检索结果-内蒙古大学图书馆

Pattern Recognition and Artificial intelligence (PRAI), International Conference on

作者： You Wang Zehao Wang Jingchuan Wang Rui Guo Peng Xiao Institute of Medical Robotics and Department of Automation Ministry of Education Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai China State Grid Intelligence Technology CO. LTD

The motion primitive-based state lattice trajectory planning method has been widely used in the field of trajectory planning. However, due to the limitations of the search space and resolution of motion primitives, and the lack of consideration of scenario information during offline generation of motion primitives, the tractor-trailer vehicles can easily fall into "jackknife phenomenon" when making large pose adjustments in narrow scenarios, which brings dilemma for trajectory planning. In this paper, a trajectory planning algorithm is proposed based on a general model of tractor-trailer vehicle, which combines global planning and local optimization. The method first generates a series of motion primitives, including forward and backward driving conditions, and then an A ∗ based global state lattice planner is used to obtain a planning result, which is imported as the initial solution into the local trajectory optimizer based on PI 2 − CMA (Path Integral Policy Improvement with Covariance Matrix Adaptation) algorithm and dynamic potential method. Experiments show that this method significantly improves the performance in the obstacle avoidance, "jackknife phenomenon" avoidance and curvature compared to traditional motion primitive-based state lattice planning methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Comprehensive Feature Aggregation Network for Road Scene Segmentation

Cross-Modality Comprehensive Feature Aggregation Network for...

引用

International Symposium on Computer Science and Intelligent controls (ISCSIC)

作者： Yale Yang Zihao Zhang Huifang Hou Wenwen Zhang Chunsheng Zhuang College of Information Science and Engineering Henan University of Technology Zhengzhou China Key Laboratory of Grain Information Processing and Control Ministry of Education Henan Key Laboratory of Grain Photoelectric Detection and Control and school of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou China School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou China Henan Academy of Sciences Zhengzhou China

ISBN: (数字)9798350380286

ISBN: (纸本)9798350380293

RGB-thermal semantic segmentation is a potential solution for reliable semantic scene understanding under adverse weather and complex lighting conditions. However, past studies have primarily focused on the design of fusion paradigms. Unfortunately, these methods have not fully considered the modality differences caused by different imaging mechanisms, thereby reducing the performance of pixel-level semantic analysis. In response to this issue, this paper proposes an innovative Cross-Modality Comprehensive Feature Aggregation Network (CFANet). This method first designs a Cross-Modality Feature Rectification Module (CFRM) to align modality differences; then, it constructs a Global-Local Fusion Module (GLF) to sharpen object edges and refine the segmentation map. Results on two urban scene understanding datasets demonstrate that CFANet can effectively aggregate multi-layer deep features and outperform existing advanced deep learning methods in scene understanding performance.

关键词： Deep learning Semantic segmentation Roads Design methodology Semantics Lighting Imaging Reliability Meteorology Intelligent control

来源：评论

学校读者我要写书评

暂无评论

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEEP NEURAL NETWORKS 8

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEE...

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Zhang, Xiao Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the expressivity of the DNN. This paper provides a novel and meticulous perspective to look into DNNs: Instead of just counting the number of the linear regions, we study their local properties, such as the inspheres, the directions of the corresponding hyperplanes, the decision boundaries, and the relevance of the surrounding regions. We empirically observed that different optimization techniques lead to completely different linear regions, even though they result in similar classification accuracies. We hope our study can inspire the design of novel optimization techniques, and help discover and analyze the behaviors of DNNs. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Adversarial attacks and defenses in physiological computing:a systematic review

引用

National Science Open 2023年第1期2卷 62-90页

作者： Dongrui Wu Jiaxin Xu Weili Fang Yi Zhang Liuqing Yang Xiaodong Xu Hanbin Luo Xiang Yu Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China School of Civil and Hydraulic Engineering Huazhong University of Science and TechnologyWuhan 430074China College of Public Administration Huazhong University of Science and TechnologyWuhan 430074China Electrical Engineering and Computer Science Department University of MichiganAnn Arbor MI 48109USA School of Management and Sino-European Institute for Intellectual Property Huazhong University of Science and TechnologyWuhan 430074China

Physiological computing uses human physiological data as system inputs in real *** includes,or significantly overlaps with,brain-computer interfaces,affective computing,adaptive automation,health informatics,and physiological signal based *** computing increases the communication bandwidth from the user to the computer,but is also subject to various types of adversarial attacks,in which the attacker deliberately manipulates the training and/or test examples to hijack the machine learning algorithm output,leading to possible user confusion,frustration,injury,or even ***,the vulnerability of physiological computing systems has not been paid enough attention to,and there does not exist a comprehensive review on adversarial attacks to *** study fills this gap,by providing a systematic review on the main research areas of physiological computing,different types of adversarial attacks and their applications to physiological computing,and the corresponding defense *** hope this review will attract more research interests on the vulnerability of physiological computing systems,and more importantly,defense strategies to make them more secure.

关键词： physiological computing brain-computer interfaces health informatics biometrics machine learning adversarial attack

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Network-Based Electromagnetic Signal Classification: A Semi- Supervised Learning Framework

引用

China Communications 2020年第10期17卷 157-169页

作者： Huaji Zhou Licheng Jiao Shilian Zheng Lifeng Yang Weiguo Shen Xiaoniu Yang Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial IntelligenceXidian UniversityXi'an 710071China Science and Technology on Communication Information Security Control Laboratory Jiaxing 314033China

Generative adversarial network(GAN)has achieved great success in many fields such as computer vision,speech processing,and natural language processing,because of its powerful capabilities for generating realistic *** this paper,we introduce GAN into the field of electromagnetic signal classification(ESC).ESC plays an important role in both military and civilian ***,in many specific scenarios,we can’t obtain enough labeled data,which cause failure of deep learning methods because they are easy to fall into ***,semi-supervised learning(SSL)can leverage the large amount of unlabeled data to enhance the classification performance of classifiers,especially in scenarios with limited amount of labeled *** present an SSL framework by incorporating GAN,which can directly process the raw in-phase and quadrature(IQ)signal *** to the characteristics of the electromagnetic signal,we propose a weighted loss function,leading to an effective classifier to realize the end-to-end classification of the electromagnetic *** validate the proposed method on both public RML2016.04c dataset and real-world Aircraft Communications Addressing and Reporting System(ACARS)signal *** experimental results show that the proposed framework obtains a significant increase in classification accuracy compared with the state-of-the-art studies.

关键词： generative adversarial network semi-supervised learning electromagnetic signal classification end-to-end classification weighted loss function

来源：评论

学校读者我要写书评

暂无评论

Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling

arXiv

引用

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

Tiny noise, big mistakes: adversarial perturbations induce errors in brain–computer interface spellers

引用

National Science Review 2021年第4期8卷 78-90页

作者： Xiao Zhang Dongrui Wu Lieyun Ding Hanbin Luo Chin-Teng Lin Tzyy-Ping Jung Ricardo Chavarriaga Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Civil Engineering and Mechanics Huazhong University of Science and Technology Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Swartz Center for Computational Neuroscience Institute for Neural ComputationUniversity of California San Diego Center for Advanced Neurological Engineering Institute of Engineering in Medicine University of California San Diego ZHAW Data Lab Zürich University of Applied Sciences

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 *** 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.

关键词： electroencephalogram brain-computer interfaces BCI spellers adversarial examples

来源：评论

学校读者我要写书评

暂无评论

GraphMFT: A graph network based multimodal fusion technique for emotion recognition in conversation

arXiv

引用

arXiv 2022年

作者： Li, Jiang Wang, Xiaoping Lv, Guoqing Zeng, Zhigang Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems Wuhan430074 China

Multimodal machine learning is an emerging area of research, which has received a great deal of scholarly attention in recent years. Up to now, there are few studies on multimodal Emotion Recognition in Conversation (ERC). Since Graph Neural Networks (GNNs) possess the powerful capacity of relational modeling, they have an inherent advantage in the field of multimodal learning. GNNs leverage the graph constructed from multimodal data to perform intra- and inter-modal information interaction, which effectively facilitates the integration and complementation of multimodal data. In this work, we propose a novel Graph network based Multimodal Fusion Technique (GraphMFT) for emotion recognition in conversation. Multimodal data can be modeled as a graph, where each data object is regarded as a node, and both intra- and inter-modal dependencies existing between data objects can be regarded as edges. GraphMFT utilizes multiple improved graph attention networks to capture intra-modal contextual information and inter-modal complementary information. In addition, the proposed GraphMFT attempts to address the challenges of existing graph-based multimodal conversational emotion recognition models such as MMGCN. Empirical results on two public multimodal datasets reveal that our model outperforms the State-Of-The-Art (SOTA) approaches with the accuracy of 67.90% and 61.30%. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Lithium-ion battery state-of-charge estimation using a real-time moving horizon estimation algorithm

Lithium-ion battery state-of-charge estimation using a real-...

引用

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Yan, Jiayu Li, Song Wan, Yiming Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China 29th Research Institute of China Electronics Technology Group Corporation Chengdu China

ISBN: (纸本)9781665401159

For battery management systems, it is significant to reliably estimate state-of-charge (SOC) from limited measurements in real time. Based on a nonlinear SOC-dependent equivalent circuit model, we propose a real-time moving horizon estimation (MHE) algorithm for SOC estimation. For efficient computation, the sequential quadratic programming strategy is applied, and each quadratic programming (QP) iteration is solved via the structure-exploiting forward and backward recursions. To account for the limited computation time allowed within each sampling interval, the proposed algorithm does not fully solve the receding horizon optimization problem over each sliding window, but performs fixed number of QP iterations. The simulation results show that compared to the existing fully solved MHE applied to SOC estimation, the proposed real-time MHE algorithm significantly saves computation time at the cost of a slight loss of estimation performance. © 2021 IEEE.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

arXiv

引用

arXiv 2024年

作者： Yan, Tingbing Zeng, Wenzheng Xiao, Yang Tong, Xingyu Tan, Bo Fang, Zhiwen Cao, Zhiguo Zhou, Joey Tianyi 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 School of Biomedical Engineering Southern Medical University Guangzhou510515 China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou510280 China Singapore Singapore Singapore Singapore

Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e.g., joint location), and may suffer from local information loss and low generalization ability. To alleviate these, we propose to leverage text description generated from large language models (LLM) that contain high-level human knowledge, to guide feature learning, in a global-local-global way. Particularly, during training, we design 2 prompts to gain global and local text descriptions of each action from an LLM. We first utilize the global text description to guide the skeleton encoder focus on informative joints (i.e.,global-tolocal). Then we build non-local interaction between local text and joint features, to form the final global representation (i.e., local-to-global). To mitigate the asymmetry issue between the training and inference phases, we further design a dual-branch architecture that allows the model to perform novel class inference without any text input, also making the additional inference cost neglectable compared with the base skeleton encoder. Extensive experiments on three different benchmarks show that CrossGLG consistently outperforms the existing SOTA methods with large margins, and the inference cost (model size) is only 2.8% than the previous SOTA. CrossGLG can also serve as a plug-and-play module that can substantially enhance the performance of different SOTA skeleton encoders with a neglectable cost during inference. The source code will be released soon. © 2024, CC BY.

关键词： Signal encoding

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：