Table of Content

15 November 2019 Volume 32 Issue 11

  

Fruits and Vegetables Recognition Based on Principal Component Analysis and The Ensemble of Distances

MA Suping,JU Zhiyong,WANG Gao

Electronic Science and Technology. 2019, 32(11):  1-6.  doi:10.16180/j.cnki.issn1007-7820.2019.11.001

Abstract ( 448 )   HTML ( 201 )   PDF (1062KB) ( 116 )  

Figures and Tables | References | Related Articles | Metrics

In view of the poor fruit and vegetable recognition rate of traditional algorithm, a principal component analysis and distances ensemble for K-nearest neighbor combine recognition method was proposed. This method realized the recognition of fruits and vegetables from feature description, feature dimension reduction and classifier design. For the problems of uneven light and shadow in the picture of fruits and vegetables, K-means clustering was used to divide the picture by combining with the second watershed. Aiming at the problem that the recognition rate of fruit and vegetable recognition model is not high, the color and texture features of the extracted fruit and vegetable images were composed into the feature matrix. The matrix was normalized by the PCA and integrated kNN algorithm and the dimension reduction was obtained to get the low-dimensional classification feature and to finally realize the classification of fruit and vegetable agricultural products. The experimental results showed that the algorithm had the highest recognition rate of 92.6% in the category of fruits and vegetables, and was robust to the changes of illumination and angle of view.

ECG Signal Classification Based on Filtering-Reconstruction and Convolutional Neural Network

WEI Zhangyuehao,QIAN Shengyi

Electronic Science and Technology. 2019, 32(11):  7-11.  doi:10.16180/j.cnki.issn1007-7820.2019.11.002

Abstract ( 403 )   HTML ( 16 )   PDF (838KB) ( 89 )  

Figures and Tables | References | Related Articles | Metrics

Automatic classification of ECG signals by computers can relieve work pressure of doctors and greatly improve diagnosis speed and accuracy. Aiming at the problem of complex feature extraction process and weak anti-interference ability in traditional algorithms, this paper proposed an ECG signal classification algorithm combined with filtering-reconstruction and convolutional neural networks. Firstly, the traditional signal filtering and heartbeat sequence reconstruction were used to remove the noise interference in the original ECG signal, and then the convolutional neural network was constructed to automatically learn the ECG signal feature and completed the classification. The results of the classification experiments on the PhysioNet/CinC Challenge 2017 dataset showed that this method had an average F₁ (the average of the precision and recall ratio) of 0.8471, which was better than the methods based on artificial feature extraction and conventional convolutional network, and had strong anti-interference ability.

A Stereo Matching Using Double Layer Support Windows Based on RGB Map and Disparity Map

LI Xiaolin,LI Wenguo,LI Hao

Electronic Science and Technology. 2019, 32(11):  12-18.  doi:10.16180/j.cnki.issn1007-7820.2019.11.003

Abstract ( 270 )   HTML ( 7 )   PDF (1080KB) ( 37 )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that traditional local matching support window is difficult to use pixel information with long distance and gray distance, a stereoscopic matching algorithm using double layer support windows based on disparity map and RGB map was proposed in this study. The algorithm obtained the first layer disparity support window according to the disparity map, and obtained the gray scale similar sub-support window by matching the RGB color gray value of the reference picture in the disparity support window. The aggregation matching cost was optimized by class dynamic programming algorithm with parallax window, gray window and central pixel as optimized paths. Finally, the WTA strategy was used to select the best disparity, update all disparities and iteratively optimize the disparity map until convergence of the disparity map was achieved. After evaluation by the Middlebury platform, the average mismatch rate of the new algorithm was 5.15%.

Gland Cell Image Segmentation Algorithm Based on Improved U-Net Network

BEI Chenyuan,YU Haibin,PAN Mian,JIANG Jie,LÜ Bingyun

Electronic Science and Technology. 2019, 32(11):  18-22.  doi:10.16180/j.cnki.issn1007-7820.2019.11.004

Abstract ( 407 )   HTML ( 7 )   PDF (894KB) ( 102 )  

Figures and Tables | References | Related Articles | Metrics

This paper proposed a full convolutional neural network model with attention module to solve the problem that multi-scale targets and information loss affect the segmentation accuracy of gland images in the automatic segmentation process. This model followed the encoder-decoder structure. Firstly, the atrous spatial pyramid pooling was added to the encoder path, and the original residual convolution layer was replaced by the atrous residual convolution layer in the encoder path. Secondly, the attention module was added to the decoder path to make the model output high-resolution feature map and improve the segmentation accuracy of the multi-scale object. The experimental results showed that the proposed network model had fewer parameters, high segmentation precision and good robustness, besides, the average segmentation accuracy of gland images was as high as 89.7%.

AGV Multi-target Tracking Under Smart Factory

YANG Biao,LIU Xiang,TANG Xian,CHEN Junting

Electronic Science and Technology. 2019, 32(11):  23-27.  doi:10.16180/j.cnki.issn1007-7820.2019.11.005

Abstract ( 348 )   HTML ( 6 )   PDF (787KB) ( 37 )  

Figures and Tables | References | Related Articles | Metrics

Aiming at identifying, occluding and losing similar objects in AGV tracking under logistics warehouse, the study proposed a multi-target tracking method which combined background modeling with Kalman filter. Because logistics AGV has the same color, the proposed method tracked a specific logistics car with the help of Camshift's color tracking feature. At the same time, Kalman filter was used to add motion information and make use of dynamic information of target. To solve the problems of AGV recognition, occlusion and loss under the same color, the influence of noise was removed. Experiment showed that this algorithm could distinguish similar AGV cars and track them in real time.

Traffic Sign Recognition Method Based on Improved Convolutional Neural Network

YUAN Xiaoping,WANG Gang,WANG Yefeng,WANG Zheyuan,SUN Hui

Electronic Science and Technology. 2019, 32(11):  28-32.  doi:10.16180/j.cnki.issn1007-7820.2019.11.006

Abstract ( 420 )   HTML ( 16 )   PDF (955KB) ( 89 )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the low recognition rate of small scale traffic signs in intelligent transportation system, an improved convolution neural network method for traffic sign recognition was proposed in this paper.This method could improve the detection rate of small-scale traffic signs by adding an optimized RPN network to the low-level feature map of Faster R-CNN algorithm.In addition, Max Pooling method was used to fully fuse the local details and global semantic features of the image. The experimental results on TT-100K data set showed that the proposed method could significantly improve the recognition rate of small-scale traffic signs.

A Liver Capsule Extraction Algorithm Based on High Frequency Ultrasound Images

FU Guangxia,LIU Xiang,SONG Jialin,ZHAO Jingwen

Electronic Science and Technology. 2019, 32(11):  33-37.  doi:10.16180/j.cnki.issn1007-7820.2019.11.007

Abstract ( 238 )   HTML ( 3 )   PDF (995KB) ( 35 )  

Figures and Tables | References | Related Articles | Metrics

Research on Indoor Positioning Algorithm for Multi-distance Fusion

ZHU Zhilin,WANG Yinong,LIU Wenyu

Electronic Science and Technology. 2019, 32(11):  38-42.  doi:10.16180/j.cnki.issn1007-7820.2019.11.008

Abstract ( 647 )   HTML ( 4 )   PDF (881KB) ( 32 )  

Figures and Tables | References | Related Articles | Metrics

Currently, WiFi is frequently used in an indoor environment. The access point will be switched between two adjacent-AP, and a large number of WiFi access logs are cumulatively generated. WiFi access logs contain the received signal strength indication required for positioning, and accessing the data in the log by using the WiFi in the positioning system greatly simplifies the positioning and deployment complexity. This paper proposed a multi-distance fusion indoor positioning algorithm based on the WiFi log in two adjacent AP environments. The new algorithm was compared with the path loss model positioning method through experimental simulation. The experimental results show that the new algorithm had the characteristics of easy deployment, low cost and low complexity. When the number of training samples reached 300, the stable positioning effect could be achieved.

Implementation of PTP Time Synchronization Technology Based on FPGA

FANG Xiaoyu,WANG Jingmei,YAN Zijie,CHEN Zhuo

Electronic Science and Technology. 2019, 32(11):  43-47.  doi:10.16180/j.cnki.issn1007-7820.2019.11.009

Abstract ( 1288 )   HTML ( 37 )   PDF (906KB) ( 280 )  

Figures and Tables | References | Related Articles | Metrics

Aiming the problem of complexity, redundant structure and high cost in the implementation scheme of the existing PTP technology, this paper proposed an implementation scheme of PTP time synchronization technology based on FPGA. The timestamps of Sync and Delay_req messages were intercepted in the data link layer by establishing four kinds of messages between systems of FPGA which had the master-slave structure. Then, slave system calculated the link delay and time offset according to timestamps. Finally, the local clock of slave system was compensated to achieve the goal of time synchronization. ChipScope Pro tool provided by Xilinx was used to capture the time information of master and slave system, as well as to test time accuracy and success rate for board level verification in this study. The experimental results showed that the designed system could reach nanosecond accuracy in time synchronization, and the success rate of synchronization was basically maintained at 99.99%.

Simulation Analysis of Local Compression Characteristics of Foam Aluminum Silicon Alloy Sandwich Panels

ZHANG Hualin,ZHAO Ang,ZHU Zhengjiang,HU Yuebo

Electronic Science and Technology. 2019, 32(11):  47-51.  doi:10.16180/j.cnki.issn1007-7820.2019.11.010

Abstract ( 204 )   HTML ( 2 )   PDF (998KB) ( 22 )  

Figures and Tables | References | Related Articles | Metrics

In order to investigate the mechanism of the influence of porosity and pore size on the local mechanical properties of the foam aluminum silicon alloy sandwich panels, the proposed study analyzed the effects of different porosities and different apertures on the local compressive properties and energy absorption characteristics of the foam aluminum silicon alloy sandwich panels. The foam aluminum silicon alloy sandwich panel model was established by C++ and ANSYS, and the finite element simulation was carried out by Abaqus. The results showed that the elastic modulus, yield stress and absorbed energy of the foam aluminum silicon alloy sandwich panels decreased with the increase of porosity under the same pore size. At the same porosity, the modulus of elasticity, yield strength and energy absorption increased with the decrease of pore size.

A Review of Self-Organizing Motion Control Based on Swarm Intelligence

ZHANG Zhao,ZHANG Tianqi

Electronic Science and Technology. 2019, 32(11):  52-57.  doi:10.16180/j.cnki.issn1007-7820.2019.11.011

Abstract ( 321 )   HTML ( 6 )   PDF (817KB) ( 73 )  

References | Related Articles | Metrics

This paper firstly expounded the related concepts such as swarm, collective, swarm intelligence, swarm control and swarm system, and then reviewed the related research works and contents of self-organized motion control based on swarm intelligence, including the swarm control system model, the various collective control strategies and control algorithms in the swarm control, the system behaviors based on the swarm intelligence and the various intelligent optimization algorithms based on the swarm control extension. Finally, the future development trend of swarm self-organized motion control research was pointed out.

Direct Instantaneous Torque Control of Switched Reluctance Motor Based on Fuzzy Self-tuning PI

ZHAO Hui,JIN Hai

Electronic Science and Technology. 2019, 32(11):  58-63.  doi:10.16180/j.cnki.issn1007-7820.2019.11.012

Abstract ( 245 )   HTML ( 1 )   PDF (1190KB) ( 23 )  

Figures and Tables | References | Related Articles | Metrics

Noise is a big problem for switched reluctance motor. Aiming at the problem of large torque ripple in the operation of switched reluctance motor, the motor model obtained by finite element calculation was used to conduct the fuzzy PI direct instantaneous torque control of switched reluctance motor in MATLAB simulation. The Ansoft electromagnetic field simulation software was adopted to establish a three-phase 4/6 switched reluctance motor, and the obtained flux linkage data was introduced into the MATLAB motor model. Subsequently, a Simulink simulation experimental platform with a fuzzy PI direct instantaneous torque control was set up by the obtained model. Simulation results showed the system started to respond at 0.01 s and the torque was floating between 0.05~0.1 Nom. Therefore, the application of the motor model obtained by finite element to the simulation experiment of fuzzy PI direct instantaneous torque control could improve the system response and effectively suppressed the torque ripple.

Study on the Motion of Materials in Charging Drum by Fluent

CHANG Wei,HUANG Yayu

Electronic Science and Technology. 2019, 32(11):  64-69.  doi:10.16180/j.cnki.issn1007-7820.2019.11.013

Abstract ( 301 )   HTML ( 1 )   PDF (1499KB) ( 50 )  

Figures and Tables | References | Related Articles | Metrics

Charging materials in drum is a complex dynamic process. In order to reveal the inherent laws and physics of the charging system, the fluid-solid coupling model of air flow and tobacco was established by using professional CFD software Fluent to simulate the kinetic characteristic and trajectory of granular materials in charging drum. The results showed that the fluid-solid coupling model used to simulate the tobacco charging process was reliable and valid, revealing the motion state of tobacco leaves in the drum. Moreover, at the same speed, the smaller the particle size of tobacco leaves, the more uniform the looseness. The rotational speed of the drum had little effect on the trajectory of tobacco granules.

A High Dimensional Data Clustering Algorithm Combining Greedy Selection and Feature Weighting

XIANG Zhihua,SHAO Yali

Electronic Science and Technology. 2019, 32(11):  70-73.  doi:10.16180/j.cnki.issn1007-7820.2019.11.014

Abstract ( 283 )   HTML ( 6 )   PDF (744KB) ( 27 )  

Figures and Tables | References | Related Articles | Metrics

In order to solve the problem that traditional clustering algorithms can not cluster high-dimensional data, a high-dimensional data clustering algorithm combining greedy selection and feature weighting was proposed. By clustering one-dimensional feature data, the clustering results of one-dimensional data were obtained first, and then all dimension data were clustered by adding dimension clustering weights to achieve clustering of high-dimensional data. The results showed that the algorithm can accurately cluster sparse high-dimensional data samples and meet the needs of high-dimensional data clustering processing, and had good practical application value.

Research on High Speed Data Acquisition and Processing System Based on SCM Control

WANG Jiwei

Electronic Science and Technology. 2019, 32(11):  74-77.  doi:10.16180/j.cnki.issn1007-7820.2019.11.015

Abstract ( 403 )   HTML ( 19 )   PDF (592KB) ( 75 )  

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that the data processing rate of the existing single-chip computer was low, which was not conducive to high-speed data acquisition and processing, this paper studied and designed a high-speed data acquisition and processing system based on single-chip computer control. In data acquisition, A/D high-speed sampling chip was used to achieve high-speed data acquisition. In order to meet the needs of high-speed data processing and storage, this paper used the IDE interface hard disk of PC terminal as the storage device of the system. In addition, in order to coordinate the process of data acquisition and data processing, high-speed dual-port RAM was controlled by single-chip computer core control module to realize high-speed data caching, thus realizing high-speed and non-destructive data transmission from A/D sampling chip to IDE hard disk. The high-speed data acquisition and processing system based on single-chip computer control in this paper was more integrated in data acquisition and data processing, and had high engineering application value.

Research on Information Security Evaluation Algorithm Based on Hierarchical Protection

ZHA Hongze

Electronic Science and Technology. 2019, 32(11):  78-82.  doi:10.16180/j.cnki.issn1007-7820.2019.11.016

Abstract ( 339 )   HTML ( 13 )   PDF (709KB) ( 52 )  

Figures and Tables | References | Related Articles | Metrics

The key issue for evaluating information security systems is the establishment and analysis of risk assessment indicators. Aiming at this problem, this paper proposed an information security risk assessment method based on hierarchical protection and establishes an information system security assessment model. Based on GBT 20984-2007, a hierarchical structure was established for host security and network security, and the calculation and analysis of the model were completed by using the weight calculation method RISK-Weight algorithm. The example's results showed that the evaluation method reduced the influence of human subjective factors and achieved a quantitative assessment of the security science of information systems.

Research on Partial Discharge Detection Technology of Electrical Equipment Insulation System

ZHUO Xiaodong

Electronic Science and Technology. 2019, 32(11):  83-86.  doi:10.16180/j.cnki.issn1007-7820.2019.11.017

Abstract ( 466 )   HTML ( 13 )   PDF (611KB) ( 71 )  

Figures and Tables | References | Related Articles | Metrics

Domestic SF6 gas-insulated electrical equipment often has partial discharge faults, expounds the common causes of partial discharge faults, proposes ultrasonic detection technology for partial discharge of electrical equipment, performs partial discharge fault detection and diagnosis on electrical equipment, and simultaneously applied to power transformers. On line monitoring for was given a test map of the power transformer. The ultrasonic verification of SF6 gas-insulated electrical equipment was carried out. The results showed that the ultrasonic technology can detect the corona discharge and suspension discharge of electrical equipment sensitively.