检索结果-内蒙古大学图书馆

IEEE International Conference on image processing

作者： Zihan Ni Jia Chen Nong Sang Changxin Gao Leyuan Liu Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

This paper proposes an efficient model named Light YOLO for hand gesture recognition on the embedded platforms. Light YOLO improves accuracy, speed, and model size, in three aspects. To deal with the small scale gestures in practical applications, we strengthen the YOLOv2 with a spatial refinement module to obtain fine-grained features. To accelerate the refined network, we propose a selective-dropout channel pruning approach to prune the redundancy convolution kernels in the network. Moreover, we introduce a dataset for hand gesture recognition in complex scenes. The experimental results on this dataset show that the proposed Light YOLO significantly improve the YOLOv2 network, i.e., accuracy from 96.80% to 98.06%, speed form 40PFS to 125FPS, and size form 250M to 4MB.

关键词： Gesture recognition Feature extraction Detectors Acceleration Taylor series Kernel Cost function

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale YOLOv2 for Hand Detection in Complex Scenes

Multi-Scale YOLOv2 for Hand Detection in Complex Scenes

引用

International Conference on control, Automation, Robotics and Vision (ICARCV)

作者： Jia Chen Zihan Ni Nong Sang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

This paper presents a model named Multi-Scale YOLOv2 (MS-YOLOv2) for hand detection in complex scenes. The proposed MS-YOLOv2 is implemented by introducing three modules to YOLOv2, including a Multi-Scale Feature Refinement Module to acquire fine-grained features, a Channel Importance Evaluation Module to recalibrate feature channels and a Hard Example Punishment Module to get rid of hand interference areas. Experiment results show that the proposed MS-YOLOv2 makes much performance improvement to YOLOv2, but with little computational complexity gain. On our dataset, the proposed MS-YOLOv2 can achieve 98.2% of AP and 97.9% of AR. Moreover, on the VIVA challenge, the proposed MS-YOLOv2 achieves AP/AR of 85.1%/45.8% at Level-1 and 80.1%/45.9% at Level-2.

关键词： Feature extraction Detectors Object detection Skin Color Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

3D-EPI Blip-Up/Down Acquisition (BUDA) with CAIPI and Joint Hankel Structured Low-Rank Reconstruction for Rapid Distortion-Free High-Resolution T2* Mapping

arXiv

引用

arXiv 2022年

作者： Chen, Zhifeng Liao, Congyu Cao, Xiaozhi Poser, Benedikt A. Xu, Zhongbiao Lo, Wei-Ching Wen, Manyi Cho, Jaejin Tian, Qiyuan Wang, Yaohui Feng, Yanqiu Xia, Ling Chen, Wufan Liu, Feng Bilgic, Berkin School of Biomedical Engineering Guangdong Provincial Key Laboratory of Medical Image Processing Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology Southern Medical University Guangzhou China Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Department of Radiology Harvard Medical School CharlestownMA United States Department of Data Science and AI Faculty of IT Monash University ClaytonVIC Australia Department of Radiology Stanford University Stanford CA United States Maastricht Brain Imaging Center Faculty of Psychology and Neuroscience University of Maastricht Netherlands Department of Radiotherapy Cancer Center Guangdong Provincial People's Hospital Guangdong Academy of Medical Science Guangzhou China Siemens Medical Solutions BostonMA United States Department of Chemical Pathology The Chinese University of Hong Kong Hong Kong Division of Superconducting Magnet Science and Technology Institute of Electrical Engineering Chinese Academy of Sciences Beijing China Guangdong-Hong Kong-Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence Key Laboratory of Mental Health of the Ministry of Education Southern Medical University Guangzhou China Department of Biomedical Engineering Zhejiang University Hangzhou China Research Center for Healthcare Data Science Zhejiang Lab Hangzhou China School of Information Technology and Electrical Engineering The University of Queensland BrisbaneQLD Australia Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States

Purpose: This work aims to develop a novel distortion-free 3D-EPI acquisition and image reconstruction technique for fast and robust, high-resolution, whole-brain imaging as well as quantitative T2* mapping. Methods: 3D-Blip-Up and -Down Acquisition (3D-BUDA) sequence is designed for both single- and multi-echo 3D GRE-EPI imaging using multiple shots with blip-up and -down readouts to encode B0 field map information. Complementary k-space coverage is achieved using controlled aliasing in parallel imaging (CAIPI) sampling across the shots. For image reconstruction, an iterative hard-thresholding algorithm is employed to minimize the cost function that combines field map information informed parallel imaging with the structured low-rank constraint for multi-shot 3D-BUDA data. Extending 3D-BUDA to multi-echo imaging permits T2* mapping. For this, we propose constructing a joint Hankel matrix along both echo and shot dimensions to improve the reconstruction. Results: Experimental results on in vivo multi-echo data demonstrate that, by performing joint reconstruction along with both echo and shot dimensions, reconstruction accuracy is improved compared to standard 3D-BUDA reconstruction. CAIPI sampling is further shown to enhance the image quality. For T2* mapping, T2* values from 3D-Joint-CAIPI-BUDA and reference multi-echo GRE are within limits of agreement as quantified by Bland-Altman analysis. Conclusions: The proposed technique enables rapid 3D distortion-free high-resolution imaging and T2* mapping. Specifically, 3D-BUDA enables 1-mm isotropic whole-brain imaging in 22 s at 3 T and 9 s on a 7 T scanner. The combination of multi-echo 3D-BUDA with CAIPI acquisition and joint reconstruction enables distortion-free whole-brain T2* mapping in 47 s at 1.1×1.1×1.0 mm3 resolution. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Sleep Stage Classification

Deep Learning for Sleep Stage Classification

引用

Chinese Automation Congress (CAC)

作者： Yang Wang Dongrui Wu Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

Scoring of sleep stages plays an important role in the diagnosis of sleep-related diseases. Scoring by visual inspection is time-consuming and heavily depends on the experience of experts. Thus, there is an urgent need for an automatic sleep stage classification system. This paper proposes a novel compact convolutional neural network (C-CNN) using only single-channel EEG signal. Compared with traditional machine learning approaches based on hand-engineered features, our approach provides an end-to-end solution that requires almost no prior knowledge and preprocessing while achieving better performance. Experiments on the expanded Sleep-EDF database verified its effectiveness and efficiency. In addition, we notice the issue of class imbalance in sleep stages, and a class-imbalance metric, the balanced classification accuracy (BCA), is introduced. At the cost of a little drop in accuracy, which is still higher than existing classification methods, the introduction of class-imbalance weights can significantly increase the BCA metric and result in a higher recall for each sleep stage. This paper also proposes a recurrent neural network based on the attention mechanism and bidirectional long short-term memory (LSTM), which provides better performance than C-CNN but requires more training time.

关键词： Feature extraction Sleep Electroencephalography Training Convolution Brain modeling Deep learning

来源：评论

学校读者我要写书评

暂无评论

Micro Channel for Analyzing Mechanical Adaption of Cancer Cell

Micro Channel for Analyzing Mechanical Adaption of Cancer Ce...

引用

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Pengyun Li Xiaoming Liu Xiaoqing Tang Masaru Kojima Jian Huang Qiang Huang Tatsuo Arai Beijing Advanced Innovation Center for Intelligent Robots and Systems and the Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China Osaka University 1-3 Machikaneyama Toyonaka Osaka Japan Key Laboratory of Ministry of Education for Image Processing and Intelligent Control the School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728150734

ISBN: (纸本)9781728150741

It was reported that cancer cells could biologically respond and adapt to the confined environment during migration in extracellular matrix (ECM). But it is not clearly studied that how cancer cells respond and adapt to confined environment in mechanical way. Thus, in this study, we designed and fabricated a kind of one-layer micro channel to mimic confined environment for analyzing mechanical adaption of cell. This micro channel could apply sequential mechanical stresses on a number of cells with high throughput, and the time of cells passing through five rows of micro channels were used to evaluate their adaptability to the sequential and confined space. In experiments, each cell suffered 20 times of mechanical stresses after passing through 20 squeezing channels arranged in 5 rows. We observed the sequential squeezing processes under microscope and investigated the passing time using a high-speed camera. The preliminary results indicated that cancer cells could pass through and adapt to the confined environment faster than normal cells.

关键词：

来源：评论

学校读者我要写书评

暂无评论

$H_{\infty}$ consensus control of fractional-order multi-agent systems over the directed graph

$H_{\infty}$ consensus control of fractional-order multi-age...

引用

Chinese control Conference (CCC)

作者： Lin Chen Wen-Sen Wang Hao Wu Yan Lei Jiang-Wen Xiao Key Laboratory of Image Processing and Intelligent Control Ministry of Education State grid shanxi electric power research institute

In this paper, the H ∞ consensus of fractional-order multi-agent systems with directed communication graph is investigated. It's the first time to introduce the H ∞ control to investigate the consensus problem of the fractional-order multi-agent systems. In view of Mittag-Leffler stability theory and fractional Lyapunov directed method, a sufficient condition is presented to guarantee all the agents reach consensus with the desired H ∞ performance. Finally, the results are verified by several numerical simulations.

关键词： Multi-agent systems control systems Laplace equations Eigenvalues and eigenfunctions Power system stability Stability analysis Graph theory

来源：评论

学校读者我要写书评

暂无评论

Spatial filtering for brain computer interfaces: A comparison between the common spatial pattern and its variant

arXiv

引用

arXiv 2018年

作者： He, He Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology Wuhan China

The electroencephalogram (EEG) is the most popular form of input for brain computer interfaces (BCIs). However, it can be easily contaminated by various artifacts and noise, e.g., eye blink, muscle activities, powerline noise, etc. Therefore, the EEG signals are often filtered both spatially and temporally to increase the signal-to-noise ratio before they are fed into a machine learning algorithm for recognition. This paper considers spatial filtering, particularly, the common spatial pattern (CSP) filters for EEG classification. In binary classification, CSP seeks a set of filters to maximize the variance for one class while minimizing it for the other. We first introduce the traditional solution, and then a new solution based on a slightly different objective function. We performed comprehensive experiments on motor imagery to compare the two approaches, and found that generally the traditional CSP solution still gives better results. We also showed that adding regularization to the covariance matrices can improve the final classification performance, no matter which objective function is used. Copyright © 2018, The Authors. All rights reserved.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

MIME-KNN: Improve KNN Classifier Performance Include Classification Accuracy and Time Consumption

MIME-KNN: Improve KNN Classifier Performance Include Classif...

引用

2018 International Conference on Computer Science and Software Engineering (CSSE 2018)

作者： Taizhang Shang Xiang Xia Jun Zheng School of Automation Huazhong University of Science and Technology (HUST) Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education

The K Nearest Neighbor(KNN) classifier has been widely used in the applications of data mining and machine learning, because of its simple implementation and distinguished performance. However, because the distance between all training samples and test samples have to be calculated, when there are too many samples or samples have huge features dimensionality, the time complexity and space complexity are high. The paper proposes a KNN algorithm with the minimum intra-class distance and the maximum extra-class distance(MIME-KNN). By finding a transformation matrix, the algorithm minimizes the intra-class distance and maximizes the distance between classes, which can improve the classification performance of traditional KNN algorithm. At the same time, the algorithm will also reduce the dimensionality of the samples to achieve the purpose of reducing time and space complexity. Experimental results show that the MIME-KNN work well in practical.

关键词： MIME-KNN Improve KNN Classifier Performance Include Classification Accuracy and Time Consumption

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Ensemble Learning for Class Imbalance Problems

Unsupervised Ensemble Learning for Class Imbalance Problems

引用

Chinese Automation Congress

作者： Zihan Liu Dongrui Wu Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology Wuhan China

Ensemble learning, which aggregates multiple base (weak) learners to obtain a strong learner, is an effective approach for improving the generalization performance of a machine learning model. Several completely unsupervised ensemble learning approaches have been proposed in the literature for binary classification. However, most of them only considered the case that the two classes are balanced, and hence their performances deteriorate when there is significant class imbalance, which often happens in practice. This paper proposes a spectral meta-learner for class imbalance (SMLCI) approach to explicitly consider the class imbalance. Experiments on 12 UCI datasets from various domains verified that SMLCI significantly outperformed the individual base classifiers, and also five existing unsupervised ensemble learning approaches, when the balanced classification accuracy is used as the performance measure.

关键词： Ensemble learning Unsupervised learning Class imbalance Binary classification

来源：评论

学校读者我要写书评

暂无评论

A WOA-based algorithm for parameter optimization of support vector regression and its application to condition prognostics 36

A WOA-based algorithm for parameter optimization of support ...

引用

第36届中国控制会议

作者： LI Sai FANG Huajing School of Automation Key Laboratory of Image Processing and Intelligent ControlMinistry of EducationHuazhong University of Science and Technology

ISBN: (纸本)9781538629185

Condition monitoring is very important for system safety and condition-based *** series prediction capabilities of machine learning like support vector regression(SVR) can be utilized for ***,choosing optimal parameters for SVR is an important step in SVR model design,which heavily affects the performance of ***,a whale optimization algorithm(WOA) based algorithm is proposed for SVR parameters *** proposed algorithm has been evaluated through some benchmark ***,the proposed method with moving window technology is used to condition prognostics of the Tennessee Eastman *** and engineering application show that the SVR-WOA method is effective,by noting that the computation time is shortened in some application scenarios.

关键词： Support vector regression Whale optimization algorithm Parameter optimization Condition prognostics

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：