检索结果-南通市图书馆

Fault Classification for On-board Equipment of High-speed Railway Based on attention Capsule Network

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2021年第5期18卷 814-825页

作者： Lu-Jie Zhou Jian-Wu Dang Zhen-Hai Zhang School of Automation and Electrical Engineering Lanzhou Jiaotong UniversityLanzhou 730070China Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphic&Image Processing Lanzhou 730070China

The conventional troubleshooting methods for high-speed railway on-board equipment, with over-reliance on personnel experience, is characterized by one-sidedness and low efficiency. In the process of high-speed train operation, numerous text-based onboard logs are recorded by on-board computers. Machine learning methods can help technicians make a correct judgment of fault types using the on-board log reasonably. Therefore, a fault classification model of on-board equipment based on attention capsule networks is proposed. This paper presents an empirical exploration of the application of a capsule network with dynamic routing in fault classification. A capsule network can encode the internal spatial part-whole relationship between various entities to identify the fault types. As the importance of each word in the on-board log and the dependencies between them have a significant impact on fault classification, an attention mechanism is incorporated into the capsule network to distill important information. Considering the imbalanced distribution of normal data and fault data in the on-board log, the focal loss function is introduced into the model to adjust the imbalanced data. The experiments are conducted on the on-board log of a railway bureau and compared with other baseline models. The experimental results demonstrate that our model outperforms the compared baseline methods, proving the superiority and competitiveness of our model.

关键词： On-board equipment fault classification capsule network attention mechanism focal loss

VAECGAN:a generating framework for long-term prediction in multivariate time series

在线全文

学校读者我要写书评

暂无评论

Cybersecurity 2021年第1期4卷 337-348页

作者： Xiang Yin Yanni Han Zhen Xu Jie Liu Institute of Information Engineering Chinese Academy of SciencesSchool of Cyber SecurityUniversity of Chinese Academy of SciencesBeijingChina Institute of Information Engineering Chinese Academy of SciencesBeijingChina Network information department China Mobile Communications Group Co.LtdBeijingChina

Long-term prediction is still a difficult problem in data *** usually use various kinds of methods of Recurrent Neural Network to ***,with the increase of the prediction step,the accuracy of prediction decreases *** order to improve the accuracy of long-term prediction,we propose a framework Variational Auto-Encoder Conditional Generative Adversarial Network(VAECGAN).Our model is divided into three *** first part is the encoder net,which can encode the exogenous sequence into latent space vectors and fully save the information carried by the exogenous *** second part is the generator net which is responsible for generating prediction *** the third part,the discriminator net is used to classify and feedback,adjust data generation and improve prediction ***,extensive empirical studies tested with five real-world datasets(NASDAQ,SML,Energy,EEG,KDDCUP)demonstrate the effectiveness and robustness of our proposed approach.

关键词： Long-term prediction Multivariate time series attention mechanism Generating framework

3D Point Cloud Semantic Segmentation Based PAConv and SE_variant

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Instrumentation 2023年第4期10卷 27-38页

作者： ZHANG Ying SUN Yue WU Lin ZHANG Lulu MENG Bumin School of automation and electronic information Xiangtan UniversityXiangtan 411105China

With the increasing popularity of 3D sensors(e.g.,Kinect)and light field cameras,technologies such as driverless,smart home and virtual reality have become hot spots for engineering *** an important part of 3D vision tasks,point cloud semantic segmentation has received a lot of attention from *** this work,we focus on realistically collected indoor point cloud data and propose a point cloud semantic segmentation method based on PAConv and SE_*** SE_variant module captures global perception from a broad perspective of feature space by fusing different pooling methods,which fully utilize the channel information of point *** effectiveness of the method is verified by comparing with other methods on S3DIS and ScanNetV2 semantic tagging benchmarks,and achieving 65.3%mIoU in S3DIS,47.6%mIoU in *** results of the ablation experiments verify the effectiveness of the key modules and analyze how to use the attention mechanism to improve the 3D semantic segmentation performance.

关键词： Semantic Segmentation Point Cloud SE_variant attention mechanism

Neural Dialogue Model with Retrieval attention for Personalized Response Generation

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第1期62卷 113-122页

作者： Cong Xu Zhenqi Sun Qi Jia Dezheng Zhang Yonghong Xie Alan Yang School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing100083China Beijing Key Laboratory of Knowledge Engineering for Materials Science University of Science and Technology BeijingBeijing100083China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Amphenol AssembleTech HoustonTX 77070US

With the success of new speech-based human-computer interfaces,there is a great need for effective and friendly dialogue agents that can communicate with people naturally and ***,the lack of personality and consistency is one of critical problems in neural dialogue *** this paper,we aim to generate consistent response with fixed profile and background information for building a realistic dialogue *** on the encoder-decoder model,we propose a retrieval mechanism to deliver natural and fluent response with proper information from a profile ***,in order to improve the efficiency of training the dataset related to profile information,we adopt a method of pre-training and adjustment for general dataset and profile *** model is trained by social dialogue data from *** to both automatic and human evaluation metrics,the proposed model significantly outperforms standard encoder-decoder model and other improved models on providing the correct profile and high-quality responses.

关键词： Dialogue system LSTM encoder-decoder model attention mechanism

Algorithm of Helmet Wearing Detection Based on AT-YOLO Deep Mode

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第10期69卷 159-174页

作者： Qingyang Zhou Jiaohua Qin Xuyu Xiang Yun Tan Neal NXiong College of Computer Science and Information Technology Central South University of Forestry&TechnologyChangsha410004China Department of Mathematics and Computer Science Northeastern State UniversityTahlequah74464OKUSA

The existing safety helmet detection methods are mainly based on one-stage object detection algorithms with high detection speed to reach the real-time detection requirements,but they can’t accurately detect small objects and objects with ***,we propose a helmet detection algorithm based on the attention mechanism(AT-YOLO).First of all,a channel attention module is added to the YOLOv3 backbone network,which can adaptively calibrate the channel features of the direction to improve the feature utilization,and a spatial attention module is added to the neck of the YOLOv3 network to capture the correlation between any positions in the feature map so that to increase the receptive field of the ***,we use DIoU(Distance Intersection over Union)bounding box regression loss function,it not only improving the measurement of bounding box regression loss but also increases the normalized distance loss between the prediction boxes and the target boxes,which makes the network more accurate in detecting small objects and faster in ***,we explore the training strategy of the network model,which improves network performance without increasing the inference *** show that the mAP of the proposed method reaches 96.5%,and the detection speed can reach 27 *** with other existing methods,it has better performance in detection accuracy and speed.

关键词： Safety helmet detection attention mechanism convolutional neural network training strategies

Mach Number Prediction for a Wind Tunnel Based on the CNN-LSTM-attention Method

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Instrumentation 2023年第4期10卷 64-82页

作者： ZHAO Luping WU Kunyang College of Information Science and Engineering Northeastern UniversityShenyang 11081China

The test section’s Mach number in wind tunnel testing is a significant metric for evaluating system *** quality of the flow field in the wind tunnel is contingent upon the system's capacity to maintain stability across various working *** process flow in wind tunnel testing is inherently complex,resulting in a system characterized by nonlinearity,time lag,and multiple working *** implement the predictive control algorithm,a precise Mach number prediction model must be ***,this report studies the method for Mach number prediction modelling in wind tunnel flow fields with various working ***,this paper introduces a continuous transonic wind *** key physical quantities affecting the flow field of the wind tunnel are determined by analyzing its structure and blowing ***,considering the nonlinear and time-lag characteristics of the wind tunnel system,a CNN-LSTM model is employed to establish the Mach number prediction model by combining the 1D-CNN algorithm with the LSTM model,which has long and short-term memory ***,the attention mechanism is incorporated into the CNN-LSTM prediction model to enable the model to focus more on data with greater information importance,thereby enhancing the model's training *** application results ultimately demonstrate the efficacy of the proposed approach.

关键词： Wind Tunnel Test,Mach Number Prediction CNN-LSTM attention mechanism

SA-FRCNN:An Improved Object Detection Method for Airport Apron Scenes

在线全文

学校读者我要写书评

暂无评论

Transactions of Nanjing University of Aeronautics and Astronautics 2021年第4期38卷 571-586页

作者： LYU Zonglei CHEN Liyun College of Computer Science and Technology Civil Aviation University of ChinaTianjin 300300P.R.China Information Technology Research Base of Civil Aviation Administration of China Tianjin 300300P.R.China

The airport apron scene contains rich contextual information about the spatial position *** object detectors only considered visual appearance and ignored the contextual *** addition,the detection accuracy of some categories in the apron dataset was ***,an improved object detection method using spatial-aware features in apron scenes called SA-FRCNN is *** method uses graph convolutional networks to capture the relative spatial relationship between objects in the apron scene,incorporating this spatial context into feature ***,an attention mechanism is introduced into the feature extraction process,with the goal to focus on the spatial position and key features,and distance-IoU loss is used to achieve a more accurate *** experimental results show that the mean average precision of the apron object detection based on SAFRCNN can reach 95.75%,and the detection effect of some hard-to-detect categories has been significantly *** proposed method effectively improves the detection accuracy on the apron dataset,which has a leading advantage over other methods.

关键词： airport apron scene object detection graph convolutional network spatial context attention mechanism

ANC: attention Network for COVID-19 Explainable Diagnosis Based on Convolutional Block attention Module

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2021年第6期127卷 1037-1058页

作者： Yudong Zhang Xin Zhang Weiguo Zhu Jiangsu Key Laboratory of Advanced Manufacturing Technology Huaiyin Institute of TechnologyHuai’an223003China Department of Medical Imaging The Fourth People’s Hospital of Huai’anHuai’an223002China School of Informatics University of LeicesterLeicesterLE17RHUK

Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network forCOVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed toavoid overfitting. Then, convolutional block attention module (CBAM) was integrated to our model, the structureof which is fine-tuned. Finally, Grad-CAM was used to provide an explainable diagnosis. Results: The accuracyof our ANC methods on two datasets are 96.32% ± 1.06%, and 96.00% ± 1.03%, respectively. Conclusions: Thisproposed ANC method is superior to 9 state-of-the-art approaches.

关键词： Deep learning convolutional block attention module attention mechanism COVID-19 explainable diagnosis

An Analysis of the Evolution of Online Public Opinion on Public Health Emergencies by Combining CNN-BiLSTM + attention and LDA

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2023年第4期11卷 190-199页

作者： Hanlu Lei Hu Wang Linli Wang Yuhang Dong Jingjie Cheng Kui Cai School of Management Wuhan University of Technology Wuhan China Wuhan Huaxia University of Technology Wuhan China

In this paper, the Foxconn epidemic event in Zhengzhou was taken as an example to analyze the evolution of online public opinion on public health emergencies. In order to improve the performance of online public opinion analysis, based on the life cycle theory and LDA theory, the emotional changes of Internet users in four stages of the Foxconn incident centered on the evolution of inscription were divided. The emotions of netizen speech at different stages are analyzed based on CNN-BiLSTM + attention model, which uses Convolutional Neural Network (CNN) to extract local features. Bi-directional Long Short-Term Memory (BiLSTM) is used to efficiently extract contextual semantic features and long distance dependencies, and then combined with attention mechanism to add emotional features. Finally, Softmax classifier realizes text emotion prediction. The experimental results show that: compared with TextCNN, BiLSTM, BiLSTM + Attenion, CNN-BiLSTM model, the emotion classification model has better effects in the accuracy rate, accuracy rate, recall rate and F value. By analyzing the emotional distribution and evolution trend of public opinion under “text topic”, the paper accurately deconstructs the development characteristics of public opinion in public health emergencies, in order to provide reference for relevant departments to deal with public opinion in public health emergencies. .

关键词： Public Health Emergencies Emotional Evolution CNN-BiLSTM attention mechanism LDA