Table of Content

15 January 2024 Volume 37 Issue 1
    Research on Real Estate Price Index Based on Sparrow Search Optimization SVR Model
    LAN Ruijie,MENG Weigao,GENG Jinqiang
    Electronic Science and Technology. 2024, 37(1):  1-8.  doi:10.16180/j.cnki.issn1007-7820.2024.01.001
    Abstract ( 47 )   HTML ( 4 )   PDF (1302KB) ( 17 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to solve the data acquisition lag problem of traditional economic indicators as an influencing factor of housing prices, and the uncertainty of parameter selection in the machine learning model when predicting housing prices, the network search data is used as the explanatory variable of the house price index, and Sparrow Search Algorithm(SSA) is used to establish the SSA-SVR(Support Vector Regression)model to optimize the penalty factor C of SVR and the parameter g of the RBF(Radical Basic Function) kernel function in this study. Comparison among the established SSA-SVR model with PSO(Particle Swarm Optimization)-SVR, GA(Genetic Algorithm)-SVR,WOA(Whale Optimization Algorithm)-SVR, GS(Grid Search)-SVR and benchmark SVR show that the correlation coefficient of SSA-SVR(0.99), root mean square error(6.71), mean absolute error(5.24), mean square error(45.13) and mean absolute percentage error(0.26%) are better than those of the other five models. The results show that the SVR model optimized by the sparrow search algorithm has better global optimization ability in housing price prediction, which can improve the prediction accuracy and prediction ability of the model.

    Marx Pulse Source with Multistage Resonant Charging
    FU Yizhao,LI Zi
    Electronic Science and Technology. 2024, 37(1):  9-16.  doi:10.16180/j.cnki.issn1007-7820.2024.01.002
    Abstract ( 43 )   HTML ( 2 )   PDF (4930KB) ( 10 )  
    Figures and Tables | References | Related Articles | Metrics

    Marx generator is a classic pulse power generator. In order to better meet the practical needs of high voltage, bipolar and high efficiency, a multi-stage resonant charging Marx pulse generator is proposed, which uses a series resonant charging power supply and a series core magnetic ring transformer to charge the Marx pulse generator in groups. The Marx pulse generator with multi-stage resonant charging of two symmetrical structures is built and its performance is verified, including the unipolar generator and the bipolar pulse generator with variable polarity. The circuit consists of a group of 3-way 8-stage Marx with positive polarity and a group of 3-way 8-stage Marx with negative polarity, totaling 48 stages. The experimental results show that the unipolar Marx generator with variable polarity can generate positive or negative voltage pulses of 30 kV, and the bipolar generator can output ± 10 kV voltage pulses to no-load and 50 kΩ resistive load. Through the signal control of Field Program Gate Array(FPGA), the repetition frequency can be adjusted within the range of 1 Hz~1 kHz, the pulse width can be adjusted within the range of 1~200 ms, and the front and back edges of the pulse are within 50 ns. The relaxation time between positive and negative pulses is 0.2~200.0 μs.

    Semi-Supervised Medical Image Segmentation Method Based on Meta-Learning and Neural Architecture Search
    YU Zhihong,LI Feifei
    Electronic Science and Technology. 2024, 37(1):  17-23.  doi:10.16180/j.cnki.issn1007-7820.2024.01.003
    Abstract ( 57 )   HTML ( 6 )   PDF (1999KB) ( 18 )  
    Figures and Tables | References | Related Articles | Metrics

    Most medical image segmentation methods mainly focus on training and evaluating in the same or similar medical data domain, which need lots of pixel-level annotations. However, these models face challenges in out-of-distribution medical data set, which is known as "domain shift" problem. A fixed U-shaped segmentation structure is usually used to solve this problem, resulting in it not being better adapted to specific partition tasks.A gradient-based meta-learning and neural architecture search method is proposed in this study, which can adjust the segmentation network according to specific tasks to achieve good performance and have good generalization ability. This method mainly uses the specific task to carry out the architecture search module to further improve the segmentation effect, and then uses the gradient-based meta-learning training algorithm to improve the generalization ability.On the public dataset M&Ms, under the 5% label data, its Dice and Hausdorff distance are 79.62% and 15.38%. Under 2% label data, its Dice and Hausdorff distance are 74.03% and 17.05%.Compared with other mainstream methods, the proposed method has better generalization ability.

    Research on Task Scheduling of Heterogeneous Platform Signal Processing
    LI Yudong,MA Jinquan,XIE Zongfu,SHEN Xiaolong
    Electronic Science and Technology. 2024, 37(1):  24-32.  doi:10.16180/j.cnki.issn1007-7820.2024.01.004
    Abstract ( 36 )   HTML ( 3 )   PDF (1068KB) ( 11 )  
    Figures and Tables | References | Related Articles | Metrics

    The simple parallel computing or single heterogeneous platform can no longer meet the requirements of signal processing and task schedulingwith large computation and high complexity, so heterogeneous multi platform system has become the development trend of signal processing and task scheduling. In view of improving the throughput of the platform, utilization rate of the processor and perception of the task,this study investigates the signal processing model of heterogeneous multi-platform, and the scheduling tasks and hardware and software resources are modeled by directed acyclic graph.Based on the proposed scheduling algorithms, the task scheduling is summarized and compared. It is found that the hybrid scheduling algorithm based on task perception can meet the platform scheduling requirements well.It is a trend of future research to use mixed scheduling algorithm based on task perception to solve task scheduling in signal processing.

    Sparrow Optimization Algorithm for Task Scheduling of Heterogeneous Processing Platform
    SHEN Xiaolong,MA Jinquan,JI Yawei,XIE Zongfu,LI Yiting,LI Yudong
    Electronic Science and Technology. 2024, 37(1):  33-40.  doi:10.16180/j.cnki.issn1007-7820.2024.01.005
    Abstract ( 20 )   HTML ( 4 )   PDF (3115KB) ( 10 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problems of unbalanced distribution task quantity of the each precessor,incomplete performance of the each processor and inefficient system operation in heterogeneous signal processing platform,a sparrow optimization algorithm for heterogeneous processing platform is proposed in this study, which takes advantage of the strong global optimization ability of sparrow algorithm and efficient working mechanism within sparrow population.Based on the classical sparrow algorithm, this study proposes a binary or codec rule that meets the task scheduling, and maps discrete task assignment scheme to continuous sparrow position information.The processor load balance index is taken as the fitness function and the optimal solution is selected in each iteration. When the sparrow traverses the task, the task priority shunt sorting strategy is adopted to adopt different computing formulas for communication-intensive tasks and computing dense tasks to obtain the order of traversing more in accordance with the characteristics of the task, and generates random tasks.Finally, the proposed algorithm is compared with the ICPA(Improved Critical Path Agorithm). The simulation results show that when compared with the ICPA, the an average optimization rate of load balance index of the proposed algorithm is 60%, and the load of each processor is more balanced, and the overall performance of the heterogeneous processing platform can be better utilized.

    Obstacle Target Positioning Based on LiDAR Scanning Angle Correction
    ZHANG Mingkun,CAI Wenyu,ZHANG Shuai
    Electronic Science and Technology. 2024, 37(1):  41-47.  doi:10.16180/j.cnki.issn1007-7820.2024.01.006
    Abstract ( 25 )   HTML ( 6 )   PDF (3491KB) ( 7 )  
    Figures and Tables | References | Related Articles | Metrics

    When two-dimensional Laser Radar (LiDAR) is used for obstacle detection, the position change of mobile robot's own attitude usually leads to the change of LiDAR reference position, which will produce a large error in the positioning calculation of obstacle. In this study, an obstacle target location method based on LiDAR scanning angle correction is proposed. The K-means clustering algorithm is used to divide the LiDAR point cloud data, and then the angle correction processing is performed on the clustered data, so that the processed data information is more consistent with the real value. Finally, each cluster data is enveloped to improve the accuracy of LiDAR scanning data. The test results show that the the proposed method can improve the positioning accuracy and meet the requirement of accurate obstacle positioning.

    Design of Gigabit Ethernet Port Communication Based on FPGA
    LAN Wei,HAN Yanzhe,HU Xiao
    Electronic Science and Technology. 2024, 37(1):  48-54.  doi:10.16180/j.cnki.issn1007-7820.2024.01.007
    Abstract ( 76 )   HTML ( 5 )   PDF (1331KB) ( 28 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problem of Ethernet transmission rate and real-time in embedded field, a design of Gigabit Ethernet port communication based on FPGA(Field Programmable Gate Array)is proposed. This study designs the forwarding function of Gigabit Ethernet switch, and implements end-to-end data communication based on label forwarding. Datagrams with label are sent by CPU(Central Processing Unit), and are outputted through Gigabit Ethernet interface, and are sent to FPGA through RGMII(Reduced Gigabit Media Independent Interface)port. FPGA judges output port number field in label through internal logic and removes label, and outputs datagrams to connecting device from corresponding Gigabit Ethernet interface. Peripherals input datagrams through Gigabit Ethernet ports, and send datagrams to FPGA through SGMII(Serial Gigabit Media Independent Interface) protocol. FPGA adds labels through internal logic and outputs them to CPU through polling, so as to realize interworking of connecting devices of multiple Gigabit Ethernet interface. The experimental results reveal the feasibility and effectiveness of the FPGA logic. The transmission rate reaches 1 Gbit·s-1, the datagrams forwarding delay is less than 100 μs, and the packet loss rate is 0%,which indicates that the data transmission stability is high, and the proposed design meets the actual needs of existing projects.

    Train Bearings Diagnosis Method for Wayside Acoustic Signal Based on Spatial-Frequency Joint Filtering
    ZHANG Yanzhe,HU Dingyu,SHI Wei,LIAO Aihua
    Electronic Science and Technology. 2024, 37(1):  55-60.  doi:10.16180/j.cnki.issn1007-7820.2024.01.008
    Abstract ( 21 )   HTML ( 3 )   PDF (2579KB) ( 6 )  
    Figures and Tables | References | Related Articles | Metrics

    Existing train bearing trackside acoustic diagnosis methods mostly focus on doppler effect removal and spatial filter optimization, while ignoring the impact noise and cyclostationary noise in the trackside environment. To address this problem, a trackside acoustic diagnosis method combining beamforming and target band selection for train axlebox is proposed in this study. The proposed method acquires train bearing array acoustic signals by microphone array, corrects the signal distortion by time domain interpolation resampling method, extracts the target bearing direction signal using beamforming spatial domain filter, selects the optimal demodulation band and extracts the band-pass signal using ICS2gram, and the envelope analysis of the band-pass signal is carried out to realize bearing diagnosis. The experimental results show that the proposed method can effectively avoid the influence of impact noise and cyclostationary noise in the trackside sound field environment, accurately extract the target bearing signals and diagnose the bearing faults, showing better effect when compared with the existing methods.

    Research and Application of Polar Code Encoding and Decoding in 5G Communication
    GAO Jie
    Electronic Science and Technology. 2024, 37(1):  61-65.  doi:10.16180/j.cnki.issn1007-7820.2024.01.009
    Abstract ( 80 )   HTML ( 5 )   PDF (580KB) ( 27 )  
    References | Related Articles | Metrics

    In order to optimize the implementation complexity and information transmission speed of the fifth generation communication technology, the Polar code based on channel polarization phenomenon gradually receives great attention and research, and forms many industry standards and research conclusions. In recent years, the development and optimization of Polar code encoding and decoding technology promotes the popularity of the fifth generation communication technology, and the rapid application of the new generation communication technology greatly promotes the further iteration of the underlying encoding and decoding technology. By reviewing the research history of Polar code encoding and decoding technology, the research status and context of Polar code encoding and decoding technology in the fifth generation communication are summarized. On this basis, the problems and requirements of current coding and decoding theory are analyzed and discussed in depth, and the research ideas and trends of the underlying coding and decoding theory in the future communication technology are proposed.

    Research on Identification of Urban Illegal Vehicles Based on Random Forest Model
    HUANG Zixuan,LI Qiaoxing
    Electronic Science and Technology. 2024, 37(1):  66-71.  doi:10.16180/j.cnki.issn1007-7820.2024.01.010
    Abstract ( 24 )   HTML ( 4 )   PDF (841KB) ( 9 )  
    Figures and Tables | References | Related Articles | Metrics

    The rapid development of regional economy and society does not match the development of traffic demand, which provides market opportunities for illegal taxi operation. ETC(Electronic Toll Collection) data of urban expressways can effectively check illegal taxi operation on expressways, so as to optimize operation order and improve management level. This study extracts the effective fields of ETC data, uses the random forest algorithm to establish the illegal taxi operation recognition classifier, adds the classifiers of the CART(Classification and Regression Tree) classification tree model and the binary logistic regression model to conduct performance comparison, and makes an empirical analysis with the ETC index data of a highway in a southwest city from February 6, 2022 to March 8, 2022. The results show that performance the random forest model classifier is better than that of the CART classification tree model classifier and the binary logistic regression model classifier, and its accuracy score of the proposed model is 98.75%.

    Research Progress of Medical Image Segmentation Method Based on Deep Learning
    LI Zenghui,WANG Wei
    Electronic Science and Technology. 2024, 37(1):  72-80.  doi:10.16180/j.cnki.issn1007-7820.2024.01.011
    Abstract ( 260 )   HTML ( 19 )   PDF (2075KB) ( 51 )  
    Figures and Tables | References | Related Articles | Metrics

    Medical image processing technology has developed rapidly with the rise of deep learning. The medical image segmentation technology based on deep learning has become the mainstream method in the segmentation field, which solves the shortcomings of the traditional segmentation method's insufficient segmentation accuracy. This technology has been maturely applied to the segmentation of some pathological images. This study introduces and compares the segmentation methods based on deep learning in recent years, and focuses on the major contributions of U-Net and its improved models in the segmentation field, and summarizes the common medical image modalities and evaluation indicators of segmentation algorithms and commonly used segmentation data sets. Finally, the future development of medical image segmentation technology is prospected.

    Review of Text Classification Research Based on Deep Learning
    WANG Jiawei,YU Xiao
    Electronic Science and Technology. 2024, 37(1):  81-86.  doi:10.16180/j.cnki.issn1007-7820.2024.01.012
    Abstract ( 129 )   HTML ( 16 )   PDF (769KB) ( 34 )  
    Figures and Tables | References | Related Articles | Metrics

    Compared with traditional machine learning models, deep learning models attempts to imitate human learning ideas and automatically perform feature extraction from massive data through computers.Text classification is an important application in natural language processing and plays a key role in text information processing.In the past few years, research on text classification has surged and achieved good results.This study briefly introduces text classification methods based on traditional models and deep learning models,and reviews advanced text classification methods, with a focus on models for deep learning.The deep learning methods, research progress and achievements used in text classification in recent years are introduced and summarized, and the development trend of deep learning in the field of text classification and the difficulties are summarized and prospected in this study.


Monthly,Founded in September 1987
Competent Authorities:
Ministry of Education of the People's Republic of China
Sponsored by:Xidian University
Chief Editor:Liao Guisheng
Executive Editor:Wan Liancheng
Editor:Hei Lei
Editor and Publisher:
The Editorial Department of Electronic Science and Technology
Distribution Abroad:
China Intermational Book Trading Corporation
P.O.BOx 399,Beijing 100044,China
P.O.Box 375,2 Taibai Road(South),Xi'an 710071,China
Unit Price:$20.00