Computer Science Review最新文献

A systematic review of explainability in computational intelligence for optimization 优化计算智能中可解释性的系统综述

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-05-22 DOI: 10.1016/j.cosrev.2025.100764

José Almeida , João Soares , Fernando Lezama , Steffen Limmer , Tobias Rodemann , Zita Vale

{"title":"A systematic review of explainability in computational intelligence for optimization","authors":"José Almeida , João Soares , Fernando Lezama , Steffen Limmer , Tobias Rodemann , Zita Vale","doi":"10.1016/j.cosrev.2025.100764","DOIUrl":"10.1016/j.cosrev.2025.100764","url":null,"abstract":"<div><div>This systematic review explores the need for explainability in computational intelligence methods for optimization, such as metaheuristic optimizers, including evolutionary algorithms and swarm intelligence. The work focuses on four aspects: (1) the contribution of Explainable AI (XAI) methods to interpreting metaheuristic performance; (2) the influence of problem features on search behavior and explainability; (3) the role of mathematical theory in providing transparent explanations; and (4) the potential of metaheuristics to enhance the explainability of AI models, such as machine learning (ML). XAI methods such as SHAP, LIME, and visualization techniques provide valuable insights into metaheuristic performance, while landscape analysis and quality diversity approaches reveal algorithm performance across different problem landscapes. The review also explores how metaheuristic algorithms can enhance the interpretability of ML models, turning black-box models into more transparent systems. The work moves on to proposing ”Explainergy,” a novel concept for integrating explainability into metaheuristic algorithms within the energy domain, enhancing the transparency and usability of optimization models.</div><div>This review is a foundation for future research combining explainability with evolutionary computation and metaheuristic optimization to address real-world challenges in diverse fields, including energy systems.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100764"},"PeriodicalIF":13.3,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144105812","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

Abstractive text summarization: A comprehensive survey of techniques, systems, and challenges 抽象文本摘要：对技术、系统和挑战的全面调查

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-05-20 DOI: 10.1016/j.cosrev.2025.100762

Norah Almohaimeed, Aqil M. Azmi

{"title":"Abstractive text summarization: A comprehensive survey of techniques, systems, and challenges","authors":"Norah Almohaimeed, Aqil M. Azmi","doi":"10.1016/j.cosrev.2025.100762","DOIUrl":"10.1016/j.cosrev.2025.100762","url":null,"abstract":"<div><div>Abstractive text summarization addresses information overload by generating paraphrased content that mimics human expression, yet it faces significant computational and linguistic challenges. This paper presents a detailed functional taxonomy of abstractive summarization, structured along four dimensions: techniques (including structure-based, semantic, and deep learning approaches, including large language models), system architectures (ranging from single-model to multi-agent and human-in-the-loop interactive systems), evaluation methods (covering lexical, semantic, and human-centered assessments), and datasets. Our taxonomy explicitly distinguishes techniques from architectures to clarify how methodological strategies are operationalized in practice. We examine pressing multilingual challenges such as linguistic complexity, data scarcity, and performance disparities in cross-lingual transfer, particularly for low-resource languages. Additionally, we address persistent issues such as factual inaccuracies, content hallucinations, and biases in widely used evaluation metrics. The paper highlights emerging trends—including cross-lingual summarization, interactive summarization systems, and ethically grounded frameworks—as key directions for future research. This synthesis not only maps the current landscape but also outlines pathways to enhance the accuracy, reliability, and applicability of abstractive summarization in real-world settings.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100762"},"PeriodicalIF":13.3,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144098344","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 quantum image processing: Representation, applications and future perspectives 量子图像处理的系统综述：表征、应用和未来展望

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-05-06 DOI: 10.1016/j.cosrev.2025.100763

Umar Farooq , Parvinder Singh , Atul Kumar

{"title":"A systematic review of quantum image processing: Representation, applications and future perspectives","authors":"Umar Farooq , Parvinder Singh , Atul Kumar","doi":"10.1016/j.cosrev.2025.100763","DOIUrl":"10.1016/j.cosrev.2025.100763","url":null,"abstract":"<div><div>Quantum image processing uses quantum hardware to revolutionize the storage, recovery, processing, and security of quantum images across diverse applications. Although researchers have explored various facets of quantum image processing, a comprehensive systematic literature review encompassing all domains is essential for theoretical and experimental progress. This article aims to bridge this gap by systematically analyzing advancements in this field, drawing insights from a thorough review of 135 research articles published beyond 2003. Our study examines core components of quantum image processing, such as quantum image representations, advanced algorithms, transformative techniques like Quantum Fourier and Wavelet Transforms, and robust security measures. It further explores the synergy between quantum machine learning and image processing for improved classification and recognition. In addition, the study also discusses the limitations of existing research, summarizes its essential aspects, highlights gaps and challenges, and finally, provides recommendations for future research and innovations.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100763"},"PeriodicalIF":13.3,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906539","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 comprehensive review of few-shot object detection on aerial imagery 航空图像上的小镜头目标检测技术综述

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-05-02 DOI: 10.1016/j.cosrev.2025.100760

Khang Nguyen , Nhat-Thanh Huynh , Duc-Thanh Le , Dien-Thuc Huynh , Thi-Thanh-Trang Bui , Truong Dinh , Khanh-Duy Nguyen , Tam V. Nguyen

{"title":"A comprehensive review of few-shot object detection on aerial imagery","authors":"Khang Nguyen , Nhat-Thanh Huynh , Duc-Thanh Le , Dien-Thuc Huynh , Thi-Thanh-Trang Bui , Truong Dinh , Khanh-Duy Nguyen , Tam V. Nguyen","doi":"10.1016/j.cosrev.2025.100760","DOIUrl":"10.1016/j.cosrev.2025.100760","url":null,"abstract":"<div><div>With the development of technology, drones, and satellites play an important role in human life. Related research problems receive great attention, especially in the computer vision community. Notably, the object detection models on aerial imagery take part in many applications in both civil and military domains. Although it has great potential and has achieved many achievements, it cannot be denied that object detection faces many challenges such as the small size and the quality of training datasets. The few-shot paradigm was explored to tackle that challenge. In this paper, we intensively investigate 55 state-of-the-art few-shot object detection methods using many different learning styles such as meta-learning and transfer learning. Moreover, we analyzed 12 aerial imagery datasets and benchmarked state-of-the-art methods on three popular datasets, namely, DIOR, NWPU VHR-10, and DOTA. These datasets reflect the richness of classes and the complexity of real-world conditions. From the experimental results and analysis, we discuss insights and pave the way to the future outlook of this research.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100760"},"PeriodicalIF":13.3,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143899493","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

The Beauty and the Beast: A survey on process algebras and cybersecurity 美女与野兽：过程代数与网络安全的调查

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-04-23 DOI: 10.1016/j.cosrev.2025.100758

Gabriele Costa, Silvia De Francisci, Rocco De Nicola

{"title":"The Beauty and the Beast: A survey on process algebras and cybersecurity","authors":"Gabriele Costa, Silvia De Francisci, Rocco De Nicola","doi":"10.1016/j.cosrev.2025.100758","DOIUrl":"10.1016/j.cosrev.2025.100758","url":null,"abstract":"<div><div>Process algebras (PAs) provide the mathematical foundation for several verification techniques and have profoundly influenced many areas of computer science. One of the main reasons for their success is their compact yet expressive and flexible syntax, which allows for the modeling of the relevant aspects of computation while abstracting away the irrelevant ones. Cybersecurity is no exception, and most authors acknowledge the importance of PAs in this field. However, estimating the impact of PAs is not trivial.</div><div>In this survey, we consider lines of research that employ PAs to address security problems. Our systematization of knowledge aims to assess and measure the impact of PAs. To achieve this goal, we start by briefly reviewing the evolution of PAs. Then, we analyze the literature by mapping each contribution to three cybersecurity sub-fields: <em>secure development</em>, <em>attack modeling</em>, and <em>vulnerability assessment</em>. Our methodology follows the chronological development of process algebras and identifies the emerging features specifically introduced for dealing with security problems. Although our analysis confirms that PAs have been greatly influential in general, it provides a fine-grained understanding of how PAs have shaped research in cybersecurity. Interestingly, our work highlights that some application areas remain underexplored, thus providing the research community with valuable insights on future directions.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100758"},"PeriodicalIF":13.3,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864756","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 survey on aspect sentiment triplet extraction methods and challenges 面向情感三元提取方法及挑战综述

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-04-23 DOI: 10.1016/j.cosrev.2025.100761

Wang Zou , Xia Sun , Xiaodi Zhao , Jun Feng , Yunfei Long , Yaqiong Xing

{"title":"A survey on aspect sentiment triplet extraction methods and challenges","authors":"Wang Zou , Xia Sun , Xiaodi Zhao , Jun Feng , Yunfei Long , Yaqiong Xing","doi":"10.1016/j.cosrev.2025.100761","DOIUrl":"10.1016/j.cosrev.2025.100761","url":null,"abstract":"<div><div>Aspect-based sentiment analysis (ABSA) has gradually become an important technique for mining online reviews and is widely popular across various domains, such as producer–consumer, pharmaceutical reviews, political campaigns, and celebrity popularity. Aspect sentiment triplet extraction (ASTE) is a core technique within the ABSA, as it automatically extracts aspect terms, opinion terms, and sentiment polarity triplets from textual data. Since the ASTE task is a relatively recent research direction, there is still a lack of comprehensive summaries and syntheses of the research in this task. To address this issue, this paper provides a comprehensive introduction to various methods, performance evaluations, challenges, and future research directions for the ASTE task. Specifically, we categorize the current ASTE approaches into six types: Pipeline, End-to-end, Generative, MRC-based, Table-filling, and Span-based methods. Subsequently, we provide a detailed introduction to the characteristics of each method, along with their strengths and weaknesses. Additionally, we organize the performance of these methods on two benchmark datasets, ASTE-Data-v1 and ASTE-Data-v2. Finally, we discuss the challenges faced in current work and potential future directions.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100761"},"PeriodicalIF":13.3,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143859282","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

Bridging the gap: A survey of document retrieval techniques for high-resource and low-resource languages 弥合差距：高资源语言和低资源语言的文档检索技术调查

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-04-16 DOI: 10.1016/j.cosrev.2025.100756

Samreen Kazi , Shakeel Khoja , Ali Daud

引用次数: 0

A comprehensive survey with critical analysis for deepfake speech detection 对深度假语音检测的全面调查和批判性分析

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-04-16 DOI: 10.1016/j.cosrev.2025.100757

Lam Pham , Phat Lam , Dat Tran , Hieu Tang , Tin Nguyen , Alexander Schindler , Florian Skopik , Alexander Polonsky , Hai Canh Vu

{"title":"A comprehensive survey with critical analysis for deepfake speech detection","authors":"Lam Pham , Phat Lam , Dat Tran , Hieu Tang , Tin Nguyen , Alexander Schindler , Florian Skopik , Alexander Polonsky , Hai Canh Vu","doi":"10.1016/j.cosrev.2025.100757","DOIUrl":"10.1016/j.cosrev.2025.100757","url":null,"abstract":"<div><div>Thanks to advancements in deep learning, speech generation systems now power a variety of real-world applications, such as text-to-speech for individuals with speech disorders, voice chatbots in call centers, cross-linguistic speech translation, etc. While these systems can autonomously generate human-like speech and replicate specific voices, they also pose risks when misused for malicious purposes. This motivates the research community to develop models for detecting synthesized speech (e.g., fake speech) generated by deep-learning-based models, referred to as the Deepfake Speech Detection task. As the Deepfake Speech Detection task has emerged in recent years, there are not many survey papers proposed for this task. Additionally, existing surveys for the Deepfake Speech Detection task tend to summarize techniques used to construct a Deepfake Speech Detection system rather than providing a thorough analysis. This gap motivated us to conduct a comprehensive survey, providing a critical analysis of the challenges and developments in Deepfake Speech Detection (This work is a part of our projects of STARLIGHT, EUCINF, and DEFAME FAKEs). Our survey is innovatively structured, offering an in-depth analysis of current challenge competitions, public datasets, and the deep-learning techniques that provide enhanced solutions to address existing challenges in the field. From our analysis, we propose hypotheses on leveraging and combining specific deep learning techniques to improve the effectiveness of Deepfake Speech Detection systems. Beyond conducting a survey, we perform extensive experiments to validate these hypotheses and propose a highly competitive model for the task of Deepfake Speech Detection. Given the analysis and the experimental results, we finally indicate potential and promising research directions for the Deepfake Speech Detection task.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100757"},"PeriodicalIF":13.3,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838005","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

Advancements in image encryption: A comprehensive review of design principles and performance metrics 图像加密的进展：对设计原则和性能指标的全面回顾

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-04-11 DOI: 10.1016/j.cosrev.2025.100759

Biswarup Yogi , Ajoy Kumar Khan

{"title":"Advancements in image encryption: A comprehensive review of design principles and performance metrics","authors":"Biswarup Yogi , Ajoy Kumar Khan","doi":"10.1016/j.cosrev.2025.100759","DOIUrl":"10.1016/j.cosrev.2025.100759","url":null,"abstract":"<div><div>With the rise of digital image sharing in fields like healthcare, defence, and multimedia, strong image encryption is needed to protect sensitive information. This study provides a detailed overview of the analysis of image encryption algorithms, focusing on their design principles and performance metrics. This study covers different encryption methods, from traditional symmetric and asymmetric to modern chaos-based and quantum encryption. The design principles include substitution-permutation, diffusion, and key generation strategies. They are carefully evaluated to understand their actual input towards achieving high security. This study discusses key performance metrics such as encryption speed, sensitivity to key changes, statistical and differential attacks, computational complexity, and efficiency required to analyze the feasibility of various algorithms in practical applications. Explores issues such as the balance between security and resource limits, scalability, and adaptability to new threats. The analysis highlights the strengths and weaknesses of existing techniques, providing useful insights for developing next-generation encryption methods for specific applications. The combination of theoretical concepts along with performance evaluations presented in this work thus provides a significant and valuable reference source for research and practice aimed at designing effective yet secure image encryption algorithms in this rapidly growing world of technology.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100759"},"PeriodicalIF":13.3,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143815567","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 survey on quantum-safe blockchain security infrastructure 量子安全区块链安全基础设施研究

IF 13.3 1区计算机科学

Computer Science Review Pub Date : 2025-04-10 DOI: 10.1016/j.cosrev.2025.100752

Arya Wicaksana

{"title":"A survey on quantum-safe blockchain security infrastructure","authors":"Arya Wicaksana","doi":"10.1016/j.cosrev.2025.100752","DOIUrl":"10.1016/j.cosrev.2025.100752","url":null,"abstract":"<div><div>Security infrastructure is vital in blockchain for its decentralized and distributed characteristics. Blockchain security infrastructure comprises several components: cryptographic algorithms, consensus protocols, key and identity management, network architecture, and smart contract deployment and execution. These components are vulnerable to the advancement of quantum computing and the realization of more powerful quantum computers. Classical security countermeasures used across the entire blockchain security infrastructure are exposed to quantum computing attacks. The exploitation is catastrophic to the sustainability of blockchain research and applications. This paper outlines the blockchain security infrastructure and quantum-safe solutions. The promising quantum-resistant cryptographic algorithms released by the National Institute of Standards and Technology (NIST) are evaluated for their relevance and use in blockchain security infrastructure. This paper also discusses the practical implementation and adoption of quantum-safe solutions for blockchain security infrastructure, including recent developments on the quantum-safe blockchain. The holy grail in adopting quantum-safe solutions for blockchain security infrastructure solutions is without sacrificing scalability and decentralization.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"57 ","pages":"Article 100752"},"PeriodicalIF":13.3,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143807674","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