Pub Date : 2026-01-28DOI: 10.1016/j.eswa.2026.131322
Jiangjing Zhou , Vladimir Mazalov
We analyze Nash-stable coalition partitions in a differential game with heterogeneous player populations; as a leading application, we study an asymmetric game of pollution control. Type-I players are non-vulnerable to pollution and do not internalize damages in their production choices, whereas Type-II players fully internalize the damages. We characterize optimal feedback strategies under alternative coalition partitions, establish conditions for Nash-stable partitions for fixed numbers of Type-I and Type-II players, and identify when vulnerable players can incentivize non-vulnerable players to cooperate in emission control. We prove that, under a non-transferable payoff scheme, no Nash-stable coalition partition exists, whereas under a transferable scheme with the CIS value, a stable partition can be achieved. We also provide a compact compute-allocate-verify module that, given the model parameters and a feasible-partition set, computes feedback Nash equilibrium, allocates CIS values, and verifies unilateral deviations to identify Nash-stable coalition partitions.
{"title":"Decision support for buying cooperation in Nash-stable coalition partitions for environmental differential games","authors":"Jiangjing Zhou , Vladimir Mazalov","doi":"10.1016/j.eswa.2026.131322","DOIUrl":"10.1016/j.eswa.2026.131322","url":null,"abstract":"<div><div>We analyze Nash-stable coalition partitions in a differential game with heterogeneous player populations; as a leading application, we study an asymmetric game of pollution control. Type-I players are non-vulnerable to pollution and do not internalize damages in their production choices, whereas Type-II players fully internalize the damages. We characterize optimal feedback strategies under alternative coalition partitions, establish conditions for Nash-stable partitions for fixed numbers of Type-I and Type-II players, and identify when vulnerable players can incentivize non-vulnerable players to cooperate in emission control. We prove that, under a non-transferable payoff scheme, no Nash-stable coalition partition exists, whereas under a transferable scheme with the CIS value, a stable partition can be achieved. We also provide a compact compute-allocate-verify module that, given the model parameters and a feasible-partition set, computes feedback Nash equilibrium, allocates CIS values, and verifies unilateral deviations to identify Nash-stable coalition partitions.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"310 ","pages":"Article 131322"},"PeriodicalIF":7.5,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081110","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}
Generative adversarial networks (GANs) often suffer from unstable training, and degraded performance under data-scarce or multi-category conditions. To address these challenges, we propose GEGAN, a gradient-guided evolutionary framework that maintains a population of generators and updates them collaboratively using explicit gradient directions. A gradient-guided mutation operator assigns complementary learning behaviors to individuals, balancing global exploration and local convergence, while an accept-reject mechanism preserves improvements across generations. We establish convergence to an approximate local equilibrium under mild smoothness assumptions, providing theoretical foundations for the hybrid design. Extensive experiments demonstrate that GEGAN consistently enhances image quality and diversity, achieving the highest ranks on Fq, Fd, and MMD with statistically significant gains over canonical and evolutionary GANs.
{"title":"GEGAN: gradient-guided evolutionary framework for GAN optimization","authors":"Wenwen Jia , Qi Yu , Xijun Liang , Mengzhen Li , Ling Jian","doi":"10.1016/j.eswa.2026.131257","DOIUrl":"10.1016/j.eswa.2026.131257","url":null,"abstract":"<div><div>Generative adversarial networks (GANs) often suffer from unstable training, and degraded performance under data-scarce or multi-category conditions. To address these challenges, we propose GEGAN, a gradient-guided evolutionary framework that maintains a population of generators and updates them collaboratively using explicit gradient directions. A gradient-guided mutation operator assigns complementary learning behaviors to individuals, balancing global exploration and local convergence, while an accept-reject mechanism preserves improvements across generations. We establish convergence to an approximate local equilibrium under mild smoothness assumptions, providing theoretical foundations for the hybrid design. Extensive experiments demonstrate that GEGAN consistently enhances image quality and diversity, achieving the highest ranks on <em>F<sup>q</sup>, F<sup>d</sup></em>, and MMD with statistically significant gains over canonical and evolutionary GANs.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"310 ","pages":"Article 131257"},"PeriodicalIF":7.5,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-28DOI: 10.1016/j.eswa.2026.131328
Hongye Li , Qianlong Dang
In the process of multimodal multi-objective optimization, retaining the promising solutions with good diversity is beneficial to balance the diversity and convergence. However, many multimodal multi-objective evolutionary algorithms usually adopt the principle of convergence-first in the process of selecting solutions, resulting in the loss of a large number of promising solutions. Therefore, this paper proposes a graph neural network (GNN) based multimodal multi-objective evolutionary algorithm (GNNMMOEA), which retains more promising solutions by classifying solutions. Firstly, a graph data with pseudo labels is designed to take advantage of solution distribution and dominance relationships. Secondly, a graph neural network model with a residual structure is constructed, which obtains the ability to distinguish the good and bad solutions in the population by training the above graph data. On this basis, a selection mechanism based on classification probability is proposed, which retains promising solutions and eliminates poor solutions by ranking the classification probability of GNN. Finally, GNNMMOEA transfers the classification knowledge of training data to the environment selection through GNN and makes a more reasonable selection, balancing the diversity and convergence. Experimental results on four test suites and a practical problem indicate that GNNMMOEA outperforms the other eight advanced algorithms, and surpasses the closest competitors by 23.35% and 22.22% in the decision space and the objective space, respectively.
{"title":"Multimodal multi-objective evolutionary algorithm assisted by graph neural networks based selection mechanism","authors":"Hongye Li , Qianlong Dang","doi":"10.1016/j.eswa.2026.131328","DOIUrl":"10.1016/j.eswa.2026.131328","url":null,"abstract":"<div><div>In the process of multimodal multi-objective optimization, retaining the promising solutions with good diversity is beneficial to balance the diversity and convergence. However, many multimodal multi-objective evolutionary algorithms usually adopt the principle of convergence-first in the process of selecting solutions, resulting in the loss of a large number of promising solutions. Therefore, this paper proposes a graph neural network (GNN) based multimodal multi-objective evolutionary algorithm (GNNMMOEA), which retains more promising solutions by classifying solutions. Firstly, a graph data with pseudo labels is designed to take advantage of solution distribution and dominance relationships. Secondly, a graph neural network model with a residual structure is constructed, which obtains the ability to distinguish the good and bad solutions in the population by training the above graph data. On this basis, a selection mechanism based on classification probability is proposed, which retains promising solutions and eliminates poor solutions by ranking the classification probability of GNN. Finally, GNNMMOEA transfers the classification knowledge of training data to the environment selection through GNN and makes a more reasonable selection, balancing the diversity and convergence. Experimental results on four test suites and a practical problem indicate that GNNMMOEA outperforms the other eight advanced algorithms, and surpasses the closest competitors by 23.35% and 22.22% in the decision space and the objective space, respectively.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"310 ","pages":"Article 131328"},"PeriodicalIF":7.5,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-28DOI: 10.1016/j.eswa.2026.131348
Yu Shi , Ziyan Liu , Yongyan Liang , Zhi Yang , Ruixin Liang , Chongyang Ye
Pneumatic compression modalities (PCMs) dynamically exert active external interfacial pressures along contact body area for clinical treatment and daily healthcare of chronic venous disorders (CVD). However, few studies provided efficient and operable strategies to promote pressure control and performance evaluation of multimodal PCMs for various application requirements. Therefore, this study developed the novel biometric-based design and visualization approaches through the three-dimensional (3D) theoretical contact and fluid–solid interaction (FSI) numerical models. Based on anthropometric characterization, the relationships between the air inflation mass with pressure generation of PCMs were quantified for determination of bladder parametric variables. Then, user expected compression levels were achieved by varying the air mass flow ratio and inflation time. Sequentially, the FSI biomechanical simulation models were established for pressure delivery prediction of leg-PCM systems. Through the experimental validation, the pressure values obtained by the proposed design (pressure discrepancy ratio: 16.55%) and visualization (pressure discrepancy ratio: 13.77%) systems had reasonable accuracy with predesigned user-oriented pressure dosages. Therefore, this study contributes to providing the evidence-based guidance of device development and pressure estimation, thus facilitates the effective improvement of venous hemodynamics for proactive compression treatment.
{"title":"Biometric-based design and visualized evaluation systems for multimodal pneumatic compression therapeutic modalities","authors":"Yu Shi , Ziyan Liu , Yongyan Liang , Zhi Yang , Ruixin Liang , Chongyang Ye","doi":"10.1016/j.eswa.2026.131348","DOIUrl":"10.1016/j.eswa.2026.131348","url":null,"abstract":"<div><div>Pneumatic compression modalities (PCMs) dynamically exert active external interfacial pressures along contact body area for clinical treatment and daily healthcare of chronic venous disorders (CVD). However, few studies provided efficient and operable strategies to promote pressure control and performance evaluation of multimodal PCMs for various application requirements. Therefore, this study developed the novel biometric-based design and visualization approaches through the three-dimensional (3D) theoretical contact and fluid–solid interaction (FSI) numerical models. Based on anthropometric characterization, the relationships between the air inflation mass with pressure generation of PCMs were quantified for determination of bladder parametric variables. Then, user expected compression levels were achieved by varying the air mass flow ratio and inflation time. Sequentially, the FSI biomechanical simulation models were established for pressure delivery prediction of leg-PCM systems. Through the experimental validation, the pressure values obtained by the proposed design (pressure discrepancy ratio: 16.55%) and visualization (pressure discrepancy ratio: 13.77%) systems had reasonable accuracy with predesigned user-oriented pressure dosages. Therefore, this study contributes to providing the evidence-based guidance of device development and pressure estimation, thus facilitates the effective improvement of venous hemodynamics for proactive compression treatment.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"310 ","pages":"Article 131348"},"PeriodicalIF":7.5,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-28DOI: 10.1016/j.eswa.2026.131370
Jun Yu , Shengzhao Li , Huijie Liu , Qi Liu , Chang Tan , Zhiyuan Cheng , Jinze Wu
Process-oriented evaluation of classroom instruction is vital for assessing student learning quality and teacher instructional effectiveness. In recent years, object detection-based methods have been widely applied to classroom behavior recognition, yet they struggle with the unique challenges of real-world classrooms: small student objects due to distant cameras, frequent occlusions, and subtle, fine-grained behaviors like “Gaze” and “Turn”. To address these issues, this paper proposes EduYOLO, a novel classroom Behavior Recognition Framework Based on High-Resolution Feature Attention Fusion (HRFAF) module, which is architected around three dedicated components: a Key Region Perception Backbone that enhances the representation of crucial action regions, a Fine-Grained Action Modeling Neck that captures intricate behavioral patterns, and a High-Resolution Prediction Head that significantly improves small object detection. This holistic design synergistically strengthens the capability of model to perceive local details and complex postures. Furthermore, we design the FM-IoU loss function for bounding box regression, integrating focal weighting and multi-point distance constraints to enhance localization stability. Extensive experiments conducted on the self-constructed CSCB-Dataset and SCB-Data3 demonstrate that the proposed EduYOLO achieves superior detection accuracy and generalization performance compared with existing methods, confirming its effectiveness and robustness for real-world classroom behavior recognition tasks. To support reproducible research, our code is available at: https://github.com/datadance/EduYolo.
{"title":"EduYOLO: A classroom behavior recognition framework based on high-resolution feature attention fusion","authors":"Jun Yu , Shengzhao Li , Huijie Liu , Qi Liu , Chang Tan , Zhiyuan Cheng , Jinze Wu","doi":"10.1016/j.eswa.2026.131370","DOIUrl":"10.1016/j.eswa.2026.131370","url":null,"abstract":"<div><div>Process-oriented evaluation of classroom instruction is vital for assessing student learning quality and teacher instructional effectiveness. In recent years, object detection-based methods have been widely applied to classroom behavior recognition, yet they struggle with the unique challenges of real-world classrooms: small student objects due to distant cameras, frequent occlusions, and subtle, fine-grained behaviors like “Gaze” and “Turn”. To address these issues, this paper proposes EduYOLO, a novel classroom Behavior Recognition Framework Based on High-Resolution Feature Attention Fusion (HRFAF) module, which is architected around three dedicated components: a Key Region Perception Backbone that enhances the representation of crucial action regions, a Fine-Grained Action Modeling Neck that captures intricate behavioral patterns, and a High-Resolution Prediction Head that significantly improves small object detection. This holistic design synergistically strengthens the capability of model to perceive local details and complex postures. Furthermore, we design the FM-IoU loss function for bounding box regression, integrating focal weighting and multi-point distance constraints to enhance localization stability. Extensive experiments conducted on the self-constructed CSCB-Dataset and SCB-Data3 demonstrate that the proposed EduYOLO achieves superior detection accuracy and generalization performance compared with existing methods, confirming its effectiveness and robustness for real-world classroom behavior recognition tasks. To support reproducible research, our code is available at: <span><span>https://github.com/datadance/EduYolo</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"311 ","pages":"Article 131370"},"PeriodicalIF":7.5,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-28DOI: 10.1016/j.eswa.2026.131360
mohammad ghasempour , yuan yuan , hadi amirpour , hongjie he , christian timmerer
With the ever-increasing amount of digital video content, efficient encryption is crucial to protect visual content across diverse platforms. Existing methods often incur excessive bitrate overhead due to content variability. Furthermore, since most videos are already compressed, encryption in the compressed domain is essential to avoid processing overhead and re-compression quality loss. However, achieving both format compliance and compression efficiency while ensuring that the decoded content remains unrecognizable is challenging in the compressed domain, since only limited information is available without full decoding. This paper proposes an adaptive compressed domain video encryption (ACDC) method that dynamically adjusts the encryption strategy according to content characteristics. Two tunable parameters derived from the bitstream information enable adaptation to various application requirements. An adaptive syntax integrity method is employed to produce format-compliant bitstreams without full decoding. Experimental results show that ACDC reduces bitrate overhead by 48.2% and achieves a 31-fold speedup in encryption time compared to the latest state of the art, while producing visually unrecognizable outputs.
{"title":"Adaptive compressed domain video encryption","authors":"mohammad ghasempour , yuan yuan , hadi amirpour , hongjie he , christian timmerer","doi":"10.1016/j.eswa.2026.131360","DOIUrl":"10.1016/j.eswa.2026.131360","url":null,"abstract":"<div><div>With the ever-increasing amount of digital video content, efficient encryption is crucial to protect visual content across diverse platforms. Existing methods often incur excessive bitrate overhead due to content variability. Furthermore, since most videos are already compressed, encryption in the compressed domain is essential to avoid processing overhead and re-compression quality loss. However, achieving both format compliance and compression efficiency while ensuring that the decoded content remains unrecognizable is challenging in the compressed domain, since only limited information is available without full decoding. This paper proposes an adaptive compressed domain video encryption (ACDC) method that dynamically adjusts the encryption strategy according to content characteristics. Two tunable parameters derived from the bitstream information enable adaptation to various application requirements. An adaptive syntax integrity method is employed to produce format-compliant bitstreams without full decoding. Experimental results show that ACDC reduces bitrate overhead by 48.2% and achieves a 31-fold speedup in encryption time compared to the latest state of the art, while producing visually unrecognizable outputs.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"311 ","pages":"Article 131360"},"PeriodicalIF":7.5,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-27DOI: 10.1016/j.eswa.2026.131346
Runmin Wang , Xingdong Song , Zukun Wan , Han Xu , Congzhen Yu , Tianming Ma , Yajun Ding , Shengyou Qian
Visual Question Answering (VQA) evaluates the visual-textual reasoning capabilities of intelligent agents. However, existing methods are often susceptible to various biases. In particular, language bias leads models to rely on spurious question-answer correlations as shortcut solutions, while distribution bias caused by dataset imbalance encourages models to overfit head classes and overlook tail classes. To address these long-standing challenges, we propose a Dual-Space Intervention (DSI) approach that tackles these two biases from a unified yet complementary perspective. Two key innovations are included in our work: (1) In the input space, we adopt an adaptive question shuffling strategy to alleviate language bias by adjusting perturbation strength according to question bias, ensuring models develop a deeper understanding of the problem context, rather than relying on spurious word-answer correlations; (2) In the output space, we propose a novel label rebalancing mechanism that moderates head-class dominance based on long-tailed statistics, improving robustness to distribution bias. This approach reduces the disproportionately high variance in head logits relative to tail logits, improving tail class recognition accuracy. Extensive experiments on four benchmarks (VQA-CP v1, VQA-CP v2, VQA-CE, and SLAKE-CP) demonstrate our method’s superiority, with VQA-CP v1 and SLAKE-CP achieving state-of-the-art performance at 63.14% and 37.61% respectively. The code will be released at https://github.com/songxdr3/DSI.
{"title":"Dual-space intervention for mitigating bias in robust visual question answering","authors":"Runmin Wang , Xingdong Song , Zukun Wan , Han Xu , Congzhen Yu , Tianming Ma , Yajun Ding , Shengyou Qian","doi":"10.1016/j.eswa.2026.131346","DOIUrl":"10.1016/j.eswa.2026.131346","url":null,"abstract":"<div><div>Visual Question Answering (VQA) evaluates the visual-textual reasoning capabilities of intelligent agents. However, existing methods are often susceptible to various biases. In particular, language bias leads models to rely on spurious question-answer correlations as shortcut solutions, while distribution bias caused by dataset imbalance encourages models to overfit head classes and overlook tail classes. To address these long-standing challenges, we propose a Dual-Space Intervention (DSI) approach that tackles these two biases from a unified yet complementary perspective. Two key innovations are included in our work: (1) In the input space, we adopt an adaptive question shuffling strategy to alleviate language bias by adjusting perturbation strength according to question bias, ensuring models develop a deeper understanding of the problem context, rather than relying on spurious word-answer correlations; (2) In the output space, we propose a novel label rebalancing mechanism that moderates head-class dominance based on long-tailed statistics, improving robustness to distribution bias. This approach reduces the disproportionately high variance in head logits relative to tail logits, improving tail class recognition accuracy. Extensive experiments on four benchmarks (VQA-CP v1, VQA-CP v2, VQA-CE, and SLAKE-CP) demonstrate our method’s superiority, with VQA-CP v1 and SLAKE-CP achieving state-of-the-art performance at 63.14% and 37.61% respectively. The code will be released at <span><span>https://github.com/songxdr3/DSI</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"311 ","pages":"Article 131346"},"PeriodicalIF":7.5,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-27DOI: 10.1016/j.eswa.2026.131345
Shuai Wang , Ruina Mao
Existing pre-trained foundation models have demonstrated strong generalization and transfer capabilities across diverse domains. However, directly fine-tuning all parameters of pre-trained models for medical image classification requires massive labeled data, making it inefficient and resource-intensive. To address this, we aim to leverage semi-supervised learning (SSL) techniques to reduce the need for massive annotations for efficient fine-tuning. In this context, we propose PromptMed, a parameter-efficient framework for semi-supervised medical image classification, which consists of three key components: Prompt Noise Injection (PNI), Class-Balanced Prompt Adaptation (CBPA), and Contrastive Feature Consistency (CFC). Specifically, we introduce PNI to enhance the robustness of prompt representations and enable effective prompt-based consistency training. PNI applies Gaussian noise of varying strengths to prompt tokens, serving as a form of representation-level augmentation. To mitigate class imbalance, we design a CBPA mechanism that dynamically assigns higher noise to minority classes based on recent class distributions, encouraging better representation learning for hard categories. Additionally, to promote feature consistency, especially for minority and visually similar classes, we incorporate a CFC on the vision branch features. These three components work synergistically to enable PromptMed to achieve robust, balanced, and highly discriminative medical image classification with significantly reduced trainable parameters. Extensive experiments on multiple medical image datasets demonstrate that our approach achieves state-of-the-art performance while significantly reducing the number of trainable parameters.
{"title":"PromptMed: Prompt-driven semi-supervised medical image classification with class-balanced consistency and contrastive learning","authors":"Shuai Wang , Ruina Mao","doi":"10.1016/j.eswa.2026.131345","DOIUrl":"10.1016/j.eswa.2026.131345","url":null,"abstract":"<div><div>Existing pre-trained foundation models have demonstrated strong generalization and transfer capabilities across diverse domains. However, directly fine-tuning all parameters of pre-trained models for medical image classification requires massive labeled data, making it inefficient and resource-intensive. To address this, we aim to leverage semi-supervised learning (SSL) techniques to reduce the need for massive annotations for efficient fine-tuning. In this context, we propose PromptMed, a parameter-efficient framework for semi-supervised medical image classification, which consists of three key components: Prompt Noise Injection (PNI), Class-Balanced Prompt Adaptation (CBPA), and Contrastive Feature Consistency (CFC). Specifically, we introduce PNI to enhance the robustness of prompt representations and enable effective prompt-based consistency training. PNI applies Gaussian noise of varying strengths to prompt tokens, serving as a form of representation-level augmentation. To mitigate class imbalance, we design a CBPA mechanism that dynamically assigns higher noise to minority classes based on recent class distributions, encouraging better representation learning for hard categories. Additionally, to promote feature consistency, especially for minority and visually similar classes, we incorporate a CFC on the vision branch features. These three components work synergistically to enable PromptMed to achieve robust, balanced, and highly discriminative medical image classification with significantly reduced trainable parameters. Extensive experiments on multiple medical image datasets demonstrate that our approach achieves state-of-the-art performance while significantly reducing the number of trainable parameters.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"310 ","pages":"Article 131345"},"PeriodicalIF":7.5,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-27DOI: 10.1016/j.eswa.2026.131339
Xi Liu , Jun Liu
Aerial Edge Computing has recently received significant research attention due to its remarkable potential for dynamically deploying computing power. We address the problem of service scheduling in aerial edge computing, in which uncrewed aerial vehicles (UAVs) are deployed to mission areas to provide sensor data collection and analysis services. Two types of sensing tasks are considered: single-zone service and multiple-zone service. The first category refers to UAVs that remain in a single zone. The second category refers to a UAV traversing several areas to collect sensing data to meet user requirements. The objective is to maximize the overall utility of the UAVs. The service scheduling problem is formulated as an ordinal potential game to achieve a stable system state. A distributed algorithm based on reinforcement learning is proposed. An improved search-state formulation is introduced to accelerate convergence and enhance search efficiency. The proposed scheduling algorithm is demonstrated to achieve a Nash equilibrium in where no UAV can improve its utility by unilaterally deviating. Additionally, the approximation performance of the proposed scheduling algorithm and the game’s price of anarchy are presented. The results indicate that the proposed algorithm provides higher utility to UAVs and adapts effectively to diverse distribution environments.
{"title":"Reinforcement learning-driven service allocation via potential game modeling in aerial edge computing","authors":"Xi Liu , Jun Liu","doi":"10.1016/j.eswa.2026.131339","DOIUrl":"10.1016/j.eswa.2026.131339","url":null,"abstract":"<div><div>Aerial Edge Computing has recently received significant research attention due to its remarkable potential for dynamically deploying computing power. We address the problem of service scheduling in aerial edge computing, in which uncrewed aerial vehicles (UAVs) are deployed to mission areas to provide sensor data collection and analysis services. Two types of sensing tasks are considered: single-zone service and multiple-zone service. The first category refers to UAVs that remain in a single zone. The second category refers to a UAV traversing several areas to collect sensing data to meet user requirements. The objective is to maximize the overall utility of the UAVs. The service scheduling problem is formulated as an ordinal potential game to achieve a stable system state. A distributed algorithm based on reinforcement learning is proposed. An improved search-state formulation is introduced to accelerate convergence and enhance search efficiency. The proposed scheduling algorithm is demonstrated to achieve a Nash equilibrium in where no UAV can improve its utility by unilaterally deviating. Additionally, the approximation performance of the proposed scheduling algorithm and the game’s price of anarchy are presented. The results indicate that the proposed algorithm provides higher utility to UAVs and adapts effectively to diverse distribution environments.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"310 ","pages":"Article 131339"},"PeriodicalIF":7.5,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-27DOI: 10.1016/j.eswa.2026.131225
Sebastian Zarębski , Krzysztof Rusek , Piotr Chołda
This paper introduces Linear Model of Latent Dirichlet Allocation (LMLDA), a novel methodology for software test optimization that directly addresses the gap between computationally-prohibitive large language models (LLMs) and semantically-shallow heuristics. Our primary contribution is a lightweight, interpretable, and cost-efficient model specifically designed for high-stakes industrial Continuous Integration and Continuous Development (CI/CD) environments where security and traceability are essential. The novelty of LMLDA lies in its integration of Latent Dirichlet Allocation (LDA) for the semantic analysis of code modifications and test content, with a classifier based on logistic regression concepts for the training phase, yet offering prediction capabilities that align with the computational simplicity of linear regression. This approach uniquely predicts the probability of test failure based on semantic interactions, enabling precise, bug-centric prioritization rather than relying on indirect diversity proxies. A large-scale industrial case study at NOKIA demonstrates LMLDA’s practical effectiveness, achieving an average 64% reduction in test suite size while maintaining 88% precision in bug detection and accelerating critical bug discovery by an average of 8 h per cycle.
{"title":"Regression test optimization for software of the cellular network base stations: A language-based approach","authors":"Sebastian Zarębski , Krzysztof Rusek , Piotr Chołda","doi":"10.1016/j.eswa.2026.131225","DOIUrl":"10.1016/j.eswa.2026.131225","url":null,"abstract":"<div><div>This paper introduces Linear Model of Latent Dirichlet Allocation (LMLDA), a novel methodology for software test optimization that directly addresses the gap between computationally-prohibitive large language models (LLMs) and semantically-shallow heuristics. Our primary contribution is a lightweight, interpretable, and cost-efficient model specifically designed for high-stakes industrial Continuous Integration and Continuous Development (CI/CD) environments where security and traceability are essential. The novelty of LMLDA lies in its integration of Latent Dirichlet Allocation (LDA) for the semantic analysis of code modifications and test content, with a classifier based on logistic regression concepts for the training phase, yet offering prediction capabilities that align with the computational simplicity of linear regression. This approach uniquely predicts the probability of test failure based on semantic interactions, enabling precise, bug-centric prioritization rather than relying on indirect diversity proxies. A large-scale industrial case study at NOKIA demonstrates LMLDA’s practical effectiveness, achieving an average 64% reduction in test suite size while maintaining 88% precision in bug detection and accelerating critical bug discovery by an average of 8 h per cycle.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"311 ","pages":"Article 131225"},"PeriodicalIF":7.5,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146081703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号