Data Analysis Applications Research Articles

Feature Enhanced Spatial–Temporal Trajectory Similarity Computation

AbstractTrajectory similarity computation is a fundamental function in many applications of urban data analysis, such as trajectory clustering, trajectory compression, and route planning. In this paper, we study trajectory similarity computation on the road network. However, existing methods have been designed primarily for road network trajectories with spatial information, while ignoring the important temporal information in the real world. To solve this problem, we propose a Feature Enhanced Spatial–Temporal trajectory similarity computation framework FEST, which is a graph neural network (GNN) and sequence model pipeline. We first use the GNN model to capture global information on the road network. In particular, we enhance the process with multi-graph to learn multiple signals from the road network on different aspects. In addition to the original road network topology signal, we also take into account the content signal to learn spatial–temporal features from trajectory traffic, as well as the adaptive similarity signal of the road network to learn hidden features. From these three signals, we construct a multi-graph and use GCN to learn road intersection embedding jointly. Next, we propose a feature-enhanced Transformer with spatial–temporal information to learn correlation within the trajectory, and we further use mean-pooling to get the final trajectory embedding. We compare FEST with six trajectory similarity computation methods on two real-world datasets. The results show that FEST consistently outperforms all baselines and can improve the accuracy of the best-performing baseline.

Next generation sequencing: Forensic applications and policy considerations

AbstractNext generation sequencing (NGS) or massively parallel sequencing (MPS) is a high‐throughput technology that can be used to analyze DNA and RNA molecules with greater sensitivity, scalability, and speed than traditional Sanger sequencing. NGS systems are slowly gaining popularity in forensic science and may eventually become the future of forensic DNA analysis. The data generated can be utilized to conduct an array of forensic biology analyses such as short tandem repeats (STR) profiling, forensic genetic genealogy, predictive DNA phenotyping, and more. However, the adoption of NGS for forensic casework is associated with a lot of ethical, social, and legal concerns. This article provides a comprehensive review of NGS systems, data analysis, and forensic applications. It also provides policy considerations that aim to reduce harm and bias, while promoting informed consent, standardization, transparency, and accountability.This article is categorized under: Forensic Biology > Interpretation of Biological Evidence Forensic Biology > Ethical and Social Implications Forensic Biology > Forensic DNA Technologies

ScaDA: A novel statistical method for differential analysis of single-cell chromatin accessibility sequencing data.

Single-cell ATAC-seq sequencing data (scATAC-seq) has been widely used to investigate chromatin accessibility on the single-cell level. One important application of scATAC-seq data analysis is differential chromatin accessibility (DA) analysis. However, the data characteristics of scATAC-seq such as excessive zeros and large variability of chromatin accessibility across cells impose a unique challenge for DA analysis. Existing statistical methods focus on detecting the mean difference of the chromatin accessible regions while overlooking the distribution difference. Motivated by real data exploration that distribution difference exists among cell types, we introduce a novel composite statistical test named "scaDA", which is based on zero-inflated negative binomial model (ZINB), for performing differential distribution analysis of chromatin accessibility by jointly testing the abundance, prevalence and dispersion simultaneously. Benefiting from both dispersion shrinkage and iterative refinement of mean and prevalence parameter estimates, scaDA demonstrates its superiority to both ZINB-based likelihood ratio tests and published methods by achieving the highest power and best FDR control in a comprehensive simulation study. In addition to demonstrating the highest power in three real sc-multiome data analyses, scaDA successfully identifies differentially accessible regions in microglia from sc-multiome data for an Alzheimer's disease (AD) study that are most enriched in GO terms related to neurogenesis and the clinical phenotype of AD, and AD-associated GWAS SNPs.

Fault Monitoring and Analysis of Distributed New Energy Grids Using Simulation Data Models

Data analysis is essential for fault identification and detection in smart grids in order to maintain grid monitoring. Many DL algorithms have been developed recently for data analysis applications related to smart grids. To resolve these challenges, the study suggests a Deep Neural Network (DNN) for data-driven fault location detection and type of fault classification by exploiting the Modified Sand Cat Swarm Optimization (MSCSO) optimization. Here, the DNN is used to diagnose the faults and determine the position of the sites. Numerous synthetic field data sets derived from simulated models of different transmission line types are used for training and testing. The position and type of faults are predicted by the DNN classifier based on the fault signal features, in which the DNN weights are ideally tuned using a novel MSCSO optimization method that is the improved concept of Sand Cat Swarm Optimization (SCSO). Lastly, MATLAB/Simulink is used to implement the suggested DNN-based method for fault classification and its localization in transmission line. An intellectual IEEE 6-node network model is utilized to confirm the efficacy and reliability of these methods. The outcomes demonstrated its effectiveness in giving the system operator precise and detailed analytics for fault identification.

Enhanced Diabetes Prediction and Monitoring through Integration of Multimodal Data Using XGBoost

Abstract: Diabetes is a critical and become more complicated disease that can cause serious health problems if it is not adequately managed. The early diagnosis and treatment of diabetes is a critical component of the condition that can be greatly aided by data analysis and predictive algorithms. Through the use of data mining techniques, such as classification and prediction models, it is possible to analyse various elements of diabetes data and extract useful information that can be used for the early detection and prediction of the condition. One machine learning technique that can effectively and highly precisely predict diabetes is the XGBoost classifier. This method makes use of the gradient-boosting architecture and can handle large and intricate datasets with independent high-dimensional feature sets. Conversely, it is crucial to remember that the choice of the best algorithm for diabetes prediction could depend on the specifics of the data as well as the area of study being investigated. Data analysis and prediction methods can be applied not only to anticipate diabetes but also to monitor the disease's progression, find risk factors for diabetes and its complications, and assess the effectiveness of treatment. By using these techniques, medical professionals can obtain important insights into the disease's underlying causes, which helps them make informed decisions about patient management. The early detection and management of diabetes, a chronic disease that is rapidly expanding and poses major health risks, has the potential to be significantly improved through the application of data analysis and prediction algorithms. An accuracy rate of 89% was achieved by the XGBoost classifier, which demonstrated the highest level of performance.

Review on the Use of Data Analysis for Customer Segmentation and Personalization in Marketing Strategies

This paper studies the application of data analysis in the field of customer segmentation and personalization. With the advent of the era of big data, enterprises and organizations have rich data resources that contain important information about customer behavior, preferences, and purchasing habits. Through data analytics, companies can better understand customer needs and provide personalized products and services, thereby improving customer satisfaction and loyalty. This study aims to explore the application of data analytics in the field of customer segmentation and personalization, and provides some common data analysis methods. Data analysis methods include probabilistic methods and Bayesian methods, among others. Through case studies, the application of data analysis in the field of e-commerce is explained. The research results show that data analytics has important value and potential applications in customer segmentation and personalized marketing. However, data analysis still faces some challenges and limitations in practice, including data security and quality issues. Future research can continue to explore methods and techniques for data analysis, solve problems such as data privacy and security, and apply data analysis in more fields.

A scalable and transparent data pipeline for AI-enabled health data ecosystems.

Transparency and traceability are essential for establishing trustworthy artificial intelligence (AI). The lack of transparency in the data preparation process is a significant obstacle in developing reliable AI systems which can lead to issues related to reproducibility, debugging AI models, bias and fairness, and compliance and regulation. We introduce a formal data preparation pipeline specification to improve upon the manual and error-prone data extraction processes used in AI and data analytics applications, with a focus on traceability. We propose a declarative language to define the extraction of AI-ready datasets from health data adhering to a common data model, particularly those conforming to HL7 Fast Healthcare Interoperability Resources (FHIR). We utilize the FHIR profiling to develop a common data model tailored to an AI use case to enable the explicit declaration of the needed information such as phenotype and AI feature definitions. In our pipeline model, we convert complex, high-dimensional electronic health records data represented with irregular time series sampling to a flat structure by defining a target population, feature groups and final datasets. Our design considers the requirements of various AI use cases from different projects which lead to implementation of many feature types exhibiting intricate temporal relations. We implement a scalable and high-performant feature repository to execute the data preparation pipeline definitions. This software not only ensures reliable, fault-tolerant distributed processing to produce AI-ready datasets and their metadata including many statistics alongside, but also serve as a pluggable component of a decision support application based on a trained AI model during online prediction to automatically prepare feature values of individual entities. We deployed and tested the proposed methodology and the implementation in three different research projects. We present the developed FHIR profiles as a common data model, feature group definitions and feature definitions within a data preparation pipeline while training an AI model for "predicting complications after cardiac surgeries". Through the implementation across various pilot use cases, it has been demonstrated that our framework possesses the necessary breadth and flexibility to define a diverse array of features, each tailored to specific temporal and contextual criteria.

Application of big data analytics to forecast future waste trends and inform sustainable planning

Urbanization and industrialization have caused a substantial rise in garbage production, creating substantial environmental, economic, and social difficulties. Precise prediction of future waste patterns is essential for sustainable waste management and strategic planning. Big Data Analytics (BDA) presents a potential method for examining large quantities of waste-related data, revealing trends, and offering practical insights. This review article examines the utilization of Big Data Analytics (BDA) in predicting future waste patterns, emphasizing its capacity to provide valuable insights for sustainable planning and decision-making. The study examines several techniques, tools, and case studies, and explores the obstacles and future prospects in this new discipline.

Artificial Intelligence (AI) in working capital management: Practices and future potential

This study delves into how artificial intelligence (AI) transforms working capital management by addressing the limitations of traditional methods. The focus is to critically review research publications, case studies and industry reports using qualitative research methodology to examine how AI improves operational efficiency and decision-making in this area. The study demonstrates the practical application of advanced machine learning algorithms and big data analytics in optimizing inventory management, enhancing demand forecasting and improving cash flow predictions. A thorough review of recent research and case studies reveals additional benefits, including automated reconciliations, debtor risk analysis, accelerated cash inflows, invoice processing and proactive working capital management. Despite challenges in integrating AI with legacy systems, the potential for substantial improvements in financial health and operational efficiency is significant. The study also suggests future research directions, such as developing comprehensive AI-driven applications for broader working capital considerations, creating empirical validation frameworks for model performance and addressing ethical considerations to fully harness AI's potential in optimizing working capital management.

Application of data element mapping and analysis for system definition to enable model‐based systems engineering

AbstractIn the connected age of the model‐based enterprise and model‐based systems engineering (MBSE), new systems engineering tools are needed to move from a functional, document‐centric, hierarchical view of data and information to the individual units of data or data element level view. Data element mapping and analysis (DEMA) is a technology‐agnostic analytical methodology that combines traditional functional analysis techniques, systems engineering elicitation practices, and novel data mapping techniques to provide a holistic view of a system's data and information flows at the individual units of data (data element level). In this research, DEMA was utilized to enable an enhanced system definition for the development of a verification and validation process as applied to a modeling and simulation environment. DEMA uncovered and visually mapped the hidden flow of approximately 1600 data vessel occurrences as inputs or outputs to 79 functional activities in 23 disparate storage locations. The results reveal that DEMA is a practical tool for both improving existing systems and defining new systems. The data element level view captured by DEMA can be used to define the interconnections between the system elements that are input to systems modeling language (SysML) models. Therefore, DEMA is a necessary and novel tool that can be used to enable system digitalization.

Harnessing Data Analytics for Enhanced Understanding and Management of Depression Disorders in Mental Health Care

Depression is a widespread and incapacitating mental health condition that affects millions of people around the world.The integration of data analytics into mental health care presents a transformative opportunity to enhance the understanding, diagnosis, and management of depression. This paper explores the application of data analytics in identifying patterns and trends from diverse data sources such as electronic health records (EHRs) and social media. Through advanced techniques including machine learning, natural language processing (NLP), and predictive modeling, data analytics facilitates early detection of depressive symptoms, the development of personalized treatment plans, and continuous patient monitoring. Additionally, the aggregation and analysis of large- scale data provide valuable insights for public health strategies aimed at reducing the prevalence and impact of depression. This paper highlights the critical role of interdisciplinary collaboration in leveraging data analytics to improve mental health outcomes and underscores the importance of robust safeguards to ensure patient confidentiality and trust. Keywords Data Analytics, Depression, Mental Health, Predictive Modeling, Machine Learning, Natural Language Processing, Electronic Health Records

Application of Big Data Analysis and Cloud Computing Technology

Application of Big Data Analysis and Cloud Computing Technology

Maintenance optimization methodology of edge cloud collaborative systems based on a gateway cost index in IIoT

In the Industrial Internet of Things (IIoT), cloud computing faces enormous data processing pressure and security challenges due to the surge in industrial devices and sensors, especially in real-time data processing and analysis applications. However, fewer researchers study the reliability of data transmission and the maintenance of data interruption processing of edge cloud collaborative systems (ECCS) in IIoT. This paper proposes a maintenance optimization methodology of ECCS based on a gateway cost index. Firstly, a reliability model of different network topologies of ECCS is proposed considering key communication indicators of task runtime, packet loss rate, and bandwidth. Then, considering the impact of external environments on ECCS, an importance-based Gateway Cost Index is proposed. A maintenance optimization is studied by conducting a multi-objective programming. The specific maintenance steps are analyzed when the intelligent gateways of ECCS are subjected to large-scale failures caused by external interference. At last, two numerical examples with star topology and bus topology are provided to demonstrate the proposed methods.

Shopping marketplace analysis based on customer insights using social media analytics

Using the recent advances in data analytics, Companies can leverage sentiment analysis to identify trends and areas for improvement of their market strategy and operation planning. This analysis allows them to understand the sentiments expressed by customers and accurately predict customer behavior. Social media platforms have fundamentally altered the field of digital marketing. The findings of this research try to provide:•Potential implications for businesses aiming to optimize their product offerings and enhance customer satisfaction within specific cultural contexts.•A case study has been designed for understanding customers' perceptions and satisfaction levels toward various shops, including local ethnic stores and big chain stores.The paper has conducted a literature review around main pillars like application of data analytics on social media, and sales strategies for establishing a marketplace using data analytics. Exploring the utilization of social media and customer feedback, the paper has proposed a conceptual model for creating insights for extraction of shopping experiences and factors used for customer purchasing decision making.

AI-POWERED PREDICTIVE ANALYTICS FOR INTELLECTUAL PROPERTY RISK MANAGEMENT IN SUPPLY CHAIN OPERATIONS: A BIG DATA APPROACH

The rapid advancement of technology and the increasing complexity of global supply chains have heightened the need for robust intellectual property (IP) risk management strategies. This study explores the application of artificial intelligence (AI) and big data analytics in enhancing IP risk management within supply chains. A comprehensive literature review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, identifying 578 records through database searches and an additional 90 records through other sources. After removing duplicates, 568 records were screened, with 196 full-text articles assessed for eligibility. Ultimately, 135 articles were included in the final synthesis. The findings reveal that AI-driven predictive analytics significantly enhance the detection and mitigation of IP risks by analyzing large volumes of data from various sources, such as patent filings, market trends, and social media. Big data analytics tools like Hadoop and Spark facilitate real-time monitoring and early identification of potential IP threats, providing a comprehensive view of the supply chain landscape. Several successful case studies across different industries, including pharmaceuticals, electronics, and fashion, demonstrate the practical applications of these technologies in addressing IP risks. However, the review also highlights several challenges, including data quality, scalability, model interpretability, data privacy, and integration with legacy systems. Despite these challenges, the benefits of AI and big data analytics in IP risk management are substantial, enabling organizations to protect their intellectual assets more effectively. The study underscores the need for future research to address these challenges and explore innovative solutions to maximize the potential of AI and big data analytics in IP risk management. By investing in the necessary infrastructure and expertise, organizations can enhance their resilience and maintain a competitive edge in the global market.

Geometry import into virtual reality visualization engine for HEP experiments at BM@N

Modern visualization and multimedia platforms, such as Unity, provide immersive interaction for HEP experiment data analysis. In this work, we present the method for importing the detector geometry, solids hierarchy, and materials from GDML format directly to Unity. This method is based on parsing files in GDML format and generating the geometry using mesh generation algorithms and Constructive Solid Geometry methods. The provided method is applied to the BM@N experiment at NICA accelerator complex in Joint Institute of Nuclear Research and can be used in virtual reality and augmented reality applications for data analysis and outreach events in high energy physics experiments.

Data modeling analysis of GFRP tubular filled concrete column based on small sample deep meta learning method.

The meta-learning method proposed in this paper addresses the issue of small-sample regression in the application of engineering data analysis, which is a highly promising direction for research. By integrating traditional regression models with optimization-based data augmentation from meta-learning, the proposed deep neural network demonstrates excellent performance in optimizing glass fiber reinforced plastic (GFRP) for wrapping concrete short columns. When compared with traditional regression models, such as Support Vector Regression (SVR), Gaussian Process Regression (GPR), and Radial Basis Function Neural Networks (RBFNN), the meta-learning method proposed here performs better in modeling small data samples. The success of this approach illustrates the potential of deep learning in dealing with limited amounts of data, offering new opportunities in the field of material data analysis.

An Investigation in to Sports Analytics and Related Tools

This study explores the application of sports analytics and the utilization of various tools in the sports industry. Sports analytics, also known as sports data analytics, is the application of data analysis and statistical approaches to extract important insights. Additionally, it aids in making well-informed judgments and enhancing performance in the realm of sports. Sports data analytics include a diverse array of methods and approaches, such as statistical analysis, machine learning, data visualization, predictive modeling, and optimization algorithms. The objective of sports business analytics is to get practical insights from a dataset in order to enhance decision-making and foster innovation in the sports industry

Review on the Use of Data Analysis for Customer Segmentation and Personalization in Marketing

Marketing is a part of business that requires considering countless variables and making accurate decisions. With the development of computer science and algorithms, the advancement of data analysis methods can be applied in this field to bring great convenience. Despite a large number of data analysis models being constructed, there is a lack of review articles that need to summarize algorithms created by previous generations. This paper starts with a lookback to the basic descriptive and predictive data analysis methods following with the introduction and further explanation of customer segmentation and personalization. Combined with the basic marketing methods, we studied the application of data analytics to business industry. Moreover, this paper presents case study that highlight the application of data analysis in different areas: online retail, e-commerce and transportation. Finally we use each case to find utilization of data analytics to derive meaningful insights and facilitation decision-making.

Big data in visual field testing for glaucoma.

Recent technological advancements and the advent of ever-growing databases in health care have fueled the emergence of "big data" analytics. Big data has the potential to revolutionize health care, particularly ophthalmology, given the data-intensive nature of the medical specialty. As one of the leading causes of irreversible blindness worldwide, glaucoma is an ocular disease that receives significant interest for developing innovations in eye care. Among the most vital sources of data in glaucoma is visual field (VF) testing, which stands as a cornerstone for diagnosing and managing the disease. The expanding accessibility of large VF databases has led to a surge in studies investigating various applications of big data analytics in glaucoma. In this study, we review the use of big data for evaluating the reliability of VF tests, gaining insights into real-world clinical practices and outcomes, understanding new disease associations and risk factors, characterizing the patterns of VF loss, defining the structure-function relationship of glaucoma, enhancing early diagnosis or earlier detection of progression, informing clinical decisions, and improving clinical trials. Equally important, we discuss current challenges in big data analytics and future directions for improvement.