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

Optimal Fault Detection Observer Design using Excluding Degree

Optimal Fault Detection Observer Design using Excluding Degr...

引用

IEEE Conference on Decision and control

作者： Feng Xu Yiming Wan Ye Wang Division of Information Science and Technology Shenzhen International Graduate School Tsinghua University Shenzhen P.R. China School of Artificial Intelligence and Automation Huazhong University of Science and Technology and Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan P.R. China Department of Electrical and Electronic Engineering The University of Melbourne Parkville VIC Australia

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

This paper proposes a novel optimal gain design method for robust fault detection using set-valued observers. First, a new fault detection performance specification is proposed for set-valued observers based on a new notion named the excluding degree of the origin from a zonotope. Second, a fractional programming problem is formulated to describe fault detection optimality of set-valued observers. Third, optimal fault detection gains are obtained by solving the fractional programming problem. Finally, numerical examples are used to illustrate the effectiveness of the proposed method.

关键词： Fault detection Design methodology Observers Programming Computational complexity Optimization Numerical stability

来源：评论

学校读者我要写书评

暂无评论

Towards Environmentally Adaptive Odor Source Localization: Fuzzy Lévy Taxis Algorithm and Its Validation in Dynamic Odor Plumes

Towards Environmentally Adaptive Odor Source Localization: F...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Xinxing Chen Jian Huang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728164793

ISBN: (纸本)9781728164809

In this paper, we propose a bio-inspired Fuzzy Lévy Taxis algorithm to solve the robotic odor source localization problem in dynamic odor plumes. According to the proposed algorithm, the robot is programmed to move for a length with a turning angle at each step until reaching the odor source. The movement length and the turning angle follow two specific probability distribution, of which the parameters are adaptive through a fuzzy logic system. The proposed algorithm was compared with the Adaptive Lévy Taxis algorithm in simulated pseudo-Gaussian plumes. Our proposed algorithm shows a higher success rate and efficiency. The algorithm has also been systematically evaluated in simulated filament-based odor plumes under various environmental conditions. The results revealed that the performance of the proposed algorithm is consistently good in various environmental conditions in terms of success rate, number of steps and distance overhead to find the odor source.

关键词： Public transportation Heuristic algorithms Turning Robot sensing systems Adaptation models Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Battery Parameter Identification Using Recursive Least Squares with Variable Directional Forgetting

Battery Parameter Identification Using Recursive Least Squar...

引用

International Conference on control and Automation (ICCA)

作者： Kun Zhu Yiming Wan Chenou Li Xin Luo Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728190938

ISBN: (纸本)9781728190945

An accurate battery model is important to perform various tasks of battery management. Battery model parameters change with working conditions, thus requiring continuous update for parameter estimation. The recursive least-squares algorithm with a forgetting strategy is widely used to estimate time-varying parameters online. However, the online data vary with battery operations, so the data may fail to contain sufficient excitation. When the online data is not persistently exciting, most existing forgetting strategies in battery literature suffer from covariance blowup, which means the algorithm cannot identify parameters reliably. In order to cope with non-persistent excitation, a recursive least-squares algorithm with variable direction forgetting is presented in this paper for battery parameter estimation. Instead of discounting all old information, it performs forgetting only in the direction of sufficient excitation. The forgetting factor can adaptively adjust based on excitation, which enhances trade-off between stability and tracking capability of the algorithm. A battery simulation model with time-varying parameters is used to illustrate the effectiveness of our proposed algorithm.

关键词： Batteries State of charge Electronic countermeasures Computational modeling Parameter estimation Load modeling Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Fault detection of lithium-ion batteries subject to probabilistic parametric uncertainties 11

Fault detection of lithium-ion batteries subject to probabil...

引用

11th CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2019

作者： Liu, Yuhao Wan, Yiming Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

ISBN: (纸本)9781728106816

The fault detection task in lithium-ion battery management system (BMS) is critical to the safety and reliability of rechargeable and hybrid electric vehicles. To explicitly account for inevitable errors of battery model parameters, a robust fault detection method is proposed in this paper. The residual generator is established by exploiting an equivalent circuit model. The effect of uncertainties on the residual is parametrized as polynomial dependence on probabilistic uncertain parameters and noises. Then Gaussian mixtures are adopted to derive the residual distribution. To account for residual uncertainties in the detection decision, the weighted sum of distances from the generated residual to each Gaussian component of the residual distribution is proposed. Simulation results illustrate that our proposed method outperforms the conventional approach that does not consider parametric uncertainties. © 2019 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Keypoint-Based Feature Matching For Partial Person Re-Identification

Keypoint-Based Feature Matching For Partial Person Re-Identi...

引用

IEEE International Conference on image processing

作者： Chuchu Han Changxin Gao Nong Sang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

As a derivative of person re-identification (re-ID), partial re- ID aims to retrieve a partial pedestrian across holistic person images captured by non-overlapping cameras. This task is more challenging and closer to real-world applications. Since we cannot locate the part of the partial image, the misaligned region compromises the performance greatly when directly (a) compare a partial pedestrian with a holistic one. To alleviate this issue, we propose a Keypoint-Based Feature Matching (KBFM) network, which constructs a simple and effective framework for partial re-ID. Specifically, our architecture explicitly leverages the keypoints generated by pose estimation. Based on the visible keypoints, coordinates of the corresponding visible region can be computed. And the keypoint-based feature embeddings can be generated by bilinear sampling. When matching two images, we extract their features on the basis of shared visible keypoints, avoiding the misalignment and disturbance. Moreover, considering the triplet loss cannot be flexibly built in the partial re-ID pipeline, we improve the original sampling method and achieve significant performance. Extensive experimental results on two widely used benchmarks demonstrate significant performance improvements of our method over most state-of-the-art methods.

关键词： Feature extraction Cameras Task analysis Pose estimation Training Pipelines Generative adversarial networks

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：