检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Real-Time computing and Robotics, RCAR 2019

作者： Zuo, Guoyu Lu, Jiahao Chen, Kexin Yu, Jianjun Huang, Xiangsheng Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781728137261

This paper proposes a robotic imitation learning method which integrates the deterministic off-policy reinforcement learning and generative adversarial network. This method allows the robot to implement the grasping task rapidly by learning the reward function from the demonstration data. Firstly, the discriminator is used to learn the reward function from demonstrations, which can guide the generator to complete the robot grasping task. Secondly, the deep deterministic policy gradient method is used as the generator for learning action policy on the basis of discriminator. In particular, the demonstration data is also input into the generator to ensure its performance. Finally, three experiments on the Push and Pick- and-Place tasks are conducted in the GYM robotic environment. Results show that the learning speed of our method is much faster than the stochastic GAIL method, and it can effectively train from the demonstration data in different states of the task. The proposed method can complete the robot grasping task without environmental reward quickly and improve the stability of the training process. © 2018 IEEE

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Rain Removal from images based on Computer Vision and conditional Generative Adversarial Networks 3

Rain Removal from images based on Computer Vision and condit...

引用

2020 3rd International Conference on Advanced Algorithms and Control Engineering, ICAACE 2020

作者： Li, Yunfei Wang, Lidan Chen, Taixing Wang, Ziyuan Duan, Shukai College of Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing 400715 China

In view of the quick development of modern computer technology, more pictures of natural scenes have been collected and analyzed for application in military fields, scientific research, and computer vision fields related to object detection. However, the sharpness of these pictures collected will be affected by rain and snow, which will reduce the visibility of things in the pictures. This will not only affect the viewing, but also affect scientific research fields such as autonomous driving and video surveillance. Therefore, the research on image rain removing is very practical. An improved algorithm model named pixel-GAN is proposed in this article, which based on conditional Generative Adversarial Networks (cGAN). This new method regards the problem of removing rain from specific images as the style conversion problem. What we improved is that a VGG-16 module is added to the original network to extract perceptual loss as a new part of the loss function. We show the excellent rain-removing ability of the improved algorithm and also illustrate the reason why we add the perceptual loss. Compared with other existing methods, there is no need to set a prior model, the training speed is faster and the proposed model finally generates higher quality pictures. © Published under licence by IOP Publishing Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Toward Building Human-Like Sequential Memory Using Brain-Inspired Spiking Neural Models

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年第6期36卷 10143-10155页

作者： Malu Zhang Xiaoling Luo Jibin Wu Ammar Belatreche Siqi Cai Yang Yang Haizhou Li School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Key Laboratory of Higher Education of Sichuan Province for Enterprise Informationalization and Internet of Things Sichuan University of Science and Engineering Yibin China Department of Data Science and Artificial Intelligence Department of Computing The Hong Kong Polytechnic University Hung Hom Hong Kong Department of Computer and Information Sciences Faculty of Engineering and Environment Northumbria University Newcastle upon Tyne U.K. Department of Electrical and Computer Engineering National University of Singapore Lower Kent Ridge Rd Singapore Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong (CUHK) Shenzhen China

The brain is able to acquire and store memories of everyday experiences in real-time. It can also selectively forget information to facilitate memory updating. However, our understanding of the underlying mechanisms and coordination of these processes within the brain remains limited. However, no existing artificial intelligence models have yet matched human-level capabilities in terms of memory storage and retrieval. This study introduces a brain-inspired spiking neural model that integrates the learning and forgetting processes of sequential memory. The proposed model closely mimics the distributed and sparse temporal coding observed in the biological neural system. It employs one-shot online learning for memory formation and uses biologically plausible mechanisms of neural oscillation and phase precession to retrieve memorized sequences reliably. In addition, an active forgetting mechanism is integrated into the spiking neural model, enabling memory removal, flexibility, and updating. The proposed memory model not only enhances our understanding of human memory processes but also provides a robust framework for addressing temporal modeling tasks.

关键词： Neurons Biological system modeling Computational modeling Brain modeling Dendrites (neurons) Oscillators Neural activity Membrane potentials Encoding Adaptation models

来源：评论

学校读者我要写书评

暂无评论

A DC-Ka-Band 7-Bit Passive Attenuator with Capacitive-Compensation-Based Bandwidth Extension Technique in 55-nm CMOS

A DC-Ka-Band 7-Bit Passive Attenuator with Capacitive-Compen...

引用

作者： Zhang, Zijiang Li, Nayu Gao, Huiyan Li, Min Wang, Shaogang Kuan, Yen-Cheng Song, Chunyi Yu, Xiaopeng Gu, Qun Jane Xu, Zhiwei Ocean College Institute of Marine Electronics and Intelligent Systems Zhejiang University Zhoushan China College of Information Science and Electronic Engineering Institute of VLSI Design Zhejiang University Hangzhou China Department of Electrical and Computer Engineering University of California at Davis DavisCA United States Engineering Research Center of Oceanic Sensing Technology and Equipment Ministry of Education Zhoushan316021 China Key Laboratory of Ocean Observation-Imaging Testbed of Zhejiang Province Zhoushan316021 China International College of Semiconductor Technology National Chiao Tung University Hsinchu30010 Taiwan

This article presents a 7-bit wideband passive attenuator with low insertion loss (IL) and high attenuation accuracy in 55-nm CMOS technology. The $\pi $ -type and bridge-T-type attenuation units utilize an effective capacitive compensation technique, whose bandwidth extension mechanism is detailed in a single-unit pole-zero analysis. The matching-induced performance deterioration is investigated to minimize amplitude and phase errors at the chip level. The fabricated attenuator demonstrates a 32.4-dB attenuation range with a 0.255-dB resolution and a 3.5-8.4-dB IL from dc to 32 GHz. The measured root-mean-square (rms) amplitude and phase errors are below 0.32 dB and 5.33°, respectively. The attenuator occupies a 0.054-mm2 core area and consumes negligible power. © 1963-2012 IEEE.

关键词： Insertion losses

来源：评论

学校读者我要写书评

暂无评论

Ensemble of online sequential extreme learning machine based on cross-validation 4

Ensemble of online sequential extreme learning machine based...

引用

2020 4th International Workshop on Advanced Algorithms and Control Engineering, IWAACE 2020

作者： Wei, Liyun Wang, Lidan Li, Yunfei Duan, Shukai College of Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing400715 China

The online sequential extreme learning machine (OS-ELM) was proposed as an evolution of the Extreme learning machine (ELM) in 2006. The learning algorithm can learn data by fixing or changing the size of the chunk (a block of data). Compared with other online algorithms, it has faster training speed, and the generalization performance is better. The proposed ensemble of neural networks further demonstrates that the use of the neural network sets with multiple consensus schemes has a greater improvement over the stability of a single network. The basic idea of cross-validation is to group the original data sets, part of which is to train as the training set and the other part of which is to verify as the test set, so the algorithm can reduce the over-fitting problem of the data to a certain extent, and extract more valid information in the limited data set. In this paper, a new ensemble of online sequential extreme learning machine based on cross-validation (ENOS-ELM) is proposed. Through application of cross-validation and integration to the training stage, the accuracy of the algorithm in classification is further improved. © Published under licence by IOP Publishing Ltd.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Entropy state calculation model for integrated energy systems

引用

Applied Energy 2025年 394卷

作者： Li, Yizhe Wang, Dan Li, Jiaxi Jia, Hongjie Zhou, Tianshuo Liu, Jiawei Cheng, Hao State key laboratory of Intelligent Power Distribution Equipment and System Tianjin University Nankai District Tianjin300072 China Key Laboratory of Smart Energy & Information Technology of Tianjin Municipality Tianjin300072 China State Grid Hunan Electric Power Company Limited Economic & Technical Research Institute Changsha China Hunan Key Laboratory of Energy Internet Supply-demand and Operation Changsha China

The integration of renewable energy sources and multi-energy networks in integrated energy systems (IES) introduces significant challenges related to energy degradation, driven by exergy losses during energy conversion/transmission and uncertainty-induced usability reduction. To address these issues, this study proposes a novel entropy state calculation model and analytical framework for assessing energy quality degradation within IES. By unifying thermodynamic entropy (quantifying physical exergy loss) and information entropy (capturing uncertainty-driven energy mismatch), the model integrates physical and information systems into a cohesive entropy state framework. The methodology is validated through a case study on a real-world IES in Tianjin, China (TJBC), demonstrating its capability to reveal entropy state distributions across subsystems under varying network structures and operational modes. Results highlight the dominance of energy conversion processes (e.g., combined heat and power units) in system-wide entropy increase and the critical role of renewable uncertainty in local energy quality degradation. The proposed framework provides a unified metric for optimizing energy efficiency, guiding infrastructure planning, and mitigating energy degradation in high-renewable-penetration IES, contributing to sustainable and high-quality energy system development. © 2025 The Authors

关键词： Conversion efficiency

来源：评论

学校读者我要写书评

暂无评论

Parameter Estimation of Redundant System 15th

Parameter Estimation of Redundant System

引用

15th International Conference on intelligent information Hiding and Multimedia Signal Processing, IIH-MSP 2019, held in conjunction with the 12th International Conference on Frontiers of information technology, Applications and Tools, FITAT 2019

作者： Xie, Chao-Fan Xu, Lin Zhang, Fuquan Xu, Lu-Xiong Department of Electrical Engineering I-Shou University KaohsiungTaiwan Taiwan Electronic Information and Engineering Institute Fuqing Branch of Fujian Normal University Fuqing FuzhouFuJian China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China School of Software Beijing Institute of Technology Beijing100081 China Key Laboratory of Nondestructive Testing Fuqing Branch of Fujian Normal University Fuqing FuzhouFuJian China

ISBN: (纸本)9789811397134

The components usually are redundant and they are often connected to larger systems in series or in parallel. For large systems, the order estimation formulas of different types of components are very important which are deduced by collecting the data of overall faults. The estimation properties in the sense of probability are given. It is the asymptotic convergence of probability. Continue to improve variance estimator to achieve asymptotically minimum uniform variance estimator. This ensures the practicability of the theoretical formula. Further study uses computer simulation to estimate series and parallel systems in which the components are redundant, and it gives the specific handing framework. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Computer simulation Estimation Redundant

来源：评论

学校读者我要写书评

暂无评论

Multi-level feature fusion model-based real-time person re-identification for forensics

Multi-level feature fusion model-based real-time person re-i...

引用

作者： Wang, Shiqin Xu, Xin Liu, Lei Tian, Jing School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China Artificial Intelligence Institute Wuhan University of Science and Technology Wuhan430065 China Institute of Systems Science National University of Singapore Singapore119615 Singapore

Person forensics aims to retrieve the specified person across non-overlapping cameras. It is difficult owing to the appearance variations caused by occlusion, human pose change, background clutter, illumination variation, etc. In this scenario, current models face great challenges in extracting effective features. Recent deep learning models mainly focus on extracting representative deep features to cope with appearance variations, while handcrafted features are not fully explored. In this paper, a multi-level feature fusion model (MFFM) is designed to combine both deep features and handcrafted features in real time. MFFM is first utilized to describe person appearance. Then, local binary pattern (LBP) and histogram of oriented gradient (HOG) are extracted to cope with geometric change and illumination variance. Using LBP and HOG, 11.89% on the CUHK03, 15.30% on the Market-1501 and 8.25% on the VIPeR top-1 recognition accuracy improvement for the proposed method are achieved with only 9.66%, 4.90%, and 7.59% extra processing time. Experimental results indicate MFFM can achieve the best performance compared to the state-of-the-art models on the Market1501, CUHK03, and VIPeR datasets. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

A pathway design framework for rational low-carbon policies based on model predictive control

引用

Applied Energy 2025年 396卷

作者： Li, Daimeng Xu, Jiahe Ma, Ruifei Zhang, Xuan Wu, Qiuwei Institute of Data and Information Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen518055 China College of Electrical and Power Engineering Key Laboratory of Cleaner Intelligent Control on Coal & Electricity Ministry of Education Taiyuan University of Technology Taiyuan China

Climate change presents a profound global challenge, urging nations to transition toward low-carbon development. However, despite increasing attention, existing research lacks an integrated and dynamically adaptive framework to support rational policy design across complex low-carbon economy (LCE) systems. This study develops a comprehensive pathway design framework for LCEs, capable of identifying key drivers of economic growth and carbon emissions, and formulating optimized development trajectories under varying carbon reduction targets and policy constraints. We construct an LCE model that incorporates economic, environmental, social, energy, and policy dimensions, using hierarchical regression and an autoregressive with exogenous inputs (ARX) model to capture the multifaceted drivers of growth and emissions. To optimize development pathways, we employ Economic Model Predictive Control (EMPC) and Tracking Model Predictive Control (TMPC). Drawing on historical data from China, we establish and validate an integrated framework for low-carbon policy design. Our findings demonstrate that targeted stimulation of low-carbon consumption patterns and the strategic promotion of green technologies, such as new energy vehicles, can effectively decouple economic growth from carbon emissions—offering viable pathways to meet climate goals without compromising development objectives. The proposed framework significantly enhances our understanding of causal relationships within the LCE system, captures system feedback, supports dynamic optimization, and accommodates a wide range of policy instruments. It enables policymakers to explore alternative low-carbon policy pathways under varying constraints, facilitating more rational and adaptive resource allocation. The framework's dynamic optimization mechanism ensures continued relevance and effectiveness in the face of evolving climate targets. © 2025 Elsevier Ltd

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

A spectrum-based shortcut method for topological systems

arXiv

引用

arXiv 2023年

作者： Xu, Jian Mei, Feng Zhu, Yan-Qing College of Electronics and Information Engineering Guangdong Ocean University Guangdong Engineering Technology Research Center of Intelligent Ocean Sensor Network and Equipment guangdong Zhanjiang524088 China Guangdong Provincial Smart Ocean Sensing Networks and Equipment Engineering Technology Research Center Zhanjiang524088 China State Key Laboratory of Quantum Optics and Quantum Optics Devices Institute of Laser Spectroscopy Shanxi University Shanxi Taiyuan030006 China Quantum Science Center of Guangdong-Hong Kong-Macau Great Bay Area 3 Binlang Road Shenzhen China Guangdong-Hong Kong Joint Laboratory of Quantum Matter Department of Physics HK Institute of Quantum Science & Technology The University of Hong Kong Pokfulam Road Hong Kong

The need for fast and robust quantum state transfer is an essential element in scalable quantum information processing, leading to widespread interest in shortcuts to adiabaticity for speeding up adiabatic quantum protocols. However, shortcuts to adiabaticity for systems with more than a few levels is occasionally challenging to compute in theory and frequently difficult to implement in experiments. In this work, we develop a protocol for constructing shortcuts to adiabaticity through the multi-state Landau-Zener approach and a stricter adiabatic condition. Importantly, our protocol only requires a few pieces of information about the energy spectrum and just adjusts the evolutionary rate of the system. It means that our protocol has broad applicability to theoretical models and does not require increasing the difficulty of the experiment. As examples, we apply our protocol to state transfer in the two-level Landau-Zener model, the non-Hermitian Su-Schrieffer-Heeger (SSH) model and the topological Thouless pump model and find that it can speed up the manipulation speed while remaining robust to Hamiltonian errors. Furthermore, based on the experimental friendliness of our findings, it can potentially be extended to many-body systems, dissipation cases, or Floquet processes. Overall, the proposed shortcut protocol offers a promising avenue for enhancing the efficiency and reliability of quantum state transfer protocols. © 2023, CC0.

关键词： Topology

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：