WIREs Data Mining and Knowledge Discovery最新文献

{"title":"AI‐Assisted Literature Review: Integrating Visualization and Geometric Features for Insightful Analysis","authors":"Grigorios Papageorgiou, Ekaterini Skamnia, Polychronis Economou","doi":"10.1002/widm.70016","DOIUrl":"https://doi.org/10.1002/widm.70016","url":null,"abstract":"Rapid advancements in technology and Artificial Intelligence have increased the volume of scientific research, making it challenging for researchers and scholars to keep pace with the evolving literature and state‐of‐the‐art techniques and methods. Traditional review papers offer a way to mitigate these difficulties but are often time‐consuming and labor‐intensive. This article introduces a novel AI‐assisted narrative review methodology that integrates advanced text retrieval and visualization techniques, enhanced with geometric features, to address this. The proposed approach relies on the automatic identification of research topics/clusters within a large different document corpus of different time periods. This approach not only facilitates the systematic exploration of trends over time but also serves as a valuable adjunct, enabling experts to focus on specific, homogeneous areas within scientific fields/clusters. Initially, the methodology in its generality and mapping of the evolution of emerging topics are described, revealing the temporal dynamics and interconnections within the literature of time series anomalies. Subsequently, the proposed method is applied to time series data and an in‐depth exploration of the identified dominant cluster is presented. The cluster involves advanced techniques and models for anomaly detection in time series analysis. Focusing on such a homogeneous subfield enables the derivation of a wealth of characteristics and outcomes regarding the evolution of this topic, revealing its temporal dynamics and trends. The review process demonstrates the effectiveness of the proposed AI‐driven approach in literature reviews and provides researchers with a powerful tool to synthesize and interpret complex, dynamically changing, advanced scientific fields.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"46 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143898093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neuromorphic Computing and Applications: A Topical Review","authors":"Pavan Kumar Enuganti, Basabdatta Sen Bhattacharya, Teresa Serrano Gotarredona, Oliver Rhodes","doi":"10.1002/widm.70014","DOIUrl":"https://doi.org/10.1002/widm.70014","url":null,"abstract":"Neuromorphic computers achieve energy efficiency by emulating brain structure and event‐driven processing that reduces energy consumption significantly. An increasing interest in this technology started in the initial years of this millennium, sparked by the awareness and concern on the ever‐increasing power demands of modern‐day computing. In current times, there are several neuromorphic computers and sensors that continue to be developed in both industry and academic research. The focus of this survey is on the neuromorphic computing applications of these devices that include brain‐inspired neural networks, brain‐inspired artificial neural networks, and Hybrid circuits comprising both artificial and brain‐inspired units of computation. Many of these applications use neuromorphic sensors as input devices. We have surveyed three specific neuromorphic computers viz. SpiNNaker, TrueNorth, Loihi, and one neuromorphic sensor viz. Dynamic vision sensor (DVS)‐based electronic retina; the demonstration of neuromorphic computing and applications using these devices far outnumbers those on the others that are currently available, which forms the basis of our choice. The applications include low‐power cognitive machine intelligence as well as neuropathological understanding and knowledge discovery. Overall, our survey identifies the potential for neuromorphic computing to provide low power, low cost, and dynamic solutions for societal and scientific problems in the not‐too‐distant future.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143889727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Systematic Review on Process Mining for Curricular Analysis","authors":"Daniel Calegari, Andrea Delgado","doi":"10.1002/widm.70005","DOIUrl":"https://doi.org/10.1002/widm.70005","url":null,"abstract":"Educational Process Mining (EPM) is a data analysis technique that is used to improve educational processes. It is based on Process Mining (PM), which involves gathering records (logs) of events to discover process models and analyze the data from a process‐centric perspective. One specific application of EPM is curriculum mining, which focuses on understanding the learning program students follow to achieve educational goals. This is important for institutional curriculum decision‐making and quality improvement. Therefore, academic institutions can benefit from organizing the existing techniques, capabilities, and limitations. We conducted a systematic literature review to identify works on applying PM to curricular analysis and provide insights for further research. We reviewed 27 primary studies published across seven major databases. Our analysis classified these studies into five main research objectives: discovery of educational trajectories, identification of deviations in student behavior, bottleneck analysis, dropout/stopout analysis, and generation of recommendations. Key findings highlight challenges such as standardization to facilitate cross‐university analysis, better integration of process and data mining techniques, and improved tools for educational stakeholders. This review provides a comprehensive overview of the current landscape in curricular process mining and outlines specific research opportunities to support more robust and actionable curricular analyses in educational settings.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"74 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143872832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"How AI Contributes to Poverty Alleviation: A Systematic Literature Review","authors":"Sepehr Ghazinoory, Mercedeh Pahlavanian, Mehdi Fatemi, Fatemeh Parvin, Sayna Ahad Bhat","doi":"10.1002/widm.70003","DOIUrl":"https://doi.org/10.1002/widm.70003","url":null,"abstract":"Artificial intelligence and smart city initiatives are pivotal to achieving sustainable development goals, particularly in poverty alleviation. Artificial intelligence has high potential in controlling, monitoring, and alleviating poverty, offering innovative solutions that can improve living conditions and welfare. AI‐assisted poverty alleviation requires a comprehensive approach to creating supportive institutions, appropriate regulations, comprehensive training programs, and resource allocation. This article systematically reviews the AI‐poverty literature based on problem‐oriented innovation system functions. By screening existing articles, it analyzes 30 sources specifically focused on AI‐enhanced poverty control to highlight the articles' focus and identify the neglected functions. The findings can help governments, policymakers, and scholars guide decisions to address poverty through AI and fill the existing gaps and shortcomings.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143857474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transforming Disaster Risk Reduction With AI and Big Data: Legal and Interdisciplinary Perspectives","authors":"Kwok P. Chun, Thanti Octavianti, Nilay Dogulu, Hristos Tyralis, Georgia Papacharalampous, Ryan Rowberry, Pingyu Fan, Mark Everard, Maria Francesch‐Huidobro, Wellington Migliari, David M. Hannah, John Travis Marshall, Rafael Tolosana Calasanz, Chad Staddon, Ida Ansharyani, Bastien Dieppois, Todd R. Lewis, Juli Ponce, Silvia Ibrean, Tiago Miguel Ferreira, Chinkie Peliño‐Golle, Ye Mu, Manuel Davila Delgado, Elizabeth Silvestre Espinoza, Martin Keulertz, Deepak Gopinath, Cheng Li","doi":"10.1002/widm.70011","DOIUrl":"https://doi.org/10.1002/widm.70011","url":null,"abstract":"Managing complex disaster risks requires interdisciplinary efforts. Breaking down silos between law, social sciences, and natural sciences is critical for all processes of disaster risk reduction. It is essential to explore how AI enhances understanding of legal frameworks and environmental management, while also examining how legal and environmental factors may limit AI's role in society. From a co‐production review perspective, drawing on insights from lawyers, social scientists, and environmental scientists, principles for responsible data mining are proposed based on safety, transparency, fairness, accountability, and contestability. This discussion offers a blueprint for interdisciplinary collaboration to create adaptive law systems based on AI integration of knowledge from environmental and social sciences. When social networks are useful for mitigating disaster risks based on AI, the legal implications related to privacy and liability of the outcomes of disaster management must be considered. Fair and accountable principles emphasize environmental considerations and foster socioeconomic discussions related to public engagement. AI also has an important role to play in education, bringing together the next generations of law, social sciences, and natural sciences to work on interdisciplinary solutions in harmony. Although emerging AI approaches can be powerful tools for disaster management, they must be implemented with ethical considerations and safeguards to address concerns about bias, transparency, and privacy. The responsible execution of AI approaches, based on the dynamic interplay between AI, law, and environmental risk, promotes sustainable and equitable practices in data mining.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"90 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143837122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Algorithmic Profiling and Facial Recognition in EU Border Control: Examining ETIAS Decision‐Making, Privacy and Law","authors":"Abhishek Thommandru, Varda Mone, Fayzulloyev Shokhijakhon, Giyosbek Mirzayev","doi":"10.1002/widm.70013","DOIUrl":"https://doi.org/10.1002/widm.70013","url":null,"abstract":"The growing use of algorithmic and biometric technologies in border control is part of a larger trend in global security governance that has significant legal and ethical implications for their effect on individual rights and procedural justice. As central features in the EU's shifting security regime, ETIAS and facial recognition technologies deploy algorithmic profiling and biometric risk assessment to screen visa‐exempt third‐country nationals. The research systematically examines the decision‐making processes of ETIAS and the overall facial recognition system, demonstrating the interplay between algorithmic risk assessments and discretionary human discretion by national authorities. It contends that the algorithmic profiling lack of transparency, combined with sweeping national security exceptions, produces a procedural void, in which the right to reasoned decisions and effective remedies is compromised. Second, the use of interoperable databases and risk indicators puts core data protection principles into jeopardy, notably purpose limitation and the right to be forgotten. This paper also argues that ETIAS and the application of facial recognition technologies represent a larger trend toward “techno‐regulatory assemblages” in EU governance, where technological infrastructures increasingly influence legal and administrative decisions. It critically assesses whether the human oversight mechanisms incorporated within ETIAS National Units are adequate to prevent the risks involved in automated decision‐making, especially in the face of strict time pressures and security requirements. The study detects a latent paradox: though these systems aim to strengthen a “Security Union,” they might inadvertently lead to an “Insecurity Union” by undermining transparency, procedural protections, and citizen rights.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"31 10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143822888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping the Landscape of Personalization: A Comprehensive Review of Prediction and Trends in Recommendation Systems","authors":"Tamanna Sachdeva, Lalit Mohan Goyal, Mamta Mittal","doi":"10.1002/widm.70006","DOIUrl":"https://doi.org/10.1002/widm.70006","url":null,"abstract":"Recommendation systems (RSs) have become indispensable features in nearly all web applications. Sifting through data and alleviating information overload, these systems offer more streamlined and personalized recommendations. E‐commerce giants such as Amazon, Netflix, and YouTube are offering recommendations to users based on their interests, past experiences, demographic information, etc. hence, increasing the user's engagement on these applications. This study offers a comprehensive review of recommendation systems, covering their types, fundamental techniques, and emerging trends, with a focus on the predictive models and algorithms that power personalization. This study shows how in comparison to traditional collaborative and content‐based recommendation systems‐building techniques, the novel approaches of deep learning, graph‐based techniques, meta‐learning, few‐shot learning, exploration, and federated learning offer promising prospects to improve recommendation systems' scalability, privacy‐preserving abilities, and accuracy. These advanced methods deliver more diverse, context‐aware, and personalized recommendations by leveraging large‐scale data and complex predictive algorithms. Furthermore, this paper depicts forthcoming trajectories in the field of recommendation systems, including the adoption of graph‐based approaches, federated learning, and the exploration of ethical considerations. By mapping the current landscape of prediction‐driven personalization and identifying emerging trends, this review serves as a valuable resource for scholars and practitioners seeking to deepen their understanding of the field and drive innovation in recommendation systems. Readers can expect to gain insights into both foundational and cutting‐edge techniques and how these can shape the future of personalized recommendations.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Brief Review on Benchmarking for Large Language Models Evaluation in Healthcare","authors":"Leona Cilar Budler, Hongyu Chen, Aokun Chen, Maxim Topaz, Wilson Tam, Jiang Bian, Gregor Stiglic","doi":"10.1002/widm.70010","DOIUrl":"https://doi.org/10.1002/widm.70010","url":null,"abstract":"This paper reviews benchmarking methods for evaluating large language models (LLMs) in healthcare settings. It highlights the importance of rigorous benchmarking to ensure LLMs' safety, accuracy, and effectiveness in clinical applications. The review also discusses the challenges of developing standardized benchmarks and metrics tailored to healthcare‐specific tasks such as medical text generation, disease diagnosis, and patient management. Ethical considerations, including privacy, data security, and bias, are also addressed, underscoring the need for multidisciplinary collaboration to establish robust benchmarking frameworks that facilitate LLMs' reliable and ethical use in healthcare. Evaluation of LLMs remains challenging due to the lack of standardized healthcare‐specific benchmarks and comprehensive datasets. Key concerns include patient safety, data privacy, model bias, and better explainability, all of which impact the overall trustworthiness of LLMs in clinical settings.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Comprehensive Review on Data‐Driven Methods of Lithium‐Ion Batteries State‐of‐Health Forecasting","authors":"Thien Pham, Hung Bui, Mao Nguyen, Quang Pham, Vinh Vu, Triet Le, Tho Quan","doi":"10.1002/widm.70009","DOIUrl":"https://doi.org/10.1002/widm.70009","url":null,"abstract":"Lithium‐ion batteries are widely used in moving devices due to their many advantages compared to other battery types. The prevalence of Lithium‐ion batteries is evident, playing its clear role in the operation of small devices as well as large systems such as electric vehicles, flying devices, mobile devices, and more. Monitoring lithium‐ion battery health is crucial for assessing, minimizing degradation, preventing explosions, and enabling timely replacements. Assessing health often involves predicting state‐of‐health (SoH) or remaining useful life (RUL), with numerous studies dedicated to this field. Hence, many research studies have been conducted on predicting SoH, with a primary focus on data‐driven methods based on machine learning, owing to the recent advancements in artificial intelligence (AI) techniques. To provide a systematic overview of the trends in this emerging problem, we present a comprehensive survey of classified SoH forecasting methods, with a primary focus on data‐driven approaches. The paper also offers an in‐depth focus on recent advancements in deep learning (DL) models, an area that has not been thoroughly discussed previously. Furthermore, we highlight the importance of input features and emphasize the critical role of temporal attributes incorporated into the models. The insights provided in this paper offer readers a comprehensive understanding of the field, equipping them to effectively advance related future work.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Systematic Survey of Graph Convolutional Networks for Artificial Intelligence Applications","authors":"Amutha Sadasivan, Kavipriya Gananathan, Joe Dhanith Pal Nesamony Rose Mary, Surendiran Balasubramanian","doi":"10.1002/widm.70012","DOIUrl":"https://doi.org/10.1002/widm.70012","url":null,"abstract":"Graph Convolutional Networks (GCNs) have become an essential tool for handling graph‐structured data, enhancing the functionality of conventional convolutional neural networks (CNNs) in non‐Euclidean contexts. GCNs are particularly proficient in tasks such as node classification, link prediction, and graph clustering by collecting information from neighboring nodes. These models are utilized in a range of domains, including recommendation systems, social network analysis, bioinformatics, and computer vision. GCNs demonstrate significant effectiveness in challenges like citation prediction and knowledge graph completion, where both the structure of the graph and the information from the nodes are crucial. Emerging from the field of graph signal processing, GCNs have been enhanced by a variety of models that combine spectral and spatial convolution methods. Despite these improvements, there remain obstacles to fully harnessing the structural information of graphs, which is a vital component of network science. This survey presents an extensive review of GCNs and introduces a new taxonomy that classifies models into five categories: supervised, unsupervised, semi‐supervised, weakly‐supervised, and self‐supervised GCNs. We emphasize recent innovations, discuss present challenges, and propose promising avenues for future investigations.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"227 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143797836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}