Computer Science Review最新文献_第6页

Context-aware security and machine learning for access control: A systematic mapping and taxonomies 用于访问控制的上下文感知安全和机器学习：系统的映射和分类法

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-12-18 DOI: 10.1016/j.cosrev.2025.100880

Vítor Kehl Matter, Márcio Garcia Martins, Jorge Luis Victória Barbosa

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.

本研究探讨了通过集成上下文感知安全（CAS）和机器学习（ML）来增强智能环境中的用户安全。一份涵盖2013年至2024年出版物的系统地图分析了75项结合CAS、安全性和ML的主要研究，特别是在访问控制和身份验证的背景下。分析显示，基于上下文数据管理信息访问的访问控制（AC）成为一个主要的兴趣领域，有30项研究专门针对CAS和ML中的AC进行了研究。主要贡献包括上下文感知、安全机制、ML技术和AC机制的分类。这些分类法对这个跨学科领域的研究现状进行了分类和说明。主要发现突出了几个挑战，例如由于安全数据的敏感性而难以获得数据集，以及深入探索CAS， AC和ML集成的研究数量有限。因此，CAS中ML的潜在优势，特别是对于AC，仍然未得到充分利用，传统技术继续主导该领域。该研究表明，需要进一步研究将机器学习有效地集成到CAS中，以使空调系统现代化，提高对动态环境的适应性。解决这些挑战可以在物联网和移动环境中带来更安全、响应更快、用户友好的系统。

{"title":"Context-aware security and machine learning for access control: A systematic mapping and taxonomies","authors":"Vítor Kehl Matter, Márcio Garcia Martins, 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":"2025-12-18","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}

引用次数: 0

A systematic review of deep learning-based models for elderly and human activity recognition 基于深度学习的老年人和人类活动识别模型的系统综述

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-12-12 DOI: 10.1016/j.cosrev.2025.100879

Mukesh Dalal , Payal Mittal

The ageing population in India and globally has highlighted the significant need for research on elderly activity detection and enhancing safety measures for elderly individuals living alone. This is crucial due to their increased vulnerability to accidents when unattended. By monitoring their behaviors and providing prompt assistance, potential dangers can be mitigated. Recently, deep learning and sensor-based methods have been applied in activity recognition; however, Elderly Activity Recognition (EAR) research is limited compared to Human Activity Recognition (HAR). Existing surveys are failing to provide a detailed analysis of datasets, models, and performance metrics. This paper presents a systematic and detailed review of existing state-of-the-art deep learning models for EAR and HAR based on the PRISMA approach. Further, a comparative analysis of the existing literature is done by using standard evaluation metrics. The paper delineates a wide range of publicly available datasets encompassing diverse subjects, numbers of instances, sensor or image/video modalities, and their respective download sources. The paper emphasises the research trends and highlights research gaps for EAR, including fall detection and reduced mobility patterns. It proposes adaptations of existing HAR methods to address these challenges and provides a practical guide for choosing suitable models and datasets for monitoring elderly activities, thus filling a gap in current research.

印度和全球的人口老龄化凸显了研究老年人活动检测和加强独居老年人安全措施的重大必要性。这一点至关重要，因为在无人看管的情况下，它们更容易发生事故。通过监控他们的行为并及时提供帮助，可以减轻潜在的危险。近年来，深度学习和基于传感器的方法已被应用于活动识别；然而，与人类活动识别（HAR）相比，老年人活动识别（EAR）的研究有限。现有的调查未能提供对数据集、模型和性能指标的详细分析。本文对基于PRISMA方法的EAR和HAR的现有最先进的深度学习模型进行了系统和详细的回顾。此外，通过使用标准评价指标对现有文献进行比较分析。本文描述了广泛的公开可用数据集，包括不同的主题、实例数量、传感器或图像/视频模式，以及它们各自的下载来源。本文强调了EAR的研究趋势和研究差距，包括跌倒检测和减少移动模式。它提出了对现有HAR方法的调整以应对这些挑战，并为选择合适的模型和数据集来监测老年人活动提供了实用指南，从而填补了当前研究中的空白。

{"title":"A systematic review of deep learning-based models for elderly and human activity recognition","authors":"Mukesh Dalal , Payal Mittal","doi":"10.1016/j.cosrev.2025.100879","DOIUrl":"10.1016/j.cosrev.2025.100879","url":null,"abstract":"<div><div>The ageing population in India and globally has highlighted the significant need for research on elderly activity detection and enhancing safety measures for elderly individuals living alone. This is crucial due to their increased vulnerability to accidents when unattended. By monitoring their behaviors and providing prompt assistance, potential dangers can be mitigated. Recently, deep learning and sensor-based methods have been applied in activity recognition; however, Elderly Activity Recognition (EAR) research is limited compared to Human Activity Recognition (HAR). Existing surveys are failing to provide a detailed analysis of datasets, models, and performance metrics. This paper presents a systematic and detailed review of existing state-of-the-art deep learning models for EAR and HAR based on the PRISMA approach. Further, a comparative analysis of the existing literature is done by using standard evaluation metrics. The paper delineates a wide range of publicly available datasets encompassing diverse subjects, numbers of instances, sensor or image/video modalities, and their respective download sources. The paper emphasises the research trends and highlights research gaps for EAR, including fall detection and reduced mobility patterns. It proposes adaptations of existing HAR methods to address these challenges and provides a practical guide for choosing suitable models and datasets for monitoring elderly activities, thus filling a gap in current research.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100879"},"PeriodicalIF":12.7,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145731224","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}

引用次数: 0

Backdoors to satisfaction continued 满足的后门还在继续

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-12-12 DOI: 10.1016/j.cosrev.2025.100868

Serge Gaspers , Stefan Szeider

A backdoor set is a set of variables of a propositional formula such that fixing the truth values of the variables in the backdoor set moves the formula into some polynomial-time decidable class. If we know a small backdoor set, we can reduce the question of whether the given formula is satisfiable to the same question for one or several easy formulas that belong to the tractable class under consideration. Continuing our 2012 survey, we review parameterized complexity results for problems that arise in the context of backdoor sets, such as the problem of finding a backdoor set of size, depth, or treewidth at most

k

, parameterized by

k

.

后门集是一个命题公式的一组变量，当确定了后门集中变量的真值后，这个命题公式就变成了一个多项式时间可决定的类。如果我们知道一个小的后门集，我们可以将给定公式是否可满足的问题约简为一个或几个属于考虑的可处理类的简单公式的同一个问题。继续我们2012年的调查，我们回顾了后门集上下文中出现的问题的参数化复杂性结果，例如寻找大小、深度或树宽最多为k的后门集的问题，参数化为k。

引用次数: 0

Learning-based approaches for wireless PHY layers from the perspective of conventional machine learning to foundation models: A comprehensive survey 从传统机器学习到基础模型的角度看无线物理层的基于学习的方法：综合调查

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-12-10 DOI: 10.1016/j.cosrev.2025.100870

Tesfahunegn Minwuyelet Mengistu , K.M. Faisal , Taewoon Kim , Arif Ullah , Wooyeol Choi

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.

未来的无线通信需要低延迟、超可靠的连接，以及实时管理大量物联网设备的能力。通过将机器学习（ML）、深度学习（DL）和基础模型集成到无线系统和设备中，可以解决对服务质量（QoS）的这些需求。特别是，基础模型显示出克服常规方法局限性的希望，并且观察到系统性能的改善在9.63%到12.80%之间，在某些条件下有可能超过这个范围。本文探讨了如何将ML、DL和基础模型应用于无线通信的物理层（PHY）。它涵盖了各种学习算法，如深度、循环和前馈神经网络，解释了它们的设计、训练方法和挑战。关键应用包括信道估计、星座设计、信号检测和优化信号调制方案，以实现更好的频谱效率和抗噪声能力。本文还讨论了ML、DL和基础模型如何通过改进检测性能来增强MIMO系统。此外，它还强调了在不同的通信领域中采用这些模型的挑战和机遇，包括在准确性、复杂性和泛化之间的权衡。传统的机器学习在小数据集、低计算复杂性和需要高可解释性的任务中表现更好，而深度学习方法在大规模、高维无线问题（如CSI预测、干扰分类和频谱感知）中往往优于传统方法。这项调查对智能通信系统的发展前景提供了宝贵的见解，指导从业者为下一代无线技术实施学习辅助策略。

{"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 , K.M. Faisal , Taewoon Kim , Arif Ullah , 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":"2025-12-10","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}

引用次数: 0

Isogeny-based cryptography: A comprehensive review on advancements, analysis of attacks, and future directions 基于等基因的密码学：对进展、攻击分析和未来方向的全面回顾

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-12-04 DOI: 10.1016/j.cosrev.2025.100865

Dheerendra Mishra, Rohit Raj Sharma

Recent developments in quantum computing present significant challenges to traditional cryptographic approaches, especially those relying on integer factorization and discrete logarithms. To counter these challenges, a variety of post-quantum cryptographic (PQC) methods have been proposed, including cryptographic systems based on lattices, hashing, codes, multivariate equations, and isogenies. Each of these is based on complex mathematical problems that are challenging to solve even with quantum computers. Among them, isogeny-based cryptography has garnered considerable attention for its small key sizes, making it a leading candidate for developing efficient post-quantum cryptographic primitives. This article provides an in-depth review of isogeny-based cryptographic techniques, emphasizing key exchange, zero-knowledge proofs (ZKP), and signature protocols. It begins by elucidating the foundational concepts of elliptic curves, isogenies, and the primary protocols utilizing them. The discussion then shifts to the challenges that current schemes face and examines potential research directions aimed at improving security, scalability, and functionality.

量子计算的最新发展对传统的密码方法提出了重大挑战，特别是那些依赖于整数分解和离散对数的方法。为了应对这些挑战，人们提出了各种后量子密码（PQC）方法，包括基于格、哈希、编码、多元方程和同基因的密码系统。这些都是基于复杂的数学问题，即使用量子计算机也很难解决。其中，基于等基因的密码学因其小密钥大小而引起了相当大的关注，使其成为开发高效后量子密码原语的主要候选。本文深入回顾了基于同基因的加密技术，重点介绍了密钥交换、零知识证明（ZKP）和签名协议。它首先阐明椭圆曲线的基本概念，等同源性，以及利用它们的主要协议。然后，讨论转向当前方案面临的挑战，并检查旨在提高安全性、可伸缩性和功能的潜在研究方向。

{"title":"Isogeny-based cryptography: A comprehensive review on advancements, analysis of attacks, and future directions","authors":"Dheerendra Mishra, Rohit Raj Sharma","doi":"10.1016/j.cosrev.2025.100865","DOIUrl":"10.1016/j.cosrev.2025.100865","url":null,"abstract":"<div><div>Recent developments in quantum computing present significant challenges to traditional cryptographic approaches, especially those relying on integer factorization and discrete logarithms. To counter these challenges, a variety of post-quantum cryptographic (PQC) methods have been proposed, including cryptographic systems based on lattices, hashing, codes, multivariate equations, and isogenies. Each of these is based on complex mathematical problems that are challenging to solve even with quantum computers. Among them, isogeny-based cryptography has garnered considerable attention for its small key sizes, making it a leading candidate for developing efficient post-quantum cryptographic primitives. This article provides an in-depth review of isogeny-based cryptographic techniques, emphasizing key exchange, zero-knowledge proofs (ZKP), and signature protocols. It begins by elucidating the foundational concepts of elliptic curves, isogenies, and the primary protocols utilizing them. The discussion then shifts to the challenges that current schemes face and examines potential research directions aimed at improving security, scalability, and functionality.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100865"},"PeriodicalIF":12.7,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689752","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}

引用次数: 0

Potential of artificial intelligence in deepfake media: From generation to detection mechanisms, state-of-the-art, and challenges 人工智能在深度假媒体中的潜力：从一代到检测机制、最新技术和挑战

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-12-04 DOI: 10.1016/j.cosrev.2025.100866

Shubham Sharma, Arvind Selwal

Artificial intelligence (AI) plays an important role in the generation of deepfakes by leveraging advanced machine learning models to create hyper-realistic synthetic media across visual, audio, and multimodal formats. The rapid evolution of deepfake technologies, alongside the exponential growth of digital media, demands a comprehensive and critical examination of current capabilities and challenges. Although the concept of media manipulation is not new, the sophistication and accessibility of AI-driven deepfakes present significant threats of misinformation to society and hence cause societal manipulation. This manuscript presents a systematic review of deepfake generation and detection techniques from 2017 to 2025, highlighting the progression of generative models and evaluating detection strategies. The main focus of this work is on the state-of-the-art (SOTA) techniques using adversarial networks, vision transformers (ViTs), attention mechanisms, hybrid learning frameworks, and ensemble models. The study thoroughly examines the benefits and drawbacks of existing methods. It also points out how vulnerable detection systems are to adversarial attacks and compares modern methods with traditional forensic and heuristic approaches. The paper critically analyzes the strengths and limitations of existing models, underscores the susceptibility of detection systems to adversarial attacks, and contrasts contemporary approaches with traditional forensic and heuristic-based methods. In addition to technical insights, the review puts a major focus on practical concerns such as scalability, regulatory frameworks, and the broader societal impact of the deepfake technology. By including benchmark datasets, standard tools, performance evaluation metrics, and relevant policy discussions, the manuscript presents a forward-looking perspective on the ongoing arms race between deepfake generation and detection. The study ends by highlighting the need for strong, flexible, and understandable detection systems, backed by effective policy measures, to reduce the growing risks posed by deepfakes.

人工智能（AI）通过利用先进的机器学习模型创建跨视觉、音频和多模态格式的超现实合成媒体，在深度伪造的生成中发挥着重要作用。深度伪造技术的快速发展，以及数字媒体的指数级增长，要求对当前的能力和挑战进行全面和批判性的审查。虽然媒体操纵的概念并不新鲜，但人工智能驱动的深度伪造的复杂性和可访问性对社会构成了严重的错误信息威胁，从而导致社会操纵。本文对2017年至2025年的深度伪造生成和检测技术进行了系统回顾，重点介绍了生成模型的进展和评估检测策略。这项工作的主要焦点是使用对抗网络、视觉转换器（ViTs）、注意力机制、混合学习框架和集成模型的最先进（SOTA）技术。这项研究彻底考察了现有方法的优点和缺点。它还指出了检测系统如何容易受到对抗性攻击，并将现代方法与传统的取证和启发式方法进行了比较。本文批判性地分析了现有模型的优势和局限性，强调了检测系统对对抗性攻击的敏感性，并将现代方法与传统的取证和基于启发式的方法进行了对比。除了技术见解之外，该评论还将重点放在实际问题上，例如可扩展性，监管框架以及深度伪造技术的更广泛的社会影响。通过包括基准数据集、标准工具、性能评估指标和相关政策讨论，该手稿对深度伪造生成和检测之间正在进行的军备竞赛提出了前瞻性的观点。研究报告最后强调，需要强有力、灵活和可理解的检测系统，并辅以有效的政策措施，以减少深度造假带来的日益增长的风险。

{"title":"Potential of artificial intelligence in deepfake media: From generation to detection mechanisms, state-of-the-art, and challenges","authors":"Shubham Sharma, Arvind Selwal","doi":"10.1016/j.cosrev.2025.100866","DOIUrl":"10.1016/j.cosrev.2025.100866","url":null,"abstract":"<div><div>Artificial intelligence (AI) plays an important role in the generation of deepfakes by leveraging advanced machine learning models to create hyper-realistic synthetic media across visual, audio, and multimodal formats. The rapid evolution of deepfake technologies, alongside the exponential growth of digital media, demands a comprehensive and critical examination of current capabilities and challenges. Although the concept of media manipulation is not new, the sophistication and accessibility of AI-driven deepfakes present significant threats of misinformation to society and hence cause societal manipulation. This manuscript presents a systematic review of deepfake generation and detection techniques from 2017 to 2025, highlighting the progression of generative models and evaluating detection strategies. The main focus of this work is on the state-of-the-art (SOTA) techniques using adversarial networks, vision transformers (ViTs), attention mechanisms, hybrid learning frameworks, and ensemble models. The study thoroughly examines the benefits and drawbacks of existing methods. It also points out how vulnerable detection systems are to adversarial attacks and compares modern methods with traditional forensic and heuristic approaches. The paper critically analyzes the strengths and limitations of existing models, underscores the susceptibility of detection systems to adversarial attacks, and contrasts contemporary approaches with traditional forensic and heuristic-based methods. In addition to technical insights, the review puts a major focus on practical concerns such as scalability, regulatory frameworks, and the broader societal impact of the deepfake technology. By including benchmark datasets, standard tools, performance evaluation metrics, and relevant policy discussions, the manuscript presents a forward-looking perspective on the ongoing arms race between deepfake generation and detection. The study ends by highlighting the need for strong, flexible, and understandable detection systems, backed by effective policy measures, to reduce the growing risks posed by deepfakes.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100866"},"PeriodicalIF":12.7,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689751","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}

引用次数: 0

AIoT for human emotion recognition: Potentials, challenges, and healthcare applications 用于人类情感识别的AIoT：潜力、挑战和医疗保健应用

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-11-28 DOI: 10.1016/j.cosrev.2025.100859

Shumayla Yaqoob , Farman Ullah , Najah AbuAli , Hafeez Anwar , Nasir Saeed , Mohammad Hayajneh

Emotions are critical human behavior and cognition drivers, influencing communication, decision-making, and well-being. Emotion recognition (ER) is the computational identification of emotional states, and it has therefore gained considerable attention across various fields, including human-computer interaction, mental health, and intelligent systems. This review article synthesizes recent advancements in ER enabled by the integration of the Internet of Things (IoT) and Artificial Intelligence (AI), collectively termed AIoT, with a specific focus on healthcare applications. We highlight IoT-based sensing technologies, including wearables, ambient sensors, and mobile devices, which enable continuous and non-intrusive monitoring of emotions through multimodal signals such as facial expressions, speech, EEG, ECG, and GSR. A comprehensive taxonomy is proposed that organizes sensing modalities, datasets, pre-processing methods, learning algorithms, and application domains. Both traditional machine learning methods (e.g., SVM, Random Forests) and modern deep learning approaches (e.g., CNNs, LSTMs, Transformers) are evaluated for their ability to effectively handle complex emotional data. The integration of AI and IoT is presented as essential for developing scalable, real-time, and context-sensitive emotion-aware systems for healthcare applications. We discuss key challenges such as data heterogeneity, privacy, interpretability, and limited labeled datasets along with future directions such as edge computing, federated learning, and explainable AI. This synthesis aims to guide the development of robust, personalized, AIoT-enabled emotion-aware healthcare systems.

情绪是人类行为和认知的关键驱动因素，影响着沟通、决策和幸福感。情绪识别（ER）是对情绪状态的计算识别，因此在人机交互、心理健康和智能系统等各个领域得到了相当大的关注。这篇综述文章综合了通过物联网（IoT）和人工智能（AI）（统称为AIoT）的集成实现ER的最新进展，并特别关注医疗保健应用。我们重点介绍了基于物联网的传感技术，包括可穿戴设备、环境传感器和移动设备，这些技术可以通过面部表情、语音、脑电图、心电图和GSR等多模态信号对情绪进行持续和非侵入性监测。提出了一个综合的分类，组织传感模式，数据集，预处理方法，学习算法和应用领域。传统的机器学习方法（例如，SVM，随机森林）和现代深度学习方法（例如，cnn, lstm, Transformers）都被评估为有效处理复杂情感数据的能力。人工智能和物联网的集成对于开发用于医疗保健应用的可扩展、实时和上下文敏感的情绪感知系统至关重要。我们讨论了数据异构、隐私、可解释性和有限标记数据集等关键挑战，以及边缘计算、联邦学习和可解释人工智能等未来方向。这种综合旨在指导健壮的、个性化的、支持aiiot的情绪感知医疗保健系统的发展。

{"title":"AIoT for human emotion recognition: Potentials, challenges, and healthcare applications","authors":"Shumayla Yaqoob , Farman Ullah , Najah AbuAli , Hafeez Anwar , Nasir Saeed , Mohammad Hayajneh","doi":"10.1016/j.cosrev.2025.100859","DOIUrl":"10.1016/j.cosrev.2025.100859","url":null,"abstract":"<div><div>Emotions are critical human behavior and cognition drivers, influencing communication, decision-making, and well-being. Emotion recognition (ER) is the computational identification of emotional states, and it has therefore gained considerable attention across various fields, including human-computer interaction, mental health, and intelligent systems. This review article synthesizes recent advancements in ER enabled by the integration of the Internet of Things (IoT) and Artificial Intelligence (AI), collectively termed AIoT, with a specific focus on healthcare applications. We highlight IoT-based sensing technologies, including wearables, ambient sensors, and mobile devices, which enable continuous and non-intrusive monitoring of emotions through multimodal signals such as facial expressions, speech, EEG, ECG, and GSR. A comprehensive taxonomy is proposed that organizes sensing modalities, datasets, pre-processing methods, learning algorithms, and application domains. Both traditional machine learning methods (e.g., SVM, Random Forests) and modern deep learning approaches (e.g., CNNs, LSTMs, Transformers) are evaluated for their ability to effectively handle complex emotional data. The integration of AI and IoT is presented as essential for developing scalable, real-time, and context-sensitive emotion-aware systems for healthcare applications. We discuss key challenges such as data heterogeneity, privacy, interpretability, and limited labeled datasets along with future directions such as edge computing, federated learning, and explainable AI. This synthesis aims to guide the development of robust, personalized, AIoT-enabled emotion-aware healthcare systems.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100859"},"PeriodicalIF":12.7,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145613574","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}

引用次数: 0

Exploring transparency in pathological image analysis: A comprehensive review of explainable artificial intelligence (XAI) techniques 探索病理图像分析中的透明性：可解释人工智能（XAI）技术的全面回顾

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-11-27 DOI: 10.1016/j.cosrev.2025.100863

Lingling Yuan , Yutong Gu , Yan Han , Tianming Du , Marcin Grzegorzek , Chen Li

Pathological image analysis is a key component of digital pathology. The integration of artificial intelligence (AI) has substantially enhanced diagnostic efficiency. However, these models often lack transparency, and their black-box nature limits clinical trust and broader adoption. Although existing reviews have explored the application of explainable AI (XAI) in pathology, most use incomplete or inconsistent taxonomies and lack evaluation frameworks that consider multiple dimensions. The lack of a clear taxonomy and evaluation framework makes it difficult to compare results, identify suitable approaches, and assess the strengths and limitations of XAI methods from multiple perspectives. To address these gaps, this review presents a taxonomy from five perspectives and introduces the PathXAI-2 L minimal evaluation framework. Specifically, it provides a comprehensive overview of key tasks in pathological image analysis, commonly used datasets and their biases, and preprocessing strategies, algorithmic frameworks, and evaluation metrics. Based on this foundation, it proposes a five-dimensional taxonomy of XAI methods, organized by model dependency, explanation scope, explanation stage, explanatory modality, and evidential strength. The evidence perspective is used to distinguish between correlation and causality, by grouping explanations into association, sensitivity, and intervention levels. This review further examines two important factors influencing explainability results: the sensitivity of XAI methods to dataset choice, and the role of external resources in supporting explanations. At the technical level, this review groups XAI methods into seven representative types and introduces XAI tools in pathology. Finally, it proposes a minimal evaluation framework called PathXAI-2 L, focused on the functional and human layers, while highlighting key challenges and future directions for application-grounded evaluation. By integrating tasks, datasets, methods, and evaluation strategies, this review provides a comprehensive reference for advancing both technical progress and clinical impact in pathology XAI.

病理图像分析是数字病理学的关键组成部分。人工智能（AI）的融合大大提高了诊断效率。然而，这些模型往往缺乏透明度，而且它们的黑箱性质限制了临床信任和更广泛的采用。虽然现有的综述已经探讨了可解释人工智能（XAI）在病理学中的应用，但大多数使用不完整或不一致的分类，缺乏考虑多个维度的评估框架。由于缺乏清晰的分类法和评估框架，因此很难从多个角度比较结果、确定合适的方法以及评估XAI方法的优势和局限性。为了解决这些差距，本文从五个方面介绍了一种分类方法，并介绍了PathXAI-2 L最小评估框架。具体来说，它提供了病理图像分析的关键任务的全面概述，常用的数据集及其偏差，预处理策略，算法框架和评估指标。在此基础上，提出了基于模型依赖性、解释范围、解释阶段、解释形态和证据强度的XAI方法五维分类。证据视角通过将解释分为关联、敏感性和干预水平来区分相关性和因果关系。本文进一步探讨了影响可解释性结果的两个重要因素：XAI方法对数据集选择的敏感性，以及外部资源在支持解释方面的作用。在技术层面，本文将XAI方法分为7种代表性类型，并介绍了病理学中的XAI工具。最后，提出了一个名为PathXAI-2 L的最小评估框架，重点关注功能和人的层面，同时强调了基于应用的评估的关键挑战和未来方向。通过整合任务、数据集、方法和评估策略，本综述为推进病理XAI的技术进步和临床影响提供了全面的参考。

{"title":"Exploring transparency in pathological image analysis: A comprehensive review of explainable artificial intelligence (XAI) techniques","authors":"Lingling Yuan , Yutong Gu , Yan Han , Tianming Du , Marcin Grzegorzek , Chen Li","doi":"10.1016/j.cosrev.2025.100863","DOIUrl":"10.1016/j.cosrev.2025.100863","url":null,"abstract":"<div><div>Pathological image analysis is a key component of digital pathology. The integration of artificial intelligence (AI) has substantially enhanced diagnostic efficiency. However, these models often lack transparency, and their black-box nature limits clinical trust and broader adoption. Although existing reviews have explored the application of explainable AI (XAI) in pathology, most use incomplete or inconsistent taxonomies and lack evaluation frameworks that consider multiple dimensions. The lack of a clear taxonomy and evaluation framework makes it difficult to compare results, identify suitable approaches, and assess the strengths and limitations of XAI methods from multiple perspectives. To address these gaps, this review presents a taxonomy from five perspectives and introduces the PathXAI-2 L minimal evaluation framework. Specifically, it provides a comprehensive overview of key tasks in pathological image analysis, commonly used datasets and their biases, and preprocessing strategies, algorithmic frameworks, and evaluation metrics. Based on this foundation, it proposes a five-dimensional taxonomy of XAI methods, organized by model dependency, explanation scope, explanation stage, explanatory modality, and evidential strength. The evidence perspective is used to distinguish between correlation and causality, by grouping explanations into association, sensitivity, and intervention levels. This review further examines two important factors influencing explainability results: the sensitivity of XAI methods to dataset choice, and the role of external resources in supporting explanations. At the technical level, this review groups XAI methods into seven representative types and introduces XAI tools in pathology. Finally, it proposes a minimal evaluation framework called PathXAI-2 L, focused on the functional and human layers, while highlighting key challenges and future directions for application-grounded evaluation. By integrating tasks, datasets, methods, and evaluation strategies, this review provides a comprehensive reference for advancing both technical progress and clinical impact in pathology XAI.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"60 ","pages":"Article 100863"},"PeriodicalIF":12.7,"publicationDate":"2025-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145610126","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}

引用次数: 0

Advanced work packaging in construction management through systematic review and socio-technical framework for digital integration 通过系统审查和数字集成的社会技术框架，在施工管理中进行先进的工作包装

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-11-27 DOI: 10.1016/j.cosrev.2025.100856

Hamza Aamir , Wesam Salah Alaloul , Abdul Mateen Khan , Muhammad Ali Musarat

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.

高级工作包（AWP）作为一种结构化的方法，在建设项目中提高效率、生产力和协调性，已经获得了越来越多的关注。然而，目前的研究仍然是分段的，往往是描述性的，数字技术在建设项目中的整合有限。因此，本研究进行系统回顾，统一现有文献，批判性地评估AWP在推进建筑自动化方面的作用。通过这种方式，我们初步筛选了5个主要数据库共719篇出版物，从中选择了57篇发表于2013年至2024年间的高度相关的研究进行深入分析。文献计量制图和关键词共现分析用于确定研究趋势、专题集群和知识差距，而批判性综合强调概念重叠和方法缺陷。研究结果表明，虽然AWP框架已被广泛讨论，但大多数研究优先考虑成本和进度分析，而对建筑信息模型（BIM）、人工智能（AI）和机器学习应用的关注有限。为了解决这一差距，提出了一种新的社会技术概念框架，该框架围绕先决条件、中间过程、输出和反馈构建，并明确嵌入支持人工智能的预测分析、基于bim的模型验证和自动监控系统。该框架通过强调验证策略、自适应反馈循环以及组织和技术维度的集成，超越了描述性模型。该研究承认与潜在的选择偏差、数据库限制和定性主观性相关的局限性，但也为研究、行业实践和政策提供了可操作的启示。其贡献在于将AWP从描述性规划工具推进到用于建设项目交付的数字集成和全球适应性方法。

{"title":"Advanced work packaging in construction management through systematic review and socio-technical framework for digital integration","authors":"Hamza Aamir , Wesam Salah Alaloul , Abdul Mateen Khan , 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":"2025-11-27","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}

引用次数: 0

From mathematical to AI-based methods: A review of marine PNT data fusion and uncertainty handling 从数学到人工智能：海洋PNT数据融合与不确定性处理综述

IF 12.7 1区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Computer Science Review

Pub Date : 2025-11-27 DOI: 10.1016/j.cosrev.2025.100864

Natalia Ziółkowska, Joanna Szłapczyńska

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.

准确可靠的定位、导航和授时（PNT）系统的发展越来越依赖于计算机科学的进步，特别是数据融合和不确定性处理。海上导航的科学研究主要集中在轨迹预测、路线规划和避碰等领域，而所有这些主题都高度依赖于所提供数据的准确性和鲁棒性。然而，定位和不确定性处理方法仍然面临局限性，包括测量缺失或不准确，欺骗和干扰攻击的威胁增加，以及对动态海上条件的有限适应性。以前的评论没有系统地解决定位精度、数据融合和不确定性处理，也没有始终如一地应用透明的方法，在可重复性和覆盖范围上留下空白。本文通过介绍从传统数学方法到基于人工智能的解决方案的结构化综合技术来解决这些差距，以提高海上导航的准确性和可靠性。遵循系统评价和荟萃分析（PRISMA）指南的首选报告项目，以确保方法的透明度。这篇综述有几个独特的贡献。它提供了基于prisma的船舶定位和不确定性处理方法的系统概述，并尝试解决关键研究问题，包括现有的解决方案、挑战和新出现的机会。此外，深入讨论了人工智能增强导航系统的潜力，并提出了解决当前局限性的未来研究方向。这些贡献共同为提高海上航行的可靠性、弹性和安全性提供了路线图。

{"title":"From mathematical to AI-based methods: A review of marine PNT data fusion and uncertainty handling","authors":"Natalia Ziółkowska, 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":"2025-11-27","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}

引用次数: 0