检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, Shengjun Dong, Yunlong Xie, Dong Yao, Lisha Bailey, Colleen P. Fu, Shengli OSCAR Laboratory Department of Electrical Engineering University of North Texas DentonTX76207 United States School of Artificial Intelligence and Automation The MOE Key Laboratory of Image Processing and Intelligent Control The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China

This paper investigates the stochastic distributed nonconvex optimization problem of minimizing a global cost function formed by the summation of n local cost functions. We solve such a problem by involving zeroth-order (ZO) information exchange. In this paper, we propose a ZO distributed primal–dual coordinate method (ZODIAC) to solve the stochastic optimization problem. Agents approximate their own local stochastic ZO oracle along with coordinates with an adaptive smoothing parameter. We show that the proposed algorithm achieves the convergence rate of O(√p/√T) for general nonconvex cost functions. We demonstrate the efficiency of proposed algorithms through a numerical example in comparison with the existing state-of-the-art centralized and distributed ZO algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

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

Research on SDN Multi Controller Deployment based on K-means...

引用

2020 International Conference on 5G Mobile Communication and information Science, MCIS-5G 2020

作者： Yue, Li Junyan, Chen Chuxin, Liang Xiaochun, Lei School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Cloud Computing and Big Data Collaborative Innovation Center Guilin541001 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 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. © 2020 Published under licence by IOP Publishing Ltd.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Fully Circuit Implementation of a two-layer Memristive Neural Network for Pattern Recognition

Fully Circuit Implementation of a two-layer Memristive Neura...

引用

International Conference on information Science and Technology (ICIST)

作者： Mian Li Xiaoping Wang Zhanfei Chen School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665412667;9781665429412

In this paper, a fully circuit implementation of Memristive Neural Network (MNN) is proposed. The forward calculation of the network is based on winner-take-all (WTA) mechanism. The weight updating is achieved through the difference of pre-spike and post-spike, which is more close to the biological weight adjustment mechanism. The network is implemented in a full circuit without additional control units. The designed circuit consists of four modules. The memristive crossbar array module with one-memristor (1M) unit structure can effectively calculate the vector-matrix multiplication with only one step. The switch S is replaced by the transistor in the designed leaky-integrate-and-fire (LIF) module, which can control the integration and leakage of the membrane voltage and realize the lateral inhibition between output neurons. Connecting the integrated monostable trigger and the difference circuit, the post-spike generating module can output the required post-spike. The signal switch module realizes the switching of signals connected to memristors by using voltage-controlled switches. The combination of two modules validly realizes weight updating. The functions of four modules are verified separately. We performed a simulation experiment of 5×3 pixels image classification based on the designed circuit in PSPICE. The circuit output results and the high classification accuracy prove the circuit can be effectively applied in pattern recognition. The noise experiment shows the robustness of the designed circuit.

关键词： Training Neurons Switches Robustness Pattern recognition Integrated circuit modeling Task analysis

来源：评论

学校读者我要写书评

暂无评论

Distributed Online Optimization for Charging and Discharging of Plug-in Electric Vehicles

Distributed Online Optimization for Charging and Discharging...

引用

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Haiming Xiong Ming Chi Zhi-Wei Liu Dandan Hu Liang-Liang Zhu Cheng Jiang Jun-Ping Gui Yao Rao School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan China School of Management South-Central University for Nationalities Wuhan China Nari Group Corporation State Grid Electric Power Research Institute Nanjing China State Grid Electric Power Research Institute Wuhan Efficiency Evaluation Company Limited Wuhan China

The increasing number of uncoordinated charging and discharging for plug-in electric vehicles (PEVs) poses new challenges to the operation of the distribution network. We introduce a dynamic price mechanism so that charging at peak load will lead to an increase in cost. Then, a distributed online charging and discharging scheduling scheme for PEVs based on the dynamic price mechanism is proposed, considering the minimization of charging cost and battery degradation cost. Unlike most of the existing studies that require the future information of PEVs to schedule charging, the proposed algorithm can solve the scheduling problem for PEVs by taking advantage of a distributed alternating direction method of multipliers (ADMM). Simulation results demonstrate the effectiveness and correctness of the proposed scheduling scheme.

关键词： Plug-in electric vehicles Schedules Costs Heuristic algorithms Simulation Dynamic scheduling Minimization

来源：评论

学校读者我要写书评

暂无评论

Performing DNA Strand Displacement with DNA Polymerase 14th

Performing DNA Strand Displacement with DNA Polymerase

引用

14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Wang, Zhiyu Hu, Yingxin Chen, Zhekun Liao, Sulin Huang, Yabing Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan730074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan730074 China Department of Pathology Renmin Hospital of Wuhan University Wuhan430060 China

ISBN: (纸本)9789811534140

Significant improvements to the dynamic DNA nano science have emerged in recent years, primarily due to the elaborate design of toehold-mediated DNA strand displacement (TMSD). However, it remains an ongoing challenge to design huge-scaled TMSD based sophisticated dynamic DNA structures without base-pair mismatching or unwanted secondary structures, because the sequence design complexity of TMSD will dramatically increase as the scale increases. Here we report a new polymerase triggered strand displacement (PTSD) mechanism to realize DNA strand displacement with the potential of constructing complicated dynamic DNA nanostructures. By employing proper polymerase with strand displacement activity, the target strand in a duplex will be displaced and freed during the polymerization. In this manner, DNA strand displacement takes place without considering the design complexity of branch migration domain. The mechanism was successfully applied in constructing one-layer and two-layer circuits in which the parameters involved were explored, suggesting that PTSD is feasible and able to be harnessed to construct cascading DNA circuits with high complexity. © 2020, Springer Nature Singapore Pte Ltd.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

MMTrans-MT: A Framework for Multimodal Emotion Recognition Using Multitask Learning

MMTrans-MT: A Framework for Multimodal Emotion Recognition U...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Jinrui Shen Jiahao Zheng Xiaoping Wang the School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China the School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

With the development of deep learning, emotion recognition tasks are more inclined to use multimodal data and adequate supervised information to improve accuracy. In this work, MMTrans-MT (Multimodal Transformer-Multitask), the framework for multimodal emotion recognition using multitask learning is proposed. It has three modules: modalities representation module, multimodal fusion module, and multitask output module. Three modalities, i.e, words, audio and video, are comprehensively utilized to carry out emotion recognition by a simple but efficient fusion model based on Transformer. As for multitask learning, the two tasks are defined as categorical emotion classification and dimensional emotion regression. Considering a potential mapping relationship between two kinds of emotion model, multitask learning is adopted to make the two tasks promote each other and improve recognition accuracy. We conduct experiments on CMU-MOSEI and IEMOCAP datasets. Comprehensive experiments show that the accuracy of recognition using multimodal information is higher than that using unimodal information. Adopting multitask learning promotes the performance of emotion recognition.

关键词： Learning systems Deep learning Emotion recognition Correlation Computational modeling Task analysis Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

IF2Net: Innately Forgetting-Free Networks for Continual Learning

arXiv

引用

arXiv 2023年

作者： Li, Depeng Wang, Tianqi Xu, Bingrong Kawaguchi, Kenji Zeng, Zhigang Suganthan, Ponnuthurai Nagaratnam The School of Artificial Intelligence and Automation The Institute of Artificial Intelligence Huazhong University of Science and Technology The Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China The School of Automation Wuhan University of Technology Wuhan430070 China The School of Computing National University of Singapore 117417 Singapore The School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore The KINDI Center for Computing Research College of Engineering Qatar University Doha Qatar

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated how to design an Innately Forgetting-Free Network (IF2Net) for continual learning context. This study proposed a straightforward yet effective learning paradigm by ingeniously keeping the weights relative to each seen task untouched before and after learning a new task. We first presented the novel representation-level learning on task sequences with random weights. This technique refers to tweaking the drifted representations caused by randomization back to their separate task-optimal working states, but the involved weights are frozen and reused (opposite to well-known layer-wise updates of weights). Then, sequential decision-making without forgetting can be achieved by projecting the output weight updates into the parsimonious orthogonal space, making the adaptations not disturb old knowledge while maintaining model plasticity. IF2Net allows a single network to inherently learn unlimited mapping rules without telling task identities at test time by integrating the respective strengths of randomization and orthogonalization. We validated the effectiveness of our approach in the extensive theoretical analysis and empirical study. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video

Real-time Multi-person Eyeblink Detection in the Wild for Un...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wenzheng Zeng Yang Xiao Sicheng Wei Jinfang Gan Xintao Zhang Zhiguo Cao Zhiwen Fang Joey Tianyi Zhou Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Biomedical Engineering Southern Medical University Guangzhou China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou China Centre for Frontier AI Research Agency for Science Technology and Research (A*STAR) Singapore Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

Real-time eyeblink detection in the wild can widely serve for fatigue detection, face anti-spoofing, emotion analysis, etc. The existing research efforts generally focus on single-person cases towards trimmed video. However, multi-person scenario within untrimmed videos is also important for practical applications, which has not been well concerned yet. To address this, we shed light on this research field for the first time with essential contributions on dataset, theory, and practices. In particular, a large-scale dataset termed MPEblink that involves 686 untrimmed videos with 8748 eyeblink events is proposed under multi-person conditions. The samples are captured from uncon-strainedfilms to reveal “in the wild“ characteristics. Meanwhile, a real-time multi-person eyeblink detection method is also proposed. Being different from the existing counter-parts, our proposition runs in a one-stage spatio-temporal way with end-to-end learning capacity. Specifically, it simultaneously addresses the sub-tasks of face detection, face tracking, and human instance-level eyeblink detection. This paradigm holds 2 main advantages: (1) eyeblink features can be facilitated via the face's global context (e.g., head pose and illumination condition) with joint optimization and interaction, and (2) addressing these sub-tasks in parallel instead of sequential manner can save time remarkably to meet the real-time running requirement. Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video. Our method also outperforms existing approaches by large margins and with a high inference speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A method for detecting floating objects on water based on edge computing

A method for detecting floating objects on water based on ed...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： He Li Shuaipeng Yang Jinjiang Liu Honglin Fang Zhumu Fu Rui Zhang Huimei Jia Lianmeng Lv Henan Costar Group Co. Ltd Nanyang Henan China College of Information Engineering Henan University of Science and Technology Luoyang Henan China Henan Engineering Research Center of Intelligent Processing for Big Data of Digital Image School of Computer Science and Technology Nanyang Normal University Nanyang China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunication Beijing China Xi'an Hengpin Electronic Technology Co. Ltd Xi’an China

With the development and application of computer vision, many target detection networks are applied to the detection of floating objects in rivers. For the detection problems such as small targets easily missed and misdetected in water surface floating object detection tasks and difficult to deploy models. An edge computing-oriented approach to river floater detection is proposed. First, a four-fold down-sampling feature layer is added to the YOLOv5 network which enhances more target detail features and improves the detection capability of small objects. Second, CA (Coordinate Attention) is added to the Backbone to suppress background noise interference, and different pooling is used to accommodate different hierarchical features. Then, a bilinear interpolation method is adopted for up-sampling to avoid the loss of small object features. Design a data enhancement algorithm for small targets based on Mosaic to increase the number of small objects and enrich the training background. Finally, for the edge computing architecture platform, the channel pruning algorithm is used to prune and compress the model structure to adapt to the computing capability of edge devices. The experimental results show that the method can effectively improve the detection capability of the network for floating objects on the water surface. The detection accuracy can reach 93.6%, and the detection speed can be maintained at 36 frames per second, which can achieve high-precision real-time detection of floating objects on the water surface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NiuEM: A Nested-iterative Unsupervised Learning Model for Single-particle Cryo-EM image processing

NiuEM: A Nested-iterative Unsupervised Learning Model for Si...

引用

2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

作者： Hu, Rui Cai, Jiaming Zheng, Wangjie Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Jiao Tong University Department of Bioinformatics and Biostatistics Shanghai200240 China

ISBN: (纸本)9781728162157

Cryo-electron microscopy (cryo-EM) has become a mainstream technology for solving spatial structures of biomacromolecules, while the processing of cryo-EM images is a very challenging task. One of the great challenges is the high noise in the images. A common method is to cluster the images with close projecting angles to get mean images, which are used for 3D reconstruction. However, due to the extremely low signal-to-noise-ratio, common clustering methods often fail to obtain high-quality mean images, leading to poorly reconstructed structures. In this study, we present a new unsupervised learning framework, called NiuEM, to discriminate images captured from different angles and yield cluster-mean images. NiuEM first generates pseudo-labels and then exploits both contrastive loss and cross-entropy loss for training convolutional layers to learn feature representations. Moreover, the pseudo-labels are updated iteratively to enhance the reliability of labels. We assess the performance of NiuEM on four data sets via both visualized and quantitative experiments. Especially, two kinds of metrics are adopted to measure the performance, regarding the clustering quality and the resolution of reconstructed 3D models, respectively. The experimental results show that NiuEM achieves very competitive clustering accuracy in the comparison with the state-of-the-art image clustering methods. Moreover, the cluster mean images yielded by NiuEM lead to better initial 3D models compared with the mainstream reconstruction tools. © 2020 IEEE.

关键词： image reconstruction

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：