WIREs Data Mining and Knowledge Discovery最新文献

{"title":"Continual learning and its industrial applications: A selective review","authors":"J. Lian, K. Choi, B. Veeramani, A. Hu, S. Murli, L. Freeman, E. Bowen, X. Deng","doi":"10.1002/widm.1558","DOIUrl":"https://doi.org/10.1002/widm.1558","url":null,"abstract":"In many industrial applications, datasets are often obtained in a sequence associated with a series of similar but different tasks. To model these datasets, a machine‐learning algorithm, which performed well on the previous task, may not have as strong a performance on the current task. When the architecture of the algorithm is trained to adapt to new tasks, often the whole architecture needs to be revised and the old knowledge of modeling can be forgotten. Efforts to make the algorithm work for all the relevant tasks can cost large computational resources and data storage. Continual learning, also called lifelong learning or continual lifelong learning, refers to the concept that these algorithms have the ability to continually learn without forgetting the information obtained from previous task. In this work, we provide a broad view of continual learning techniques and their industrial applications. Our focus will be on reviewing the current methodologies and existing applications, and identifying a gap between the current methodology and the modern industrial needs.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Technologies &gt; Artificial Intelligence</jats:list-item> <jats:list-item>Fundamental Concepts of Data and Knowledge &gt; Knowledge Representation</jats:list-item> <jats:list-item>Application Areas &gt; Business and Industry</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"101 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142317577","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":"Lead–lag effect of research between conference papers and journal papers in data mining","authors":"Yue Huang, Runyu Tian","doi":"10.1002/widm.1561","DOIUrl":"https://doi.org/10.1002/widm.1561","url":null,"abstract":"The examination of the lead–lag effect between different publication types, incorporating a temporal dimension, is very significant for assessing research. In this article, we introduce a novel framework to quantify the lead–lag effect between the research topics of conference papers and journal papers. We first identify research topics via the text‐embedding‐based topic modeling technique BERTopic, then extract the research topics of each time slice, construct and visualize the similarity matrix of topics to reveal the time‐lag direction and finally quantify the lead–lag effect by four proposed indicators, as well as by average influence topic similarity comparison maps. We conduct a detailed analysis of 19,166 bibliographic data for top conference papers and journal papers from 2015 to 2019 in the data mining field, calculate the similarity of topics obtained by BERTopic between each time slice divided by quarters. The results show that journal paper topics lag behind conference paper topics in the data mining field. The most significant lead–lag effect is 2.5 years, with approximately 33.45% of topics affected by this lag. The methodology presented here holds potential for broader application in the analysis of lead–lag effects across diverse research areas, offering valuable insights into the state of research development and informing policy decisions.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Application Areas &gt; Science and Technology</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"35 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142317538","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":"From 3D point‐cloud data to explainable geometric deep learning: State‐of‐the‐art and future challenges","authors":"Anna Saranti, Bastian Pfeifer, Christoph Gollob, Karl Stampfer, Andreas Holzinger","doi":"10.1002/widm.1554","DOIUrl":"https://doi.org/10.1002/widm.1554","url":null,"abstract":"We present an exciting journey from 3D point‐cloud data (PCD) to the state of the art in graph neural networks (GNNs) and their evolution with explainable artificial intelligence (XAI), and 3D geometric priors with the human‐in‐the‐loop. We follow a simple definition of a “digital twin,” as a high‐precision, three‐dimensional digital representation of a physical object or environment, captured, for example, by Light Detection and Ranging (LiDAR) technology. After a digression into transforming PCD into images, graphs, combinatorial complexes and hypergraphs, we explore recent developments in geometric deep learning (GDL) and provide insight into the application of these network architectures for analyzing and learning from graph‐structured data. We emphasize the importance of the explainability of these models and recognize that the ability to interpret and validate the results of complex models is a crucial aspect of their wider adoption.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Technologies &gt; Artificial Intelligence</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236376","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":"Digital twins in healthcare: Applications, technologies, simulations, and future trends","authors":"Mohamed Abd Elaziz, Mohammed A. A. Al‐qaness, Abdelghani Dahou, Mohammed Azmi Al‐Betar, Mona Mostafa Mohamed, Mohamed El‐Shinawi, Amjad Ali, Ahmed A. Ewees","doi":"10.1002/widm.1559","DOIUrl":"https://doi.org/10.1002/widm.1559","url":null,"abstract":"The healthcare industry has witnessed significant interest in applying DTs (DTs), due to technological advancements. DTs are virtual replicas of physical entities that adapt to real‐time data, enabling predictions of their physical counterparts. DT technology enhances understanding of disease occurrence, enabling more accurate diagnoses and treatments. Integrating emerging technologies like big data, cloud computing, Virtual Reality (VR), and internet‐of‐things (IoT) provides a solid foundation for DT implementation in healthcare. However, defining DTs within the healthcare context still has become increasingly challenging. Therefore, exploring the potential of DTs in healthcare contributes to research, emphasizing their transformative impact on personalized medicine and precision healthcare. In this study, we present diverse healthcare applications of DTs, including healthcare 4.0, cardiac analysis, monitoring and management, data privacy, socio‐ethical, and surgical. Moreover, this paper discusses the software and simulations of DTs that can be used in these applications of healthcare, as well as, the future trends of DTs in healthcare.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Application Areas &gt; Health Care</jats:list-item> <jats:list-item>Technologies &gt; Computational Intelligence</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142144170","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 taxonomy of automatic differentiation pitfalls","authors":"Jan Hückelheim, Harshitha Menon, William Moses, Bruce Christianson, Paul Hovland, Laurent Hascoët","doi":"10.1002/widm.1555","DOIUrl":"https://doi.org/10.1002/widm.1555","url":null,"abstract":"Automatic differentiation is a popular technique for computing derivatives of computer programs. While automatic differentiation has been successfully used in countless engineering, science, and machine learning applications, it can sometimes nevertheless produce surprising results. In this paper, we categorize problematic usages of automatic differentiation, and illustrate each category with examples such as chaos, time‐averages, discretizations, fixed‐point loops, lookup tables, linear solvers, and probabilistic programs, in the hope that readers may more easily avoid or detect such pitfalls. We also review debugging techniques and their effectiveness in these situations.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Technologies &gt; Machine Learning</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142131050","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":"Advancements in Q‐learning meta‐heuristic optimization algorithms: A survey","authors":"Yang Yang, Yuchao Gao, Zhe Ding, Jinran Wu, Shaotong Zhang, Feifei Han, Xuelan Qiu, Shangce Gao, You‐Gan Wang","doi":"10.1002/widm.1548","DOIUrl":"https://doi.org/10.1002/widm.1548","url":null,"abstract":"This paper reviews the integration of Q‐learning with meta‐heuristic algorithms (QLMA) over the last 20 years, highlighting its success in solving complex optimization problems. We focus on key aspects of QLMA, including parameter adaptation, operator selection, and balancing global exploration with local exploitation. QLMA has become a leading solution in industries like energy, power systems, and engineering, addressing a range of mathematical challenges. Looking forward, we suggest further exploration of meta‐heuristic integration, transfer learning strategies, and techniques to reduce state space.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Technologies &gt; Computational Intelligence</jats:list-item> <jats:list-item>Technologies &gt; Artificial Intelligence</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142007588","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":"Exploring the convergence of Metaverse, Blockchain, and AI: A comprehensive survey of enabling technologies, applications, challenges, and future directions","authors":"Mueen Uddin, Muath Obaidat, Selvakumar Manickam, Shams Ul Arfeen Laghari, Abdulhalim Dandoush, Hidayat Ullah, Syed Sajid Ullah","doi":"10.1002/widm.1556","DOIUrl":"https://doi.org/10.1002/widm.1556","url":null,"abstract":"The Metaverse, distinguished by its capacity to integrate the physical and digital realms seamlessly, presents a dynamic virtual environment offering diverse opportunities for engagement across innovation, entertainment, socialization, and commercial endeavors. However, the Metaverse is poised for a transformative evolution through the convergence of contemporary technological advancements, including artificial intelligence (AI), Blockchain, Robotics, augmented reality, virtual reality, and mixed reality. This convergence is anticipated to revolutionize the global digital landscape, introducing novel social, economic, and operational paradigms for organizations and communities. To comprehensively elucidate the future potential of this technological fusion and its implications for digital innovation, this research endeavors to undertake a thorough analysis of scholarly discourse and research pertaining to the Metaverse, AI, Blockchain, and associated technologies. This survey delves into various critical facets of the Metaverse ecosystem, encompassing component analysis, exploration of digital currencies, assessment of AI utilization in virtual environments, and examination of Blockchain's role in enhancing digital content and data security. Leveraging articles retrieved from esteemed digital repositories including ScienceDirect, IEEE Xplore, Springer Nature, Google Scholar, and ACM, published between 2017 and 2023, this study adopts an analytical approach to engage with these materials. Through rigorous examination and discourse, this research aims to provide insights into the emerging trends, challenges, and future directions in the convergence of the Metaverse, Blockchain, and AI.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Application Areas &gt; Industry Specific Applications</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142007490","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":"The evolution of frailty assessment using inertial measurement sensor‐based gait parameter measurements: A detailed analysis","authors":"Arslan Amjad, Shahzad Qaiser, Monika Błaszczyszyn, Agnieszka Szczęsna","doi":"10.1002/widm.1557","DOIUrl":"https://doi.org/10.1002/widm.1557","url":null,"abstract":"Frailty is a significant issue in geriatric health, may cause adverse effects such as falls, delirium, weight loss, or physical decline. Over time, various methods have been developed for measuring frailty, including clinical judgment, the frailty index, the clinical frailty scale, and the comprehensive geriatric assessment. These traditional frailty assessment approaches rely on healthcare professionals, which can lead to inaccuracy and require frequent clinic visits, making it burdensome for elderly patients. This review paper explores the latest trends in frailty assessment by measuring gait parameters using wearable sensors, specifically the inertial measurement unit (IMU). The aim of this study is to provide a comprehensive overview of objective methods for evaluating and quantifying frailty. We focus on the application of machine learning (ML) and deep learning (DL) techniques to IMU gait data, highlighting key aspects of recent publications such as algorithms, sensor types, sample sizes, and performance evaluations. By examining the strengths and challenges of each technique, this review aims to guide future studies on utilizing cost‐effective and portable devices integrated with clinical data. This integration can help to propose optimized IMU gait parameters or ML models to detect early‐stage frailty. This advances the emerging trend of intelligent, individualized, and efficient healthcare systems for older adults.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Application Areas &gt; Health Care</jats:list-item> <jats:list-item>Technologies &gt; Machine Learning</jats:list-item> <jats:list-item>Technologies &gt; Artificial Intelligence</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141980646","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":"Medical intelligence for anxiety research: Insights from genetics, hormones, implant science, and smart devices with future strategies","authors":"Faijan Akhtar, Md Belal Bin Heyat, Arshiya Sultana, Saba Parveen, Hafiz Muhammad Zeeshan, Stalin Fathima Merlin, Bairong Shen, Dustin Pomary, Jian Ping Li, Mohamad Sawan","doi":"10.1002/widm.1552","DOIUrl":"https://doi.org/10.1002/widm.1552","url":null,"abstract":"This comprehensive review article embarks on an extensive exploration of anxiety research, navigating a multifaceted landscape that incorporates various disciplines, such as molecular genetics, hormonal influences, implant science, regenerative engineering, and real‐time cardiac signal analysis, all while harnessing the transformative potential of medical intelligence [medical + artificial intelligence (AI)]. By addressing fundamental research questions, this study investigated the molecular and hormonal foundations underlying anxiety disorders, shedding light on the intricate interplay of genetic and hormonal factors contributing to the etiology and progression of anxiety. Furthermore, this review delves into the emerging implications of biomaterials, defibrillators, and state‐of‐the‐art devices for anxiety research, elucidating their potential roles in diagnosis, treatment, and patient management. A pivotal contribution of this review is the development and exploration of an AI‐driven model for real‐time cardiac signal analysis. This innovative approach offers a promising avenue for enhancing the precision and timeliness of anxiety diagnosis and monitoring. Leveraging machine learning and AI techniques enables the accurate classification of persons with anxiety based on real‐time cardiac data, thereby ushering in a new era of personalized and data‐driven mental health care. Identifying emerging themes and knowledge gaps lays the foundation for future research directions and offers a roadmap for scholars and practitioners to navigate this intricate field. In conclusion, this comprehensive review serves as a vital resource, consolidating diverse perspectives and fostering a deeper understanding of anxiety disorders from biological, engineering, and technological standpoints, ultimately contributing to advancing mental health research and clinical practice.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Application Areas &gt; Health Care</jats:list-item> <jats:list-item>Application Areas &gt; Science and Technology</jats:list-item> <jats:list-item>Technologies &gt; Classification</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141891726","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 quantum computing based drug design","authors":"Poulami Das, Avishek Ray, Siddhartha Bhattacharyya, Jan Platos, Vaclav Snasel, Leo Mrsic, Tingwen Huang, Ivan Zelinka","doi":"10.1002/widm.1553","DOIUrl":"https://doi.org/10.1002/widm.1553","url":null,"abstract":"Design and development of new drug molecules are essential for the survival of human society. New drugs are designed for therapeutic purposes to combat new diseases. Besides treating new diseases, new drug development is also needed to treat pre‐existing diseases more effectively and reduce the existing drugs' side effects. The design of drugs involves several steps, from the discovery of the drug molecule to its commercialization in the market. One of the most critical steps in drug design is to find the molecular interactions between the target (infected) molecule and the drug molecule. Several complex chemical equations need to be solved to determine the molecular interactions. In the late 20th Century, the advancement of computational technologies has made the solution of chemical equations relatively easier and faster. Moreover, the design of drug molecules involves multi‐criteria optimization. Classical computational methodologies have been used for drug design since the end of the 20th Century. However, nowadays, more advanced computational methodologies are inevitable in designing drugs for new diseases and drugs with fewer side effects. In this context, the quantum computing paradigm has proved beneficial in drug design due to its advanced computational capabilities. This paper presents a state‐of‐the‐art comprehensive review of the quantum computing‐based methodologies involved in drug design. A comparative study is made about the different quantum‐aided drug design methods, stating each methodology's merits and demerits. The review work presented in this manuscript will help new researchers assess the present state‐of‐the‐art concept of quantum‐based drug design.This article is categorized under:<jats:list list-type=\"simple\"> <jats:list-item>Technologies &gt; Structure Discovery and Clustering</jats:list-item> <jats:list-item>Technologies &gt; Computational Intelligence</jats:list-item> <jats:list-item>Application Areas &gt; Health Care</jats:list-item> </jats:list>","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141726298","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}