检索结果-内蒙古大学图书馆

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

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

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

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

EEG-Based Driver Drowsiness Estimation Using Feature Weighted Episodic Training

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2019年第11期27卷 2263-2273页

作者： Cui, Yuqi Xu, Yifan Wu, Dongrui Huazhong Univ Sci & Technol Minist Educ Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Key Lab Wuhan 430074 Hubei Peoples R China

Drowsy driving is pervasive, and also a major cause of traffic accidents. Estimating a driver's drowsiness level by monitoring the electroencephalogram (EEG) signal and taking preventative actions accordingly may improve driving safety. However, individual differences among different drivers make this task very challenging. A calibration session is usually required to collect some subject-specific data and tune the model parameters before applying it to a new subject, which is very inconvenient and not user-friendly. Many approaches have been proposed to reduce the calibration effort, but few can completely eliminate it. This paper proposes a novel approach, feature weighted episodic training (FWET), to completely eliminate the calibration requirement. It integrates two techniques: feature weighting to learn the importance of different features, and episodic training for domain generalization. Experiments on EEG-based driver drowsiness estimation demonstrated that both feature weighting and episodic training are effective, and their integration can further improve the generalization performance. FWET does not need any labelled or unlabelled calibration data from the new subject, and hence could be very useful in plug-and-play brain-computer interfaces.

关键词： Drowsy driving domain generalization EEG episodic training feature weighting

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Flow Model-Based Impact Assessment of Cyberattacks for Critical Infrastructures

引用

IEEE SYSTEMS JOURNAL 2019年第4期13卷 3944-3955页

作者： Zhu, Qianxiang Qin, Yuanqing Zhou, Chunjie Fei, Li Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China

Critical infrastructures (CIs) are essential for the national security, economy, and public safety, whose protection against cyberattacks has become the focus of significant attention. Impact assessment plays an important role in this protection, which provides real-time situations for security managers. The assessment of CIs not only need to analyze the cyberattack's impact on any specific station, but also to consider the spreading process of the negative impact. However, few research in this domain consider the above two aspects simultaneously due to the complexity of CIs and their operation. To tackle this problem, a hierarchical flow model (HFM)-based impact assessment is presented. In this approach, a novel HFM method is proposed to describe a system from a function system perspective, which combines a flow model and hierarchical knowledge. By using this method, a CI model which considers cyber-physical interaction within a station, dependence among stations, and the topological structure of the physical network is established. Next, based on the CI model, an impact assessment is proposed to quantify the loss which is caused by the impact spreading within the CI network. Finally, case studies on a gas supply system are conducted to verify the effectiveness of the proposed approach.

关键词： Critical infrastructures cybersecurity protection hierarchical flow model impact assessment system of systems

来源：评论

学校读者我要写书评

暂无评论

Multichannel Synchronous Hydrodynamic Gating Coupling with Concentration Gradient Generator for High-Throughput Probing Dynamic Signaling of Single Cells

引用

ANALYTICAL CHEMISTRY 2020年第17期92卷 12062-12070页

作者： Guo, Yiran Gao, Zhaolong Liu, Yinan Li, Shunji Zhu, Jinchi Chen, Peng Liu, Bi-Feng Huazhong Univ Sci & Technol Hubei Bioinformat & Mol Imaging Key Lab Syst Biol ThemeDept Biomed EngnColl Life Sci & Key Lab Biomed Photon MOEWuhan Natl Lab Optoelec Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Image Proc & Intelligent Control Key Lab Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Coll Life Sci & Technol Dept Genet Wuhan 430074 Peoples R China

Cell signaling greatly affected by complicated and temporally dynamic extracellular microenvironments controls most of the physiological functions in vivo. To reconstruct or simulate such microenvironments in vitro represents a fundamental approach for revealing the underlying mechanisms of those sophisticated processes. Recent advances in microfluidics have added a new dimension to cell signaling analysis, for example, concentration gradient generators (amplitude aspect) or hydrodynamic gating strategy (frequency aspect), but it is still challengeable to capture single-cell dynamic signaling in response to a mimicked extracellular microenvironment with varied stimuli waveforms of different amplitude and frequency in a high-throughput manner. In this article, we proposed a novel microfluidic strategy coupling multichannel synchronous hydrodynamic gating with microfluidic concentration gradient generators (mu MHG-CGG) to probe dynamic signaling of single cells with high throughput. The mu MHG-CGG allows rapid delivery of dynamic chemical signals in both high frequency (as high as 670 mHz) and multiple amplitude domains at the same time and simultaneously high-throughput probing cell dynamics at single-cell resolution in real time. By applying the proposed system, the mechanisms for encoding/decoding systems (termed "frequency coding" or "amplitude coding") via GPCRs-mediated signaling pathways responding to histamine (HA) and adenosine triphosphate (ATP) in single HeLa cells were investigated. The optimal drug concentrations of single cells responses to HA and ATP individually or in combination were also successfully discussed, allowing us to obtain both single-cell heterogeneity and statistics from the cell population.

关键词： Calcium Cell signaling Fluid dynamics Fluorescence Biotechnology

来源：评论

学校读者我要写书评

暂无评论

A study on a special DNA nanotube assembled from two single-stranded tiles

引用

NANOTECHNOLOGY 2019年第11期30卷 115602页

作者： Xu, Fei Wu, Tingfang Shi, Xiaolong Pan, Linqiang Huazhong Univ Sci & Technol Sch Automat Key Lab Image Informat Proc & Intelligent Control Educ Minist China Wuhan 430074 Hubei Peoples R China

Single-stranded tile (SST) strategy offers precise control over the circumferences of nanotubes while the kinetic trap in the process of the self-assembly prevents the formation of wider tubes. Here, we report a simple and efficient method to build DNA nanotubes using only 2 SSTs via one-pot annealing. The diameters of the 2-SST nanotubes were much larger than what the kinetic trap theory would predict, indicating a new mechanism was at play in the formation of these nanotubes. Further investigation suggested that the 2-SST nanotubes were assembled through a hierarchical pathway that involved an intermediate formation of 2-SST nano-lines.

关键词： DNA nanotube self-assembly hierarchical assembly DNA nanotechnology drug delivery

来源：评论

学校读者我要写书评

暂无评论

V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results

arXiv

引用

arXiv 2024年

作者： Wang, Jiaqi Zang, Yuhang Zhang, Pan Chu, Tao Cao, Yuhang Sun, Zeyi Liu, Ziyu Dong, Xiaoyi Wu, Tong Lin, Dahua Chen, Zeming Wang, Zhi Meng, Lingchen Yao, Wenhao Yang, Jianwei Wu, Sihong Chen, Zhineng Wu, Zuxuan Jiang, Yu-Gang Wu, Peixi Chai, Bosong Nie, Xuan Yan, Longquan Wang, Zeyu Zhou, Qifan Wang, Boning Huang, Jiaqi Xu, Zunnan Li, Xiu Yuan, Kehong Zu, Yanyan Hao, Jiayao Gao, Qiong Jiao, Licheng Shanghai AI Laboratory China Chinese University of Hong Kong Hong Kong Shanghai Jiao Tong University China Wuhan University China Shenzhen International Graduate School Tsinghua University China Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Microsoft Research Redmond United States University of Science and Technology of China China Zhejiang University China Northwestern Polytechnical University China Northwest University China Tsinghua Shenzhen International Graduate School Tsinghua University China Intelligent Perception and Image Understanding Lab Xidian University China

Detecting objects in real-world scenes is a complex task due to various challenges, including the vast range of object categories, and potential encounters with previously unknown or unseen objects. The challenges necessitate the development of public benchmarks and challenges to advance the field of object detection. Inspired by the success of previous COCO [15] and LVIS [11] Challenges, we organize the V3Det Challenge 2024 in conjunction with the 4th Open World Vision Workshop: Visual Perception via Learning in an Open World (VPLOW) at CVPR 2024, Seattle, US. This challenge aims to push the boundaries of object detection research and encourage innovation in this field. The V3Det Challenge 2024 consists of two tracks: 1) Vast Vocabulary Object Detection: This track focuses on detecting objects from a large set of 13204 categories, testing the detection algorithm's ability to recognize and locate diverse objects. 2) Open Vocabulary Object Detection: This track goes a step further, requiring algorithms to detect objects from an open set of categories, including unknown objects. In the following sections, we will provide a comprehensive summary and analysis of the solutions submitted by participants. By analyzing the methods and solutions presented, we aim to inspire future research directions in vast vocabulary and open-vocabulary object detection, driving progress in this field. Challenge homepage: https://***/challenge. © 2024, CC BY-NC-SA.

关键词： Object detection

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：