检索结果-内蒙古大学图书馆

Bi-stage learning differential evolution for multimodal optimization problems

Swarm and Evolutionary Computation 2025年 96卷

作者： Wang, Chang-Long Wang, Zi-Jia Huang, Yi-Biao Duan, Dan-Ting Zhan, Zhi-Hui Kwong, Sam Zhang, Jun School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China Hanyang University ERICA Korea Republic of College of Artificial Intelligence Nankai University Tianjin330350 China Data Science Lingnan University Hong Kong

Multimodal optimization problems (MMOPs) require the identification of multiple optimal solutions for decision makers. To address MMOPs, algorithms must enhance the population diversity to find more global optimal regions while simultaneously refine the solution accuracy on each optimum. Therefore, in this paper, we introduces a bi-stage learning differential evolution (BLDE) with two learning stages: the pre-learning Find stage and the post-learning Refine stage. First of all, a bi-stage learning niching technique (BLNT) is proposed, which forms wide niches for full exploration in the pre-learning Find stage, while adaptively adjusts the niche radius for each individual to refine its corresponding solution accuracy in the post-learning Refine stage. Subsequently, a bi-stage learning mutation strategy (BLMS) is developed, enabling each individual to adaptively choose the suitable mutation strategy, achieving effective guidance for evolution. Moreover, different from other DE-based multimodal algorithms with only one selection operator, a bi-stage learning selection strategy (BLSS) is proposed to determine the suitable selection operator in different learning stages and preserve the promising individuals. The widely-used multimodal benchmark functions from CEC2015 competition are employed to evaluate the performance of BLDE. The results demonstrate that BLDE generally outperforms or at least comparable with other state-of-the-art multimodal algorithms, including the champion of CEC2015 competition. Moreover, BLDE is further applied to the real-world multimodal nonlinear equation system (NES) problems to demonstrate its applicability. © 2025 Elsevier B.V.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Provable Sim-to-real Transfer in Continuous Domain with Partial Observations

arXiv

引用

arXiv 2022年

作者： Hu, Jiachen Zhong, Han Jin, Chi Wang, Liwei School of Computer Science Peking University China Center for Data Science Peking University China Department of Electrical and Computer Engineering Princeton University United States National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Center for Data Science Peking University Beijing Institute of Big Data Research China

Sim-to-real transfer trains RL agents in the simulated environments and then deploys them in the real world. Sim-to-real transfer has been widely used in practice because it is often cheaper, safer and much faster to collect samples in simulation than in the real world. Despite the empirical success of the sim-to-real transfer, its theoretical foundation is much less understood. In this paper, we study the sim-to-real transfer in continuous domain with partial observations, where the simulated environments and real-world environments are modeled by linear quadratic Gaussian (LQG) systems. We show that a popular robust adversarial training algorithm is capable of learning a policy from the simulated environment that is competitive to the optimal policy in the real-world environment. To achieve our results, we design a new algorithm for infinite-horizon average-cost LQGs and establish a regret bound that depends on the intrinsic complexity of the model class. Our algorithm crucially relies on a novel history clipping scheme, which might be of independent interest. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Beyond K-Means++: Towards Better Cluster Exploration with Geometrical Information

SSRN

引用

SSRN 2023年

作者： Ping, Yuan Li, Huina Hao, Bin Guo, Chun Wang, Baocang School of Information Engineering Xuchang University Xuchang461000 China Shenzhen Here Data Technology Co. LTD Shenzhen518000 China College of Computer Science and Technology Guizhou University Guiyang550025 China

Despite remarkable efficiency, k-means and its variants suffer from a strong dependence on the prior knowledge K and the hypothesis of circle-like pattern. This causes algorithms to divide the input space instead of discovering non-predetermined data patterns. Thus, we propose a beyond k-means++ which infers and utilizes the explicit clusters by emphasizing the local geometrical information for better cluster exploration}. To avoid the K dependence, a novel framework of iterative division and aggregation (IDA) over k-means++ is presented. It begins with any , then increases and reduces K along with the procedure of clusters' division and aggregation, respectively. To break through the circle-like pattern limitation, we introduce a reasonability checking strategy (RCS) for cluster division. Given local geometrical information, RCS achieves arbitrary cluster shape support by rejecting edge patterns with distinguished convergence direction and merging adjacent clusters with pseudo-edge patterns. Furthermore, we design an edge shrinkage strategy (ESS). Taking edge patterns as the cluster prototype, it benefits accuracy by effectively avoiding representability reduction due to irregular distribution. To compensate for the loss of efficiency, a near maximin and random sampling algorithm is suggested for large-scale data with high dimensionality. Experimental results confirm that beyond k-means++ is featured by handling arbitrary cluster shapes with remarkable accuracy. © 2023, The Authors. All rights reserved.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fault Diagnosis of Rotating Machine Via Expansive Dual-Attention Fusion Transformer Enhanced by Semi-Supervisedlearning

SSRN

引用

SSRN 2023年

作者： Liu, Sijie Li, Jin Zhou, Nan Chen, Geng Lu, Kuan Wu, Yafeng School of Power and Energy Northwestern Polytechnical University Shaanxi Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi’an710129 China School of Mechanics Civil Engineering and Architecture Northwestern Polytechnical University Two Shaanxi Xi’an710129 China

The precise identification of faults is an essential component in the effective operation and maintenance of rotating machinery(RM). The growing adoption of deep learning can possibly be attributed to the abundance of automatically generated monitoring data and its strong capacity to effectively learn and detect errors. The efficacy of deep learning techniques is consistently high when a limited amount of fault data is available or when a two-stage diagnostic approach is utilized, including manual feature extraction followed by fault classification. To address these challenges, we offer a novel architecture called Expansive Dual-Attention Fusion Transformer (EDAF-Transformer). This structure combines Convolutional Attention Neural Network with Transfomer, and it is specifically designed to handle limited labeled data. Additionally, we boost the performance of EDAF-Transformer by the implementation of a semi-supervised approach. First, we introduce a primary theory transformer. Then Expansive Dual-branch Attention Module (EDAEM) consists of the Expansive multi-scale channel attention (EMSCA) with multi-scale learning, which is designed to expand the receptive field and fused multi-scale information. Therefore, the EDAFM and TwinSparse Self-Attneiton Fusion Transformer encoder Module are integrated in a cascaded manner to construct a deep network for intelligent fault diagnosis. Moreover, an uncertainty self-training semisupervised strategy based on a balanced unlabeled sample selection is implemented, which could further enhance the generalization of EDAF-Transformer and achieve a better performance. The proposed semi-EDAF-Transformer fault diagnosis method has been extensively tested on publicly available motor bearing data as well as a specially arranged transmission shaft dataset. These experiments demonstrate that this method outperforms other intelligent fault diagnosis methods. © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "A federated learning approach for classifying chest diseases from chest X-ray images" [Biomed. Signal Process. Control 100(Part A) (2025) 107107] (Biomedical Signal Processing and Control (2025) 100(PA), (S1746809424011650), (10.1016/***.2024.107107))

引用

Biomedical Signal Processing and Control 2025年 106卷

作者： Satapathy, Sandeep Kumar Cho, Sung-Bae Mishra, Shruti Sah, Sweeti Kamaldeep Mohanty, Sachi Nandan Dinesh, J. Department of Computer Science Yonsei University 50 Yonsei-ro Sudaemoon-gu Seoul03722 Korea Republic of Centre for Advanced Data Science Vellore Institute of Technology Tamil Nadu Chennai600127 India Department of Computer Engineering National Institute of Technology Haryana Kurukshetra136119 India Department of Media Engineering National Institute of Technical Teachers Training and Research Chandigarh160019 India VIT-AP University Andhra Pradesh Amaravati522237 India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

The authors regret the omission of Mr. Dinesh J, school of computer Science and engineering, Vellore Institute of Technology, Chennai, who initially undertook this work as a capstone project under the supervision of Dr. Sandeep Kumar Satapathy. His contributions in the early stages were instrumental in shaping the direction of this study. We sincerely acknowledge his efforts and appreciate his role in the initial development of this work. The correct order of authors list have been updated as above. The authors would like to apologise for any inconvenience caused. © 2024 Elsevier Ltd

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Routing Protocol Design to Perform Cost Efficient data Communication over Wireless Sensor Networks

An Enhanced Routing Protocol Design to Perform Cost Efficien...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Dattatraya Arun Jadhav Sajja Suneel M. Amina Begum Meghana Harsh Ghogare Madhan Sekhar Murri Parashuram Shankar Vadar Electronic and telecommunication department Keystone school of Engineering pune Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Department of ECE Oxford College of Engineering Venmani Tamilnadu India byteXL-Department of Computer Science and Engineering Parul University Vadodara Department of Management Studies Vignan’s Institute of Information Technology(A) AP India Yashwantrao Chavan School of Rural Development Shivaji University Kolhapur Maharashtra India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

This research introduces a groundbreaking approach to address the challenges of cost-efficient data communication in Wireless Sensor Networks (WSNs) through the development of a novel routing protocol named Cost-Efficient Enhanced Routing Protocol (CEERP). WSNs, characterized by resource-constrained sensor nodes and dynamic environmental conditions, necessitate innovative routing strategies to optimize energy consumption and enhance overall network performance. CEERP leverages a sophisticated methodology that integrates Energy Consumption Modeling, Adaptive Routing Decisions, alongside Optimization and Fine-Tuning. The Energy Consumption Modeling method systematically analyzes various factors influencing energy dynamics in sensor nodes, facilitating the creation of accurate mathematical models. These models inform CEERP’s routing algorithm, enabling intelligent decisions based on predicted energy consumption patterns. The protocol adapts dynamically to real-time variations in network conditions, ensuring responsiveness to changing environmental factors. Implementation and Simulation validate CEERP’s performance in diverse scenarios, while Optimization and Fine-Tuning finetune parameters for optimal efficiency. Security and reliability measures are integrated to safeguard data integrity. The research concludes with a comprehensive evaluation of CEERP’s effectiveness, positioning it as a promising solution for achieving cost-efficient and reliable data communication in WSNs. The proposed methodology and CEERP contribute to the advancement of routing protocols for WSNs, offering a holistic and adaptive approach to address the unique challenges posed by resource-constrained environments.

关键词： Wireless sensor networks Energy consumption Adaptation models Routing Routing protocols Mathematical models data communication

来源：评论

学校读者我要写书评

暂无评论

Policy Representation via Diffusion Probability Model for Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Yang, Long Huang, Zhixiong Lei, Fenghao Zhong, Yucun Yang, Yiming Fang, Cong Wen, Shiting Zhou, Binbin Lin, Zhouchen School of Artificial Intelligence Peking University Beijing China College of Computer Science and Technology Zhejiang University China MOE Frontiers Science Center for Brain and Brain-Machine Integration College of Computer Science Zhejiang University China Institute of Automation Chinese Academy of Sciences Beijing China School of Computer and Data Engineering NingboTech University China College of Computer Science and Technology Hangzhou City University China

Popular reinforcement learning (RL) algorithms tend to produce a unimodal policy distribution, which weakens the expressiveness of complicated policy and decays the ability of exploration. The diffusion probability model is powerful to learn complicated multimodal distributions, which has shown promising and potential applications to RL. In this paper, we formally build a theoretical foundation of policy representation via the diffusion probability model and provide practical implementations of diffusion policy for online model-free RL. Concretely, we character diffusion policy as a stochastic process induced by stochastic differential equations, which is a new approach to representing a policy. Then we present a convergence guarantee for diffusion policy, which provides a theory to understand the multimodality of diffusion policy. Furthermore, we propose the DIPO, which implements model-free online RL with DIffusion POlicy. To the best of our knowledge, DIPO is the first algorithm to solve model-free online RL problems with the diffusion model. Finally, extensive empirical results show the effectiveness and superiority of DIPO on the standard continuous control Mujoco benchmark. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Type-Representation Enhanced Event Detection via Structure Encoder

Type-Representation Enhanced Event Detection via Structure E...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Yuming Feng Linmeng Huang Haozhe Liang Xiaolong Jin Saiping Guan Jiafeng Guo School of Computer Science and Technology University of Chinese Academy of Sciences Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Institute of Systems Engineering Academy of Military Science Beijing

Event detection, aiming to detect whether a sentence contains the type of events of interest, is one of the important tasks in information Extraction. There exist many methods for event detection, which usually treat event detection as a classification problem. These existing methods suffer from the imbalanced training data of different event types. To relieve this problem, this paper proposes a new Type-Representation-Enhanced Event Detection (TREED) method, which introduce hierarchical event type representations to enhance classification accuracy. Specifically, TREED first models the hierarchical relationship among event types in the dataset; Next, upon interactions between the representations of trigger words and event types, it obtains the new representations of trigger words integrating event type information. Finally, TREED classifies the events based on the obtained more accurate trigger word representations. Experimental results on a commonly used benchmark dataset, ACE-2005, demonstrate that the proposed model can improve both accuracy and recall of the event detection task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding Oversquashing in GNNs through the Lens of Effective Resistance

arXiv

引用

arXiv 2023年

作者： Black, Mitchell Wan, Zhengchao Nayyeri, Amir Wang, Yusu School of Electrical Engineering and Computer Science Oregon State University CorvallisOR United States Halıcıoǧlu Data Science Institute University of California San Diego San DiegoCA United States

Message passing graph neural networks (GNNs) are a popular learning architectures for graph-structured data. However, one problem GNNs experience is oversquashing, where a GNN has difficulty sending information between distant nodes. Understanding and mitigating oversquashing has recently received significant attention from the research community. In this paper, we continue this line of work by analyzing oversquashing through the lens of the effective resistance between nodes in the input graph. Effective resistance intuitively captures the "strength" of connection between two nodes by paths in the graph, and has a rich literature spanning many areas of graph theory. We propose to use total effective resistance as a bound of the total amount of oversquashing in a graph and provide theoretical justification for its use. We further develop an algorithm to identify edges to be added to an input graph to minimize the total effective resistance, thereby alleviating oversquashing. We provide empirical evidence of the effectiveness of our total effective resistance based rewiring strategies for improving the performance of GNNs. © 2023, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Aerial Collaborative Secure Communication Optimization via Generative Diffusion Model-enabled Deep Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Chuang Sun, Geng Li, Jiahui Wu, Qingqing Wang, Jiacheng Niyato, Dusit Liu, Yuanwei The College of Computer Science and Technology Jilin University Changchun130012 China The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China The College of Computer Science and Technology Jilin University Changchun130012 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore The Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China The College of Computing and Data Science Nanyang Technological University 639798 Singapore The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom

Due to flexibility and low-cost, unmanned aerial vehicles (UAVs) are increasingly crucial for enhancing coverage and functionality of wireless networks. However, incorporating UAVs into next-generation wireless communication systems poses significant challenges, particularly in sustaining high-rate and long-range secure communications against eavesdropping attacks. In this work, we consider a UAV swarm-enabled secure surveillance network system, where a UAV swarm forms a virtual antenna array to transmit sensitive surveillance data to a remote base station (RBS) via collaborative beamforming (CB) so as to resist mobile eavesdroppers. Specifically, we formulate an aerial secure communication and energy efficiency multi-objective optimization problem (ASCEE-MOP) to maximize the secrecy rate of the system and to minimize the flight energy consumption of the UAV swarm. To address the non-convex, NP-hard and dynamic ASCEE-MOP, we propose a generative diffusion model-enabled twin delayed deep deterministic policy gradient (GDMTD3) method. Specifically, GDMTD3 leverages an innovative application of diffusion models to determine optimal excitation current weights and position decisions of UAVs. The diffusion models can better capture the complex dynamics and the trade-off of the ASCEE-MOP, thereby yielding promising solutions. Simulation results highlight the superior performance of the proposed approach compared with traditional deployment strategies and some other deep reinforcement learning (DRL) benchmarks. Moreover, performance analysis under various parameter settings of GDMTD3 and different numbers of UAVs verifies the robustness of the proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：