap and call to action for the respective communities. Full article

This study investigates how the Federal Open Market Committee’s (FOMC) statements impact healthcare spending, mental health trends, and stock performance in healthcare and tech sectors By analyzing FOMC’s sentiment from 2018 to 2024, we found that higher sentiment correlates with increased depressive disorders (2019–2021) and tech stock returns, especially for the “Magnificent Seven” (like Apple and Amazon). Although healthcare stocks showed weaker ties to sentiment, Granger causality tests suggest some influence, hinting at ways to adjust stock strategies based on FOMC trends. These results highlight how central bank communication can shape both mental health dynamics and investment decisions in healthcare and technology. Full article

This study compares three machine learning and deep learning models—Support Vector Regression (SVR), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM)—for predicting market prices using the NGX All-Share Index dataset. The models were evaluated using multiple error metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Percentage Error (MPE), and R-squared. RNN and LSTM were tested with both 30 and 60-day windows, with performance compared to SVR. LSTM delivered better R-squared values, with a 60-day LSTM achieving the best accuracy (R-squared = 0.993) when using a combination of endogenous market data and technical indicators. SVR showed reliable results in certain scenarios but struggled in fold 2 with a sudden spike that shows a high probability of not capturing the entire underlying NGX pattern in the dataset correctly, as witnessed by the high validation loss during the period. Additionally, RNN faced the vanishing gradient problem that limits its long-term performance. Despite challenges, LSTM’s ability to handle temporal dependencies, especially with the inclusion of On-Balance Volume, led to significant improvements in prediction accuracy. The use of the Optuna optimisation framework further enhanced model training and hyperparameter tuning, contributing to the performance of the LSTM model. Full article

The ability to automate and personalize the recommendation of multimedia contents to consumers has been gaining significant attention recently. The burgeoning demand for digitization and automation of formerly analog communication processes has caught the attention of researchers and professionals alike. In light of the recent interest and anticipated transition to fully autonomous vehicles, this study proposes a text–image embedding method recommender system for the optimization of personalized multimedia content for in-vehicle infotainment. This study leverages existing pre-trained text embedding models and pre-trained image feature extraction methods. Previous research to date has focused mainly on textual-only or image-only analyses. By employing similarity measurements, this study demonstrates how recommendation of the most relevant multimedia content to consumers is enhanced through text–image embedding. Full article

Competitive intelligence (CI) is a critical tool for startups, enabling informed decision making through the systematic gathering and analysis of relevant information. This study aims to identify and prioritize the key factors influencing CI in startups, providing actionable insights for entrepreneurs, educators, and support organizations. Through a systematic literature review, key variables and components impacting competitive intelligence were identified. Two surveys were conducted to refine these components. The first employed a five-point Likert scale to evaluate the significance of each component, while the second used a pairwise comparison approach involving ten experts in CI and startup mentorship. Utilizing the fuzzy Analytical Network Process (ANP), this study ranked Technology Intelligence as the most critical factor, followed by market and Strategic Intelligence. Competitor Intelligence and Internet intelligence were deemed moderately important, while Organizational Intelligence ranked lowest. These findings emphasize the importance of technology-driven insights and market awareness in fostering startups’ competitive advantage and informed decision making. This study provides a structured framework to guide startups in prioritizing CI efforts, offering practical strategies for navigating dynamic market conditions and achieving long-term success. Full article

Determining the ‘best-fitting’ distribution for data is an important problem in data analysis. Specifically, observing how the distribution of data changes as values below (or above) a threshold are omitted from analyses can be of use in various applications, from animal movement to the modelling of natural phenomena. Such truncated distributions, known as hazard functions, are widely studied and well understood in survival analysis, although rarely widely used in data analysis. Here, by considering the hazard and reverse-hazard functions, we demonstrate a qualitative assessment of the ‘best-fit’ distribution of data. Specifically, we highlight the potential advantages of this method when determining whether power-law behaviour may or may not be present in data. Finally, we demonstrate this approach using some real-world datasets. Full article

The rapid expansion of big data has transformed research practices across disciplines, yet disparities exist in its adoption among U.S. institutions of higher education. This study examines trends in NSF-funded big data-driven research across research domains, institutional classifications, and directorates. Using a quantitative approach and natural language processing (NLP) techniques, we analyzed NSF awards from 2006 to 2022, focusing on seven NSF research areas: Biological Sciences, Computer and Information Science and Engineering, Engineering, Geosciences, Mathematical and Physical Sciences, Social, Behavioral and Economic Sciences, and STEM Education (formally known as Education and Human Resources). Findings indicate a significant increase in big data-related awards over time, with CISE (Computer and Information Science and Engineering) leading in funding. Machine learning and artificial intelligence are dominant themes across all institutions’ classifications. Results show that R1 and non-minority-serving institutions receive the majority of big data-driven research funding, though HBCUs have seen recent growth due to national diversity initiatives. Topic modeling reveals key subdomains such as cybersecurity and bioinformatics benefiting from big data, while areas like Biological Sciences and Social Sciences engage less with these methods. These findings suggest the need for broader support and funding to foster equitable adoption of big data methods across institutions and disciplines. Full article

This bibliometric review investigates the advancements in machine learning techniques for predictive maintenance, focusing on the use of Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) for fault detection in wheelset axle bearings. Using data from Scopus and Web of Science, the review analyses key trends, influential publications, and significant contributions to the field from 2000 to 2024. The findings highlight the performance of ANNs in handling large datasets and modelling complex, non-linear relationships, as well as the high accuracy of SVMs in fault classification tasks, particularly with small-to-medium-sized datasets. However, the study also identifies several limitations, including the dependency on high-quality data, significant computational resource requirements, limited model adaptability, interpretability challenges, and practical implementation complexities. This review provides valuable insights for researchers and engineers, guiding the selection of appropriate diagnostic models and highlighting opportunities for future research. Addressing the identified limitations is crucial for the broader adoption and effectiveness of machine learning-based predictive maintenance strategies across various industrial contexts. Full article

Predicting ncRNA–protein interactions (NPIs) is essential for understanding regulatory roles in cellular processes and disease mechanisms, yet experimental methods are costly and time-consuming. In this study, we propose NPI-WGNN, a novel weighted graph neural network model designed to enhance NPI prediction by incorporating topological insights from graph structures. Our approach introduces a bipartite version of the high-order common neighbor (HOCN) similarity metric to assign edge weights in an ncRNA–protein network, refining node embeddings via weighted node2vec. We further enrich these embeddings with centrality measures, such as degree and Katz centralities, to capture network hierarchy and connectivity. To optimize prediction accuracy, we employ a hybrid GNN architecture that combines graph convolutional network (GCN), graph attention network (GAT), and GraphSAGE layers, each contributing unique advantages: GraphSAGE offers scalability, GCN provides a global structural perspective, and GAT applies dynamic neighbor weighting. An ablation study confirms the complementary strengths of these layers, showing that their integration improves predictive accuracy and robustness across varied graph complexities. Experimental results on three benchmark datasets demonstrate that NPI-WGNN outperforms state-of-the-art methods, achieving up to 96.1% accuracy, 97.5% sensitivity, and an F1-score of 0.96, positioning it as a robust and accurate framework for ncRNA–protein interaction prediction. Full article

Breast cancer is the most prevalent type of disease among women. It has become one of the foremost causes of death among women globally. Early detection plays a significant role in administering personalized treatment and improving patient outcomes. Mammography procedures are often used to detect early-stage cancer cells. This traditional method of mammography while valuable has limitations in its potential for false positives and negatives, patient discomfort, and radiation exposure. Therefore, there is a probe for more accurate techniques required in detecting breast cancer, leading to exploring the potential of machine learning in the classification of diagnostic images due to its efficiency and accuracy. This study conducted a comparative analysis of pre-trained CNNs (ResNet50 and VGG16) and vision transformers (ViT-base and SWIN transformer) with the inclusion of ViT-base trained from scratch model architectures to effectively classify mammographic breast cancer images into benign and malignant cases. The SWIN transformer exhibits superior performance with 99.9% accuracy and a precision of 99.8%. These findings demonstrate the efficiency of deep learning to accurately classify mammographic breast cancer images for the diagnosis of breast cancer, leading to improvements in patient outcomes. Full article

The Bayesian information criterion (BIC) is a widely used statistical tool originally derived for fully observed data. The BIC formula includes the sample size and the number of estimated parameters in the penalty term. However, not all variables are available for every subject in planned missingness designs. This article demonstrates that a modified BIC, tailored for planned missingness designs, outperforms the original BIC. The modification adjusts the penalty term by using the average number of estimable parameters per subject rather than the total number of model parameters. This new criterion was successfully applied to item response theory models in two simulation studies. We recommend that future studies utilizing planned missingness designs adopt the modified BIC formula proposed here. Full article

Recent technology and equipment advancements have provided us with opportunities to better analyze Alzheimer’s disease (AD), where we could collect and employ the data from different image and genetic modalities that may potentially enhance the predictive performance. To perform better clustering in AD analysis, in this paper, we propose a novel model to leverage data from all different modalities/views, which can learn the weights of each view adaptively. Different from previous vanilla Non-negative matrix factorization which assumes data is linearly separable, we propose a simple yet efficient method based on kernel matrix factorization, which is not only able to deal with non-linear data structure but also can achieve better prediction accuracy. Experimental results on the ADNI dataset demonstrate the effectiveness of our proposed method, which indicates promising prospects for kernel application in AD analysis. Full article

Sentiment analysis is a technique used to understand the public’s opinion towards an event, product, or organization. For example, sentiment analysis can be used to understand positive or negative opinions or attitudes towards electric vehicle (EV) brands. This provides companies with valuable insight into the public’s opinion of their products and brands. In the field of natural language processing (NLP), transformer models have shown great performance compared to traditional machine learning algorithms. However, these models have not been explored extensively in the EV domain. EV companies are becoming significant competitors in the automotive industry and are projected to cover up to 30% of the United States light vehicle market by 2030 In this study, we present a comparative study of large language models (LLMs) including bidirectional encoder representations from transformers (BERT), robustly optimised BERT (RoBERTa), and a generalised autoregressive pre-training method (XLNet) using Lucid Motors and Tesla Motors YouTube datasets. Results evidenced that LLMs like BERT and her variants are off-the-shelf algorithms for sentiment analysis, specifically when fine-tuned. Furthermore, our findings present the need for domain adaptation whilst utilizing LLMs. Finally, the experimental results showed that RoBERTa achieved consistent performance across the EV datasets with an F1 score of at least 92%. Full article