检索结果-内蒙古大学图书馆

Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellers

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Xiao Wu, Dongrui Ding, Lieyun Luo, Hanbin Lin, Chin-Teng Jung, Tzyy-Ping Chavarriaga, Ricardo Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Civil Engineering and Mechanics Huazhong University of Science and Technology Wuhan430074 China Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Sydney2007 Australia La Jolla CA92093 United States Center for Advanced Neurological Engineering Institute of Engineering in Medicine UCSD La Jolla CA92093 United States ZHAW DataLab Zürich University of Applied Sciences Winterthur8401 Switzerland

An electroencephalogram (EEG) based brain-computer interface (BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g., amyotrophic lateral sclerosis patients, who have no other effective means of communication with another person or a computer. Most studies so far focused on making EEG-based BCI spellers faster and more reliable;however, few have considered their security. This study, for the first time, shows that P300 and steady-state visual evoked potential BCI spellers are very vulnerable, i.e., they can be severely attacked by adversarial perturbations, which are too tiny to be noticed when added to EEG signals, but can mislead the spellers to spell anything the attacker wants. The consequence could range from merely user frustration to severe misdiagnosis in clinical applications. We hope our research can attract more attention to the security of EEG-based BCI spellers, and more broadly, EEG-based BCIs, which has received little attention before. Copyright © 2020, The Authors. All rights reserved.

关键词： Electroencephalography

学校读者我要写书评

暂无评论

Network Resilience

arXiv 2020年

作者： Liu, Xueming Li, Daqing Ma, Manqing Szymanski, Boleslaw K. Eugene Stanley, H. Gao, Jianxi Key Laboratory of Image Information Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China School of Reliability and Systems Engineering Beihang University Beijing100191 China College of Safety Science and Engineering Civil Aviation University of China Tianjin 300300 China Department of Computer Science Rensselaer Polytechnic Institute TroyNY12180 United States Network Science and Technology Center Rensselaer Polytechnic Institute TroyNY12180 United States Center for Polymer Studies Department of Physics Boston University BostonMA02215 United States

Many systems on our planet shift abruptly and irreversibly from the desired state to an undesired state when forced across a "tipping point". Some examples are mass extinctions within ecosystems, cascading failures in infrastructure systems, and changes in human and animal social networks. The ability to avoid such regime shifts or to recover quickly from such a non-resilient state demonstrates a system's resilience;system resilience is a quality that enables a system to adjust its activities to retain its basic functionality when errors and failures occur. In the past 50 years, attention has been paid almost exclusively to low-dimensional systems;scholars have focused on the calibration of the resilience functions of such systems and the identification of indicators of early warning signals based on two to three connected components. In recent years, taking advantage of network theory and the availability of lavish real datasets, network scientists have begun to explore real-world complex networked multidimensional systems, as well as their resilience functions and early warning indicators. This report presents a comprehensive review of resilience functions and regime shifts in complex systems in domains such as ecology, biology, society, and infrastructure. The research approach includes empirical observations, experimental studies, mathematical modeling, and theoretical analysis. We also review the definitions of some ambiguous terms, including robustness, resilience, and stability. Copyright © 2020, The Authors. All rights reserved.

关键词： Complex networks

Learning a discriminative feature network for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yu, Changqian Wang, Jingbo Peng, Chao Gao, Changxin Yu, Gang Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology Key Laboratory of Machine Perception Peking University Megvii Inc.

Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction. To tackle these two problems, we propose a Discriminative Feature Network (DFN), which contains two sub-networks: Smooth Network and Border Network. Specifically, to handle the intra-class inconsistency problem, we specially design a Smooth Network with Channel Attention Block and global average pooling to select the more discriminative features. Furthermore, we propose a Border Network to make the bilateral features of boundary distinguishable with deep semantic boundary supervision. Based on our proposed DFN, we achieve stateof-the-art performance 86.2% mean IOU on PASCAL VOC 2012 and 80.3% mean IOU on Cityscapes dataset. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantic Segmentation

Affect estimation in 3d space using multi-task active learning for regression

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wu, Dongrui Huang, Jian 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

—Acquisition of labeled training samples for affective computing is usually costly and time-consuming, as affects are intrinsically subjective, subtle and uncertain, and hence multiple human assessors are needed to evaluate each affective sample. Particularly, for affect estimation in the 3D space of valence, arousal and dominance, each assessor has to perform the evaluations in three dimensions, which makes the labeling problem even more challenging. Many sophisticated machine learning approaches have been proposed to reduce the data labeling requirement in various other domains, but so far few have considered affective computing. This paper proposes two multi-task active learning for regression approaches, which select the most beneficial samples to label, by considering the three affect primitives simultaneously. Experimental results on the VAM corpus demonstrated that our optimal sample selection approaches can result in better estimation performance than random selection and several traditional single-task active learning approaches. Thus, they can help alleviate the data labeling problem in affective computing, i.e., better estimation performance can be obtained from fewer labeling queries. Copyright © 2018, The Authors. All rights reserved.

关键词： Regression analysis

Impulsive Multisynchronization of Coupled Multistable Neural Networks with Time-Varying Delay

学校读者我要写书评

暂无评论

IEEE Transactions on Neural Networks and Learning Systems 2017年第7期28卷 1560-1571页

作者： Wang, Yan-Wu Yang, Wu Xiao, Jiang-Wen Zeng, Zhi-Gang School of Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China

This paper studies the synchronization problem of coupled delayed multistable neural networks (NNs) with directed topology. To begin with, several sufficient conditions are developed in terms of algebraic inequalities such that every subnetwork has multiple locally exponentially stable periodic orbits or equilibrium points. Then two new concepts named dynamical multisynchronization (DMS) and static multisynchronization (SMS) are introduced to describe the two novel kinds of synchronization manifolds. Using the impulsive control strategy and the Razumikhin-Type technique, some sufficient conditions for both the DMS and the SMS of the controlled coupled delayed multistable NNs with fixed and switching topologies are derived, respectively. Simulation examples are presented to illustrate the effectiveness of the proposed results. © 2012 IEEE.

关键词： Topology

Dynamic vehicle scheduling based on HTN 36

学校读者我要写书评

暂无评论

Dynamic vehicle scheduling based on HTN

第36届中国控制会议

作者： Yindong Shen Zhongyi Zeng Zhewei Wu School of Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology) Ministry of Education

ISBN: (纸本)9781538629185

Vehicle scheduling plays a crucial role in public transport bus companies. An efficient schedule can help bus companies reduce operating costs while being an essential guide to daily operations. However, the precompiled schedule is usually hard to be adhered to in practice due to the diversity of traffic and driving conditions. Therefore, dynamic vehicle scheduling becomes an important supplement to the daily operations. In this paper, a dynamic vehicle scheduling approach based on Hierarchical Task Network(HTN) is proposed. In the approach, two dynamic vehicle scheduling strategies are devised according to the practical scheduling philosophy. The first is to reschedule for individual vehicle independently, the objective is to maximize the execution of the precompiled schedule. The second is to reschedule for multiple vehicles simultaneously, which aims to maintain the scheduled headways. The two strategies are achieved in the HTN planning through different task decomposition processes, which are constrained by vehicle resources currently available. To verify the feasibility, this approach is implemented based on the Simple Hierarchical Ordered Planner 2(SHOP2), which is a domainindependent and state-based forward HTN planner. Experimental results show that the approach has good adaptability to solve dynamic vehicle schedule problem, meanwhile, it can be helpful to deal with the abnormal services agilely and hence to increase the service quality of public transit.

关键词： public transit dynamic vehicle scheduling scheduling strategies HTN planning SHOP2

Heterogeneous belief formation method based on BP neural network

学校读者我要写书评

暂无评论

Heterogeneous belief formation method based on BP neural net...

2018 2nd International Conference on Electronic Information Technology and Computer Engineering (EITCE 2018)

作者： Yifan Zhuang Hongwei Wang Xi Chen School of Automation Huazhong University of Science and Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China School of Management Huazhong University of Science and Technology

The BDI model has always been the focus of subject modeling research, which includes three kinds of thinking states of the rational subject: Belief, Desire and Intention. Belief is the cognition of agent to the world;it is a collection of environmental information, other agent information, and its own information that the agent has;and it is also the basis of the agent's thinking activity. Due to differences in the individual's living environment and experience, the formation of heterogeneous beliefs is an important issue in the BDI model study. This article divides individual belief set into two parts: knowledge belief and achievable belief. This article proposes an overall framework for the formation of individual heterogeneity beliefs: First, the individual's knowledge experience is modeled, and the empirical knowledge is structured and quantified into binary propositions;then the BP neural network learn and memory propositions of different combinations to form heterogeneous beliefs. Experiments show that this method can simulate the heterogeneity of individual beliefs caused by the individual's own experience, and can realize the belief generation mechanism of gradual information flow, limited attention and heterogeneous priors.

关键词： agent Heterogeneous belief formation method based on BP neural network

IMPROVING PERSON RE-IDENTIFICATION BY ADAPTIVE HARD SAMPLE MINING

学校读者我要写书评

暂无评论

IMPROVING PERSON RE-IDENTIFICATION BY ADAPTIVE HARD SAMPLE M...

IEEE International Conference on image processing

作者： Kezhou Chen Yang Chen Chuchu Han Nong Sang Changxin Gao Ruolin Wang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China School of Civil Engineering Wuhan University Wuhan China

The field of person re-identification has made significant advances riding on the wave of deep learning. However, owing to the fact that there are much more easy examples than those meaningful hard examples in dataset, the training tends to stagnate quickly and the model may suffer from over-fitting. Therefore, the hard sample mining method is fateful to optimize the model and improve the learning efficiency. In this paper, an Adaptive Hard Sample Mining algorithm is proposed for training a robust person re-identification model. No need for hand-picking the images in the batch or designing the loss function for both positive and negative pairs, we can briefly calculate the hard level by comparing the prediction result with the true label of the sample. Meanwhile, an adaptive threshold of hard level can make the algorithm not only stay in step with training process harmoniously but also alleviate the under-fitting and over-fitting problem simultaneously. Besides, the designed network to implement the approach has good generalization performance that can be combined with various of existing models readily. Experimental results on Market-1501 and DukeMTMC-reID datasets clearly demonstrate the effectiveness of the proposed algorithm.

关键词： Training Adaptation models Computational modeling Machine learning Robustness Cameras Task analysis

Event-Triggered Distributed Extended Kalman Filtering with Randomly Occurring Deception Attack: A Variance-Constrained Approach

学校读者我要写书评

暂无评论

Event-Triggered Distributed Extended Kalman Filtering with R...

第37届中国控制会议

作者： Weihao Song Jianan Wang Jiayuan Shan Housheng Su School of Aerospace Engineering Beijing Institute of Technology School of Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology

In this paper, a distributed extended Kalman filtering algorithm is developed for a class of discrete-time nonlinear systems subject to stochastic disturbances and randomly occurring deception attacks. In order to utilize the limited communication and computation resources efficiently, the event-triggered communication scheme is introduced such that data transmission is executed only when the predefined condition is violated. Furthermore, a set of independent Bernoulli random variables with known statistical properties is defined to characterize the phenomenon of randomly occurring deception attacks. An upper bound for the estimation error covariance considering the event-triggered meachanism and linearization errors is derived via the varianceconstrained approach. The filter gain for each node can be calculated recursively by solving two Raccati-like difference equations to minimize such an upper bound, which is suitable for online application. Finally, an illustrative example is presented to verify the feasibility and effectiveness of the proposed algorithm.

关键词： Distributed filtering Event-triggered scheme Deception attacks Variance constraints