检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Boshen Li, Yuxi Tu, Yuanpeng Peng, Jinlong Wang, Yabiao Wu, Cunlin Xiao, Yang Zhao, Cairong YouTu Lab Tencent Shanghai China Tongji University Shanghai 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

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via identifying noisy data with a coarse small-loss criterion to mitigate the interference from noisy labels, ignoring the fact that the difficulties of noisy samples are different, thus a rigid and unified data selection pipeline cannot tackle this problem well . In this paper, we first propose a coarse-to-fine robust learning method called CREMA, to handle noisy data in a divide-and-conquer manner. In coarse-level, clean and noisy sets are firstly separated in terms of credibility in a statistical sense. Since it is practically impossible to categorize all noisy samples correctly, we further process them in a fine-grained manner via modeling the credibility of each sample. Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set. Meanwhile, for samples categorized into the noisy set, a selective label update strategy is proposed to correct noisy labels while mitigating the problem of correction error. Extensive experiments are conducted on benchmarks of different modality, including image classification (CIFAR, Clothing1M etc) and text recognition (IMDB), with either synthetic or natural semantic noises, demonstrating the superiority and generality of CREMA. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Spatio-Temporal Scale Based Affective Neural Network for Emotion Detection in Conversation

A Spatio-Temporal Scale Based Affective Neural Network for E...

引用

Chinese Automation Congress (CAC)

作者： Jiang Li Xiaoping Wang Shanglin Lei Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology (HUST) Wuhan China Institute of Artificial Intelligence Huazhong University of Science and Technology (HUST) Wuhan China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China Key Laboratory of Brain-inspired Intelligent Systems Hubei Province Wuhan China

Emotion Detection in Conversation (EDC) has been implemented in numerous domains and is under increasing attention. The EDC task is highly challenging due to the need to incorporate both the context of the utterance and the identity of the participant. Some existing EDC approaches employ redundant network structures and inadequately model contextual utterances, resulting in limited performance gains. In this work, we devise a Spatio-Temporal scale based Affective neural Network (STANet) in a simplistic and efficacious manner. STANet consists of two main components, i.e., spatial scale network and temporal scale network, which are applied to extract spatial scale and temporal scale information in the conversation, respectively. Prior to spatio-temporal scale modeling, we encode the identity information of participants to examine its impact on the performance of emotion detection. We conduct substantial comparative experiments and ablation studies on three conversational emotion datasets, and the results demonstrate that our STANet realizes superior performance without taking advantage of external knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Master-Slave Synchronization of Neural Networks With Unbounded Delays via Adaptive Method

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第5期53卷 3277-3287页

作者： Zhang, Hao Zhou, Yufeng Zeng, Zhigang Huazhong Agr Univ Coll Informat Wuhan 430070 Peoples R China Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Wuhan Univ Sci & Technol Engn Res Ctr Met Automat & Measurement Technol Wuhan 430081 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

Master-slave synchronization of two delayed neural networks with adaptive controller has been studied in recent years;however, the existing delays in network models are bounded or unbounded with some derivative constraints. For more general delay without these restrictions, how to design proper adaptive controller and prove rigorously the convergence of error system is still a challenging problem. This article gives a positive answer for this problem. By means of the stability result of unbounded delayed system and some analytical techniques, we prove that the traditional centralized adaptive algorithms can achieve global asymptotical synchronization even if the network delays are unbounded without any derivative constraints. To describe the convergence speed of the synchronization error, adaptive designs depending on a flexible omega-type function are also provided to control the synchronization error, which can lead exponential synchronization, polynomial synchronization, and logarithmically synchronization. Numerical examples on delayed neural networks and chaotic Ikeda-like oscillator are presented to verify the adaptive designs, and we find that in the case of unbounded delay, the intervention of omega-type function can promote the realization of synchronization but may destroy the convergence of control gain, and this however will not happen in the case of bounded delay.

关键词： Synchronization Delays Biological neural networks Adaptive systems Convergence Stability criteria Asymptotic stability Adaptive control delayed neural networks master-slave synchronization unbounded delay

来源：评论

学校读者我要写书评

暂无评论

Optimize TSK Fuzzy Systems for Regression Problems: Minibatch Gradient Descent With Regularization, DropRule, and AdaBound (MBGD-RDA)

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2020年第5期28卷 1003-1015页

作者： Wu, Dongrui Yuan, Ye Tan, Yihua Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Minist Educ Wuhan 430074 Peoples R China

Takagi-Sugeno-Kang (TSK) fuzzy systems are very useful machine learning models for regression problems. However, to our knowledge, there has not existed an efficient and effective training algorithm that ensures their generalization performance and also enables them to deal with big data. Inspired by the connections between TSK fuzzy systems and neural networks, we extend three powerful neural network optimization techniques, i.e., minibatch gradient descent (MBGD), regularization, and AdaBound, to TSK fuzzy systems, and also propose three novel techniques (DropRule, DropMF, and DropMembership) specifically for training TSK fuzzy systems. Our final algorithm, MBGD with regularization, DropRule, and AdaBound, can achieve fast convergence in training TSK fuzzy systems, and also superior generalization performance in testing. It can be used for training TSK fuzzy systems on datasets of any size;however, it is particularly useful for big datasets, on which currently no other efficient training algorithms exist.

关键词： AdaBound Adaptive-network-based fuzzy inference system (ANFIS) DropRule fuzzy systems minibatch gradient descent (MBGD) regularization

来源：评论

学校读者我要写书评

暂无评论

Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2020年第5期28卷 1117-1127页

作者： Zhang, Wen Wu, Dongrui Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

Transfer learning makes use of data or knowledge in one problem to help solve a different, yet related, problem. It is particularly useful in brain-computer interfaces (BCIs), for coping with variations among different subjects and/or tasks. This paper considers offline unsupervised cross-subject electroencephalogram (EEG) classification, i.e., we have labeled EEG trials from one or more source subjects, but only unlabeled EEG trials from the target subject. We propose a novel manifold embedded knowledge transfer (MEKT) approach, which first aligns the covariance matrices of the EEG trials in the Riemannian manifold, extracts features in the tangent space, and then performs domain adaptation by minimizing the joint probability distribution shift between the source and the target domains, while preserving their geometric structures. MEKT can cope with one or multiple source domains, and can be computed efficiently. We also propose a domain transferability estimation (DTE) approach to identify the most beneficial source domains, in case there are a large number of source domains. Experiments on four EEG datasets from two different BCI paradigms demonstrated that MEKT outperformed several state-of-the-art transfer learning approaches, and DTE can reduce more than half of the computational cost when the number of source subjects is large, with little sacrifice of classification accuracy.

关键词： Covariance matrices Electroencephalography Manifolds Feature extraction Task analysis Geometry Symmetric matrices Brain-computer interfaces electroencephalogram Riemannian manifold transfer learning

来源：评论

学校读者我要写书评

暂无评论

Complementation-Reinforced Attention Network for Person Re-Identification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2020年第10期30卷 3433-3445页

作者： Han, Chuchu Zheng, Ruochen Gao, Changxin Sang, Nong Huazhong Univ Sci & Technol Key Lab Minist Educ Image Proc & Intelligent Control Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

Fine-grained information has been proved helpful for person re-identification, and multi-head attention mechanism offers a feasible solution for this. However, we observe severe redundancy among the multiple branches, which might make the learned representation over-emphasize certain discriminative regions and correspondingly ignore other potentially informative regions. Therefore, we tackle this issue by two aspects yielding the so-called Complementation-Reinforced Attention Network (CRAN). One is the redundancy among branches, and we propose to impose complementing constraints among multiple attention heads. The constraints are two-fold: on the one hand, it encourages each branch to attend to complementary attention regions;on the other hand, it enforces orthogonality among the learned features of different regions in the embedding space. The other is the redundancy among query positions for each attention head. So we simplify the attention block by sparsifying the query positions. Besides, in order to achieve efficient retrieval, we propose an adaptive feature fusion method for dimensional reduction. Compared with the commonly used feature ensemble, our method effectively reduces the dimensionality while keeping the discriminative ability. We demonstrate the effectiveness of our method on MSMT17, Market-1501, DukeMTMC-reID, and CUHK03 datasets.

关键词： Task analysis Redundancy Feature extraction Head Visualization Optimization Measurement Person re-identification attention complementation

来源：评论

学校读者我要写书评

暂无评论

A strategy for programming the regulation of in vitro transcription with application in molecular circuits

引用

NANOSCALE 2021年第10期13卷 5429-5434页

作者： Hu, Yingxin Xie, Chun Xu, Fei Pan, Linqiang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Educ Minist China Key Lab Image Informat Proc & Intelligent Control Wuhan 130074 Hubei Peoples R China Shijiazhuang Tiedao Univ Coll Informat Sci & Technol Shijiazhuang 050043 Hebei Peoples R China

In vitro transcription is a convenient platform for fabricating nanodevices and has been used for assembling synthetic networks. However, it remains challenging to regulate synthetic cell-free in vitro transcription by multiple stimuli in a simple and programmable way. We proposed a strategy to regulate in vitro transcription by controlling the transcription templates' promoter domain via variable DNA inputs. To demonstrate the utility of this strategy, various logic circuits and cascading circuits were implemented. With the advantage of simplicity, modularity, programmability, and extensibility, the proposed strategy has potential in biocomputing, bioanalytical, and therapeutic applications.

关键词： Transcription

来源：评论

学校读者我要写书评

暂无评论

Thermal constraint control of reversible solid oxide cell for optimal system efficiency

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2025年 134卷 198-211页

作者： Xu, Yuanwu Yin, Jie Wang, Jingjing Wu, Xiao-long Peng, Jingxuan Tang, Ruifeng Zou, Suhang Fu, Xiaowei Li, Xi Wuhan Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430081 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Educ Minist Wuhan 430074 Hubei Peoples R China Nanchang Univ Sch Informat Engn Nanchang 330031 Jiangxi Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore Huazhong Univ Sci & Technol China Poland Belt & Rd Joint Lab Measurement & Con Wuhan 430074 Hubei Peoples R China Shenzhen Huazhong Univ Sci & Technol Res Inst Shenzhen 518055 Peoples R China

Reversible solid oxide cell (RSOC) demonstrates considerable promise in multimodal energy conversion architectures, particularly as a technology for hydrogen-based energy storage systems. Nevertheless, under dynamic operating regimes with time-varying current inputs, realizing time-efficient and reliable transitions to steadystate operation remains difficult. This difficulty arises from the intricate coupling of thermal, electrical, and gaseous processes within the RSOC system. This study aims to address these challenges by developing a 5 kW mathematical model of the RSOC system. The proposed model enables systematic investigation of thermal safety issues arising during current switching operations while introducing a thermal constraint control strategy to enhance both system efficiency and thermal safety performance. This efficiency-driven study employs the Grid Search algorithm to identify optimal steady-state operating points for the RSOC system, ensuring strict adherence to safety constraints across varying current inputs. Furthermore, by integrating the pre-identified optimal operating points as feedforward control with Model Predictive control (MPC)-based feedback correction, this hybrid strategy effectively mitigates stack temperature gradient overshoot while synchronously ensuring optimal system efficiency throughout current transition processes. Under simulated variable current inputs, the proposed RSOC system model and control strategy demonstrate the capability to constrain stack temperature gradient overshoot within 2.3K while enhancing transient efficiency by 5 %-8 %, achieving a peak system efficiency of 85 %. It provides a novel methodology for safe and efficient working with intermittent renewable energy.

关键词： Reversible solid oxide cell Optimal efficiency Grid search Model predictive control Temperature control

来源：评论

学校读者我要写书评

暂无评论

Active Disturbance Rejection Attitude control for Hypersonic Vehicle Based on intelligent Stochastic Robust Optimization Method

引用

COMPLEXITY 2020年第1期2020卷

作者： Wang, Bo Liu, Wei Cheng, Zhongtao Liu, Lei Wang, Yongji Huazhong Univ Sci & Technol Minist Educ Image Proc & Intelligent Control Artificial Intelligence & Automat Sch Key Lab Wuhan 430074 Peoples R China

This paper designs a double-loop cascade active disturbance rejection control (ADRC) to overcome the external disturbances and parameter uncertainty during hypersonic vehicle flight. The vehicle attitude angle and attitude angular velocity are regulated in outer loop and inner loop, respectively. A stochastic robust approach is employed to further tune the ADRC parameters for better control performances. The Monte Carlo sampling of uncertain parameter is adopted to evaluate the stochastic robust performance. An improved differential evolution algorithm that combines neighborhood field optimization and triangular mutation is employed as the numerical solver. Simulation results show that the ADRC controller with optimized parameters manifests improved robustness as well as good control performances.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Bandpass Effect and Its Compensation Method for Diagnosis in a Closed-Loop control System

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2020年第3期25卷 1679-1689页

作者： Yao, Yuan Li, Yesong Yin, Quan Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Image Proc & Intelligent Control Key Lab Wuhan 430074 Peoples R China

Motor current signal analysis is an effective technique for fault diagnosis in the motor drive system. However, in the closed-loop control (CLC) system, the amplitude of periodic faulty harmonic is suppressed by the impact of CLC characteristics, so the severity assessment of faults may fail. In this article, a model reference method based on the theoretical analysis of CLC characteristics is proposed to deal with this problem. First, the faulty harmonic in the q-axis current is extracted from the field-oriented control process as a fault indicator. Then, the bandpass effect is revealed to describe the variation of amplitudes of harmonics in the current spectrum. The variation is caused by the control parameter and architecture in the CLC system. Finally, to improve diagnostic performance, a model reference method is proposed to compensate for the aforementioned variation. The model is established by experimentally measuring the amplitude-frequency response of the closed-loop speed control system. The bandpass effect of the CLC system is validated by simulations in the MATlab/Simulink environment. Furthermore, experimental validations are conducted on a ball screw platform. The results show that the proposed method is effective to compensate the bandpass effect and helps to achieve better diagnostic performance.

关键词： Bandpass effect closed-loop control (CLC) system fault diagnosis model reference method motor current signal analysis (MCSA)

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：