Pub Date : 2025-07-22DOI: 10.1109/TAI.2025.3591082
Hung Guei;Yan-Ru Ju;Wei-Yu Chen;Ti-Rong Wu
MuZero has achieved superhuman performance in various games by using a dynamics network to predict the environment dynamics for planning, without relying on simulators. However, the latent states learned by the dynamics network make its planning process opaque. This article aims to demystify MuZero’s model by interpreting the learned latent states. We incorporate observation reconstruction and state consistency into MuZero training and conduct an in-depth analysis to evaluate latent states across two board games: 9$,boldsymboltimes,$9 Go and Gomoku, and three Atari games: Breakout, Ms. Pacman, and Pong. Our findings reveal that while the dynamics network becomes less accurate over longer simulations, MuZero still performs effectively by using planning to correct errors. Our experiments also show that the dynamics network learns better latent states in board games than in Atari games. These insights contribute to a better understanding of MuZero and offer directions for future research to improve the performance, robustness, and interpretability of the MuZero algorithm.
{"title":"Demystifying MuZero Planning: Interpreting the Learned Model","authors":"Hung Guei;Yan-Ru Ju;Wei-Yu Chen;Ti-Rong Wu","doi":"10.1109/TAI.2025.3591082","DOIUrl":"https://doi.org/10.1109/TAI.2025.3591082","url":null,"abstract":"MuZero has achieved superhuman performance in various games by using a dynamics network to predict the environment dynamics for planning, without relying on simulators. However, the latent states learned by the dynamics network make its planning process opaque. This article aims to demystify MuZero’s model by interpreting the learned latent states. We incorporate observation reconstruction and state consistency into MuZero training and conduct an in-depth analysis to evaluate latent states across two board games: 9<inline-formula><tex-math>$,boldsymboltimes,$</tex-math></inline-formula>9 Go and Gomoku, and three Atari games: Breakout, Ms. Pacman, and Pong. Our findings reveal that while the dynamics network becomes less accurate over longer simulations, MuZero still performs effectively by using planning to correct errors. Our experiments also show that the dynamics network learns better latent states in board games than in Atari games. These insights contribute to a better understanding of MuZero and offer directions for future research to improve the performance, robustness, and interpretability of the MuZero algorithm.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"1025-1036"},"PeriodicalIF":0.0,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146176030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-22DOI: 10.1109/TAI.2025.3591094
Qiang Li;Mengdi Liu;Rihao Chang;Weizhi Nie;Shaojin Bai;Anan Liu
Chest X-rays (CXR) are widely used to diagnose chest diseases. Since patients often suffer from multiple diseases simultaneously, it is crucial to identify multiple abnormalities in a single CXR image, which is defined as a multilabel classification task. Recent methods aim to improve performance by leveraging label co-occurrences as prior knowledge. However, these statistical co-occurrences often introduce spurious correlations, which reduce the reliability of the model, and data imbalance further amplifies the harm of such spurious correlations for rare disease diagnosis. In this study, we proposed a category disentangled causal learning (CDCL) framework that considers both category-level and causal-level representations to provide robust and reliable CXR image diagnosis results. Specifically, we introduce the category attention (CA) mechanism to disentangle disease-specific features, enabling the model to effectively capture the discriminative features of each disease in the image. Additionally, we employ the label embeddings to learn a set of discriminative features at the global category level, complementing CA to enhance the effectiveness of category disentanglement. Causal intervention is then applied to the disentangled features to guide the model in learning true causal relationships, mitigating the impact of spurious correlations. The proposed CDCL framework was evaluated on the ChestX-Ray14 and CheXpert datasets, achieving mean AUC of 0.849 and 0.896, respectively. Ablation studies and visualization experiments demonstrated its competitiveness, particularly with significant improvements in rare disease identification.
{"title":"Multilabel Chest X-Ray Image Classification via Category Disentangled Causal Learning","authors":"Qiang Li;Mengdi Liu;Rihao Chang;Weizhi Nie;Shaojin Bai;Anan Liu","doi":"10.1109/TAI.2025.3591094","DOIUrl":"https://doi.org/10.1109/TAI.2025.3591094","url":null,"abstract":"Chest X-rays (CXR) are widely used to diagnose chest diseases. Since patients often suffer from multiple diseases simultaneously, it is crucial to identify multiple abnormalities in a single CXR image, which is defined as a multilabel classification task. Recent methods aim to improve performance by leveraging label co-occurrences as prior knowledge. However, these statistical co-occurrences often introduce spurious correlations, which reduce the reliability of the model, and data imbalance further amplifies the harm of such spurious correlations for rare disease diagnosis. In this study, we proposed a category disentangled causal learning (CDCL) framework that considers both category-level and causal-level representations to provide robust and reliable CXR image diagnosis results. Specifically, we introduce the category attention (CA) mechanism to disentangle disease-specific features, enabling the model to effectively capture the discriminative features of each disease in the image. Additionally, we employ the label embeddings to learn a set of discriminative features at the global category level, complementing CA to enhance the effectiveness of category disentanglement. Causal intervention is then applied to the disentangled features to guide the model in learning true causal relationships, mitigating the impact of spurious correlations. The proposed CDCL framework was evaluated on the ChestX-Ray14 and CheXpert datasets, achieving mean AUC of 0.849 and 0.896, respectively. Ablation studies and visualization experiments demonstrated its competitiveness, particularly with significant improvements in rare disease identification.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"1048-1061"},"PeriodicalIF":0.0,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146176016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anomaly detection of smelting process benefits the operation safety of fused magnesium furnaces (FMFs). While generative models that fit well complex data distributions in the latent space offer an effective way to anomaly detection, conventional generative models have difficulties in adapting to visual interferences such as dynamic water mist, dust, and on-site lighting changes. To this end, this article establishes a new frequency-domain feature reconstruction network with memory units for anomaly detection of fused magnesium furnaces. This network utilizes high-frequency filtering to extract features in the frequency domain to suppress the adverse effects of brightness variations caused by fluctuations in the furnace flame. Using the extracted frequency domain features, wavelet sampling is integrated with memory units for reconstruction to eliminate interferences in the frequency domain while preserving anomalous features, thereby alleviating overgeneralization. Moreover, a new adaptive threshold calculation method is proposed for the anomaly detection of FMFs. Finally, the effectiveness of the proposed method is demonstrated by using the image collected from a real FMF.
{"title":"Frequency-Domain Feature Reconstruction Network With Memory Units for Anomaly Detection of Fused Magnesium Furnaces","authors":"Qiang Liu;Yuxin Wang;Chao Yang;Jialin An;Yiu-ming Cheung","doi":"10.1109/TAI.2025.3591089","DOIUrl":"https://doi.org/10.1109/TAI.2025.3591089","url":null,"abstract":"Anomaly detection of smelting process benefits the operation safety of fused magnesium furnaces (FMFs). While generative models that fit well complex data distributions in the latent space offer an effective way to anomaly detection, conventional generative models have difficulties in adapting to visual interferences such as dynamic water mist, dust, and on-site lighting changes. To this end, this article establishes a new frequency-domain feature reconstruction network with memory units for anomaly detection of fused magnesium furnaces. This network utilizes high-frequency filtering to extract features in the frequency domain to suppress the adverse effects of brightness variations caused by fluctuations in the furnace flame. Using the extracted frequency domain features, wavelet sampling is integrated with memory units for reconstruction to eliminate interferences in the frequency domain while preserving anomalous features, thereby alleviating overgeneralization. Moreover, a new adaptive threshold calculation method is proposed for the anomaly detection of FMFs. Finally, the effectiveness of the proposed method is demonstrated by using the image collected from a real FMF.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"1037-1047"},"PeriodicalIF":0.0,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-18DOI: 10.1109/TAI.2025.3590703
Riya Tapwal
In this article, we present FlexiFed, a framework designed to enhance federated learning (FL) by addressing the challenges of device inclusivity and data prioritization. FL systems typically exclude low-resource devices, known as stragglers, due to their limited computational power, leading to the loss of valuable and often unique data. Additionally, current FL systems lack transparency, making it difficult to prioritize the contributions of individual devices. FlexiFed overcomes these issues by enabling stragglers to share simplified outputs, such as predictions and key feature importance scores, instead of full model updates. This reduces their computational and communication burden. The framework integrates explainability techniques to identify and emphasize critical data, ensuring rare and significant contributions are prioritized during training. FlexiFed distinguishes itself from similar frameworks by combining hierarchical aggregation with explainability-driven prioritization, directly addressing the need for fairness and transparency in diverse and resource-constrained environments.
{"title":"Stragglers Reimagined: Explainability-Driven Adaptive Federated Learning for Resource Constrained IoMT System","authors":"Riya Tapwal","doi":"10.1109/TAI.2025.3590703","DOIUrl":"https://doi.org/10.1109/TAI.2025.3590703","url":null,"abstract":"In this article, we present FlexiFed, a framework designed to enhance federated learning (FL) by addressing the challenges of device inclusivity and data prioritization. FL systems typically exclude low-resource devices, known as stragglers, due to their limited computational power, leading to the loss of valuable and often unique data. Additionally, current FL systems lack transparency, making it difficult to prioritize the contributions of individual devices. FlexiFed overcomes these issues by enabling stragglers to share simplified outputs, such as predictions and key feature importance scores, instead of full model updates. This reduces their computational and communication burden. The framework integrates explainability techniques to identify and emphasize critical data, ensuring rare and significant contributions are prioritized during training. FlexiFed distinguishes itself from similar frameworks by combining hierarchical aggregation with explainability-driven prioritization, directly addressing the need for fairness and transparency in diverse and resource-constrained environments.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"1002-1011"},"PeriodicalIF":0.0,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146176015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-18DOI: 10.1109/TAI.2025.3590691
Sidi Mohammed Alaoui;Khalifa Djemal;Ehsan Sedgh Gooya;Amir Ali Feiz;Ayman Al Falou
Optimizing sensor networks for localizing atmospheric pollution sources and enhancing estimation accuracy remains a significant challenge in air pollution studies. To address this, various techniques have been recently developed. Among them, machine learning has demonstrated its ability to model and optimize complex problems, including sensor network optimization. To improve the localization of atmospheric pollution sources in air quality research activities, we propose, in this article, a machine learning-driven optimization of sensor networks method (ML-OSN). The method introduces a new combination of hierarchical agglomerative clustering and Siamese neural networks, thereby improving the prediction of similarities in pollutant concentrations across different wind directions and leading to an optimized sensor network. The proposed ML-OSN method was evaluated and compared with a standard clustering approach based on the Pearson correlation coefficient, using the augmented Indianapolis dataset. The resulting optimal sensor network configuration achieved broader spatial coverage and improved source estimation accuracy, reducing the error score to 1.34 compared with 1.44 obtained with the Pearson-based approach.
{"title":"Machine Learning-Driven Optimization of a Sensor Network for Accurate Pollutant Source Identification","authors":"Sidi Mohammed Alaoui;Khalifa Djemal;Ehsan Sedgh Gooya;Amir Ali Feiz;Ayman Al Falou","doi":"10.1109/TAI.2025.3590691","DOIUrl":"https://doi.org/10.1109/TAI.2025.3590691","url":null,"abstract":"Optimizing sensor networks for localizing atmospheric pollution sources and enhancing estimation accuracy remains a significant challenge in air pollution studies. To address this, various techniques have been recently developed. Among them, machine learning has demonstrated its ability to model and optimize complex problems, including sensor network optimization. To improve the localization of atmospheric pollution sources in air quality research activities, we propose, in this article, a machine learning-driven optimization of sensor networks method (ML-OSN). The method introduces a new combination of hierarchical agglomerative clustering and Siamese neural networks, thereby improving the prediction of similarities in pollutant concentrations across different wind directions and leading to an optimized sensor network. The proposed ML-OSN method was evaluated and compared with a standard clustering approach based on the Pearson correlation coefficient, using the augmented Indianapolis dataset. The resulting optimal sensor network configuration achieved broader spatial coverage and improved source estimation accuracy, reducing the error score to 1.34 compared with 1.44 obtained with the Pearson-based approach.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"973-985"},"PeriodicalIF":0.0,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-18DOI: 10.1109/TAI.2025.3590692
Chongchong Jin;Yuanhao Cai;Yeyao Chen;Ting Luo;Zhouyan He;Yang Song
Depth image-based rendering (DIBR) is a common method for synthesizing virtual views to achieve smooth transitions in immersive media, but its immature technology often introduces distortions, adversely affecting visual quality. Obviously, accurately assessing the quality of synthesized views is crucial for monitoring and guiding the rendering process. To this end, this article proposes a no-reference deep learning-based quality assessment method for DIBR-synthesized views, which is primarily achieved by combining a contrastive learning feature enhancement network and a high–low frequency texture interaction network, abbreviated as CONTIN. Different from the traditional methods based on handcrafted feature extraction, the proposed method employs an end-to-end deep learning approach, fully exploiting the data characteristics and feature correlations. Specifically, to address the issue of sample expansion in existing deep learning methods, a contrastive sample database is first constructed by simulating various traditional and rendering distortions based on natural images, and training is performed on this database to obtain a contrastive learning feature enhancement network, which is used to extract contrastive features. Additionally, since contrastive learning tends to focus on learning abstract semantic-level features rather than pixel-level texture details, a wavelet transform decoupling is further applied to the synthetic distortion samples to construct a high–low frequency texture interaction network for extracting texture features. Finally, the two types of features are fused and regressed to generate the final quality score. Experimental results show that the proposed method achieves superior performance across three benchmark databases (namely, IRCCyN/IVC, IETR, andMCL-3D), with PLCC reaching 0.9404, 0.8380, and 0.9666, respectively, representing improvements of 0.0179, 0.0350, and 0.0175 higher than the existing best methods.
{"title":"Contrastive Learning Feature Enhancement and High–Low Frequency Texture Interaction Networks for DIBR-Synthesized View Quality Assessment","authors":"Chongchong Jin;Yuanhao Cai;Yeyao Chen;Ting Luo;Zhouyan He;Yang Song","doi":"10.1109/TAI.2025.3590692","DOIUrl":"https://doi.org/10.1109/TAI.2025.3590692","url":null,"abstract":"Depth image-based rendering (DIBR) is a common method for synthesizing virtual views to achieve smooth transitions in immersive media, but its immature technology often introduces distortions, adversely affecting visual quality. Obviously, accurately assessing the quality of synthesized views is crucial for monitoring and guiding the rendering process. To this end, this article proposes a no-reference deep learning-based quality assessment method for DIBR-synthesized views, which is primarily achieved by combining a contrastive learning feature enhancement network and a high–low frequency texture interaction network, abbreviated as CONTIN. Different from the traditional methods based on handcrafted feature extraction, the proposed method employs an end-to-end deep learning approach, fully exploiting the data characteristics and feature correlations. Specifically, to address the issue of sample expansion in existing deep learning methods, a contrastive sample database is first constructed by simulating various traditional and rendering distortions based on natural images, and training is performed on this database to obtain a contrastive learning feature enhancement network, which is used to extract contrastive features. Additionally, since contrastive learning tends to focus on learning abstract semantic-level features rather than pixel-level texture details, a wavelet transform decoupling is further applied to the synthetic distortion samples to construct a high–low frequency texture interaction network for extracting texture features. Finally, the two types of features are fused and regressed to generate the final quality score. Experimental results show that the proposed method achieves superior performance across three benchmark databases (namely, IRCCyN/IVC, IETR, andMCL-3D), with PLCC reaching 0.9404, 0.8380, and 0.9666, respectively, representing improvements of 0.0179, 0.0350, and 0.0175 higher than the existing best methods.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"986-1001"},"PeriodicalIF":0.0,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146090126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-18DOI: 10.1109/TAI.2025.3590706
Jingyang Jia;Le Wu;Shengcai Duan;Xun Chen
Gesture recognition systems based on surface electromyography (sEMG) exhibit high accuracy in laboratory settings. However, they often underperform in real-world applications due to the occurrence of unknown gestures not encountered during training. Prototype learning methods, which learn gesture prototypes and classify unknown gestures based on distances to these prototypes, effectively reject unknown gestures. However, relying solely on global feature distances may overlook subtle variations, weakening discrimination between similar features and reducing the model’s ability to identify unknown gestures resembling known ones. To address these limitations, we propose a fine-grained method that models the probability distribution of each feature point, enabling the detection of subtle differences in partial features. Specifically, we employ normalizing flows to capture detailed information at the feature-point level. This approach enhances the model’s capacity to recognize challenging unknown gestures that partially differ from known gesture patterns. In addition, we introduce synthetic unknown gestures generated by applying slight perturbations to known samples, simulating challenging unknown scenarios. We then design a novel loss function that pulls known gestures closer together while pushing synthetic unknown gestures further apart, creating a more robust rejection model. Extensive experiments on both custom and public datasets demonstrate that our method achieves an area under the curve (AUC) of 0.988 on the custom dataset and an average AUC of 0.984 and 0.782 on the two public datasets, CapgMyo-DBc and NinaproDB5, respectively. These results indicate that the proposed method provides a robust and practical solution for reliable myoelectric control in real-world applications.
{"title":"Normalizing Flow-Based Fine-Grained Modeling for Unknown Gesture Rejection in Myoelectric Pattern Recognition","authors":"Jingyang Jia;Le Wu;Shengcai Duan;Xun Chen","doi":"10.1109/TAI.2025.3590706","DOIUrl":"https://doi.org/10.1109/TAI.2025.3590706","url":null,"abstract":"Gesture recognition systems based on surface electromyography (sEMG) exhibit high accuracy in laboratory settings. However, they often underperform in real-world applications due to the occurrence of unknown gestures not encountered during training. Prototype learning methods, which learn gesture prototypes and classify unknown gestures based on distances to these prototypes, effectively reject unknown gestures. However, relying solely on global feature distances may overlook subtle variations, weakening discrimination between similar features and reducing the model’s ability to identify unknown gestures resembling known ones. To address these limitations, we propose a fine-grained method that models the probability distribution of each feature point, enabling the detection of subtle differences in partial features. Specifically, we employ normalizing flows to capture detailed information at the feature-point level. This approach enhances the model’s capacity to recognize challenging unknown gestures that partially differ from known gesture patterns. In addition, we introduce synthetic unknown gestures generated by applying slight perturbations to known samples, simulating challenging unknown scenarios. We then design a novel loss function that pulls known gestures closer together while pushing synthetic unknown gestures further apart, creating a more robust rejection model. Extensive experiments on both custom and public datasets demonstrate that our method achieves an area under the curve (AUC) of 0.988 on the custom dataset and an average AUC of 0.984 and 0.782 on the two public datasets, CapgMyo-DBc and NinaproDB5, respectively. These results indicate that the proposed method provides a robust and practical solution for reliable myoelectric control in real-world applications.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"1012-1024"},"PeriodicalIF":0.0,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146176031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-14DOI: 10.1109/TAI.2025.3582067
Nikhil Laxminarayana;Nimish Mishra;Prayag Tiwari;Sahil Garg;Bikash K. Behera;Ahmed Farouk
N. Laxminarayana, N. Mishra, P. Tiwari, S. Garg, B. K. Behera, and A. Farouk, “Quantum-assisted activation for supervised learning in healthcare-based intrusion detection systems,” IEEE Transactions on Artificial Intelligence, vol. 5, no. 3, pp. 977–984, Mar. 2024.
N. Laxminarayana， N. Mishra， P. Tiwari， S. Garg， B. K. Behera， A. Farouk，“基于医疗保健的入侵检测系统中监督学习的量子辅助激活”，《IEEE人工智能学报》，第5卷，第5期。3，第977-984页，2024年3月。
{"title":"Retraction Notice: Quantum-Assisted Activation for Supervised Learning in Healthcare-Based Intrusion Detection Systems","authors":"Nikhil Laxminarayana;Nimish Mishra;Prayag Tiwari;Sahil Garg;Bikash K. Behera;Ahmed Farouk","doi":"10.1109/TAI.2025.3582067","DOIUrl":"https://doi.org/10.1109/TAI.2025.3582067","url":null,"abstract":"N. Laxminarayana, N. Mishra, P. Tiwari, S. Garg, B. K. Behera, and A. Farouk, “Quantum-assisted activation for supervised learning in healthcare-based intrusion detection systems,” IEEE Transactions on Artificial Intelligence, vol. 5, no. 3, pp. 977–984, Mar. 2024.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 1","pages":"606-606"},"PeriodicalIF":0.0,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11080238","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145898252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-10DOI: 10.1109/TAI.2025.3586828
Randa Boukabene;Fatima Benbouzid-Si Tayeb
Community detection is a rapidly growing field, especially for multilayer networks—systems with multiple interaction types. While these networks offer great potential, analyzing them remains complex and underexplored. Recently, researchers have turned to optimization techniques to address these challenges. However, despite diverse approaches, there’s no comprehensive study consolidating these advancements. To bridge this gap, this article provides a structured review of optimization techniques for community detection in multilayer networks, classifying methods by three criteria: resolution types, optimization types, and resolution methods. This aims to clarify the field and guide future research. This effort seeks to bring clarity to the field, offering a unified perspective on existing methods, while also providing a foundation to inspire and guide future research directions.
{"title":"Optimization for Community Detection in Multilayer Networks: A Comprehensive Review and Novel Taxonomy","authors":"Randa Boukabene;Fatima Benbouzid-Si Tayeb","doi":"10.1109/TAI.2025.3586828","DOIUrl":"https://doi.org/10.1109/TAI.2025.3586828","url":null,"abstract":"Community detection is a rapidly growing field, especially for multilayer networks—systems with multiple interaction types. While these networks offer great potential, analyzing them remains complex and underexplored. Recently, researchers have turned to optimization techniques to address these challenges. However, despite diverse approaches, there’s no comprehensive study consolidating these advancements. To bridge this gap, this article provides a structured review of optimization techniques for community detection in multilayer networks, classifying methods by three criteria: resolution types, optimization types, and resolution methods. This aims to clarify the field and guide future research. This effort seeks to bring clarity to the field, offering a unified perspective on existing methods, while also providing a foundation to inspire and guide future research directions.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"1185-1200"},"PeriodicalIF":0.0,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-08DOI: 10.1109/TAI.2025.3586571
Shuokang Huang;Po-Yu Chen;Peilin Zhou;Kaihan Li;Julie A. McCann
WiFi-based human sensing is gaining popularity thanks to it not requiring additional devices and not being as intrusive as cameras. Specifically, human features can be extracted from WiFi channel state information (CSI) to recognize human activities, identities, etc. However, most previous works rely on single-task learning models for recognition (e.g., to either recognize activities OR identities solely). The lack of cross-task knowledge sharing restricts these models to task-specific features and poor generalization. Recent studies have applied multitask learning (MTL) to tackle this, but their cross-task sharing modules add vast amounts of extra parameters. Such massive parameters increase model complexity and reduce time efficiency. In this article, we propose a novel zero-parameter attention sharing transformer (ZAST) to efficiently recognize both activities and identities. In ZAST, a cross-task attention on attention (CAoA) mechanism computes the relevance of attention scores for cross-task knowledge sharing, as a new paradigm for lightweight MTL. To mitigate the perturbation caused by attention sharing, we formulate a multihead similarity loss (L-MS) for stable model training. We further equip ZAST with channelwise squeeze and excitation (CSE) that efficiently learns the channel correlations of CSI. Extensive experiments on four public datasets indicate that ZAST achieves state-of-the-art recognition performance with the lowest complexity and the highest efficiency.
{"title":"Zero-Parameter Attention Sharing Transformer for Joint Human Activity and Identity Recognition","authors":"Shuokang Huang;Po-Yu Chen;Peilin Zhou;Kaihan Li;Julie A. McCann","doi":"10.1109/TAI.2025.3586571","DOIUrl":"https://doi.org/10.1109/TAI.2025.3586571","url":null,"abstract":"WiFi-based human sensing is gaining popularity thanks to it not requiring additional devices and not being as intrusive as cameras. Specifically, human features can be extracted from WiFi channel state information (CSI) to recognize human activities, identities, etc. However, most previous works rely on single-task learning models for recognition (e.g., to either recognize activities OR identities solely). The lack of cross-task knowledge sharing restricts these models to task-specific features and poor generalization. Recent studies have applied multitask learning (MTL) to tackle this, but their cross-task sharing modules add vast amounts of extra parameters. Such massive parameters increase model complexity and reduce time efficiency. In this article, we propose a novel zero-parameter attention sharing transformer (ZAST) to efficiently recognize both activities and identities. In ZAST, a cross-task attention on attention (CAoA) mechanism computes the relevance of attention scores for cross-task knowledge sharing, as a new paradigm for lightweight MTL. To mitigate the perturbation caused by attention sharing, we formulate a multihead similarity loss (L-MS) for stable model training. We further equip ZAST with channelwise squeeze and excitation (CSE) that efficiently learns the channel correlations of CSI. Extensive experiments on four public datasets indicate that ZAST achieves state-of-the-art recognition performance with the lowest complexity and the highest efficiency.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 2","pages":"960-972"},"PeriodicalIF":0.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146176019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：