Expert Systems最新文献

{"title":"Lifecycle Models in Machine Learning Development","authors":"Antonio Crespí,&nbsp;Antoni-Lluís Mesquida,&nbsp;Maria Monserrat,&nbsp;Antonia Mas","doi":"10.1111/exsy.70029","DOIUrl":"https://doi.org/10.1111/exsy.70029","url":null,"abstract":"<div>\u0000 \u0000 <p>Machine Learning (ML) development introduces challenges that traditional software processes often struggle to address. As ML applications grow in complexity and adoption, various lifecycle models have been proposed to address the unique stages of ML development. This study systematically synthesises these models, mapping their stages and activities to provide an understanding of the ML development landscape. The findings highlight research gaps and opportunities, offering insights for advancing academic research and practical implementation.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143554835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fuzzy Particle Filtering Based Approach for Battery RUL Prediction With Uncertainty Reduction Strategies","authors":"Gwanpil Kim,&nbsp;Jason J. Jung,&nbsp;Dong Kyu Kim,&nbsp;Min Koo,&nbsp;Grzegorz J. Nalepa,&nbsp;Slawomir Nowaczyk","doi":"10.1111/exsy.70027","DOIUrl":"https://doi.org/10.1111/exsy.70027","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper proposes a two-stage framework that combines uncertainty reduction and predictive modelling to enhance the accuracy of battery Remaining Useful Life (RUL) prediction. In the first stage, a simplified fuzzy optimization learning model is introduced to mitigate uncertainty caused by abnormal capacity fluctuations in battery data. The proposed fuzzy model reconstructs degradation data into a consistent downward trend based on mid- and short-term tendencies of the battery, alleviating abnormal variability and improving suitability for predictive modelling. In the second stage, uncertainty arising during the recursive prediction process of a standalone Transformer model was mitigated through the integration of a particle filter. This approach dynamically manages prediction errors using particles, effectively controlling cumulative errors and enhancing the stability and reliability of long-term predictions. This methodology can lead to extended battery life and increased operational reliability through accurate RUL prediction. The proposed methodology is validated through experiments using NASA and CALCE battery datasets, demonstrating superior prediction accuracy and stability compared to conventional approaches by systematically reducing uncertainties.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143554853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Helping to Choose a Robust Alternative: A Sensitivity Analysis and a Software Tool for Multi-Criteria Decision-Making","authors":"Pavel Novoa-Hernández,&nbsp;David A. Pelta,&nbsp;Carlos Cruz Corona","doi":"10.1111/exsy.70031","DOIUrl":"https://doi.org/10.1111/exsy.70031","url":null,"abstract":"<div>\u0000 \u0000 <p>Multicriteria decision-making (MCDM) often involves evaluating or ranking alternatives on multiple attributes, a process that is far from trivial due to flexible preferences and uncertainty in the criteria importance. The recently proposed <b>W</b>eightless, <b>I</b>nterval-<b>B</b>ased <b>A</b>pproach (WIBA) tackles these issues by relying on an ordering of the criteria (according to their relevance) instead of explicit weights and using interval scores to evaluate alternatives. Although originally proposed for selecting solutions of interest in the context of multi-objective and many objective optimization problems, it can be adapted to rank such solutions. However, the robustness of WIBA rankings has not been studied, and sensitivity analysis approaches based on perturbations of the weights cannot be applied. Furthermore, there is no friendly environment for exploring WIBA properties. This paper addresses these gaps by (1) introducing a novel local sensitivity analysis technique to explore how small perturbations in the order of criteria affect rankings, and (2) presenting WIBApp, a freely available visual software tool that implements WIBA features, including the proposed sensitivity analysis. Using a case study on the selection of technical universities, the paper first illustrates WIBA's flexibility and utility in real-world decision scenarios, enabling decision makers to effectively deal with uncertainty and complexity, and second shows how WIBApp simplifies data management, enhances analysis and facilitates comparisons among rankings. By advancing the theoretical foundations of WIBA and providing a practical implementation, this work contributes to providing decision makers with a robust framework for handling multi-criteria problems, enhancing the reliability of rankings and supporting informed decisions.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143554268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semantic Role Labelling: A Systematic Review of Approaches, Challenges, and Trends for English and Indian Languages","authors":"Kunal Chakma,&nbsp;Sima Datta,&nbsp;Anupam Jamatia,&nbsp;Dwijen Rudrapal","doi":"10.1111/exsy.13838","DOIUrl":"https://doi.org/10.1111/exsy.13838","url":null,"abstract":"<div>\u0000 \u0000 <p>This systematic review looks at the advances, trends, and challenges within semantic role labelling (SRL) for both English and Indian languages. SRL stands as a pivotal undertaking in the realm of natural language processing (NLP), entailing the identification of semantic connections between predicates and their corresponding arguments in a given sentence. The synthesis of findings from publicly available NLP repositories in this review sheds light on the progression of SRL methodologies and their use across various linguistic contexts. The investigation examines the distinct hurdles presented by Indian languages, which are characterised by their morphological complexity and syntactic variability, juxtaposed with the more widely studied English language. Furthermore, we perform an analysis of the impact of sophisticated machine learning algorithms, particularly deep learning, on enhancing SRL efficacy across these languages. The review identifies key research gaps and proposes future research pathways to address the complex nature of SRL in multilingual environments. By offering a comprehensive overview of the evolutionary trajectory of SRL research, the primary objective of this article is to contribute to the advancement of more resilient and adaptable NLP systems capable of accommodating a myriad of languages.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143554252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Review of Abnormal Behaviour Detection in Crowd for Video Surveillance: Advances and Trends, Datasets, Opportunities and Prospects","authors":"A. Jency,&nbsp;K. Ramar","doi":"10.1111/exsy.70013","DOIUrl":"https://doi.org/10.1111/exsy.70013","url":null,"abstract":"<div>\u0000 \u0000 <p>The detection of abnormal behaviours with fast and automatic recognising is significant in crowded areas to provide higher security to the public. The adoption of deep learning and machine learning-based abnormal behaviour detection models enhances the influential detection and real-time security monitoring in crowds. The researchers have remotely evaluated the heart rate based on physiological information to detect abnormal activities in various years. Over the past few years, several progress have been made, and there are still some issues concerning processing time, accuracy, and computational complexity. The developed approaches detects the activities of anomalies like traffic rule violations, riots, fighting, and stampede, in addition, several anomalous entities such as abandoned luggage and weapons at the sensitive place automatically in time. However, the identification of video anomalies methods poses several challenges because of various environmental conditions, the ambiguous nature of the anomaly, lack of proper datasets, and the complex nature of human characteristics. In recent days, there have been only a few devoted surveys associated with deep learning related video anomaly identification as the research domain is in its initial stages. In this review work, the abnormal behaviour analysis models using deep learning are reviewed in depth in for security applications. Based on the traditionally used abnormal behaviour analysis models in crowded scenes, we widely categorised the methods into classification using object tracking, classification using handcrafted extracted features, classification using non-contact heart rate variability and blood pressure, analysing motion patterns from the visual frames, and classification using face images. We also discuss the comparative analysis of the previous methods with respect to datasets, computational infrastructure, and performance measures for both qualitative and quantitative analysis. In addition, the open and trending research challenges are analysed for future research.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143533512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cutting-Edge Deep Learning Methods for Image-Based Object Detection in Autonomous Driving: In-Depth Survey","authors":"Narges Saeedizadeh,&nbsp;Seyed Mohammad Jafar Jalali,&nbsp;Burhan Khan,&nbsp;Shady Mohamed","doi":"10.1111/exsy.70020","DOIUrl":"https://doi.org/10.1111/exsy.70020","url":null,"abstract":"<p>Object detection is a critical aspect of computer vision (CV) applications, especially within autonomous driving systems (AVs), where it is fundamental to ensuring safety and reducing traffic accidents. Recent advancements in computational resources have enabled the widespread adoption of Deep Learning (DL) techniques, significantly enhancing the efficiency and accuracy of object detection tasks. However, the technology for autonomous driving has yet to reach a level of maturity that guarantees consistent performance, reliability, and safety, with several challenges remaining unresolved. This study specifically focuses on 2D image-based object detection methods, which offer several advantages over other modalities, such as cost-effectiveness and the ability to capture visual features like colour and texture that are not detectable by LiDAR. We provide a comprehensive survey of DL-based strategies for detecting vehicles and pedestrians using 2D images, analysing both one-stage and two-stage detection frameworks. Additionally, we review the most commonly used publicly available datasets in autonomous driving research and highlight their relevance to 2D detection tasks. The paper concludes by discussing the current challenges in this domain and proposing potential future directions, aiming to bridge the gap between the capabilities of 2D image-based models and the requirements of real-world autonomous driving applications. Comparative tables are included to facilitate a clear understanding of the different approaches and datasets.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70020","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143513481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Q-GEV Based Novel Trainable Clustering Scheme for Reducing Complexity of Data Clustering","authors":"Mohamed Abd Elaziz,&nbsp;Esraa Osama Abo Zaid,&nbsp;Mohammed A. A. Al-qaness,&nbsp;Amjad Ali,&nbsp;Ali Kashif Bashir,&nbsp;Ahmed A. Ewees,&nbsp;Yasser D. Al-Otaibi,&nbsp;Ala Al-Fuqaha","doi":"10.1111/exsy.70011","DOIUrl":"https://doi.org/10.1111/exsy.70011","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper presents a new data clustering technique aimed at enhancing the performance of the trainable path-cost algorithm and reducing the computational complexity of data clustering models. The proposed method facilitates the discovery of natural groupings and behaviours, which is crucial for effective coordination in complex environments. It identifies natural groupings within a set of features and detects the best clusters with similar behaviour in the data, overcoming the limitations of traditional state-of-the-art methods. The algorithm utilises a density peak clustering method to determine cluster centers and then extracts features from paths passing through these peak points (centers). These features are used to train the support vector machine (SVM) to predict the labels of other points. The proposed algorithm is enhanced using two key concepts: first, it employs Q-Generalised Extreme Value (Q-GEV) under power normalisation instead of traditional generalised extreme value distributions, thereby increasing modelling flexibility; second, it utilises the random vector functional link (RVFL) network rather than the SVM, which helps avoid overfitting and improves label prediction accuracy. The effectiveness of the proposed clustering algorithm is evaluated through various experiments, including those on UCI benchmark datasets and real-world data, demonstrating significant improvements across multiple performance metrics, including F1 measure, Jaccard index, purity, and accuracy, highlighting its capability in accurately identifying paths between similar clusters. Its average F1 measure, Jaccard index, purity, and accuracy is measured 76.87%, 56.29%, 80.29%, and 79.64%, respectively.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143513480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable Artificial Intelligence for Business and Economics: Methods, Applications and Challenges","authors":"Qi Lyu,&nbsp;Shaomin Wu","doi":"10.1111/exsy.70017","DOIUrl":"https://doi.org/10.1111/exsy.70017","url":null,"abstract":"<p>In recent years, artificial intelligence (AI) has made significant strides in research and shown great potential in various application fields, including business and economics (B&amp;E). However, AI models are often black boxes, making them difficult to understand and explain. This challenge can be addressed using eXplainable Artificial Intelligence (XAI), which helps humans understand the factors driving AI decisions, thereby increasing transparency and confidence in the results. This paper aims to provide a comprehensive understanding of the state-of-the-art research on XAI in B&amp;E by conducting an extensive literature review. It introduces a novel approach to categorising XAI techniques from three different perspectives: samples, features and modelling method. Additionally, the paper identifies key challenges and corresponding opportunities in the field. We hope that this work will promote the adoption of AI in B&amp;E, inspire interdisciplinary collaboration, foster innovation and growth and ensure transparency and explainability.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70017","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143496932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"POI Extraction From Digital City: An Engineering Exploration With Large-Language Models","authors":"Mingzheng Sun,&nbsp;Qi Li,&nbsp;Jie Pan,&nbsp;Hongwei Wei,&nbsp;Chong Liu,&nbsp;Xin Xu,&nbsp;Yangang Li","doi":"10.1111/exsy.70001","DOIUrl":"https://doi.org/10.1111/exsy.70001","url":null,"abstract":"<div>\u0000 \u0000 <p>Point-of-interest (POI) extraction aims to extract text POIs from real-world data. Existing POI methods, such as social media-based user generating and web crawling, either require massive human resources or cannot guarantee integrity and reliability. Therefore, in this paper, an end-to-end POI extraction framework based on digital city is proposed. It is built of digital models, textures, tiles and other digital assets collected by aircraft. The extraction process for POIs consists of segmenting it into four sequential stages: collecting, segmentation, recognition and cleaning, each enhanced through fine-tuning on a proposed specialised digital scene dataset or via the development of tailored algorithms. Specifically, in the last stage, the application of large language model (LLM) is explored in the POI data cleaning field. By testing several LLMs of different scales using diverse chain-of-thought (CoT) strategies, the relatively optimal prompt scheme for different LLMs is identified regarding noise handling, formatted output and overall cleaning capability. Ultimately, POIs extracted through the proposed methodology exhibit superior quality and accuracy, surpassing the comprehensiveness of existing public commercial POI datasets, with the <i>F</i>1-score increased by 19.6%, 21.1% and 23.8% on Amap, Baidu and Google POI datasets, respectively.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143489790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Systematic Review on Text Summarization: Techniques, Challenges, Opportunities","authors":"Kanta Prasad Sharma,&nbsp;Mohd Shukri Ab Yajid,&nbsp;J. Gowrishankar,&nbsp;Rohini Mahajan,&nbsp;Anas Ratib Alsoud,&nbsp;Abhilasha Jadhav,&nbsp;Devendra Singh","doi":"10.1111/exsy.13833","DOIUrl":"https://doi.org/10.1111/exsy.13833","url":null,"abstract":"<div>\u0000 \u0000 <p>Text Summarization (TS) is a technique for condensing lengthy text passages. The objective of text summarization is to make concise and coherent summaries that contain the main ideas from a document. When thinking about a page or watching a video, researchers or readers might imagine an abbreviated version which will just catch important parts only. This paper provides an overview of research work done by different authors on this field. There are numerous machine learning and deep learning-based approaches and methods for implementing text summarization in practice because of several factors like time saving, increased productivity, effective comparative analysis, among others. In this article we explore the concept of text summarization as well as techniques, general framework, applications, evaluation measures within both Indic and Non-Indic scripts. Additionally, the article brings out some related issues between text summarization and other intelligent systems such as script nature datasets architectures latest works, and so forth. Finally, the authors presented the challenges of text summarization, as well as analytical ideas, conclusions, and future directions for text summarization.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 4","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143489791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}