检索结果-内蒙古大学图书馆

Neural networks : the official journal of the International Neural Network Society 2016年 79卷 117-27页

作者： Peng Liu Zhigang Zeng Jun Wang School of Automation Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074 China. Electronic address: liupengjz@***. Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074 China. Electronic address: hustzgzeng@***. Department of Computer Science College of Science and Engineering City University of Hong Kong Kowloon Tong Hong Kong. Electronic address: jwang.cs@cityu.edu.hk.

This paper addresses the multistability for a general class of recurrent neural networks with time-varying delays. Without assuming the linearity or monotonicity of the activation functions, several new sufficient conditions are obtained to ensure the existence of (2K+1)(n) equilibrium points and the exponential stability of (K+1)(n) equilibrium points among them for n-neuron neural networks, where K is a positive integer and determined by the type of activation functions and the parameters of neural network jointly. The obtained results generalize and improve the earlier publications. Furthermore, the attraction basins of these exponentially stable equilibrium points are estimated. It is revealed that the attraction basins of these exponentially stable equilibrium points can be larger than their originally partitioned subsets. Finally, three illustrative numerical examples show the effectiveness of theoretical results.

关键词： Cohen–Grossberg neural networks Multistability Non-monotonic activation functions Time-varying delays

Robotic Electrospinning Actuated by Non-Circular Joint Continuum Manipulator for Endoluminal Therapy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Zicong Lou, Chuqian Jin, Zhu Huang, Shaoping Liu, Ning Zou, Yun Kovac, Mirko Gao, Anzhu Yang, Guang-Zhong Institute of Medical Robotics Department of Bioengineering Shanghai Jiao Tong University Shanghai200240 China Imperial College London Empa Swiss Federal Laboratories for Materials Science and Technology Limited Hong Kong999077 Hong Kong Aerial Robotics Laboratory Imperial College London LondonSW7 2AZ United Kingdom Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

Electrospinning has exhibited excellent benefits to treat the trauma for tissue engineering due to its produced micro/nano fibrous structure. It can effectively adhere to the tissue surface for long-term continuous therapy. This paper develops a robotic electrospinning platform for endoluminal therapy. The platform consists of a continuum manipulator, the electrospinning device, and the actuation unit. The continuum manipulator has two bending sections to facilitate the steering of the tip needle for a controllable spinning direction. Non-circular joint profile is carefully designed to enable a constant length of the centreline of a continuum manipulator for stable fluid transmission inside it. Experiments are performed on a bronchus phantom, and the steering ability and bending limitation in each direction are also investigated. The endoluminal electrospinning is also fulfilled by a trajectory following and points targeting experiments. The effective adhesive area of the produced fibre is also illustrated. The proposed robotic electrospinning shows its feasibility to precisely spread more therapeutic drug to construct fibrous structure for potential endoluminal treatments. © 2021, CC BY-NC-SA.

关键词： Electrospinning

AIM 2024 Challenge on Video Saliency Prediction: Methods and Results

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhan, Gen Yang, Li Tang, Yunlong Liao, Yiting Lin, Jiongzhi Huang, Baitao Moradi, Morteza Moradi, Mohammad Rundo, Francesco Spampinato, Concetto Borji, Ali Palazzo, Simone Zhu, Yuxin Sun, Yinan Duan, Huiyu Cao, Yuqin Jia, Ziheng Hu, Qiang Min, Xiongkuo Zhai, Guangtao Fang, Hao Cong, Runmin Lu, Xiankai Zhou, Xiaofei Zhang, Wei Zhao, Chunyu Mu, Wentao Deng, Tao Tavakoli, Hamed R. Moskalenko, Andrey Bryncev, Alexey Vatolin, Dmitry Timofte, Radu ByteDance China ByteDance United States University of Rochester United States College of Electronic and Information Engineering Shenzhen University China Shenzhen Key Laboratory of Digital Creative Technology China Guangdong Key Laboratory of Intelligent Information Processing China University of Catania Italy STMicrolectronics ADG Central R&D Italy Quintic AI San Francisco United States Shanghai Jiao Tong University China School of Control Science and Engineering Shandong University China School of Software Shandong University China School of Automation Hangzhou Dianzi University China School of Information Science and Technology Southwest Jiaotong University China Nokia Technologies Finland Lomonosov Moscow State University Russia AIRI Moscow Russia MSU Institute for Artificial Intelligence Russia University of Würzburg Germany

This paper reviews the Challenge on Video Saliency Prediction at AIM 2024. The goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences. Saliency maps are widely exploited in various applications, including video compression, quality assessment, visual perception studies, the advertising industry, etc. For this competition, a previously unused large-scale audio-visual mouse saliency (AViMoS) dataset of 1500 videos with more than 70 observers per video was collected using crowdsourced mouse tracking. The dataset collection methodology has been validated using conventional eye-tracking data and has shown high consistency. Over 30 teams registered in the challenge, and there are 7 teams that submitted the results in the final phase. The final phase solutions were tested and ranked by commonly used quality metrics on a private test subset. The results of this evaluation and the descriptions of the solutions are presented in this report. All data, including the private test subset, is made publicly available on the challenge homepage - https://***/challenges/***. © 2024, CC BY.

关键词： Video analysis

Fast and accurate single-image depth estimation on mobile devices, mobile AI 2021 challenge: Report

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ignatov, Andrey Malivenko, Grigory Plowman, David Shukla, Samarth Timofte, Radu Zhang, Ziyu Wang, Yicheng Huang, Zilong Luo, Guozhong Yu, Gang Fu, Bin Wang, Yiran Li, Xingyi Shi, Min Xian, Ke Cao, Zhiguo Du, Jin-Hua Wu, Pei-Lin Ge, Chao Yao, Jiaoyang Tu, Fangwen Li, Bo Yoo, Jung Eun Seo, Kwanggyoon Xu, Jialei Li, Zhenyu Liu, Xianming Jiang, Junjun Chen, Wei-Chi Joya, Shayan Fan, Huanhuan Kang, Zhaobing Li, Ang Feng, Tianpeng Liu, Yang Sheng, Chuannan Yin, Jian Benavides, Fausto T. Computer Vision Lab ETH Zurich Switzerland Ltd AI Witchlabs Switzerland Tencent GY-Lab China Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Nanjing Artificial Intelligence Chip Research Institute of Automation Chinese Academy of Sciences China Black Sesame Technologies Inc. Singapore Singapore Visual Media Lab KAIST Korea Republic of Harbin Institute of Technology China Peng Cheng Laboratory China Multimedia and Computer Vision Laboratory National Cheng Kung University Taiwan Samsung Research UK United Kingdom OPPO Research Institute China ETH Zurich Switzerland

Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms. For this, the participants were provided with a new large-scale dataset containing RGB-depth image pairs obtained with a dedicated stereo ZED camera producing high-resolution depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the popular Raspberry Pi 4 platform with a mobile ARM-based Broadcom chipset. The proposed solutions can generate VGA resolution depth maps at up to 10 FPS on the Raspberry Pi 4 while achieving high fidelity results, and are compatible with any Android or Linux-based mobile devices. A detailed description of all models developed in the challenge is provided in this paper. Copyright © 2021, The Authors. All rights reserved.

关键词： Computer operating systems

Deep learning models for EEG-based rapid serial visual presentation event classification

学校读者我要写书评

暂无评论

Journal of information Hiding and Multimedia Signal processing 2018年第1期9卷 177-187页

作者： Zhang, Fu-Quan Mao, Zi-Jing Huang, Yu-Fei Xu, Lin Ding, Gang Yi Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China School of Software Beijing Institute of Technology Room A9-301 Juyuan Jinshan Jiyuan Fuzhou350008 China Department of Electronic Engineering University of Texas at San Antonio One UTSA Circle San Antonio Arrow Oaks 126 San AntonioTX78249 United States Innovative Information Industry Research Institute Fujian Normal University Fuqing Brunch of Fujian Normal University Campus County 1 Longjiang Road FuqingFuzhou350300 China School of Software Beijing Institute of Technology Room 611 Software Building 5 South Zhongguancun Street Haidian Beijing100081 China

We consider deep learning (DL) for event classification using electroencephalogram (EEG) measurements of brain activities. We proposed HDNN or hierarchical deep neural network, and CNN4EEG, a new convolution neural network (CNN). Both DL models are designed to improve the representation of spatial and local temporal correlations inherent in EEG data. These models were tested for image target prediction in a time-locked rapid serial visual presentation (RSVP) experiment. The performances were compared with the state-of-the-art RSVP classification algorithms including HDCA and XDAWN and with other popular machine learning algorithms. The results show that global spatial local temporal CNN (CNN4EEG) achieved a 13% improvement over the best competing non-DL algorithm and a 9% improvement over canonical CNN for image processing, and a 6% over deep neural network (DNN). Our results suggest that the unique design of temporal and spatial filters in CNN4EEG can improve the representation of EEG data, hence the prediction performance. © 2018, Ubiquitous International. All rights reserved.

关键词： Deep neural networks

Duplicate checking Strategies for Selecting Topics for Graduation Thesis Based on Maximum Public Sequence

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental Science 2019年第3期267卷

作者： Guorui Yu Li Huang Jiewen Sun Shangchun Liao School of Computer Science and Technology Wuhan University of Science and Technology phone:*** Intelligent Information Processing and Hubei Real-time Industrial Systems Laboratory. Key Laboratory of Metallurgical Equipment and Control Technology Wuhan University of Science and Technology Ministry of Education.

The system is based on the undergraduate thesis management system as the practice platform, focusing on the realization of the thesis topic check function. The current check-up detection system is based on the entire contents of the query, and does not meet the requirements for an undergraduate thesis query. According to the characteristics of the thesis, the system first divides the keywords into the topic, selects the irrelevant parts, then removes the irrelevant words, and finally checks the keywords in the topic, and realizes the efficient and accurate check for inspection.

关键词：

Strategy evolution on dynamic networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Su, Qi McAvoy, Alex Plotkin, Joshua B. Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China School of Data Science and Society University of North Carolina at Chapel Hill Chapel HillNC27599 United States Department of Mathematics University of North Carolina at Chapel Hill Chapel HillNC27599 United States Department of Biology University of Pennsylvania PhiladelphiaPA19104 United States Center for Mathematical Biology University of Pennsylvania PhiladelphiaPA19104 United States

Models of strategy evolution on static networks help us understand how population structure can promote the spread of traits like cooperation. One key mechanism is the formation of altruistic spatial clusters, where neighbors of a cooperative individual are likely to reciprocate, which protects prosocial traits from exploitation. But most real-world interactions are ephemeral and subject to exogenous restructuring, so that social networks change over time. Strategic behavior on dynamic networks is difficult to study, and much less is known about the resulting evolutionary dynamics. Here, we provide an analytical treatment of cooperation on dynamic networks, allowing for arbitrary spatial and temporal heterogeneity. We show that transitions among a large class of network structures can favor the spread of cooperation, even if each individual social network would inhibit cooperation when static. Furthermore, we show that spatial heterogeneity tends to inhibit cooperation, whereas temporal heterogeneity tends to promote it. Dynamic networks can have profound effects on the evolution of prosocial traits, even when individuals have no agency over network structures. © 2023, CC BY.

关键词：

Research on SDN Multi controller Deployment based on K-means++

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2020年第1期1606卷

作者： Li Yue Chen Junyan Liang Chuxin Lei Xiaochun School of computer and information security Guilin University of Electronic Technology Guilin 541004 China Guangxi cloud computing and big data collaborative innovation center Guilin 541001 China Guangxi key laboratory of image and graphic intelligent processing Guilin 541004 China

In large-scale SDN network, a single centralized controller can not meet the demand, and multiple controllers are needed to deal with the problem, which leads to the problem of multi control balanced deployment. In this paper, the topology of SDN switches and links is known. The main research contents are as follows: the mathematical model of SDN multi controller deployment is established, and the appropriate network topology is selected and the multi controller deployment problem is solved. In the research, the number of controllers needed in the network and the switches managed by each controller is determined by the algorithm results, and the mapping relationship between controllers and switches is established. By analyzing the deployment results of the same network topology under different algorithms, the influence of different clustering algorithms on the experimental results is obtained. At the same time, the better deployment experiment results are simulated.

关键词：

An image Denoising Method Based on Deep Residual GAN

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2020年第3期1550卷

作者： Ziyuan Wang Lidan Wang Shukai Duan Yunfei Li Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing 400715 China Schoolof Electronic and information engineering Southwest University Chongqing400715 China College of Artificiall Intelligence Southwest University Chongqing 400715 China Braininspired Computing & Intelligent Control of Chongqing Key Lab Chongqing 400715 China National & Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing 400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing 400715 China

As people come into contact with image data more often, high quality and clear images attract more attention. Many methods have been proposed to deal with image noise problem including deep learning (DL). However most of them is lack of capability when customers want more perceptual details of the image without information loss. In this paper, a deep residual network based on generative adversarial (GAN) network was proposed to complete the image denoising mission. Firstly, a generative-adversarial network structure based on residual blocks was designed. Secondly, a refined loss function was given to train the GAN network. The well designed loss function can help the generated image to be very close to the clear counterpart (ground truth) while enhancing more details in colours and brightness. Finally, extensive experiments show that our network is not only convincing for images denoising, but also effective for other image process tasks, such as image defogging, medical CT denoising etc., presenting impressive and competitive effects.

关键词：

Bayesian network for motivation classification in creative computation

学校读者我要写书评

暂无评论

Journal of information Hiding and Multimedia Signal processing 2017年第4期8卷 888-902页

作者： Zhang, Fuquan Ding, Gangyi Xu, Lin Zheng, Xiaoyan School of Software Beijing Institute of Technology Room A9#301 Jiyuan Juyuan Jinshan Fuzhou350008 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Room A9#301 Jiyuan Juyuan Jinshan Fuzhou350008 China School of Software Beijing Institute of Technology Room A9#301 Jiyuan Juyuan Jinshan Fuzhou350008 China Innovative Information Industry Research Institute Fujian Normal University Fuqing Brunch of Fujian Normal University Campus County 1# Longjiang Road FuqingFuzhou350300 China Foreign Language Institute Minjiang University Foreign Language Institute of Minjiang University Xiyuan Gong Road 200# Shangjie Minhou Fuzhou350121 China

This paper used clustered embedding features and language ontology to simulate the process of creative idea generation from human brain. Conventional creative idea generation used predefined motivation words. This study proposed a new motivation classification algorithm based on Bayesian network. We first applied the crawler algorithm to obtain motivation vocabulary corpus information. Bayesian network is applied to filter motivation words and project to a vector space for building information clustering model. Then we applied ontology theory to generating the phrase and sentence structure. By creative computing we try to discover how the idea comes from step by step and display the emergence, self-organization, self- coordination of idea creation process of human brain. From this paper, you will see the process in five steps from blurry motivations to clear creative ideas. © 2017, Ubiquitous International. All rights reserved.

关键词： Bayesian networks