Data Machine Learning Research Articles

Revolutionizing solar energy: enhancing panel efficiency with advanced machine learning techniques and data filtering

Revolutionizing solar energy: enhancing panel efficiency with advanced machine learning techniques and data filtering

Predicting potential target genes in molecular biology experiments using machine learning and multifaceted data sources

Experimental analysis of functionally related genes is key to understanding biological phenomena. The selection of genes to study is a crucial and challenging step, as it requires extensive knowledge of the literature and diverse biomedical data resources. Although software tools that predict relationships between genes are available to accelerate this process, they do not directly incorporate experiment information derived from the literature. Here, we develop LEXAS, a target gene suggestion system for molecular biology experiments. LEXAS is based on machine learning models trained with diverse information sources, including 24 million experiment descriptions extracted from full-text articles in PubMed Central by using a deep-learning-based natural language processing model. By integrating the extracted experiment contexts with biomedical data sources, LEXAS suggests potential target genes for upcoming experiments, complementing existing tools like STRING, FunCoup, and GOSemSim. A simple web interface enables biologists to consider newly derived gene information while planning experiments.

Urban aquifer health assessment and its management for sustainable water supply: an innovative approach using machine learning techniques

Water scarcity is a threat to resilient and sustainable cities as well as the resident population's well-being. This research represents a machine learning (ML) and geospatial data coupling along with groundwater sustainability management strategy (GSMS) components in a stepped methodological approach for urban, peri-urban aquifer sustainability management in Vizianagaram extended city limit in Southern India. Random forest (RF) and support vector machine (SVM) are two ML models in combination with geospatial data (hydrogeological and geo-environmental controlling factors) coupling predicted probable groundwater occurrence by categorizing different groundwater potential zones (GWPZ). The prediction accuracy determined by the area under the receiver operation curve (AUROC) demonstrated accuracy of >80 %, with the RF model being the highest at 88.40 %. Integration of GWPZ with policy and legislation, stakeholder involvement, sensitization, and linkage, along with strengths, weaknesses, opportunities, and threats (SWOT) analysis in the form of GSMS, can help policymakers, planners, and government authorities achieve sustainable measures near to reality and future adaptability.

Sleep Quality, Nutrient Intake, and Social Development Index Predict Metabolic Syndrome in the Tlalpan 2020 Cohort: A Machine Learning and Synthetic Data Study.

This study investigated the relationship between Metabolic Syndrome (MetS), sleep disorders, the consumption of some nutrients, and social development factors, focusing on gender differences in an unbalanced dataset from a Mexico City cohort. We used data balancing techniques like SMOTE and ADASYN after employing machine learning models like random forest and RPART to predict MetS. Random forest excelled, achieving significant, balanced accuracy, indicating its robustness in predicting MetS and achieving a balanced accuracy of approximately 87%. Key predictors for men included body mass index and family history of gout, while waist circumference and glucose levels were most significant for women. In relation to diet, sleep quality, and social development, metabolic syndrome in men was associated with high lactose and carbohydrate intake, educational lag, living with a partner without marrying, and lack of durable goods, whereas in women, best predictors in these dimensions include protein, fructose, and cholesterol intake, copper metabolites, snoring, sobbing, drowsiness, sanitary adequacy, and anxiety. These findings underscore the need for personalized approaches in managing MetS and point to a promising direction for future research into the interplay between social factors, sleep disorders, and metabolic health, which mainly depend on nutrient consumption by region.

Explainable artificial intelligence for predicting red blood cell transfusion in geriatric patients undergoing hip arthroplasty: Machine learning analysis using national health insurance data.

This study uses machine learning and population data to analyze major determinants of blood transfusion among patients with hip arthroplasty. Retrospective cohort data came from Korea National Health Insurance Service claims data for 19,110 patients aged 65 years or more with hip arthroplasty in 2019. The dependent variable was blood transfusion (yes vs no) in 2019 and its 31 predictors were included. Random forest variable importance and Shapley Additive Explanations were used for identifying major predictors and the directions of their associations with blood transfusion. The random forest registered the area under the curve of 73.6%. Based on random forest variable importance, the top-10 predictors were anemia (0.25), tranexamic acid (0.17), age (0.16), socioeconomic status (0.05), spinal anesthesia (0.05), general anesthesia (0.04), sex (female) (0.04), dementia (0.03), iron (0.02), and congestive heart failure (0.02). These predictors were followed by their top-20 counterparts including cardiovascular disease, statin, chronic obstructive pulmonary disease, diabetes mellitus, chronic kidney disease, peripheral vascular disease, liver disease, solid tumor, myocardial infarction and hypertension. In terms of max Shapley Additive Explanations values, these associations were positive, e.g., anemia (0.09), tranexamic acid (0.07), age (0.09), socioeconomic status (0.05), spinal anesthesia (0.05), general anesthesia (0.04), sex (female) (0.02), dementia (0.03), iron (0.04), and congestive heart failure (0.03). For example, the inclusion of anemia, age, tranexamic acid or spinal anesthesia into the random forest will increase the probability of blood transfusion among patients with hip arthroplasty by 9%, 7%, 9% or 5%. Machine learning is an effective prediction model for blood transfusion among patients with hip arthroplasty. The high-risk group with anemia, age and comorbid conditions need to be treated with tranexamic acid, iron and/or other appropriate interventions.

Feature selection based on dataset variance optimization using Hybrid Sine Cosine – Firehawk Algorithm (HSCFHA)

Feature selection plays a pivotal role in preprocessing data for machine learning (ML) models. It entails choosing a subset of pertinent features to enhance the model’s accuracy and minimize overfitting. Wrapper methods based on metaheuristics are one approach to feature selection, leveraging the predictive accuracy of a learning algorithm to form a condensed set of features. Traditionally, this method uses K-Nearest Neighbor (KNN) for maximizing accuracy as its cost function. However, this approach often yields less than optimal results in large sample spaces and demands considerable computational resources. To circumvent the shortcomings of this approach, this work proposes a novel metaheuristic algorithm, termed the Hybrid Sine Cosine Firehawk Algorithm. Furthermore, a novel feature selection technique is designed that uses this hybrid algorithm to eliminate insignificant and redundant features by incorporating the minimization of dataset variance in the cost function. Additionally, the hybridization of multiple metaheuristic algorithms produces the best features of each algorithm to improve the exploration ability. The proposed technique is tested on 22 University of California Irvine datasets containing low, medium and high dimensional datasets and compared to the traditional KNN-based approach. The technique is also compared with other state-of-the-art metaheuristic techniques, namely Particle Swarm Optimizer, Grey Wolf Optimizer, Whale Optimization Algorithm, Hybrid Ant Colony Optimizer and Improved Binary Bat Algorithm. The results show significant improvements over previous techniques in terms of minimal loss in essential data while reducing the size of the raw data in considerably less time, as well as a well-balanced confusion matrix.

AI-DRIVEN PREDICTIVE ANALYTICS IN AGRICULTURAL SUPPLY CHAINS: A REVIEW: ASSESSING THE BENEFITS AND CHALLENGES OF AI IN FORECASTING DEMAND AND OPTIMIZING SUPPLY IN AGRICULTURE

This study provides a comprehensive review of the integration and impact of Artificial Intelligence (AI) in agricultural supply chains, focusing on its role in enhancing demand forecasting and optimizing supply. The primary objective was to assess how AI-driven predictive analytics transforms agricultural practices, addressing challenges, and shaping future trends. A systematic literature review and content analysis methodology were employed, utilizing academic databases and digital libraries to source peer-reviewed articles and conference papers published between 2014 and 2024. The inclusion criteria focused on studies related to AI applications in agricultural supply chains, while exclusion criteria filtered out non-peer-reviewed and irrelevant literature. Key findings reveal that AI significantly improves the accuracy and efficiency of demand forecasting and supply chain operations in agriculture. AI technologies, including machine learning and big data analytics, have led to advancements in real-time data analysis, predictive maintenance, and resource optimization. However, challenges such as data quality, infrastructure development, and skill gaps among agricultural professionals persist. The future landscape of AI in agriculture is marked by growth opportunities and challenges, including the need for equitable AI technology access and ethical considerations. The study recommends that industry leaders and policymakers invest in infrastructure, promote AI research and development, and provide training to facilitate AI adoption. Future research should focus on developing robust AI models tailored to agriculture, exploring AI's integration with emerging technologies, and assessing AI's long-term socio-economic impacts. This study contributes to understanding AI's current applications and future potential in transforming agricultural supply chains, offering valuable insights for stakeholders in the agricultural sector.
 Keywords: Artificial Intelligence, Agricultural Supply Chains, Predictive Analytics, Demand Forecasting.

A breakthrough in creep lifetime prediction: Leveraging machine learning and service data

Improvement of data-driven techniques, specifically machine learning (ML), in material science turned it into a powerful tool for predicting materials behavior. Accordingly, this study provides a ML prediction of empirical creep lifetimes of 9Cr-1Mo ex-service heater tubes that have been used in industry for up to 47 years. Data from over 90,000 h of stress rupture tests shows that the service parameters influence creep lifetime similar to mechanical properties. Employing six different ML algorithms, viz., K Nearest Neighbors (KNN), Support Vector Regressor (SVR), Random Forest (RF), Gradient Boosting (GB), Gaussian Process (GP), and Multi-Layer Perceptron (MLP) demonstrated that the GP and MLP methods performed significantly better in predicting the creep lifetimes rather than other algorithms. Finally, a validation set involving 12 samples was conducted, and the GP algorithm showed better agreement with experimental values than other ML and Larson-Miller Parameter approaches, illustrating the capability of this model to predict creep lifetimes.

Charting the Research Terrain for Large Old Trees: Findings from a Quantitative Bibliometric Examination in the Twenty-First Century

Despite their relatively small numbers, large old trees play disproportionately important roles in global biodiversity and ecosystem functions. There is a lack of systematic reviews and quantitative analyses of the accumulated literature. Understanding the research context and evolution could pump prime research and conservation endeavors. Using the comprehensive Web of Science, we applied VOSviewer (1.6.19) and CiteSpace (6.1R2) bibliometric software to examine the large old tree research field in 2000–2022. The queries of the bibliographic database generated quantitative–visual depictions in the form of knowledge maps. The nodes denote research intensity, and inter-node linkages denote the pathways and frequencies of collaborative activities. The research outputs differed significantly in terms of regions, countries, institutions, high-citation articles, productive researchers, hot topics, and research frontiers. Conspicuous spatial disparities were displayed, with the U.S.A., China, and Australia leading in publication counts and a cluster of European countries making considerable collective contributions. The research collaboration demonstrated a dichotomy: European countries networked more by geographical propinquity, and the top three countries connected by long-distance leap-frog jumps. The entrenched discrepancies between the endowed developed domains vis-à-vis the deprived developing domains were clearly expressed. The research productivity progressed through three stages: initial, growth, and flourishing. The leading institutions, researchers, and highly cited papers were recognized. The keyword analysis pinpointed diverse research hotspots: growth dynamics, conservation and management, ecological functions, and environmental response. This study informs recommendations for future research directions and cooperation on longevity mechanisms, evolutionary adaptation, dynamic monitoring, and temporal–spatial patterns. The integrated application of GIS, machine learning, and big data technologies could strengthen research capability.

Survey Paper on A Machine Learning Approach for Multiple Disease Prediction

Machine learning techniques have revolutionized the field of healthcare by enabling accurate and timely disease prediction. The ability to predict multiple diseases simultaneously can significantly improve early diagnosis and treatment, leading to better patient outcomes and reduced healthcare costs. This research paper explores the application of machine learning algorithms in predicting multiple diseases, focusing on their benefits, challenges, and future directions. We present an overview of various machine learning models and data sources commonly used for disease prediction. Additionally, we discuss the importance of feature selection, model evaluation, and the integration of multiple data modalities for enhanced disease prediction. The research findings highlight the potential of machine learning in multi- disease prediction and its potential impact on public health. Once more, I am applying machine learning model to identify that a person is affected with few disease or not. This training model takes a sample data and train itself for predicting disease. Key Words: Disease Prediction, Na ̈ıve Bayesian Networks, Random Forest, Decision Tree, Feature , Selection KNN.

Data-driven approach for sustainable geopolymer mortar production with treated sewage sludge

ABSTRACT This paper highlights an innovative approach to address the environmental challenges associated with waste management and construction materials. The study presents a new technique for utilising treated sewage sludge in the production of eco-friendly geopolymer mortar. Sewage sludge is a byproduct generated from wastewater treatment plants that poses significant environmental issues due to its disposal problems. Geopolymer mortar, on the other hand, is a sustainable construction material that can be produced by activating industrial waste materials, such as fly ash, using alkaline activators. By integrating machine learning algorithms and data visualisation techniques, this study optimises the mix parameters of geopolymer mortar while simultaneously reducing the negative impact of sewage sludge disposal. The experimental results show that sewage sludge ash can replace fly ash and fine aggregate in 1:3 geopolymer mortar by up to 30% and 20%, respectively, without any toxic or heavy metal residues. The compressive and flexural strength of the sludge-based mortar were comparable to ordinary geopolymer mortar, while water absorption and drying shrinkage were similar to control specimens. This research offers a unique solution to promote sustainability in waste management and construction industry by utilising waste materials, including fly ash and treated sewage sludge, for geopolymer production.

A Concise Review on Applications of Bioinspired Algorithms in Electrical Power System

The integration of bioinspired algorithms into electrical power systems has gained significant attention in recent years due to their potential to address complex optimization and control problems. This paper presents a concise review on the applications of bioinspired algorithms in various aspects of electrical power systems, including power generation, transmission, distribution, and utilization. The review starts with an overview on electrical power system and then discusses the fundamental concepts of bioinspired algorithms. Next, the paper explores the application of bioinspired algorithms in power generation. It examines their use in optimizing the operation and scheduling of power plants, maximizing renewable energy integration, and improving the efficiency of power generation processes. Moving on to power transmission and distribution, the review discusses how bioinspired algorithms can be applied to optimize the routing and scheduling of power flows, enhance fault detection and diagnosis, and improve the reliability and security of the grid infrastructure. Furthermore, the utilization of bioinspired algorithms in power systems is explored, focusing on load forecasting, demand response, energy management, and power quality enhancement. Finally, the paper concludes with a summary of the main findings and future research directions. It emphasizes the need for further exploration of bioinspired algorithms in electrical power systems, including the development of hybrid algorithms and their integration with emerging technologies such as machine learning and big data analytics.

Machine learning data sources in pediatric sleep research: assessing racial/ethnic differences in electronic health record-based clinical notes prior to model training.

Pediatric sleep problems can be detected across racial/ethnic subpopulations in primary care settings. However, the electronic health record (EHR) data documentation that describes patients' sleep problems may be inherently biased due to both historical biases and informed presence. This study assessed racial/ethnic differences in natural language processing (NLP) training data (e.g., pediatric sleep-related keywords in primary care clinical notes) prior to model training. We used a predefined keyword features set containing 178 Peds B-SATED keywords. We then queried all the clinical notes from patients seen in pediatric primary care between the ages of 5 and 18 from January 2018 to December 2021. A least absolute shrinkage and selection operator (LASSO) regression model was used to investigate whether there were racial/ethnic differences in the documentation of Peds B-SATED keywords. Then, mixed-effects logistic regression was used to determine whether the odds of the presence of global Peds B-SATED dimensions also differed across racial/ethnic subpopulations. Using both LASSO and multilevel modeling approaches, the current study found that there were racial/ethnic differences in providers' documentation of Peds B-SATED keywords and global dimensions. In addition, the most frequently documented Peds B-SATED keyword rankings qualitatively differed across racial/ethnic subpopulations. This study revealed providers' differential patterns of documenting Peds B-SATED keywords and global dimensions that may account for the under-detection of pediatric sleep problems among racial/ethnic subpopulations. In research, these findings have important implications for the equitable clinical documentation of sleep problems in pediatric primary care settings and extend prior retrospective work in pediatric sleep specialty settings.

LEVERAGING BIG DATA FOR PERSONALIZED MARKETING CAMPAIGNS: A REVIEW

The burgeoning field of big data analytics has revolutionized the landscape of marketing, offering unprecedented opportunities for personalized marketing campaigns. This review aims to synthesize the current state of knowledge on leveraging big data for personalized marketing, elucidating the objectives, methodologies, key findings, and conclusions drawn from recent research in this domain. The primary objective of this review is to explore how big data analytics can be effectively utilized to tailor marketing strategies to individual consumer preferences, behaviors, and patterns. Methodologically, the review adopts a comprehensive approach, examining a wide range of studies that employ various big data tools and techniques, including machine learning algorithms, data mining, and predictive analytics, in the context of personalized marketing. Key findings indicate that big data analytics significantly enhances the ability of marketers to understand and predict consumer behavior, leading to more effective targeting and segmentation strategies. The integration of big data has shown to improve customer engagement, satisfaction, and loyalty by delivering more relevant and timely marketing messages. However, challenges such as data privacy concerns, the need for advanced analytical skills, and the potential for data inaccuracies are also highlighted. In conclusion, while big data presents substantial opportunities for personalizing marketing campaigns, its effective implementation requires careful consideration of ethical implications, investment in technological infrastructure, and ongoing skill development. Future research directions include exploring the impact of emerging technologies like artificial intelligence and the Internet of Things (IoT) on personalized marketing, and developing frameworks for ethical data usage in marketing practices. This review underscores the transformative potential of big data in reshaping personalized marketing strategies, offering valuable insights for both practitioners and researchers in the field.
 Keywords: Big Data, Marketing Strategies, Consumer Behavior, Data Analytics, Personalized Marketing, Market Segmentation, Privacy Concerns, Ethical Challenges, Digital Transformation, Artificial Intelligence (AI).

Artificial intelligence for international business: Its use, challenges, and suggestions for future research and practice

AbstractThe emergence of artificial intelligence (AI) has transformed global business, aiding operational efficiency and innovation. It utilizes machine learning and big data analytics, driving predictive market trends and strategic decision‐making. However, despite the rising discussion and accessibility of AI tools, understanding its impact on international business remains limited. This article explores AI's potential in international business strategies, practices, and activities. To address this aim, we reviewed 37 articles in the existing literature to critically explore AI within the context of international business. More specifically, we explored how AI can be applied to innovation approaches in international business, international market selection, entry modes, foreign exchange, international human resource management, international supply chains, managing across cultures, and more topics. AI has necessitated changes in workplace configurations and the need for organizational and employee adjustments in response to this technology. As a result of the foregoing issues on AI integration within international business, our analysis provided an exploratory discussion around its use, challenges, managerial implications, and suggested areas requiring future studies.

A Review of Machine Learning Approaches for Brain Positron Emission Tomography Data Analysis.

Positron emission tomography (PET) imaging has moved forward the development of medical diagnostics and research across various domains, including cardiology, neurology, infection detection, and oncology. The integration of machine learning (ML) algorithms into PET data analysis has further enhanced their capabilities of including disease diagnosis and classification, image segmentation, and quantitative analysis. ML algorithms empower researchers and clinicians to extract valuable insights from complex big PET datasets, which enabling automated pattern recognition, predictive health outcome modeling, and more efficient data analysis. This review explains the basic knowledge of PET imaging, statistical methods for PET image analysis, and challenges of PET data analysis. We also discussed the improvement of analysis capabilities by combining PET data with machine learning algorithms and the application of this combination in various aspects of PET image research. This review also highlights current trends and future directions in PET imaging, emphasizing the driving and critical role of machine learning and big PET image data analytics in improving diagnostic accuracy and personalized medical approaches. Integration between PET imaging will shape the future of medical diagnosis and research.

Process Mining Organization (PMO) Based on Machine Learning Decision Making for Prevention of Chronic Diseases

This paper discusses a methodology to improve the prevention processes of chronic diseases such as diabetes and strokes. The research motivation is to find a new methodological approach to design advanced Diagnostic and Therapeutic Care Pathways (PDTAs) based on the prediction of chronic disease using telemedicine technologies and machine learning (ML) data processing techniques. The aim is to decrease health risk and avoid hospitalizations through prevention. The proposed method defines a Process Mining Organization (PMO) model, managing risks using a PDTA structured to prevent chronic risk. Specifically, the data analysis is focused on stroke risk. First, we applied and compared the Random Forest (RF) and Gradient Boosted Trees (GBT) supervised algorithms to predict stroke risk, and then, the Fuzzy c-Means unsupervised algorithm to cluster information on the predicted results. The application of the proposed approach is able to increase the efficiency of healthcare human resources and drastically decrease care costs.

The mountains are high and the emperor is far away: Credit scoring and the infrastructure of surveillance capitalism in China

AbstractPrevious research on calculative intermediaries shows how these effectively challenge, distort, and disrupt accounting practices in ways that policy‐makers might not anticipate. The promises of surveillance capitalism—with its attendant data architectures, datafication processes, and technological sophistication—are different, supposing more accurate ways of reading individuals and greater calculative certainty overall. Yet there is little empirical research to explore how surveillance capitalism manifests itself at the organizational level, either conceptually or operationally. As a result, it remains uncertain whether such specters of omniscience are as haunting in reality as they appear in theory. We explore these themes by way of an ethnographic study into credit scoring in China, showing how intermediary organizations developed a multiplicity of credit scoring models based on machine learning and big data that differed both from original expectations and from each other. These different “renditions” of credit scoring suggest that the data architectures of surveillance capitalism are just as much subject to challenge and adaptation by intermediary organizations as calculative practices, such as accounting, are in more analog environments.

The Effect of Smart Factory on the Continuous Improvement of the Production Process: A Review

This in-depth exploration uncovers the game-changing effect of smart factories on the continuous improvement of the production process, harnessing the power of advanced technologies. By closely examining key components such as Machine Learning, Virtual Reality, Additive Manufacturing, and Big Data Analysis, this study provides a detailed understanding of how these innovations shape the smart factory landscape. It highlights the adaptability and efficacy of these techniques by showcasing real-world implementations through case studies across several industrial sectors, going beyond the technical aspects. Moreover, the review delves into the practicalities of implementation, discussing strategies like Advanced Sensing, Control, Platform, and Model (ASCPM), and Visualization, Informatics, and Digital Manufacturing (VIDM). A SWOT analysis reveals the internal strengths and weaknesses, recognizing factors like interoperability, decentralization, and modularity, while also addressing challenges such as the need for personnel training and substantial investment. Looking ahead, the paper emphasizes the exciting opportunities presented by smart factories, including sustainable development, cost reduction, and the emergence of new business models. It also addresses potential threats, such as job losses and cybersecurity concerns. Ultimately, the review paints a human picture of smart factories, showcasing their roles or significance in the continuous improvement of the production process through their transformative impact on efficiency, waste reduction, cost savings, and innovation in manufacturing. The future research recommendations underscore the need to focus

Avoiding food waste from restaurant tickets: a big data management tool

PurposeThis study aims to address the global food waste problem in restaurants by analyzing customer sales information provided by restaurant tickets to gain valuable insights into directing sales of perishable products and optimizing product purchases according to customer demand.Design/methodology/approachA system based on unsupervised machine learning (ML) data models was created to provide a simple and interpretable management tool. This system performs analysis based on two elements: first, it consolidates and visualizes mutual and nontrivial relationships between information features extracted from tickets using multicomponent analysis, bootstrap resampling and ML domain description. Second, it presents statistically relevant relationships in color-coded tables that provide food waste-related recommendations to restaurant managers.FindingsThe study identified relationships between products and customer sales in specific months. Other ticket elements have been related, such as products with days, hours or functional areas and products with products (cross-selling). Big data (BD) technology helped analyze restaurant tickets and obtain information on product sales behavior.Research limitations/implicationsThis study addresses food waste in restaurants using BD and unsupervised ML models. Despite limitations in ticket information and lack of product detail, it opens up research opportunities in relationship analysis, cross-selling, productivity and deep learning applications.Originality/valueThe value and originality of this work lie in the application of BD and unsupervised ML technologies to analyze restaurant tickets and obtain information on product sales behavior. Better sales projection can adjust product purchases to customer demand, reducing food waste and optimizing profits.