检索结果-内蒙古大学图书馆

Learning the continuous-time optimal decision law from discrete-time rewards

National science Open 2024年第5期3卷 130-147页

作者： Ci Chen Lihua Xie Kan Xie Frank Leroy Lewis Yilu Liu Shengli Xie School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou 510006China UTA Research Institute the University of Texas at ArlingtonFort Worth 76118USA Department of Electrical Engineering and Computer Science University of TennesseeKnoxville 37996USA Oak Ridge National Laboratory Oak Ridge 37830USA Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China

The concept of reward is fundamental in reinforcement learning with a wide range of applications in natural and social *** an interpretable reward for decision-making that largely shapes the system's behavior has always been a challenge in reinforcement *** this work,we explore a discrete-time reward for reinforcement learning in continuous time and action spaces that represent many phenomena captured by applying physical *** find that the discrete-time reward leads to the extraction of the unique continuous-time decision law and improved computational efficiency by dropping the integrator operator that appears in classical results with integral *** apply this finding to solve output-feedback design problems in power *** results reveal that our approach removes an intermediate stage of identifying dynamical *** work suggests that the discrete-time reward is efficient in search of the desired decision law,which provides a computational tool to understand and modify the behavior of large-scale engineering systems using the optimal learned decision.

关键词： continuous-time state and action decision law learning discrete-time reward dynamical systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Split-net: Dual transformer encoder with splitting scene text image for script identification

引用

Pattern Recognition Letters 2025年 196卷 100-108页

作者： Ayush Roy Shivakumara Palaiahnakote Umapada Pal Cheng-Lin Liu Department of Computer Science and Engineering State University of New York Buffalo United States School of Science Engineering and Environment University of Salford Manchester United Kingdom Computer Vision and Pattern Recognition Indian Statistical Institute Kolkata India State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of the Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Script identification is vital for understanding scenes and video images. It is challenging due to high variations in physical appearance, typeface design, complex background, distortion, and significant overlap in the characteristics of different scripts. Unlike existing models, which aim to tackle the script images utilizing the scene text image as a whole, we propose to split the image into upper and lower halves to capture the intricate differences in stroke and style of various scripts. Motivated by the accomplishments of the transformer, a modified script-style-aware Mobile-Vision Transformer (M-ViT) is explored for encoding visual features of the images. To enrich the features of the transformer blocks, a novel Edge Enhanced Style Aware Channel Attention Module (EESA-CAM) has been integrated with M-ViT. Furthermore, the model fuses the features of the dual encoders (extracting features from the upper and the lower half of the images) by a dynamic weighted average procedure utilizing the gradient information of the encoders as the weights. In experiments on three standard datasets, MLe2e, CVSI2015, and SIW-13, the proposed model yielded superior performance compared to state-of-the-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Directly wireless communication of human minds via non-invasive brain-computer-metasurface platform

引用

eLight 2022年第1期2卷 132-142页

作者： Qian Ma Wei Gao Qiang Xiao Lingsong Ding Tianyi Gao Yajun Zhou Xinxin Gao Tao Yan Che Liu Ze Gu Xianghong Kong Qammer HAbbasi Lianlin Li Cheng‑Wei Qiu Yuanqing Li Tie Jun Cui Institute of Electromagnetic Space Southeast UniversityNanjing 210096China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China State Key Laboratory of Millimeter Wave Southeast UniversityNanjing 210096China Center of Intelligent Metamaterials Pazhou Laboratory Guangzhou 510330China Research Center for Brain-Computer Interface Pazhou LabGuangzhou 510330China Department of Electrical and Computer Engineering National University of SingaporeSingaporeSingapore University of Glasgow James Watt School of EngineeringGlasgow G128QQUK State Key Laboratory of Advanced Optical Communication Systems and Networks Department of ElectronicsPeking UniversityBeijing 100871China

Brain-computer interfaces(BCIs),invasive or non-invasive,have projected unparalleled vision and promise for assisting patients in need to better their interaction with the *** by the BCI-based rehabilitation technologies for nerve-system impairments and amputation,we propose an electromagnetic brain-computer-metasurface(EBCM)paradigm,regulated by human’s cognition by brain signals directly and *** experimentally show that our EBCM platform can translate human’s mind from evoked potentials of P300-based electroencephalography to digital coding information in the electromagnetic domain non-invasively,which can be further processed and transported by an information metasurface in automated and wireless *** wireless communications of the human minds are performed between two EBCM operators with accurate text ***,several other proof-of-concept mind-control schemes are presented using the same EBCM platform,exhibiting flexibly-customized capabilities of information processing and synthesis like visual-beam scanning,wave modulations,and pattern encoding.

关键词： communication computer surface

来源：评论

学校读者我要写书评

暂无评论

Entropy-Guided Reinforced Open World Active 3D Object Detection Learning

Entropy-Guided Reinforced Open World Active 3D Object Detect...

引用

Chinese automation Congress (CAC)

作者： Haozhe Zhang Liyan Ma Shihui Ying Institute of Artificial Intelligence Shanghai University Shanghai China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Computer Engineering and Science School of Mechatronic Engineering and Automation Shanghai University Shanghai China Department of Mathematics School of Science Shanghai University Shanghai China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Traditional fully annotated closed set 3D object detection methods improve model performance but are impractical in real-world settings due to the emergence of new categories and the complexity of 3D annotations. Open-World Object Detection (OWOD) addresses these issues but relies heavily on manual labeling, which is costly. This paper focuses on open world active learning and proposes an entropy-guided reinforced open world active 3D object detection (EROA). EROA regards active learning as a reinforcement learning problem tailored for open driving scenarios. We use entropy as a reward metric for efficient reinforcement learning. We also leverage knowledge from the 2D domain using object-level large-scale vision-language models to enhance sample selection. Extensive experiments evidence that the proposed EROA meets the dynamic and cost-sensitive requirements of autonomous driving, enabling real-time detection of both known and unknown objects.

关键词： Measurement Solid modeling Three-dimensional displays Active learning Object detection Reinforcement learning Entropy Real-time systems Labeling Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Defending against a laser-seeding attack on continuous-variable quantum key distribution using an improved optical power limiter

引用

Physical Review A 2023年第5期108卷 052616-052616页

作者： Qingquan Peng Binwu Gao Dongyang Wang Qin Liao Zhiyue Zuo Hai Zhong Anqi Huang Ying Guo School of Automation Central South University Changsha 410083 China Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha 410073 China College of Computer Science and Electronic Engineering Hunan University Changsha 410082 China School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 China

Laser-seeding attack enables an attacker to control the source output and eavesdrops on the key information, compromising the security of the continuous-variable (CV) quantum key distribution (QKD) system. In this paper, we suggest an improved optical power limiter (OPL) to defend against a laser-seeding attack on CV QKD systems. The proposed OPL utilizes a temperature monitor to detect Eve's attacks through temperature changes, providing an effective optical component for improving the security and reliability of the CV QKD system in practical environments, which is called an OPL-T scheme. In particular, we consider the security threats of a laser-seeding attack on two common CV QKD systems and prove their theoretical security degradation. Experiments are conducted to verify the effective OPL-T, and the results show that this defense scheme has an advantage in resisting the laser-seeding attack. Numerical simulations demonstrate the security analysis on CV QKD equipped with an OPL-T, which further confirms the effectiveness of our scheme. This work provides a practical solution for the security enhancements of continuous-variable quantum communication in practical applications.

关键词： Quantum communication Quantum communication, protocols & technology

来源：评论

学校读者我要写书评

暂无评论

PCB Surface Defect Detection Based on TPBAS-YOLOv5 3

PCB Surface Defect Detection Based on TPBAS-YOLOv5

引用

3rd IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2023

作者： Luo, Changyu Chen, Shichao Wang, Kunfeng Hu, Xiangyu Wang, Kaiyuan Han, Shuangshuang Sichuan University The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Electrical Engineering Chengdu China Chinese Academy of Sciences Beijing Huairou Academy of Pararllel Sensing The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing China Beijing University of Chemical Technology School of Information Science and Technology Beijing China Beijing Technology and Business University School of Artificial Intelligence Beijing China Sichuan University School of Electrical Engineering Chengdu China Technology Beijing School of Computer and Communication Engineering and Technology Beijing Beijing China

ISBN: (纸本)9798350318470

The use of machine vision for industrial defect detection in industrial manufacturing can effectively improve the production efficiency and production quality. Due to the complex defect background, similar defects and small defect targets of printed circuit boards(PCB), the methods of using machine vision to detect PCB defects not work well. To solve these problems, this paper proposes an algorithm model TPBAS-YOLOv5, which is based on YOLOv5 and can effectively improve the accuracy and efficiency of PCB defect detection. Firstly, to improve the accuracy of the small defect detection, a transformer module is imported into the model for obtaining the information of global variables. Secondly, the P2 detection layer is added to the neck of the model layer to obtain the more feature information of the detection target, which can also improve the detection of small targets. Thirdly, to solve the problem of missing key information of detection targets , the weighted bi-directional feature pyramid network , namely BiFPN , is imported into the new network architecture, which can realize the multi-level fusion of feature information. Furthermore, an adaptive feature fusion layer ASFF is added to the model to learn the spatial weight of feature map fusion at various scales, which can achieve better trade-off efficiency for detection *** the model fuses different parts, the size of the model has not changed almost. It can still work on the edge in the industrial field. Experimental results show that TPBAS-YOLOv5 can effectively improve recall rates to 96.1%, map@0.5 to 96.6% and map0.5:0.95 to 70.3% on open-source PCB dataset. Compared with YOLOv5, it increased by 0.9%, 1.6%, and 1.6%, respectively, and the FPS reached ***, it can realize the real-time detection of irregular defects and small target defects with high accuracy, and meet the reliability and real-time requirements of PCB defect detection in industrial scenarios. © 2023 IEEE.

关键词： Printed circuit boards

来源：评论

学校读者我要写书评

暂无评论

Skin-like cryogel electronics from suppressed-freezing tuned polymer amorphization

引用

Nature Communications 2023年第1期14卷 1-10页

作者： Zhang, Xiansheng Yan, Hongwei Xu, Chongzhi Dong, Xia Wang, Yu Fu, Aiping Li, Hao Lee, Jin Yong Zhang, Sheng Ni, Jiahua Gao, Min Wang, Jing Yu, Jinpeng Ge, Shuzhi Sam Jin, Ming Liang Wang, Lili Xia, Yanzhi State Key Laboratory of Bio-Fibers and Eco-Textiles College of Textiles and Clothing Qingdao University Qingdao 266071 China Institute for Future Shandong Key Laboratory of Industrial Control Technology School of Automation Qingdao University Qingdao 266071 China College of Materials Science and Engineering Qingdao University Qingdao 266071 China CAS Key Laboratory of Engineering Plastics Institute of Chemistry Chinese Academy of Sciences Beijing 100190 China Department of Chemistry SungKyunKwan University Suwon 16419 South Korea State Key Laboratory of Fluid Power and Mechatronic Systems College of Mechanical Engineering Zhejiang University Hangzhou 310027 China College of Biological Science and Medical Engineering Donghua University Shanghai 201620 China Institute of Environmental Engineering ETH Zürich Zürich 8093 Switzerland Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Singapore

The sole situation of semi-crystalline structure induced single performance remarkably limits the green cryogels in the application of soft devices due to uncontrolled freezing field. Here, a facile strategy for achieving multifunctionality of cryogels is proposed using total amorphization of polymer. Through precisely lowering the freezing point of precursor solutions with an antifreezing salt, the suppressed growth of ice is achieved, creating an unusually weak and homogenous aggregation of polymer chains upon freezing, thereby realizing the tunable amorphization of polymer and the coexistence of free and hydrogen bonding hydroxyl groups. Such multi-scale microstructures trigger the integrated properties of tissue-like ultrasoftness (Young’s modulus <10 kPa) yet stretchability, high transparency (~92%), self-adhesion, and instantaneous self-healing (<0.3 s) for cryogels, along with superior ionic-conductivity, antifreezing (−58 °C) and water-retention abilities, pushing the development of skin-like cryogel electronics. These concepts open an attractive branch for cryogels that adopt regulated crystallization behavior for on-demand functionalities. © 2023, Springer Nature Limited.

关键词： Gels and hydrogels Polymers

来源：评论

学校读者我要写书评

暂无评论

Flexible and Scalable Deep Dendritic Spiking Neural Networks with Multiple Nonlinear Branching

arXiv

引用

arXiv 2024年

作者： Huang, Yifan Fang, Wei Ma, Zhengyu Li, Guoqi Tian, Yonghong School of Computer Science Peking University Beijing China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China Institute of Automation Chinese Academy of Sciences Beijing China

Recent advances in spiking neural networks (SNNs) have a predominant focus on network architectures, while very little attention has been paid to the underlying neuron model. The point neuron models, a cornerstone of existing deep SNNs, pose a bottleneck on the network-level expressivity since they depict somatic dynamics only. In contrast, the multi-compartment models in neuroscience offer remarkable expressivity and biological plausibility by introducing dendritic morphology and dynamics, but remain underexplored in deep learning due to their unaffordable computational overhead and inflexibility. To combine the advantages of both sides for a flexible, efficient yet more powerful computational model, we propose the dendritic spiking neuron (DendSN) incorporating multiple dendritic branches with nonlinear dynamics. Compared to the point spiking neurons, DendSN exhibits significantly higher expressivity. DendSN's flexibility enables its seamless integration into diverse deep SNN architectures. To accelerate dendritic SNNs (DendSNNs), we parallelize dendritic state updates across time steps, and develop Triton kernels for GPU-level acceleration. As a result, we can construct various large-scale DendSNNs with depth comparable to their point SNN counterparts. Next, we comprehensively evaluate DendSNNs' performance on various demanding tasks. We first propose a novel algorithm called dendritic branch gating (DBG) for continual learning. By modulating dendritic branch strengths using an additional task context signal, DBG significantly mitigates catastrophic forgetting of DendSNNs. Moreover, DendSNNs demonstrate enhanced robustness against noise and adversarial attacks compared to point SNNs, and excel in few-shot learning settings. Our work firstly demonstrates the possibility of training bio-plausible dendritic SNNs with depths and scales comparable to traditional point SNNs, and reveals superior expressivity and robustness of reduced dendritic neuron models in deep lea

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Constrained Probabilistic Pareto Dominance for Expensive Constrained Multiobjective Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Zhang, Zhiyao Wang, Yong Sun, Guangyong Pang, Tong Tang, Ke School of Automation Central South University Changsha China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha China Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering and the Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

This paper proposes a new parameterless constraint-handling technique, named constrained probabilistic Pareto dominance (CPPD), for expensive constrained multiobjective optimization problems (CMOPs). In CPPD, when comparing two solutions, in terms of each original objective, we design a new objective for each solution, which is the negative product of two probabilities calculated based on the predicted fitness mean values and the uncertainty information provided by Kriging models: 1) the probability that this solution satisfies all constraints, denoted as PoF, and 2) the probability that this solution is better than the other on the original objective, denoted as PoB. It is evident that for each solution, PoF and PoB indicate its feasibility and its optimality on the corresponding original objective, respectively. Then, Pareto dominance based on new objectives is executed. As a result, both competitive feasible solutions and promising infeasible solutions with good diversity can be preserved by CPPD. These two kinds of solutions can help the population to exploit the located feasible parts and to explore new feasible parts, respectively. Further, based on CPPD, we develop a Pareto-based Kriging-assisted constrained multiobjective evolutionary algorithm (called PEA) to deal with expensive CMOPs with two or three objectives. Finally, PEA is generalized to solve expensive constrained many-objective optimization problems, named PEA+. The effectiveness of CPPD, PEA, and PEA+ is verified by comprehensive experiments. IEEE

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Task Offloading and Primary Node Selection in Blockchain, Digital Twin, and MEC Enabled Internet of Vehicles 100

Task Offloading and Primary Node Selection in Blockchain, Di...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Du, Jianbo Fang, Huifang Li, Shulei Du, Pengfei Kong, Ziwen Kang, Jiawen Niyato, Dusit Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security School of Communications and Information Engineering Xi'an China Xidian University School of Communications Engineering Xi'an710071 China Tianyuan Ruixin Communication Technology Co. LTD. Xi'an710071 China Xihua University Engineering Research Center of Intelligent Airground Integrated Vehicle and Traffic Control Ministry of Education Chengdu610039 China Guangdong University of Technology School of Automation China Nanyang Technological University School of Computer Science and Engineering Singapore

ISBN: (纸本)9798331517786

In this paper, we investigate the safe task offloading and primary node selection in blockchain, digital twin (DT) and Multi-access Edge Computing (MEC) enabled Internet of Vehicles (IoV). Edge servers centers provide computing power for task processing for Mobile Vehicles (MVs), while blockchain can provide security guarantees for MVs during task offloading. Based on the above system, we propose a joint optimization scheme for vehicle task offloading decision and the Practical Byzantine Fault Tolerance (PBFT) consensus process. Due to the large number of optimization variables and constraints, the problem becomes more complex. Traditional convex optimization and dynamic programming methods are difficult to effectively solve this problem. To address this issue, we propose a deep reinforcement learning based algorithm that utilizes Proximal Policy Optimization (PPO). The experimental results show that the algorithm proposed in this paper outperforms the benchmark algorithm in terms of convergence and other aspects. © 2024 IEEE.

关键词： Dynamic programming

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：