检索结果-南通市图书馆

Journal of Iron and Steel Research International 2023年第5期30卷 937-948页

作者： Gong-hao Lian Qi-hao Sun Xiao-ming Liu Wei-miao Kong Ming Lv Jian-jun Qi Yong Liu Ben-ming Yuan Qiang Wang Key Laboratory of Electromagnetic Processing of Materials(Ministry of Education) Northeastern UniversityShenyang 110819LiaoningChina State Key Laboratory of Rolling and Automation Northeastern UniversityShenyang 110819LiaoningChina Shandong Iron and Steel Group Co. Ltd.Jinan 271105ShandongChina HBIS Material Technology Research Institude Shijiazhuang 050023HebeiChina Special Steel Business Department of Shandong Steel Laiwu Branch Jinan 271105ShandongChina

The internal quality inspection of the continuous casting billets is very important,and mis-inspection will seriously affect the subsequent production *** UNet-VGG16 transfer learning model was used for semantic segmentation of the central shrinkage defects of the continuous casting *** automatic recognition accuracy of the central shrinkage defects of the continuous casting billets reaches more than *** use the minimum circumscribed rectangle to quantify the geometric dimensions such as length,width and area of the central shrinkage defects and use the threshold method to rate the central shrinkage defects of the continuous casting *** results show that all the testing images are rated correctly,and this method achieves the automatic recognition and intelligent analysis of the central shrinkage defects of the continuous casting billets.

关键词： Central shrinkage Deep learning Image segmentation Circumscribed rectangle automatic recognition

automatic recognition of sonar targets using feature selection in micro-Doppler signature

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2023年第2期20卷 58-71页

作者： Abbas Saffari Seyed-Hamid Zahiri Mohammad Khishe Department of Electrical Engineering University of BirjandBirjandIran Department of Electrical Engineering Imam Khomeini Marine Science UniversityNowshahrIran

Currently,the use of intelligent systems for the automatic recognition of targets in the fields of defence and military has increased *** primary advantage of these systems is that they do not need human participation in target recognition *** paper uses the particle swarm optimization(PSO)algorithm to select the optimal features in the micro-Doppler signature of sonar *** microDoppler effect is referred to amplitude/phase modulation on the received signal by rotating parts of a target such as *** different targets'geometric and physical properties are not the same,their micro-Doppler signature is *** Inconsistency can be considered a practical issue(especially in the frequency domain)for sonar target *** using 128-point fast Fourier transform(FFT)for the feature extraction step,not all extracted features contain helpful *** a result,PSO selects the most optimum and valuable *** evaluate the micro-Doppler signature of sonar targets and the effect of feature selection on sonar target recognition,the simplest and most popular machine learning algorithm,k-nearest neighbor(k-NN),is used,which is called k-PSO in this paper because of the use of PSO for feature *** parameters measured are the correct recognition rate,reliability rate,and processing *** simulation results show that k-PSO achieved a 100%correct recognition rate and reliability rate at 19.35 s when using simulated data at a 15 dB signal-tonoise ratio(SNR)angle of 40°.Also,for the experimental dataset obtained from the cavitation tunnel,the correct recognition rate is 98.26%,and the reliability rate is 99.69%at ***,the k-PSO has an encouraging performance in automatically recognizing sonar targets when using experimental datasets and for real-world use.

关键词： Micro-Doppler signature automatic recognition Feature selection k-NN PSO

automatic recognition of Construction Worker Activities Using Deep Learning Approaches and Wearable Inertial Sensors

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第5期36卷 2111-2128页

作者： Sakorn Mekruksavanich Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication TechnologyUniversity of PhayaoPhayao56000Thailand Department of Mathematics Intelligent and Nonlinear Dynamic Innovations Research CenterFaculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok10800Thailand

The automated evaluation and analysis of employee behavior in an Industry 4.0-compliant manufacturingﬁrm are vital for the rapid and accurate diagnosis of work performance,particularly during the training of a new *** techniques for identifying and detecting worker performance in industrial applications are based on computer vision *** widespread com-puter vision-based approaches,it is challenging to develop technologies that assist the automated monitoring of worker actions at external working sites where cam-era deployment is *** the use of wearable inertial sensors,we propose a deep learning method for automatically recognizing the activities of construction *** suggested method incorporates a convolutional neural network,residual connection blocks,and multi-branch aggregate transformation modules for high-performance recognition of complicated activities such as con-struction worker *** proposed approach has been evaluated using standard performance measures,such as precision,F1-score,and AUC,using a publicly available benchmark dataset known as VTT-ConIoT,which contains genuine con-struction work *** addition,standard deep learning models(CNNs,RNNs,and hybrid models)were developed in different empirical circumstances to compare them to the proposed *** an average accuracy of 99.71%and an average F1-score of 99.71%,the experimentalﬁndings revealed that the suggested model could accurately recognize the actions of construction ***,we examined the impact of window size and sensor position on the identiﬁcation efﬁciency of the proposed method.

关键词： Complex human activity recognition wearable inertial sensors deep learning construction workers automatic recognition

automatic recognition Method for Optical Measuring Instruments Based on Machine Vision

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Transactions of Tianjin University 2008年第3期14卷 202-207页

作者：宋乐林玉池郝立果 State Key Laboratory of Precision Measuring Technology and Instruments Tianjin University

Based on a comprehensive study of various algorithms, the automatic recognition of traditional ocular optical measuring instruments is realized. Taking a universal tools microscope(UTM) lens view image as an example, a 2-layer automatic recognition model for data reading is established after adopting a series of pre-processing algorithms. This model is an optimal combination of the correlation-based template matching method and a concurrent back propagation(BP) neural network. Multiple complementary feature extraction is used in generating the eigenvectors of the concurrent network. In order to improve fault-tolerance capacity, rotation invariant features based on Zernike moments are extracted from digit characters and a 4-dimensional group of the outline features is also obtained. Moreover, the operating time and reading accuracy can be adjusted dy-namically by setting the threshold value. The experimental result indicates that the newly developed algorithm has optimal recognition precision and working speed. The average reading ratio can achieve 97.23%. The recognition method can automatically obtain the results of optical measuring instruments rapidly and stably without modifying their original structure, which meets the application requirements.

关键词： automatic recognition optical measuring instruments template matching neural network

Machine learning guided automatic recognition of crystal boundaries in bainitic/martensitic alloy and relationship between boundary types and ductile-to-brittle transition behavior

在线全文

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2021年第25期84卷 49-58页

作者： X.C.Li J.X.Zhao J.H.Cong R.D.K.Misra X.M.Wang X.L.Wang C.J.Shang Collaborative Innovation Center of Steel Technology University of Science and Technology BeijingBeijing 100083China Department of Metallurgical Materials and Biomedical EngineeringUniversity of Texas at El Paso500 W.University AvenueEl PasoTX 79968USA

Gradient boosting decision tree(GBDT)machine learning(ML)method was adopted for the first time to automatically recognize and conduct quantitative statistical analysis of boundaries in bainitic microstructure using electron back-scatter diffraction(EBSD)*** spite of lack of large sets of EBSD data,we were successful in achieving the desired accuracy and accomplishing the objective of recognizing the *** with a low model accuracy of40°)was~97%,and block boundary was~96%.The derived outcomes of ML were used to obtain insights into the ductile-to-brittle transition(DBTT)***,ML modeling approach suggested that DBTT was not determined by the density of high angle grain boundaries,but significantly influenced by the density of PAG and packet *** study underscores that ML has a great potential in detailed recognition of complex multi-hierarchical microstructure such as bainite and martensite and relates to material performance.

关键词： Machine learning Feature engineering automatic recognition Lath structure Crystallography

Study on automatic recognition of the first motion in a seismic event

在线全文

学校读者我要写书评

暂无评论

Acta Seismologica Sinica(English Edition) 2000年第5期13卷 585-590页

作者：谢永杰陶果 Xi’an China

In this paper, we have studied the waveforms of background noise in a seismograph and set up an AR model to characterize them. We then complete the modeling and the automatic recognition program. Finally, we provide t... 详细信息

关键词： seismic signal underground explosion AR model first motion automatic recognition

automatic recognition Algorithm of AM Signals Based on Spectrum and Modulation Characters

在线全文

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2012年第2期10卷 163-166页

作者： Xiao-Fei Zhang Liang Chang Pei-Ming Ren Rong Liu State Radio Monitoring Center Beijing 100027 China

To meet the actual requirement of automatic monitoring of the shortwave signals under wide band ranges, a technique for automatic recognition is studied in this paper. And basing upon the spectrum and modulation characters of amplitude modulation （AM） signals, an automatic recognition scheme for AM signals is proposed. The proposed scheme is achieved by a joint judgment with four different characteristic parameters. Experiment results indicate that the proposed scheme can effectively recognize AM signals in practice.

关键词： Amplitude modulation automatic recognition characteristic parameters shortwave radio.

Investigation into the automatic recognition of time series precursor of earthquakes

在线全文

学校读者我要写书评

暂无评论

Acta Seismologica Sinica(English Edition) 1998年第5期11卷 87-96页

作者：黄汉明范洪顺边银菊邹立晔

In this paper, a new method of quantitative description of earthquake precursors is proposed; by this method, the precursory pattern of time series can be quantitatively described with a two-dimensional matrix. On this basis, a method of automatic recognition or automatic acquirement of precursory pattern, called simply the AA method, is put forward. Then, taking North China region as an example, various seismological precursors such as the frequency, energy, b -value, etc . and various nonlinear parameter precursors such as the capacity dimension, information dimension, correlation dimension, Hurst index and its difference, etc. are analyzed and the 8 time series so obtained are recognized automatically using the proposed precursory pattern and AA method. Besides, C-method tests and very rigorous HF (history and future) tests are made. The result shows that the R-value of prediction efficacy assessment is fairly high.

关键词： earthquake prediction precursory pattern automatic recognition C-method test HF test

automatic recognition Method of Operation Status forAgricultural Machinery Based on GNSS Data Mining

在线全文

学校读者我要写书评

暂无评论

Automatic Recognition Method of Operation Status forAgricult...

Radar Signal Intra-Pulse Modulation recognition Based on Deep Residual Network

第三届中国卫星导航学术年会

作者： Yaping Cai,Caicong Wu,Mengjia Luo,Lianjun Ding,Huaihong Su Institute of Remote Sensing and GIS,Peking University,Beijing 100871,China

To meet the application requirements like the automatic recognition of operation status for agricultural machinery,farmland and rural road network data updates,and so on,the matching templates of the agricultural machinery operation status are generated by data mining based on a historical GNSS *** the field research and the historical tracks,the agricultural machinery operation is divided into four main types:parking status in the garage,transferring status on the road,working status in the field,and transferring status between the *** analysis shows that the three features,which are location,speed and direction,can be used for data mining,and the feature map of agricultural machinery operation status is made and the matching templates are *** the farmland data and road network topological diagram information are *** show that the templates have a good accuracy,better than 90%,and can meet the basic application demand mentioned above.

关键词： agricultural machinery operation status GNSS data mining automatic recognition

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2024年第2期33卷 155-162页

作者： Fuyuan Xu Guangqing Shao Jiazhan Lu Zhiyin Wang Zhipeng Wu Shuhang Xia No.8511 Research Institute of China Aerospace Science&Industry Corp(CASIC) Nanjing 210007China

In view of low recognition rate of complex radar intra-pulse modulation signal type by traditional methods under low signal-to-noise ratio(SNR),the paper proposes an automatic recog-nition method of complex radar intra-pulse modulation signal type based on deep residual *** basic principle of the recognition method is to obtain the transformation relationship between the time and frequency of complex radar intra-pulse modulation signal through short-time Fourier transform(STFT),and then design an appropriate deep residual network to extract the features of the time-frequency map and complete a variety of complex intra-pulse modulation signal type *** addition,in order to improve the generalization ability of the proposed method,label smoothing and L2 regularization are *** simulation results show that the proposed method has a recognition accuracy of more than 95%for complex radar intra-pulse modulation sig-nal types under low SNR(2 dB).

关键词： intra-pulse modulation low signal-to-noise deep residual network automatic recognition