Pub Date : 2024-03-24DOI: 10.1109/TETCI.2024.3398387
{"title":"IEEE Transactions on Emerging Topics in Computational Intelligence Information for Authors","authors":"","doi":"10.1109/TETCI.2024.3398387","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3398387","url":null,"abstract":"","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2024-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10538465","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141096294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}
Pub Date : 2024-03-24DOI: 10.1109/TETCI.2024.3398385
{"title":"IEEE Computational Intelligence Society Information","authors":"","doi":"10.1109/TETCI.2024.3398385","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3398385","url":null,"abstract":"","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2024-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10538449","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141096289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}
Pub Date : 2024-03-24DOI: 10.1109/TETCI.2024.3398383
{"title":"IEEE Transactions on Emerging Topics in Computational Intelligence Publication Information","authors":"","doi":"10.1109/TETCI.2024.3398383","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3398383","url":null,"abstract":"","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2024-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10538452","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141096367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}
Pub Date : 2024-03-22DOI: 10.1109/TETCI.2024.3369485
Zhengjun Wang;Weifeng Gao;Genghui Li;Zhenkun Wang;Maoguo Gong
Unmanned aerial vehicles (UAVs) are widely used in urban search and rescue, where path planning plays a critical role. This paper proposes an approach using off-policy reinforcement learning (RL) with an improved exploration mechanism (IEM) based on prioritized experience replay (PER) and curiosity-driven exploration to address the time-constrained path planning problem for UAVs operating in complex unknown environments. Firstly, to meet the task's time constraints, we design a rollout algorithm based on PER to optimize the behavior policy and enhance sampling efficiency. Additionally, we address the issue that certain off-policy RL algorithms often get trapped in local optima in environments with sparse rewards by measuring curiosity using the states' unvisited time and generating intrinsic rewards to encourage exploration. Lastly, we introduce IEM into the sampling stage of various off-policy RL algorithms. Simulation experiments demonstrate that, compared to the original off-policy RL algorithms, the algorithms incorporating IEM can reduce the planning time required for rescuing paths and achieve the goal of rescuing all trapped individuals.
{"title":"Path Planning for Unmanned Aerial Vehicle via Off-Policy Reinforcement Learning With Enhanced Exploration","authors":"Zhengjun Wang;Weifeng Gao;Genghui Li;Zhenkun Wang;Maoguo Gong","doi":"10.1109/TETCI.2024.3369485","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3369485","url":null,"abstract":"Unmanned aerial vehicles (UAVs) are widely used in urban search and rescue, where path planning plays a critical role. This paper proposes an approach using off-policy reinforcement learning (RL) with an improved exploration mechanism (IEM) based on prioritized experience replay (PER) and curiosity-driven exploration to address the time-constrained path planning problem for UAVs operating in complex unknown environments. Firstly, to meet the task's time constraints, we design a rollout algorithm based on PER to optimize the behavior policy and enhance sampling efficiency. Additionally, we address the issue that certain off-policy RL algorithms often get trapped in local optima in environments with sparse rewards by measuring curiosity using the states' unvisited time and generating intrinsic rewards to encourage exploration. Lastly, we introduce IEM into the sampling stage of various off-policy RL algorithms. Simulation experiments demonstrate that, compared to the original off-policy RL algorithms, the algorithms incorporating IEM can reduce the planning time required for rescuing paths and achieve the goal of rescuing all trapped individuals.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141096326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-03-21DOI: 10.1109/TETCI.2024.3372693
Ying Ma;Xiaoyan Zou;Qizheng Pan;Ming Yan;Guoqi Li
In the task of multi-label classification, it is a key challenge to determine the correlation between labels. One solution to this is the Target Embedding Autoencoder (TEA), but most TEA-based frameworks have numerous parameters, large models, and high complexity, which makes it difficult to deal with the problem of large-scale learning. To address this issue, we provide a Target Embedding Autoencoder framework based on Knowledge Distillation (KD-TEA) that compresses a Teacher model with large parameters into a small Student model through knowledge distillation. Specifically, KD-TEA transfers the dark knowledge learned from the Teacher model to the Student model. The dark knowledge can provide effective regularization to alleviate the over-fitting problem in the training process, thereby enhancing the generalization ability of the Student model, and better completing the multi-label task. In order to make the Student model learn the knowledge of the Teacher model directly, we improve the distillation loss: KD-TEA uses MSE loss instead of KL divergence loss to improve the performance of the model in multi-label tasks. Experiments on multiple datasets show that our KD-TEA framework is superior to the most advanced multi-label classification methods in both performance and efficiency.
{"title":"Target-Embedding Autoencoder With Knowledge Distillation for Multi-Label Classification","authors":"Ying Ma;Xiaoyan Zou;Qizheng Pan;Ming Yan;Guoqi Li","doi":"10.1109/TETCI.2024.3372693","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3372693","url":null,"abstract":"In the task of multi-label classification, it is a key challenge to determine the correlation between labels. One solution to this is the Target Embedding Autoencoder (TEA), but most TEA-based frameworks have numerous parameters, large models, and high complexity, which makes it difficult to deal with the problem of large-scale learning. To address this issue, we provide a Target Embedding Autoencoder framework based on Knowledge Distillation (KD-TEA) that compresses a Teacher model with large parameters into a small Student model through knowledge distillation. Specifically, KD-TEA transfers the dark knowledge learned from the Teacher model to the Student model. The dark knowledge can provide effective regularization to alleviate the over-fitting problem in the training process, thereby enhancing the generalization ability of the Student model, and better completing the multi-label task. In order to make the Student model learn the knowledge of the Teacher model directly, we improve the distillation loss: KD-TEA uses MSE loss instead of KL divergence loss to improve the performance of the model in multi-label tasks. Experiments on multiple datasets show that our KD-TEA framework is superior to the most advanced multi-label classification methods in both performance and efficiency.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":null,"pages":null},"PeriodicalIF":5.3,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141096306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2024-03-21DOI: 10.1109/TETCI.2024.3369998
Yu Xue;Kun Chen;Ferrante Neri
Generative adversarial networks (GANs) are machine learning algorithms that can efficiently generate data such as images. Although GANs are very popular, their training usually lacks stability, with the generator and discriminator networks failing to converge during the training process. To address this problem and improve the stability of GANs, in this paper, we automate the design of stable GANs architectures through a novel approach: differentiable architecture search with attention mechanisms for generative adversarial networks ( DAMGAN