Computer Science Review最新文献

{"title":"From mathematical to AI-based methods: A review of marine PNT data fusion and uncertainty handling","authors":"Natalia Ziółkowska,&nbsp;Joanna Szłapczyńska","doi":"10.1016/j.cosrev.2025.100864","DOIUrl":"10.1016/j.cosrev.2025.100864","url":null,"abstract":"<div><div>The development of accurate and reliable Positioning, Navigation, and Timing (PNT) systems increasingly depends on advancements in computer science, particularly data fusion and uncertainty handling. Scientific research in maritime navigation focuses on trajectory prediction, route planning, and collision avoidance, among other areas, whereas all mentioned topics are highly dependent on the accuracy and robustness of the provided data. However, positioning and uncertainty handling methods still face limitations, including measurement absence or inaccuracy, increased threats of spoofing and jamming attacks, and limited adaptability to dynamic maritime conditions. Previous reviews have not systematically addressed positioning accuracy, data fusion, and uncertainty handling in this context, nor have they consistently applied transparent methodologies, leaving gaps in reproducibility and coverage. This review addresses these gaps by presenting a structured synthesis of techniques to improve the accuracy and reliability of maritime navigation, ranging from traditional mathematical approaches to AI-based solutions. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines are followed to ensure methodological transparency. This review makes several unique contributions. It provides PRISMA-based systematic overview of ship positioning and uncertainty-handling methods and attempts to address key research questions, including existing solutions, challenges, and emerging opportunities. Additionally, the potential of AI to enhance navigation systems is thoroughly discussed, with future research directions to address current limitations. Together, these contributions provide a roadmap for advancing the reliability, resilience, and safety of maritime navigation.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100864"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145610125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Advanced work packaging in construction management through systematic review and socio-technical framework for digital integration","authors":"Hamza Aamir ,&nbsp;Wesam Salah Alaloul ,&nbsp;Abdul Mateen Khan ,&nbsp;Muhammad Ali Musarat","doi":"10.1016/j.cosrev.2025.100856","DOIUrl":"10.1016/j.cosrev.2025.100856","url":null,"abstract":"<div><div>Advanced Work Packaging (AWP) has gained increasing attention as a structured methodology for enhancing efficiency, productivity, and coordination in construction projects. Yet, current research remains segmented and often descriptive, with limited integration of digital technologies in construction projects. Hence, this study conducts a systematic review to unify existing literature and critically evaluate the role of AWP in advancing construction automation. In this manner, a total of 719 publications across five major databases were initially screened, from which 57 highly relevant studies published between 2013 and 2024 were selected for in-depth analysis. Bibliometric mapping and keyword co-occurrence analysis were employed to identify research trends, thematic clusters, and knowledge gaps, while critical synthesis emphasized conceptual overlaps and methodological shortcomings. The findings reveal that while frameworks for AWP have been widely discussed, most studies prioritize cost and schedule analysis with limited focus on Building Information Modeling (BIM), Artificial Intelligence (AI), and Machine Learning applications. To address this gap, a novel socio-technical conceptual framework is proposed, structured around preconditions, intermediate processes, outputs, and feedback, and explicitly embedding AI-enabled predictive analytics, BIM-based model validation, and automated monitoring systems. This framework moves beyond descriptive models by emphasizing validation strategies, adaptive feedback loops, and integration of organizational and technological dimensions. The study acknowledges limitations related to potential selection bias, database restrictions, and qualitative subjectivity, but also provides actionable implications for research, industry practice, and policy. The contribution lies in advancing AWP from a descriptive planning tool to a digitally integrated and globally adaptable methodology for construction project delivery.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100856"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145609226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Context-aware security and machine learning for access control: A systematic mapping and taxonomies","authors":"Vítor Kehl Matter,&nbsp;Márcio Garcia Martins,&nbsp;Jorge Luis Victória Barbosa","doi":"10.1016/j.cosrev.2025.100880","DOIUrl":"10.1016/j.cosrev.2025.100880","url":null,"abstract":"<div><div>This study explores the enhancement of user security in smart environments through the integration of Context-Aware Security (CAS) with Machine Learning (ML). A systematic mapping covering publications from 2013 to 2024 analyzed 75 primary studies that combine CAS, security, and ML, particularly in the context of access control and identity validation. The analysis revealed that Access Control (AC), managing information access based on contextual data, emerged as a predominant area of interest, with 30 studies specifically addressing AC within CAS and ML. The main contributions include taxonomies for context awareness, security mechanisms, ML techniques, and AC mechanisms. These taxonomies categorize and illustrate the current state of research in this interdisciplinary area. Key findings highlight several challenges, such as the difficulty of obtaining datasets due to the sensitive nature of security data, and the limited number of studies thoroughly exploring the integration of CAS, AC, and ML. Consequently, the potential benefits of ML in CAS, particularly for AC, remain underutilized, and traditional techniques continue to dominate the field. The study suggests that further research is needed to effectively integrate ML into CAS to modernize AC systems and improve adaptability to dynamic environments. Addressing these challenges could lead to more secure, responsive, and user-friendly systems in IoT and mobile environments.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100880"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Big data energy systems: A survey of practices and associated challenges","authors":"Lunodzo J. Mwinuka ,&nbsp;Massimo Cafaro ,&nbsp;Lucas Pereira ,&nbsp;Hugo Morais","doi":"10.1016/j.cosrev.2026.100927","DOIUrl":"10.1016/j.cosrev.2026.100927","url":null,"abstract":"<div><div>Energy systems generate vast amounts of data in extremely short time intervals, creating challenges for efficient data management. Traditional data management methods often struggle with scalability and accessibility, limiting their usefulness. More advanced solutions, such as NoSQL databases and cloud-based platforms, have been adopted to address these issues. Still, even these advanced solutions can encounter bottlenecks, which can impact the efficiency of data storage, retrieval, and analysis. This review explores the research trends in big data management for energy systems, highlighting the practices, opportunities and challenges. Additionally, the regulatory data requirements are highlighted using the chosen reference architectures. The review, in particular, explores the limitations of current big data storage and integration solutions and examines how new technologies are applied to the energy sector. Novel insights into emerging technologies - including data spaces, peer-to-peer overlays, and blockchains - are provided, along with practical recommendations to improve data sharing and regulatory compliance.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100927"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Machine learning in sign language: A comprehensive analysis and trend survey","authors":"Michał Kalinowski ,&nbsp;Bożena Kostek","doi":"10.1016/j.cosrev.2026.100895","DOIUrl":"10.1016/j.cosrev.2026.100895","url":null,"abstract":"<div><div>When exploring concepts such as sign language and machine learning, it is clear that this important, rapidly growing field bridges communication gaps, improves accessibility, and promotes inclusion for deaf and hard-of-hearing communities. Over the past five years, advanced machine learning has made significant progress, driven by innovative methods and emerging datasets. This paper presents recent advances in sign language translation, focusing on input methods including camera-based approaches and deep learning techniques. Key contributions from the reviewed works are identified and highlighted, showing trends in research on sign language recognition and translation. The metrics used to evaluate sign language recognition and translation are also examined. The critical features and differences of selected datasets relevant to sign language recognition are explained. The paper ends with a discussion of promising future research directions.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100895"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 comprehensive survey of image steganography: From traditional vision techniques to deep learning paradigms—Trends, challenges, and applications","authors":"Harsh Raj,&nbsp;Gopa Bhaumik","doi":"10.1016/j.cosrev.2026.100892","DOIUrl":"10.1016/j.cosrev.2026.100892","url":null,"abstract":"<div><div>Image steganography has emerged as a crucial technique within the field of information security, enabling the covert transmission of data by embedding it within digital images. Unlike cryptography, which merely obscures the content of a message, steganography conceals the existence of the communication itself, making it an effective tool for privacy-preserving applications. This concealment is achieved by exploiting the inherent redundancy and perceptual limitations of human vision, allowing modifications that remain imperceptible to observers. As digital communication continues to expand, the relevance of steganography has increased, especially in environments where secure and unobtrusive data transmission is essential. This paper provides a comprehensive analysis of existing image steganography techniques. It categorizes methods based on embedding domains such as spatial, transform domain, spread spectrum, and model-based approaches and further classifies them according to algorithmic strategies, including traditional statistical methods and deep learning architectures like Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs). The paper also examines key evaluation metrics such as imperceptibility, robustness against detection and distortion, and embedding capacity quantified using PSNR and SSIM. This study aims to identify key trends, challenges, and potential research directions in modern image steganography. The findings suggest that deep learning is steadily transforming the field, though issues such as domain adaptability, dataset diversity, and detectability remain open problems requiring further investigation.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100892"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Learning-based approaches for wireless PHY layers from the perspective of conventional machine learning to foundation models: A comprehensive survey","authors":"Tesfahunegn Minwuyelet Mengistu ,&nbsp;K.M. Faisal ,&nbsp;Taewoon Kim ,&nbsp;Arif Ullah ,&nbsp;Wooyeol Choi","doi":"10.1016/j.cosrev.2025.100870","DOIUrl":"10.1016/j.cosrev.2025.100870","url":null,"abstract":"<div><div>The future of wireless communication requires low latency, ultra-reliable connectivity, and the ability to manage a large number of IoT devices in real time. Achieving these demands for quality of service (QoS) can be addressed through machine learning (ML), deep learning (DL), and foundation models integrated into wireless systems and devices. Foundation models, in particular, show promise for overcoming the limitations of conventional approaches, and improving system performance was observed to be between 9.63 % and 12.80 %, with the possibility of exceeding this range under certain conditions. This review explores how ML, DL, and foundation models can be applied at the physical (PHY) layer in wireless communications. It covers various learning algorithms such as deep, recurrent, and feedforward neural networks, explaining their design, training methods, and challenges. Key applications include channel estimation, constellation design, signal detection, and optimizing signal modulation schemes to achieve better spectral efficiency and noise resilience. The paper also discusses how the ML, DL, and foundation models can enhance MIMO systems with improved detection performance. In addition, it highlights the challenges and opportunities in adopting these models in different communication domains, including trade-offs between accuracy, complexity, and generalization. Conventional ML performs better in scenarios with small datasets, low computational complexity, and tasks requiring high interpretability, whereas DL approaches tend to outperform traditional methods in large-scale, high-dimensional wireless problems such as CSI prediction, interference classification, and spectrum sensing. This survey offers valuable insights into the evolving landscape of intelligent communication systems, guiding practitioners in implementing learning-aided strategies for the next generation of wireless technology.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100870"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145731226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Metaheuristic algorithms: A benchmark-driven functional taxonomy and performance analysis","authors":"Abhineet Suman ,&nbsp;Gunjan ,&nbsp;Sandeep S. Udmale","doi":"10.1016/j.cosrev.2025.100884","DOIUrl":"10.1016/j.cosrev.2025.100884","url":null,"abstract":"<div><div>Metaheuristic algorithms have become a vital asset for tackling complex optimization problems that can hardly be addressed effectively using deterministic methods. This work presents a comparative and behavioral analysis of representative metaheuristic algorithms. A new, functional-behavioral taxonomy of the algorithms is proposed based on their search dynamics, convergence behavior, exploration–exploitation ratio, and landscape adaptability. The algorithms are tested in both single-objective and multi-objective contexts, using benchmark functions that model unimodal, multimodal, non-separable, and composite optimization problems. Empirical evidence indicates that both Differential Evolution and Memetic Algorithm converge quickly and correctly on unimodal landscapes. However, swarm intelligence and physics/chemistry-based algorithms, such as Particle Swarm Optimization, Whale Optimization Algorithm, and Snake Optimizer, exhibit better global exploration in multimodal and composite problems, albeit at a high computational cost. It is statistically proven that behaviorally adaptive algorithms are more stable and robust in a variety of problems. These behavioral patterns form the basis of the proposed taxonomy, which provides an evidence-based and unified framework for interpreting algorithm performance. This work takes a step further than descriptive reviews, in that it not only describes the performance of metaheuristic algorithms but also explains why they behave in a certain way, presenting a systematic basis for designing adaptive and hybrid next-generation metaheuristics.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100884"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"Deep learning-based computer vision for fish behavior recognition in intensive aquaculture: A comprehensive review","authors":"Qingxuan He ,&nbsp;Huihui Yu ,&nbsp;Hanxiang Qin ,&nbsp;Yupeng Mei ,&nbsp;Ling Xu ,&nbsp;Yingqian Chai ,&nbsp;Cuili Li ,&nbsp;Lihua Song ,&nbsp;Daoliang Li ,&nbsp;Yingyi Chen","doi":"10.1016/j.cosrev.2026.100896","DOIUrl":"10.1016/j.cosrev.2026.100896","url":null,"abstract":"<div><div>Fish behavior recognition plays a vital role in evaluating fish welfare and supporting the sustainable development of intensive aquaculture. With the strong capabilities of deep learning (DL) in extracting complex features, computer vision (CV) has become a major driver in advancing behavior recognition methods. These technologies offer essential support for intelligent aquaculture management and water quality monitoring, contributing to the transition toward sustainable, intensive, and large-scale farming practices. This review presents a comprehensive overview of the development and application of DL-based CV techniques for recognizing fish behaviors. It focuses on five representative behavioral categories: feeding, stress, disease, breeding, and cannibalism behavior, summarizing recent progress and significant methodological innovations. In addition, we introduce seven publicly available datasets, commonly used evaluation metrics, and behavioral quantification indices. The review concludes by identifying current research challenges and outlining future directions to support continued innovation in fish behavior recognition for aquaculture systems.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100896"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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":"An overview of sign language processing from natural language processing perspective","authors":"Begum Mutlu ,&nbsp;Yunus Can Bilge","doi":"10.1016/j.cosrev.2026.100907","DOIUrl":"10.1016/j.cosrev.2026.100907","url":null,"abstract":"<div><div>Natural Language Processing and Sign Language Processing share common goals and challenges, as both fields focus on enabling computers to understand and generate modes of communication to enhance interaction between humans and computers. The interaction happens differently, with one relying on spoken or written text and the other on visual-gestural input. Although sign languages possess significant linguistic complexity and expressiveness, they have traditionally been rarely addressed in the fields of computational linguistics and natural language processing research. The fields share similarities (sequence modeling, contextual understanding, representation learning) as well as face similar challenges; annotated data sparsity, ambiguity resolution, and multilingual understanding. In this paper, the key tasks that can be addressed in sign language processing, particularly from a natural language processing perspective, are identified and deeply examined. Sign language translation and production, machine translation, part of speech tagging, named entity resolution, coreference resolution, sentiment analysis, and sign language models in sign languages are included. An overview of these sign language tasks, as well as previously unexplored tasks that are very apparent in natural language processing but not in sign language processing, is provided. Moreover, possible reuses of already available sign language data from a linguistic perspective are also shared. Limitations and open challenges are identified to direct future research toward the linguistic aspects of sign languages, recognizing that more language-based methodologies may be necessary for improved understanding and communication in it.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100907"},"PeriodicalIF":12.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}