Expert Systems最新文献

{"title":"Optimizing Context and Cost in LLM-Based Unit Test Generation: A Study on External Dependency Retrieval Strategies","authors":"Javier Ferrer,&nbsp;Francisco Chicano","doi":"10.1111/exsy.70401","DOIUrl":"https://doi.org/10.1111/exsy.70401","url":null,"abstract":"<p>While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, their effectiveness in unit testing is often constrained by insufficient context regarding external dependencies. This limitation is particularly pronounced in industrial settings, where proprietary code remains opaque to the model. To address this challenge, we present a systematic empirical study of multiple strategies for context enrichment and optimization in LLM-based unit test generation, conducted on seven diverse projects (three open-source and four proprietary industrial systems), encompassing 261 distinct methods. By evaluating seven implementations (ranging from basic prompts to optimized context reduction strategies) across 10 independent runs, we analysed a total of 28,710 test suites. Our results demonstrate that combining prompt engineering with external dependency retrieval achieves an average branch coverage increase of 11.52 percentage points on industrial software over the baseline, with statistically significant improvements across all competing implementations. Beyond coverage, richer context substantially reduces generation-repair iterations, cutting median execution time by 51.3% in industrial projects. We further show that reducing external dependencies to method signatures alone decreases input token consumption by up to 46.6% (25.4% in industrial projects) while fully preserving the coverage and efficiency gains of the complete retrieval approach. To confirm that these benefits are not tied to a specific model, we replicate the core comparison across three LLM backends from different families, obtaining a consistent, statistically significant coverage improvement on industrial code in every case. These findings establish this optimized context strategy as a cost-effective solution for scalable, industrial-grade automated test generation.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70401","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BiFCL: A Bi-Level Federated Contrastive Learning Framework With Auxiliary Model-Guided Alignment","authors":"Shiqiang Zhang,&nbsp;Yang Cao,&nbsp;Yongli Yang","doi":"10.1111/exsy.70407","DOIUrl":"https://doi.org/10.1111/exsy.70407","url":null,"abstract":"<div>\u0000 \u0000 <p>Federated learning (FL) enables collaborative model training over distributed clients without sharing raw data, but its performance can degrade severely under non-independent and non - identically distributed (non-IID) client data. To address this challenge, we propose <b>BiFCL</b>, a <i>Bi-Level Federated Contrastive Learning</i> framework that improves global representation alignment through a lightweight server-side auxiliary model trained on a small public dataset. BiFCL enforces bidirectional semantic consistency: on the client side, each local model is regularized by contrastively aligning its representations to the auxiliary model; on the server side, the auxiliary model is further updated via contrastive alignment with the evolving global model, preventing stale guidance and forming a closed-loop regularization mechanism. We provide convergence guarantees for BiFCL under standard smooth non-convex assumptions. Extensive experiments on five benchmarks (MNIST, EMNIST, SVHN, CIFAR-10 and CIFAR-100) demonstrate that BiFCL consistently outperforms strong FL baselines in both final accuracy and convergence speed. Overall, BiFCL provides an effective representation-alignment strategy for heterogeneous federated learning when a small, diverse, and semantically relevant public, proxy or privacy-preserving synthetic auxiliary source is available. We also discuss practical auxiliary-data construction strategies, normalized communication cost and limitations under severe auxiliary-domain mismatch and larger-client deployments.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic Generation of Summaries From Informal Social Media Text Using Transformers","authors":"Afrodite Papagiannopoulou,&nbsp;Chrissanthi Angeli","doi":"10.1111/exsy.70399","DOIUrl":"https://doi.org/10.1111/exsy.70399","url":null,"abstract":"<div>\u0000 \u0000 <p>The exponential growth of social media has reshaped global communication and decision-making in business, politics and economics. Yet, the sheer volume and informal, unstructured nature of user-generated content present major challenges for meaningful analysis. This study introduces a novel abstractive summarisation framework designed to distill coherent and semantically rich summaries from social media discussions. Built on the T5 transformer architecture and enhanced through targeted transfer learning, the system effectively captures the fragmented, slang-rich language patterns common across platforms. Evaluation is conducted using a suite of semantic-aware metrics—including ROUGE-WE, SUPERT and Shannon entropy—alongside human-centric criteria such as coherence, fluency, consistency and lexical diversity. Results show that the proposed model consistently outperforms mainstream summarisation methods, including advanced systems like ChatGPT, particularly in preserving semantic alignment and improving readability under noisy conditions. Comparative analysis underscores the framework's robustness in handling unstructured, domain-specific discourse. These findings position the model as a valuable tool for real-time, high-volume social media analytics. Future work will explore hybrid neural quality assessment and interactive feedback mechanisms to further enhance domain adaptability and summary fluency.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Intuitionistic Fuzzy Set for Decision-Making","authors":"Yangyang Zhao,&nbsp;Fuyuan Xiao","doi":"10.1111/exsy.70375","DOIUrl":"https://doi.org/10.1111/exsy.70375","url":null,"abstract":"<div>\u0000 \u0000 <p>Intuitionistic fuzzy sets have been extensively employed to manage uncertainty in expert systems and decision-making domains. Recently, to address more sophisticated real-world problems involving multidimensional uncertainty, several theoretical frameworks have been extended into the complex domain. However, existing complex intuitionistic fuzzy sets (CIFSs) model the magnitude and phase as independent components, reducing them to isolated dimensions rather than a unified entity. This separation disrupts the coupled magnitude-phase relationship, limiting the model's ability to capture the unique interference phenomena and rich uncertainty characterizations. Therefore, we propose a novel CIFS framework grounded in the intrinsic algebraic structure of complex numbers. The proposed framework integrates magnitude and phase into a unified representation, ensuring consistency with the fundamental rules of complex arithmetic. To support this framework, we define several fundamental CIFS operations directly based on complex arithmetic. Furthermore, to address conflicting evaluations from diverse sources, we introduce a new aggregation operator capable of integrating multiple CIFSs while mitigating conflicts in expert decision-making and develop a corresponding intelligent decision-making algorithm. The effectiveness and robustness of the proposed algorithm are validated through medical diagnosis and software selection, demonstrating its practical utility in expert systems.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Self-Supervised Framework for Space Object Behaviour Characterisation","authors":"Ian Groves,&nbsp;Andrew Campbell,&nbsp;James Fernandes,&nbsp;Diego Ramírez Rodríguez,&nbsp;Paul Murray,&nbsp;Massimiliano Vasile,&nbsp;Victoria Nockles","doi":"10.1111/exsy.70382","DOIUrl":"https://doi.org/10.1111/exsy.70382","url":null,"abstract":"<p>Foundation Models, which leverage large neural networks pre-trained on unlabelled data before fine-tuning for specific tasks, are increasingly being applied to specialised domains. Recent examples include ClimaX for climate and Clay for satellite Earth observation, but a Foundation Model for Space Object Behavioural Analysis (SOBA) has not yet been developed. As orbital populations grow, automated methods for characterising space object behaviour are crucial for space safety. Here, we present a self-supervised framework for SOBA, representing a first step towards a Foundation Model for Space Object Behavioural Analysis. The backbone of this framework is a Perceiver-Variational Autoencoder (VAE) architecture, pre-trained with self-supervised reconstruction and masked reconstruction on ~227,000 light curves from the MMT-9 observatory. The VAE enables anomaly detection, space object motion prediction and generation of synthetic light curves. We fine-tuned the model for anomaly detection and motion prediction using two independent light curve simulators (CASSANDRA and GRIAL respectively), using CAD models of boxwing, Sentinel-3, SMOS and Starlink platforms. Our pre-trained model achieved a reconstruction mean squared error of 0.0012, identifying potentially anomalous light curves through reconstruction difficulty. After fine-tuning, the model scored 85% accuracy (0.92 ROC AUC) on anomaly detection and 82% accuracy (0.95 ROC AUC) on motion mode prediction (e.g., sun-pointing, spin and tumbling). Analysis of high-confidence anomaly predictions on real data revealed distinct patterns including characteristic object profiles and satellite glinting. The motion prediction model successfully differentiated between various movement behaviours such as sun-pointing, spin and tumbling. Our work demonstrates how self-supervised learning can simultaneously enable anomaly detection, motion prediction and synthetic data generation from rich representations learned in pre-training. More broadly, our work supports space safety and sustainability through automated monitoring and simulation capabilities.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70382","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic Literature Review of Deep Learning Techniques for Lung Cancer Segmentation","authors":"Muhammad Sufyan,&nbsp;Jun Qian,&nbsp;Jianqiang Li,&nbsp;Azhar Imran,&nbsp;Fahad Sabah","doi":"10.1111/exsy.70391","DOIUrl":"https://doi.org/10.1111/exsy.70391","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate lung nodule segmentation is essential for early lung cancer diagnosis and treatment planning. Although deep learning (DL) has significantly advanced automated segmentation, existing review studies often lack an integrated technical–clinical perspective and provide limited guidance for real-world deployment. In this study, we conduct a systematic literature review following PRISMA 2020 guidelines, analysing 311 publications and synthesizing 113 high-quality studies published between 2019 and 2026. This review makes three key contributions. First, we provide a structured comparison of major DL architectures, including convolutional neural networks (CNNs), transformers, generative adversarial networks (GANs) and graph neural networks (GNNs), with respect to segmentation performance and computational efficiency. Second, we identify critical barriers to clinical adoption, such as data heterogeneity, annotation scarcity, high computational cost and limited model interpretability. Third, we analyse efficiency metrics (parameters, loss function and optimization) to categorize models suitable for point-of-care, resource-constrained and mobile clinical environments. Based on these findings, we propose a roadmap for future research focusing on lightweight architectures, edge–cloud integration, federated learning and explainable AI (XAI). This study provides a clear and actionable framework to bridge the gap between DL-based segmentation research and clinical deployment.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Are Agents Listening to Each Other? Measuring What Drives Agent Actions in LLM-Based Multi-Agent Systems","authors":"Zihan Zhao,&nbsp;Yuwei Guo,&nbsp;Xiaowei Liu,&nbsp;Qun Ma,&nbsp;Hui Yu,&nbsp;Xiao Xue","doi":"10.1111/exsy.70392","DOIUrl":"https://doi.org/10.1111/exsy.70392","url":null,"abstract":"<div>\u0000 \u0000 <p>In LLM-based multi-agent simulations, message delivery does not establish that a recipient's next action depends on the message. We propose a black-box framework for per-message counterfactual attribution at multi-agent decision points (DPs). It combines pragmatic-targeted propositional perturbations, <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>FS</mi>\u0000 <mrow>\u0000 <mi>KL</mi>\u0000 <mo>-</mo>\u0000 <mtext>excess</mtext>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {mathrm{FS}}_{mathrm{KL}hbox{-} mathrm{excess}} $$</annotation>\u0000 </semantics></math>—the original-to-perturbed action distribution KL after subtraction of a same-input sampling-noise floor—and a per-DP attribution vector classified as <span>single-driver</span>, <span>mixed-driver</span> or <span>no-driver</span>. We instantiate the framework across two environments, four agent architectures and two base models. The primary analysis covers <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>793</mn>\u0000 </mrow>\u0000 <annotation>$$ 793 $$</annotation>\u0000 </semantics></math> complete operator-specific DP-conditions from <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>426</mn>\u0000 </mrow>\u0000 <annotation>$$ 426 $$</annotation>\u0000 </semantics></math> retained unique DPs. Under the original per-message reporting boundary, <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>38.7</mn>\u0000 <mo>%</mo>\u0000 </mrow>\u0000 <annotation>$$ 38.7% $$</annotation>\u0000 </semantics></math> of complete conditions are labelled <span>no-driver</span>; bundle-size-aware maximum-score calibration using held-out identity cells raises this share to <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>75.3</mn>\u0000 <mo>%</mo>\u0000 </mrow>\u0000 <annotation>$$ 75.3% $$</annotation>\u0000 </semantics></math>, indicating that the reported regime distribution is sensitive to boundary calibration. The estimand is local and one-step: it measures prompt-level next-action sensitivity at a realised DP rather than longer-horizon social influence. Code, configuration, and the archived analysis package are available in the revision3-review-v1 GitHub Release.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive Quantum-Inspired Optimisation of Neural Networks for Imbalanced Student Performance Prediction","authors":"Hanjie Xu,&nbsp;Leilei Li,&nbsp;Lingjun Xiao,&nbsp;Jiyuan Chen,&nbsp;Jun Tang","doi":"10.1111/exsy.70405","DOIUrl":"https://doi.org/10.1111/exsy.70405","url":null,"abstract":"<div>\u0000 \u0000 <p>Student performance prediction (SPP) is a critical task in educational data mining (EDM) for facilitating proactive educational interventions. However, existing predictive models face specific challenges: the high pedagogical cost of misclassifying at-risk students (class imbalance), the difficulty of feature selection in high-dimensional noisy data, and the inherent variance of solitary stochastic optimisation. To address these limitations, this article proposes an Adaptive Quantum-Inspired Optimisation Framework (SRA-ANN-E). The framework integrates three optimisation mechanisms: (1) a Cost-Sensitive Quantum (CSQ-SRA) mechanism that reconstructs the search topology via penalty barriers to prioritise minority class identification; (2) an Adaptive Collapse (AC-SRA) mechanism utilizing a stagnation-driven monitor to regulate the exploration-exploitation trade-off; and (3) an elite population ensemble strategy to mitigate stochastic variance. Validation was conducted across four heterogeneous datasets (OULAD, UCI, PISA 2022 and PISA 2015), encompassing structured logs, psychological attributes, and unstructured natural language processing features. When benchmarked against 11 baseline algorithms, SRA-ANN-E outperformed existing hybrid meta-heuristics (e.g., TLBO-ANN) and demonstrated a statistically significant, albeit marginal, advantage over modern tree-based ensembles (e.g., XGBoost), achieving an 86.80% minority recall in dropout prediction. Furthermore, coupled with SHAP-based interpretability analysis, the framework identified compact feature subsets, translating numerical outputs into interpretable pedagogical indicators (e.g., mathematics anxiety) while maintaining online inference efficiency. These results indicate the framework's viability as a reliable and interpretable decision-support instrument for academic early warning systems.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning–Driven Visual Intelligence for Chemical Instrument Monitoring: A Scoping Review From an Expert Systems Perspective","authors":"Qirui Li,&nbsp;Haiyang Luo,&nbsp;Zhiping Peng,&nbsp;Delong Cui,&nbsp;Jieguang He,&nbsp;Xiangwu Deng","doi":"10.1111/exsy.70366","DOIUrl":"https://doi.org/10.1111/exsy.70366","url":null,"abstract":"<div>\u0000 \u0000 <p>Automated visual recognition in industrial environments has become a key enabler for intelligent monitoring systems, particularly in safety-critical domains such as chemical plants. Unlike general industrial vision tasks, chemical instrument monitoring operates under stringent constraints, including harsh environments, legacy non-digital devices, and high reliability requirements for decision-making. In this context, deep learning-based visual recognition should not be viewed as an isolated perception task, but rather as a critical component within expert systems that support operational decision-making. This paper presents a comprehensive scoping review of deep learning–driven visual intelligence for industrial applications, with a specific focus on chemical instrument monitoring from an expert systems perspective. A total of 127 studies published between 2015 and 2025 are systematically analysed, covering object detection, image segmentation, and optical character recognition (OCR), along with their integration into practical monitoring pipelines. Beyond categorizing models, this review emphasizes the evolution from standalone perception models toward system-level solutions that incorporate edge deployment, data-efficient learning, and explainability. Key challenges are identified, including data scarcity due to proprietary industrial datasets, limited model generalization across dynamic environments, computational constraints in real-time deployment, and the lack of interpretability required for safety-critical decision support. Importantly, this review highlights the gap between high-performing vision models and their reliable integration into expert systems for chemical operations. Emerging trends are discussed, including synthetic data generation, domain adaptation, foundation models (e.g., SAM and open-vocabulary detection), and multimodal fusion, with a critical evaluation of their applicability and limitations in chemical instrument scenarios. By reframing industrial visual recognition within the broader context of expert systems, this work provides a structured understanding of current capabilities and outlines future directions for developing trustworthy, efficient, and human-centric intelligent monitoring systems in chemical industries.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Comprehensive Review of Generative Adversarial Networks in Deep Learning: Emerging Applications and Hybrid Architectures","authors":"Kashif Iqbal,&nbsp;Xue Yu,&nbsp;Atifa Rafique,&nbsp;David Camacho,&nbsp;Muhammad Ilyas,&nbsp;Khursheed Aurangzeb","doi":"10.1111/exsy.70397","DOIUrl":"https://doi.org/10.1111/exsy.70397","url":null,"abstract":"<div>\u0000 \u0000 <p>Generative adversarial networks (GANs) have fundamentally transformed the deep learning field since they enable the creation of synthetic data that closely matches real world data. This paper presents a comprehensive and up-to-date review of GANs variants and their revolutionary impact in several domains, and major developments in the new applications. We demonstrate the GANs architecture, versatility of GANs variants such as CycleGAN, bidirectional generative adversarial networks (BiGAN), quantum-enhanced GAN (Q-GAN) and StyleGAN. In this work, different GANs variants are analysed and combined with the proposed improvements that enhance stability and performance. Despite their outstanding performance, GANs suffer from instability and mode collapse during training. This paper examines various strategies and improvements to enhance GANs stability and performance, including hybrid architectures that integrate GANs with other deep learning models and practical utility in domain-specific expert systems. Moreover, in the context of deepfakes, it considers the ethical and legal reflections of GANs generated content. We also contribute to a comprehensive perspective on current applications and future prospects of GANs, underscoring their versatility and promise in areas such as image synthesis, medical imaging, anomaly detection, code synthesis and urban simulation.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"43 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}