检索结果-内蒙古大学图书馆

Leveraging Contaminated Datasets to Learn Clean-Data Distribution with Purified Generative Adversarial Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tian, Bowen Su, Qinliang Yu, Jianxing School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangdong China

Generative adversarial networks (GANs) are known for their strong abilities on capturing the underlying distribution of training instances. Since the seminal work of GAN, many variants of GAN have been proposed. However, existing GANs are almost established on the assumption that the training dataset is clean. But in many real-world applications, this may not hold, that is, the training dataset may be contaminated by a proportion of undesired instances. When training on such datasets, existing GANs will learn a mixture distribution of desired and contaminated instances, rather than the desired distribution of desired data only (target distribution). To learn the target distribution from contaminated datasets, two purified generative adversarial networks (PuriGAN) are developed, in which the discriminators are augmented with the capability to distinguish between target and contaminated instances by leveraging an extra dataset solely composed of contamination instances. We prove that under some mild conditions, the proposed PuriGANs are guaranteed to converge to the distribution of desired instances. Experimental results on several datasets demonstrate that the proposed PuriGANs are able to generate much better images from the desired distribution than comparable baselines when trained on contaminated datasets. In addition, we also demonstrate the usefulness of PuriGAN on downstream applications by applying it to the tasks of semi-supervised anomaly detection on contaminated datasets and PU-learning. Experimental results show that PuriGAN is able to deliver the best performance over comparable baselines on both tasks1 Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

Optimizing Binary Sequence Excitation Signals for Rapid Impedance Spectrum Measurement in Proton Exchange Membrane Fuel Cells

学校读者我要写书评

暂无评论

Optimizing Binary Sequence Excitation Signals for Rapid Impe...

第43届中国控制会议

作者： Jingzhi Lei Chuang Sheng Jingjing Wang Liansong Yu Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science and Technology State Grid Electric Power Research Institute Wuhan Nanrui Limited Liability Company Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

With the increasing demand for efficient and reliable renewable energy sources,Proton Exchange Membrane Fuel Cells(PEMFCs) have emerged as a promising *** experiments demonstrate that Electrochemical Impedance Spectroscopy(EIS) effectively differentiates various states of *** broadband signals as testing excitations significantly reduces EIS measurement time,facilitating real-time monitoring of PEMFCs' health under dynamic *** signal design requires maintaining adequate amplitude across frequency components for noise resistance while minimizing signal peak value to reduce operational *** paper introduces an EIS simulation environment,leveraging PEMFCs' impedance and electrochemical noise *** focuses on optimizing the excitation signal's amplitude-frequency distribution using discrete interval binary *** results indicate that our method achieves minimal perturbation amplitude while preserving measurement accuracy in amplitude-frequency signal design.

关键词： Proton exchange membrane fuel cell Electrochemical impedance spectroscopy Electrochemical noise Excitation signal optimization

Spiking Neural Network for Intra-cortical Brain Signal Decoding

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Song Fu, Haotian Zhang, Herui Zhang, Peng Li, Wei Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China Department of Biomedical Engineering College of Life Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Decoding brain signals accurately and efficiently is crucial for intra-cortical brain-computer interfaces. Traditional decoding approaches based on neural activity vector features suffer from low accuracy, whereas deep learning based approaches have high computational cost. To improve both the decoding accuracy and efficiency, this paper proposes a spiking neural network (SNN) for effective and energy-efficient intra-cortical brain signal decoding. We also propose a feature fusion approach, which integrates the manually extracted neural activity vector features with those extracted by a deep neural network, to further improve the decoding accuracy. Experiments in decoding motor-related intra-cortical brain signals of two rhesus macaques demonstrated that our SNN model achieved higher accuracy than traditional artificial neural networks;more importantly, it was tens or hundreds of times more efficient. The SNN model is very suitable for high precision and low power applications like intracortical brain-computer interfaces. © 2025, CC BY.

关键词： Deep neural networks

A Parallel Read-Write Circuit With Fast Amplitude-Adaptive Matching Scheme to Memristor Crossbar Array

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems I: Regular Papers 2025年

作者： Jiang, Ningye Jiang, Mingxuan Huang, Haoen Yang, Le Huang, Yi Zeng, Zhigang Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan430074 China Wuhan Institute of Technology School of Electrical and Information Engineering Wuhan430205 China University of Massachusetts Amherst Department of Electrical and Computer Engineering AmherstMA01003 United States

Memristor crossbar array (MCA) is a computing-in-memory (CIM) module for computational acceleration. However, conventional read-write (R-W) circuits for MCA rely heavily on external components and have shortcoming in long writing times. To address these issues, we propose a parallel R-W circuit with a fast amplitude-adaptive matching (AAM) scheme. The fast AAM scheme is designed to accelerate time of writing memristors in MCA by adaptively adjusting the writing voltage to match an optimal amplitude. The architecture of parallel R-W circuit are outlined with the implementation of R-W processes. The design principles of parallel R-W unit, fast AAM unit, and associated control logic are described for analyzing their functions within the circuit. By integrating the parallel R-W circuit with MCA, a computing block is leveraged in a neural network for classification tasks. The experimental results demonstrate that the neural network with multiple computing blocks maintains high accuracy across various datasets (over 80%). Furthermore, the proposed AAM scheme achieves an average 54% reduction in writing time compared to that one without AAM scheme. Compared to the pulse-width scheme, the parallel R-W circuit exhibits an average 3.05× speedup in adjusting a 5×5 MCA, and the speedup efficiency is higher as the increases of MCA size. © 2025 IEEE.

关键词： Memristors

Research and application of artificial intelligence based webshell detection model: A literature review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Mingrui Han, Lansheng Zhou, Chunjie Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

Webshell, as the"culprit" behind numerous network attacks, is one of the research hotspots in the field of cybersecurity. However, the complexity, stealthiness, and confusing nature of webshells pose significant challenges to the corresponding detection schemes. With the rise of Artificial intelligence (AI) technology, researchers have started to apply different intelligent algorithms and neural network architectures to the task of webshell detection. However, the related research still lacks a systematic and standardized methodological process, which is confusing and redundant. Therefore, following the development timeline, we carefully summarize the progress of relevant research in this field, dividing it into three stages: Start Stage, Initial Development Stage, and In-depth Development Stage. We further elaborate on the main characteristics and core algorithms of each stage. In addition, we analyze the pain points and challenges that still exist in this field and predict the future development trend of this field from our point of view. To the best of our knowledge, this is the first review that details the research related to AI-based webshell detection. It is also hoped that this paper can provide detailed technical information for more researchers interested in AI-based webshell detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

Minimal-time Deadbeat Consensus and Individual Disagreement Degree Prediction for High-order Linear Multi-agent Systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Fu-Long Zhang, Hai-Tao Xu, Bowen Hu, Zhe Ren, Wei School of Artificial Intelligence and Automation 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 School of Artificial Intelligence Optics and Electronics Northwestern Polytechnical University Xi’an710072 China Department of Electrical and Computer Engineering University of California Riverside92521 United States

In this paper, a Hankel matrix-based fully distributed algorithm is proposed to address a minimal-time deadbeat consensus prediction problem for discrete-time high-order multi-agent systems (MASs). Therein, each agent can predict the consensus value with the minimum number of observable historical outputs of its own. Accordingly, compared to most existing algorithms only yielding asymptotic convergence, the present method can attain deadbeat consensus instead. Moreover, based on the consensus value prediction, instant individual disagreement degree value of MASs can be calculated in advance as well. Sufficient conditions are derived to guarantee both the minimal-time deadbeat consensus and the instant individual disagreement degree prediction. Finally, both the effectiveness and superiority of the proposed deadbeat consensus algorithm are substantiated by numerical simulations. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Kewei Wu, Yizheng Pan, Zhiyu Li, Xingyi Xian, Ke Wang, Zhe Cao, Zhiguo Lin, Guosheng S-Lab Nanyang Technological University Singapore Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China SenseTime Research Hong Kong

Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires substantial amounts of manually annotated data, which can be both expensive and time-consuming to obtain. To address this challenge, our study explores the potential of semi-supervised learning (SSL) for class-agnostic motion prediction. Our SSL framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data by generating pseudo labels through test-time inference. To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module. This module effectively selects reliable pseudo labels and regenerates unreliable ones. Furthermore, we propose two data augmentation strategies: temporal sampling and BEVMix. These strategies facilitate consistency regularization in SSL. Experiments conducted on nuScenes demonstrate that our SSL method can surpass the self-supervised approach by a large margin by utilizing only a tiny fraction of labeled data. Furthermore, our method exhibits comparable performance to weakly and some fully supervised methods. These results highlight the ability of our method to strike a favorable balance between annotation costs and performance. Code will be available at https://***/kwwcv/SSMP. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

A Point Cloud Segmentation Method Based on Ground Point Cloud Removal and Multi-Scale Twin Range image

学校读者我要写书评

暂无评论

A Point Cloud Segmentation Method Based on Ground Point Clou...

Chinese Control Conference (CCC)

作者： Yicheng Zhou Gang Peng Hangqi Duan Zhangang Wu Xukang Zhu 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 Wuhan China Shantui Construction Machinery Co. Ltd. Jining China

Aiming at the shortcomings of traditional point cloud segmentation algorithms, this paper proposes a 3D lidar point cloud segmentation method combining ground filtering and multi-scale twin range image construction. This method fully considers the geometric space distribution characteristics of the point cloud and the randomness of the positions between objects. Based on the assumption of multi plane model, the point cloud is divided into sectors. The ground points are removed through region ground plane fitting and growth, and then the multi-scale twin range image is constructed according to non-ground points. On the basis of the twin range image, the Breadth First Search algorithm is improved, the depth-breadth joint search strategy is proposed, all the points to be clustered are traversed, and the adaptive clustering threshold is used for point cloud clustering, which realizes a point cloud segmentation method with higher accuracy and robustness. Through the experimental analysis of KITTI dataset and collected campus outdoor scene dataset, compared with the traditional point cloud segmentation algorithm, the method proposed in this paper can effectively improve the point cloud segmentation accuracy and robustness of mobile robots in complex environments.

关键词：

Lifetime Extension Control for Multi-Stack SOFC System with Inconsistent Stacks

学校读者我要写书评

暂无评论

Lifetime Extension Control for Multi-Stack SOFC System with ...

Chinese Control Conference (CCC)

作者： Zexin Li Guoqiang Liu Wei Zhao Xi Li Key Laboratory of Image Processing and Intelligent Control of Education Ministry School of Artificial Intelligence and Automation Huazhong University of Science & Technology Wuhan Hubei China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen Guangdong China

The multi-stack fuel cell system (MFCS) is an important basis for the application of solid oxide fuel cell (SOFC) technology to large-scale power generation systems. MFCS can provide higher power, longer lifetime and better reliability. Different from the single-stack fuel cell system (SFCS), there may be some inconsistencies among the stacks in the MFCS. If the inconsistencies are ignored, they will significantly affect the lifetime of the MFCS. This study focuses on the lifetime extension of multi-stack SOFC power generation systems with inconsistent stacks. Since the multi-stack system of SOFC generally cannot control the flow rate of each stack respectively, it brings a difficulty to the control of the MFCS with inconsistencies among the stacks. In order to overcome this difficulty, this paper built a multi-stack SOFC system model, which can characterize the degradation and inconsistencies among SOFC stacks. And then designed a power distribution strategy based on fuzzy control to extend the lifetime of the MFCS. The strategy was verified by simulations. The simulation results show that the strategy can effectively control the inconsistencies among the stacks and significantly extend the lifetime of the MFCS.

关键词：