检索结果-内蒙古大学图书馆

Blind noisy image separation based on a new robust independent component analysis network

Chinese Optics Letters 2006年第10期4卷 573-575页

作者：纪建田铮 Department of Computer Science & Technology Northwestern Polytechnical University Xi'an 710072 Department of Applied Mathematics Northwestern Polytechnical UniversityXi'an 710072 Key Laboratory of Education Ministry for Image Processing and Intelligent ControlHuazhong University of Science & TechnologyWuhan 430074

The separation of noisy image is a very exciting area of research, especially when no prior information is available about the noisy image. In this paper, we propose a robust independent component analysis （ICA） network for separation images contaminated with high-level additive noise or outliers. We reduce the power of additive noise by adding outlier rejection rule in ICA. Extensive computer simulations confirm robustness and the excellent performance of the resulting algorithms.

关键词： Algorithms Computer simulation Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Deep Learning-based Depression Level Estimation Based on Multi-task Learning 24

Enhancing Deep Learning-based Depression Level Estimation Ba...

引用

7th International Conference on Machine Learning and Machine Intelligence, MLMI 2024

作者： Ye, Qingxin Xie, Zhenming Sun, Hao Xin, Luyao Chen, Youwen Song, Jian Chen, Yen-Wei Provincial key Laboratory of Computational Science Huaqiao University Quanzhou China Intelligent Image Processing Lab Zhejiang University Hangzhou China Intelligent Image Processing Lab Ritsumeikan University Osaka Japan

ISBN: (纸本)9798400717833

In recent years, depression, as a serious mental illness, has received widespread attention from various sectors of society. How to identify depressive emotions in a timely manner and detect depression has become an urgent issue that needs to be addressed. Currently, many experts and scholars propose using deep learning methods to assess the level of depression. Compared to other deep learning models, Transformer models have parallel computing capabilities with their self-attention mechanism, enabling them to handle entire sequences and capture long-distance dependencies. After the success of Transformers in natural language processing, similar architectures have been introduced into the field of computer vision, promoting advancements in multi-modal research. However, how to integrate other information or tasks to improve assessment accuracy remains a challenge. In our team's preliminary work, we proposed a multi-modal adaptive fusion Transformer network for assessing depression levels. Inspired by multi-task learning, we introduced gender classification as a second auxiliary task alongside the main task of depression regression, forming a three-task learning framework including depression classification. This was done to enhance the model's performance. We validated the effectiveness of the proposed method by testing it on a public dataset (AVEC 2019 Detecting Depression with AI Sub-challenge). The experimental results show that our proposed method achieved a Concordance Correlation Coefficient (CCC) of 0.60448, which is 1.688% higher than the accuracy of the dual-task learning method (CCC = 0.5876). © 2024 Copyright held by the owner/author(s).

关键词： Multi-task learning

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

2023 China Automation Congress, CAC 2023

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

ISBN: (纸本)9798350303759

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. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection Model Based on Space-time Fusion Features and Attention Mechanism 33

Network Intrusion Detection Model Based on Space-time Fusion...

引用

第33届中国控制与决策会议

作者： Yali Wu Liting Huang Jinjin Qi Xiaoxiao Quan School of Automation and Information Engineering Xi'an University of Technology Shaanxi ProvinceKeyLaboratory of Complex System Control and Intelligent Information Processing Shaanxi Province Key Laboratory of Complex System Control and Intelligent Information Processing

ISBN: (纸本)9781665431293

To solve the problem of low performance of network intrusion detection,a deep learning intrusion detection model based on space-time fusion features and attention mechanism—CLT-net is *** this model,space-time fusion features are obtained by integrating convolutional neural network and long short-time memory network,and attention module is added to calculate the importance of the input features,and softmax function is used for *** a large number of simulation experiments on NSL-KDD data sets,CLT-net has significantly improved the convergence of the training set and the accuracy of the test *** with the traditional CNN model with similar structure and the space-time fusion CLSTM the accuracy of the model increased by 11.8% and 10.9%*** shows that this model has great potential in the application field of network intrusion detection.

关键词： Network Intrusion Detection Convolution Neural Network Long Short-term Memory Network Attention Mechanism CLT-net

来源：评论

学校读者我要写书评

暂无评论

Robust PolInSAR optimal interferogram estimation method based on generalized scattering vector

引用

Journal of Systems Engineering and Electronics 2017年第3期28卷 457-471页

作者： Zhiyong Suo Ming Li National Lab of Radar Singal Processing Xidian UniversityXi’an 710071China Beijing Aerospace Automatic Control Institute Beijing 100854China National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing 100854China

For the polarimetric synthetic aperture radar interferometry (PoIInSAR) processing, it is necessary to coregister all the images, including the coregistration of polarimetric SAR images and the coregistration of interferometric SAR images. Otherwise, the performance of the estimated optimal interferograms will be deteriorated. A generalized scattering vector (GSV) model is proposed to execute the PoIInSAR optimal interferograms estimation. The generalized scattering vector is constructed by the Pauli scattering vectors of the processing pixel and the surrounding pixels. Even though there are coregistration errors, all the polarimetric information of the current processing pixel is entirely included in the generalized scattering vector. Therefore, the GSV-based method can automatically recover the optimal scattering mechanisms of the processing pixel with coregistration errors either in interferoemetric channels or polarimetric channels. Theoretical analysis and processing results of simulated PoISARPro data and real PALSAR data validate the effectiveness and correctness of the proposed method.

关键词： polarimetric synthetic aperture radar interferometry (PoIInSAR) generalized scattering vector (GSV) optimal interferogram coregistration error Pauli basis

来源：评论

学校读者我要写书评

暂无评论

Weak value amplification via second-order correlated technique

引用

Chinese Physics B 2016年第2期25卷 58-61页

作者：崔挺黄靖正刘翔曾贵华 State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Laboratory on Navigation and Location-based Serviceand Center of Quantum Information Sensing and Processing Shanghai Jiao Tong University Shanghai Key Laboratory of Aerospace Intelligent Control Technology Shanghai Institute of Spaceflight Control Technology College of Information Science and Technology Northwest University

We propose a new framework combining weak measurement and second-order correlated technique. The theoretical analysis shows that weak value amplification （WVA） experiment can also be implemented by a second-order correlated system. We then build two-dimensional second-order correlated function patterns for achieving higher amplification factor and discuss the signal-to-noise ratio influence. Several advantages can be obtained by our proposal. For instance, detectors with high resolution are not necessary. Moreover, detectors with low saturation intensity are available in WVA setup. Finally, type-one technical noise can be effectively suppressed.

关键词： weak measurement two-dimensional second-order correlated function

来源：评论

学校读者我要写书评

暂无评论

Indoor localization with incomplete observation using set-membership filter

Indoor localization with incomplete observation using set-me...

引用

International Symposium on Micro-NanoMechatronics and Human Science, MHS 2015

作者： Wang, Yuan Huang, Jian Key Lab of Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781479966783

Indoor localization is a popular topic because of the poor performance of GPS in the indoor environment. This paper has provided a new method to achieve the goal of indoor localization. Combining the usage of posture sensors with the Radio Frequency Identification (RFID) technology, we solved the problem of plentiful tags in the traditional RFID indoor localization. The relative localization subsystem is based on posture sensors and the absolute localization subsystem is based on RFID. A set-membership theory based data fusion algorithm is proposed to fuse the data of relative localization and absolute localization. Experimental results show that the proposed data fusion algorithm could significantly reduce the accumulated error of our indoor localization system. © 2015 IEEE.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

control reconfiguration of new strap-on boosted launch vehicle [PRC] with deadlocked swing Engines

Control reconfiguration of new strap-on boosted launch vehic...

引用

作者： Liu, Lei Yin, Biao Wang, Yongji Deng, Zhixiang Department of Control Science and Engineering Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780955529337

To enhance the reliability of launch vehicle attitude control systems and prevent the control invalidation caused by swing engine deadlock, a control reconfiguration of fault-tolerant control is proposed. Firstly, the coupling identity between the channels is discussed based on the dynamic model of the vehicle. Then, under the assumption of no rolling motion, we study the swing angles reconfiguration method based on the moment balance principle, and then deduce the relationship between the swing angle of the deadlocked engines and the engines still operate well. From the rationality analysis, the safe bound of the deadlocked engine and reconfiguration conditions are proposed under several assumptions. Finally, the numerical simulation of rocket attitude control based on the discussed reconfiguration strategy is given to demonstrate that the variance of the control affect by the deadlocked engine could be rectified by other booster-engines effectively.

关键词： Launch vehicles

来源：评论

学校读者我要写书评

暂无评论

Missile-Target Situation Assessment Model Based on Reinorcement Learning

引用

Journal of Shanghai Jiaotong university(Science) 2020年第5期25卷 561-568页

作者： ZHANG Yun LU Runyan CAI Yunze Department of Automation Key Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China

In situation assessment(SA)of missile versus target fighter,the traditional SA models generally have the characteristics of strong subjectivity and poor dynamic *** paper considers SA as an expectation of future returns and establishes a missile-target simulation battle *** actor-critic(AC)algorithm in reinforcement learning(RL)is used to train the evaluation network,and a missile-target SA model is established in simulation battle *** and comparative experiments show that the model can effectively estimate the expected effect of missile attack under the current situation,and it provides an effective basis for missile attack decision.

关键词： situation assessment(SA) battle model reinforcement learning(RL) actor-critic(AC)algorithm

来源：评论

学校读者我要写书评

暂无评论

Real-time target tracking with particle filter in moving monocular camera

Real-time target tracking with particle filter in moving mon...

引用

5th International Symposium on Multispectral image processing and Pattern Recognition

作者： Liu, Guocheng Wang, Yongji Huazhong Univ Sci & Technol Key Lab Image Processing & Intelligent Control Chinese Educ Minist Wuhan 430072 Peoples R China

ISBN: (纸本)9780819469502

In this paper, we propose an improved particle filter algorithm for real-time tracking a randomly moving target in dynamic environment with a moving monocular camera. For making the tracking task robustly and effectively, color histogram based target model is integrated into particle filter algorithm. Bhattacharyya distance is used to weight samples by calculating each sample's histogram with a specified target model and it makes the measurement matching and samples' weight updating more reasonable. In order to reduce sample depletion, the improved algorithm will be able to take the latest observation into account. The experimental results confirm that the method is effective even when the monocular camera is moving and the target object is partially occluded in a clutter background.

关键词： visual tracking particle filter state-space model

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：