Pub Date : 2026-01-14DOI: 10.1016/j.cosrev.2026.100894
Deepika Saxena , Ashutosh Kumar Singh
Computational Intelligence (CI) techniques, inspired by natural and adaptive processes, have become essential tools for enhancing energy efficiency and sustainability in cloud data centers, forming the foundation of Green Cloud Resource Management (GCRM). This paper presents a comprehensive taxonomic review of key CI methodologies, including reinforcement learning, optimization algorithms, fuzzy logic, game-theoretic models, and predictive modeling, highlighting their application in critical GCRM tasks such as task scheduling, Virtual Machine (VM) placement, and VM migration. Each CI paradigm is systematically examined, detailing fundamental principles, algorithmic design, and sustainability-driven features. A meta-analytical discussion synthesizes state-of-the-art contributions, emphasizing performance metrics, complexity, scalability, and real-world applicability, while providing comparative insights into trade-offs inherent in energy-aware cloud operations. Lessons learned from prior studies are consolidated to offer practical guidance for designing adaptive, self-optimizing, and eco-efficient cloud infrastructures. Finally, the review identifies emerging trends and prioritized future research directions, advocating the integration of hybrid CI approaches, multi-objective optimization, cross-layer intelligence, and real-world deployment considerations to advance next-generation sustainable cloud environments.
{"title":"Concepts, taxonomic review, and emerging trends in computational intelligence for green cloud systems","authors":"Deepika Saxena , Ashutosh Kumar Singh","doi":"10.1016/j.cosrev.2026.100894","DOIUrl":"10.1016/j.cosrev.2026.100894","url":null,"abstract":"<div><div>Computational Intelligence (CI) techniques, inspired by natural and adaptive processes, have become essential tools for enhancing energy efficiency and sustainability in cloud data centers, forming the foundation of Green Cloud Resource Management (GCRM). This paper presents a comprehensive taxonomic review of key CI methodologies, including reinforcement learning, optimization algorithms, fuzzy logic, game-theoretic models, and predictive modeling, highlighting their application in critical GCRM tasks such as task scheduling, Virtual Machine (VM) placement, and VM migration. Each CI paradigm is systematically examined, detailing fundamental principles, algorithmic design, and sustainability-driven features. A meta-analytical discussion synthesizes state-of-the-art contributions, emphasizing performance metrics, complexity, scalability, and real-world applicability, while providing comparative insights into trade-offs inherent in energy-aware cloud operations. Lessons learned from prior studies are consolidated to offer practical guidance for designing adaptive, self-optimizing, and eco-efficient cloud infrastructures. Finally, the review identifies emerging trends and prioritized future research directions, advocating the integration of hybrid CI approaches, multi-objective optimization, cross-layer intelligence, and real-world deployment considerations to advance next-generation sustainable cloud environments.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100894"},"PeriodicalIF":12.7,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976555","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}
Pub Date : 2026-01-13DOI: 10.1016/j.cosrev.2026.100896
Qingxuan He , Huihui Yu , Hanxiang Qin , Yupeng Mei , Ling Xu , Yingqian Chai , Cuili Li , Lihua Song , Daoliang Li , Yingyi Chen
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.
{"title":"Deep learning-based computer vision for fish behavior recognition in intensive aquaculture: A comprehensive review","authors":"Qingxuan He , Huihui Yu , Hanxiang Qin , Yupeng Mei , Ling Xu , Yingqian Chai , Cuili Li , Lihua Song , Daoliang Li , 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":"2026-01-13","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}
Pub Date : 2026-01-08DOI: 10.1016/j.cosrev.2025.100887
Shenghai Li , Wentai Wu , Haotong Zhang , Yongheng Liu , Weiwei Lin , Keqin Li
Edge computing has emerged as a pivotal paradigm for overcoming the limitations of traditional cloud computing, especially in latency-sensitive applications such as autonomous driving and video streaming. As mobile applications grow in complexity, they often consist of interdependent tasks that can be modeled as workflows. Scheduling these workflows over heterogeneous resources at the network edge presents unique challenges due to the diverse characteristics of workflows and the complex nature of edge environments. Despite recent advances, a comprehensive overview of the fundamentals and state-of-the-art approaches in this field remains lacking. This survey systematically reviews workflow scheduling in edge computing by first addressing its motivation, typical application scenarios, and core challenges. The survey then introduces basic models and performance metrics, followed by a taxonomy of existing scheduling strategies categorized by research issues, optimization objectives, and techniques. Finally, we discuss open challenges and propose future research directions, providing a guide for the development of efficient edge workflow scheduling strategies.
{"title":"Revisiting workflow scheduling with the power of edge computing: Taxonomy, review, and open challenges","authors":"Shenghai Li , Wentai Wu , Haotong Zhang , Yongheng Liu , Weiwei Lin , Keqin Li","doi":"10.1016/j.cosrev.2025.100887","DOIUrl":"10.1016/j.cosrev.2025.100887","url":null,"abstract":"<div><div>Edge computing has emerged as a pivotal paradigm for overcoming the limitations of traditional cloud computing, especially in latency-sensitive applications such as autonomous driving and video streaming. As mobile applications grow in complexity, they often consist of interdependent tasks that can be modeled as workflows. Scheduling these workflows over heterogeneous resources at the network edge presents unique challenges due to the diverse characteristics of workflows and the complex nature of edge environments. Despite recent advances, a comprehensive overview of the fundamentals and state-of-the-art approaches in this field remains lacking. This survey systematically reviews workflow scheduling in edge computing by first addressing its motivation, typical application scenarios, and core challenges. The survey then introduces basic models and performance metrics, followed by a taxonomy of existing scheduling strategies categorized by research issues, optimization objectives, and techniques. Finally, we discuss open challenges and propose future research directions, providing a guide for the development of efficient edge workflow scheduling strategies.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100887"},"PeriodicalIF":12.7,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938394","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}
Solid-state drives (SSDs) have become the dominant storage solution in modern computing because of their higher performance, energy efficiency, and reliability. However, the limited endurance of NAND flash memory, caused by the degradation of memory cells through repeated Program/Erase cycles, remains a significant challenge. Wear leveling techniques play a crucial role in mitigating this problem by evenly distributing wear across memory blocks. This paper presents a comprehensive survey of wear leveling techniques, categorizing them into two major groups: erase count-based and error rate-aware approaches. This survey discusses key methodologies, design trade-offs, and the impact of wear leveling on SSDs’ performance and lifetime. By addressing these challenges, wear leveling strategies can further enhance the endurance and reliability of SSDs, making them more suitable for evolving storage demands.
{"title":"A survey on SSD wear leveling techniques","authors":"Fatemeh Serajeh Hassani , Atiyeh Gheibi-Fetrat , Sana Babayan Vanestan , Mitra Gholipoor , Sahand Zoufan , Jeong-A Lee , Hamid Sarbazi-Azad","doi":"10.1016/j.cosrev.2025.100891","DOIUrl":"10.1016/j.cosrev.2025.100891","url":null,"abstract":"<div><div>Solid-state drives (SSDs) have become the dominant storage solution in modern computing because of their higher performance, energy efficiency, and reliability. However, the limited endurance of NAND flash memory, caused by the degradation of memory cells through repeated Program/Erase cycles, remains a significant challenge. Wear leveling techniques play a crucial role in mitigating this problem by evenly distributing wear across memory blocks. This paper presents a comprehensive survey of wear leveling techniques, categorizing them into two major groups: erase count-based and error rate-aware approaches. This survey discusses key methodologies, design trade-offs, and the impact of wear leveling on SSDs’ performance and lifetime. By addressing these challenges, wear leveling strategies can further enhance the endurance and reliability of SSDs, making them more suitable for evolving storage demands.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100891"},"PeriodicalIF":12.7,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938395","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}
Pub Date : 2026-01-07DOI: 10.1016/j.cosrev.2025.100878
Souad Mohaoui , Andrii Dmytryshyn
Motion capture (MoCap) systems are indispensable tools across fields such as biomechanics, computer animation, human-robot interaction, and clinical gait analysis, owing to their ability to accurately record and analyze human movement in 3D space. Marker-based systems use reflective markers attached to subjects and video recordings to track human movement. The tracking requires markers to be detected in the video, which is not always possible due to occlusions, sensor failures, and limited camera coverage. These issues create gaps in recorded trajectories, compromising data integrity and making the motion difficult to utilize in practical applications. Therefore, a wide range of MoCap data completion techniques has been proposed to reconstruct missing trajectories while preserving the realism and dynamics of human movement. Human motion data exhibits a low-rank property due to the inherent repetitive nature of human movement as well as the correlations between joints and markers, enforced by the skeletal structure and biomechanical constraints. Low-rank completion techniques exploit this property to reconstruct missing marker positions. This paper reviews state-of-the-art low-rank completion methods for MoCap data completion, focusing specifically on optimization-based low-rank methods. These optimization approaches directly address the missing data completion problem through optimization formulations. We examine two main aspects: kinematic priors, which embed anatomical constraints, joint dependencies, and motion smoothness, and low-rank priors, which exploit inter-marker correlations through matrix and tensor formulations. We further evaluate optimization algorithms for solving these completion problems, such as alternating minimization, proximal algorithms, ADMM, and hybrid schemes, as well as the datasets and tools commonly used in the literature.
{"title":"Low-rank completion for motion capture data recovery: Approaches, constraints, and algorithms","authors":"Souad Mohaoui , Andrii Dmytryshyn","doi":"10.1016/j.cosrev.2025.100878","DOIUrl":"10.1016/j.cosrev.2025.100878","url":null,"abstract":"<div><div>Motion capture (MoCap) systems are indispensable tools across fields such as biomechanics, computer animation, human-robot interaction, and clinical gait analysis, owing to their ability to accurately record and analyze human movement in 3D space. Marker-based systems use reflective markers attached to subjects and video recordings to track human movement. The tracking requires markers to be detected in the video, which is not always possible due to occlusions, sensor failures, and limited camera coverage. These issues create gaps in recorded trajectories, compromising data integrity and making the motion difficult to utilize in practical applications. Therefore, a wide range of MoCap data completion techniques has been proposed to reconstruct missing trajectories while preserving the realism and dynamics of human movement. Human motion data exhibits a low-rank property due to the inherent repetitive nature of human movement as well as the correlations between joints and markers, enforced by the skeletal structure and biomechanical constraints. Low-rank completion techniques exploit this property to reconstruct missing marker positions. This paper reviews state-of-the-art low-rank completion methods for MoCap data completion, focusing specifically on optimization-based low-rank methods. These optimization approaches directly address the missing data completion problem through optimization formulations. We examine two main aspects: kinematic priors, which embed anatomical constraints, joint dependencies, and motion smoothness, and low-rank priors, which exploit inter-marker correlations through matrix and tensor formulations. We further evaluate optimization algorithms for solving these completion problems, such as alternating minimization, proximal algorithms, ADMM, and hybrid schemes, as well as the datasets and tools commonly used in the literature.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100878"},"PeriodicalIF":12.7,"publicationDate":"2026-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938393","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}
Early detection of dental problems, such as Furcation Radiolucency (FR), plays a vital role in ensuring effective treatment and maintaining oral health, particularly in pediatric dentistry. FR, often associated with deep dental decay, can be identified across various dental radiographic modalities, typically appearing as a dark, radiolucent area between the tooth roots. However, accurate interpretation of extraoral and intraoral dental radiographs can be challenging due to the subtle nature of early lesions and variability in image quality. This review explores the transformative potential of Artificial Intelligence (AI)- driven Computer-Aided Diagnosis (CAD) systems, which enhance the detection and analysis of FR, offering clear advantages over traditional methods. AI technologies, particularly Machine Learning (ML) and Deep Learning (DL), enhance critical stages of dental radiographic analysis, including image preprocessing, segmentation, and classification. These advancements enable early identification of subtle radiographic changes, reducing the need for invasive treatments and fostering more proactive treatment planning. The paper provides a comprehensive review of both traditional diagnostic techniques and recent AI-driven innovations, highlighting their impact on improving dental image quality, segmentation precision and classification accuracy. Focusing on powerful AI models such as U-Net, Mask Region-based Convolutional Neural Network (R-CNN), and Vision Transformers (ViTs), along with lightweight deep Convolutional Networks (ConvNets) like MobileNetV2 or EfficientNetV2, the review highlights the potential of these systems to identify dental problems more effectively and facilitate efficient clinical decision-making. Additionally, the paper addresses ongoing challenges, including the need for large-scale validation and multi-modal data integration, and offers actionable insights for researchers and dental practitioners to further leverage AI in pediatric dental care. This review bridges the gap between traditional diagnostic practices and AI-enhanced methods, underscoring the future potential of AI to revolutionize dental diagnostics and treatment planning.
{"title":"Artificial intelligence-based approaches for preprocessing, segmentation, and classification in dental radiographs for furcation detection: A comparative analysis","authors":"Priyanka , Mamta Juneja , Naveen Aggarwal , Manoj Kumar Jaiswal , Priyanka Rana","doi":"10.1016/j.cosrev.2025.100890","DOIUrl":"10.1016/j.cosrev.2025.100890","url":null,"abstract":"<div><div>Early detection of dental problems, such as Furcation Radiolucency (FR), plays a vital role in ensuring effective treatment and maintaining oral health, particularly in pediatric dentistry. FR, often associated with deep dental decay, can be identified across various dental radiographic modalities, typically appearing as a dark, radiolucent area between the tooth roots. However, accurate interpretation of extraoral and intraoral dental radiographs can be challenging due to the subtle nature of early lesions and variability in image quality. This review explores the transformative potential of Artificial Intelligence (AI)- driven Computer-Aided Diagnosis (CAD) systems, which enhance the detection and analysis of FR, offering clear advantages over traditional methods. AI technologies, particularly Machine Learning (ML) and Deep Learning (DL), enhance critical stages of dental radiographic analysis, including image preprocessing, segmentation, and classification. These advancements enable early identification of subtle radiographic changes, reducing the need for invasive treatments and fostering more proactive treatment planning. The paper provides a comprehensive review of both traditional diagnostic techniques and recent AI-driven innovations, highlighting their impact on improving dental image quality, segmentation precision and classification accuracy. Focusing on powerful AI models such as U-Net, Mask Region-based Convolutional Neural Network (R-CNN), and Vision Transformers (ViTs), along with lightweight deep Convolutional Networks (ConvNets) like MobileNetV2 or EfficientNetV2, the review highlights the potential of these systems to identify dental problems more effectively and facilitate efficient clinical decision-making. Additionally, the paper addresses ongoing challenges, including the need for large-scale validation and multi-modal data integration, and offers actionable insights for researchers and dental practitioners to further leverage AI in pediatric dental care. This review bridges the gap between traditional diagnostic practices and AI-enhanced methods, underscoring the future potential of AI to revolutionize dental diagnostics and treatment planning.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100890"},"PeriodicalIF":12.7,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145938396","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}
Pub Date : 2026-01-06DOI: 10.1016/j.cosrev.2026.100892
Harsh Raj, Gopa Bhaumik
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.
{"title":"A comprehensive survey of image steganography: From traditional vision techniques to deep learning paradigms—Trends, challenges, and applications","authors":"Harsh Raj, 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":"2026-01-06","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}
Pub Date : 2026-01-03DOI: 10.1016/j.cosrev.2025.100888
Yipeng Yin , Rao Yao , Qingying Li , Dazhong Wang , Hong Zhou , Zhijun Fang , Jianing Chen , Longjie Qian , Mingyue Wu
As Micro-CT technology continues to refine its characterization of material microstructures, industrial CT ultra-precision inspection is generating increasingly large datasets, necessitating solutions to the trade-off between accuracy and efficiency in the 3D characterization of defects during ultra-precise detection. This article provides a unique perspective on recent advances in accurate and efficient 3D visualization using Micro-CT, tracing its evolution from medical imaging to industrial non-destructive testing (NDT). Among the numerous CT reconstruction and volume rendering methods, this article selectively reviews and analyzes approaches that balance accuracy and efficiency, offering a comprehensive analysis to help researchers quickly grasp highly efficient and accurate 3D reconstruction methods for microscopic features. By comparing the principles of computed tomography with advancements in microstructural technology, this article examines the evolution of CT reconstruction algorithms from analytical methods to deep learning techniques, as well as improvements in volume rendering algorithms, acceleration, and data reduction. Additionally, it explores advanced lighting models for high-accuracy, photorealistic, and efficient volume rendering. Furthermore, this article envisions potential directions in CT reconstruction and volume rendering. It aims to guide future research in quickly selecting efficient and precise methods and developing new ideas and approaches for real-time online monitoring of internal material defects through virtual-physical interaction, for applying digital twin model to structural health monitoring (SHM).
{"title":"Three-dimensional visualization of X-ray micro-CT with large-scale datasets: Efficiency and accuracy for real-time interaction","authors":"Yipeng Yin , Rao Yao , Qingying Li , Dazhong Wang , Hong Zhou , Zhijun Fang , Jianing Chen , Longjie Qian , Mingyue Wu","doi":"10.1016/j.cosrev.2025.100888","DOIUrl":"10.1016/j.cosrev.2025.100888","url":null,"abstract":"<div><div>As Micro-CT technology continues to refine its characterization of material microstructures, industrial CT ultra-precision inspection is generating increasingly large datasets, necessitating solutions to the trade-off between accuracy and efficiency in the 3D characterization of defects during ultra-precise detection. This article provides a unique perspective on recent advances in accurate and efficient 3D visualization using Micro-CT, tracing its evolution from medical imaging to industrial non-destructive testing (NDT). Among the numerous CT reconstruction and volume rendering methods, this article selectively reviews and analyzes approaches that balance accuracy and efficiency, offering a comprehensive analysis to help researchers quickly grasp highly efficient and accurate 3D reconstruction methods for microscopic features. By comparing the principles of computed tomography with advancements in microstructural technology, this article examines the evolution of CT reconstruction algorithms from analytical methods to deep learning techniques, as well as improvements in volume rendering algorithms, acceleration, and data reduction. Additionally, it explores advanced lighting models for high-accuracy, photorealistic, and efficient volume rendering. Furthermore, this article envisions potential directions in CT reconstruction and volume rendering. It aims to guide future research in quickly selecting efficient and precise methods and developing new ideas and approaches for real-time online monitoring of internal material defects through virtual-physical interaction, for applying digital twin model to structural health monitoring (SHM).</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100888"},"PeriodicalIF":12.7,"publicationDate":"2026-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884463","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}
Pub Date : 2026-01-02DOI: 10.1016/j.cosrev.2025.100889
Soghra Nashath Omer , Panchamoorthy Saravanan , Pramilaa Kumar , M. Moniga , R. Rajeshkannan , Madhavi Reddy , M. Rajasimman , S. Venkat Kumar
Solid Waste Management (SWM) constitutes a significant challenge confronting both developed and developing countries. A crucial element of effective solid waste management is ensuring that waste bins is public spaces are adequately filled prior to the commencement of the subsequent cleaning cycle. Failure to do so can result in various hazards, including unsightly litter and unpleasant odours, which may contribute to the proliferation of diseases. Furthermore, the rapid growth of the population has markedly strained the existing SWM infrastructure, particularly in terms of sanitation facilities. The indiscriminate disposal of garbage in public area leads to environmental pollution. To mitigates waste-related issues and uphold public health standards, the implementation of a comprehensive SWM system is essential. It is important to recognize that the necessity for effective waste management extends beyond merely the collection and disposal of waste. And also, the study examines the implementation of Artificial Intelligence (AI) and Machine Learning (ML) applications in SWM, evaluate the performance of these AI and ML applications investigates the associated benefits and challenges and offers recommendations for best practices aimed at optimizing resource efficiency to enhance economic, environmental and social outcomes. The research will be advantageous for scholars, government entities, policy-makers, and various organizations involved in waste management, as it seems to evaluate current recycling rates, minimize reliance on manual labour decrease operational costs, enhance efficiency and fundamentally transform the methodologies employed in the solid waste management.
{"title":"Artificial intelligence and machine learning techniques in solid waste management: A sustainable way toward future","authors":"Soghra Nashath Omer , Panchamoorthy Saravanan , Pramilaa Kumar , M. Moniga , R. Rajeshkannan , Madhavi Reddy , M. Rajasimman , S. Venkat Kumar","doi":"10.1016/j.cosrev.2025.100889","DOIUrl":"10.1016/j.cosrev.2025.100889","url":null,"abstract":"<div><div>Solid Waste Management (SWM) constitutes a significant challenge confronting both developed and developing countries. A crucial element of effective solid waste management is ensuring that waste bins is public spaces are adequately filled prior to the commencement of the subsequent cleaning cycle. Failure to do so can result in various hazards, including unsightly litter and unpleasant odours, which may contribute to the proliferation of diseases. Furthermore, the rapid growth of the population has markedly strained the existing SWM infrastructure, particularly in terms of sanitation facilities. The indiscriminate disposal of garbage in public area leads to environmental pollution. To mitigates waste-related issues and uphold public health standards, the implementation of a comprehensive SWM system is essential. It is important to recognize that the necessity for effective waste management extends beyond merely the collection and disposal of waste. And also, the study examines the implementation of Artificial Intelligence (AI) and Machine Learning (ML) applications in SWM, evaluate the performance of these AI and ML applications investigates the associated benefits and challenges and offers recommendations for best practices aimed at optimizing resource efficiency to enhance economic, environmental and social outcomes. The research will be advantageous for scholars, government entities, policy-makers, and various organizations involved in waste management, as it seems to evaluate current recycling rates, minimize reliance on manual labour decrease operational costs, enhance efficiency and fundamentally transform the methodologies employed in the solid waste management.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100889"},"PeriodicalIF":12.7,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884462","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}
Pub Date : 2025-12-27DOI: 10.1016/j.cosrev.2025.100884
Abhineet Suman , Gunjan , Sandeep S. Udmale
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.
{"title":"Metaheuristic algorithms: A benchmark-driven functional taxonomy and performance analysis","authors":"Abhineet Suman , Gunjan , 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":"2025-12-27","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号