Loading...

Table of Content

15 June 2024 Volume 37 Issue 6
  
    Original article
    YOLOv3 Lung Nodule Detection Based on Coordinate Attention
    WANG Xinyu, ZHAO Jingwen, LIU Xiang, SHI Yunyu, SHE Yunlang
    Electronic Science and Technology. 2024, 37(6):  1-7.  doi:10.16180/j.cnki.issn1007-7820.2024.06.001
    Abstract ( 209 )   HTML ( 20 )   PDF (1807KB) ( 92 )  
    Figures and Tables | References | Related Articles | Metrics

    Lung nodules occupy fewer pixels in CT(Computed Tomography), which brings great difficulty to detection. In view of small target detection of lung nodule, this study proposes YOLOv3(You Only Look Once version 3) lung nodule detection algorithm based on coordinate attention. The backbone network adopts the improved YOLOv3, reduces the number of residual blocks and introduces the dilated convolution module to sense context information around the target. In the feature utilization, coordinate attention is introduced to capture the position, direction and cross-channel information, so as to locate lung nodules accurately. The loss function of YOLOv3 is improved, the boundary box is modeled as Gaussian distribution. Wasserstein distance is used to calculate the similarity between the two distributions instead of IoU(Intersection over Union), so as to improve the sensitivity of the target scale. The results on LUNA16 show that the average precision is 89.96% and the sensitivity is 95.37%. Compared with mainstream target detection algorithms, the precision and sensitivity of the proposed method are improved by 11.33% and 9.03%, respectively.

    Traffic Sign Detection Algorithm Incorporating Receptive Field Enhancement Module and Attention Mechanism
    YE Yuxin, JU Zhiyong, LAI Ying
    Electronic Science and Technology. 2024, 37(6):  8-16.  doi:10.16180/j.cnki.issn1007-7820.2024.06.002
    Abstract ( 116 )   HTML ( 5 )   PDF (2956KB) ( 61 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the number of shortcomings of target detection algorithm in traffic sign detection, this study proposes a traffic sign detection algorithm that incorporating receptive field enhancement module and attention mechanism. The algorithm is improved on basis of YOLOv5(You Only Look Once version 5) algorithm, the RFB (Receptive Field Block) is used to replace the SPP(Spatial Pyramid Pooling) in the original backbone, the attention mechanism modules ECAM(Efficient Channel Attention Module) and CBA (Convolutional Block Attention Module) are embedded in the feature fusion network, and the Matrix NMS (Matrix Non-Maximum Suppression) is used to sift the candidate bounding-boxes. The experimental results show that there is no change in the number of model parameters when compared with the original network, meanwhile, mean average precision of the algorithm reaches 82.31%, which is 8.59% higher than the original network, and the detection speed reaches 51.89 frame·s-1. In addition, there is no false detection or missing detection in each test scenario, which proves that the generalization ability of the algorithm is also better than original algorithm, and the algorithm can perform real-time detection of traffic signs.

    Overvoltage Suppression of Single Switch Resonant Pulse Power Supply
    LIANG Qiyu, WANG Yonggang, QIU Shengshun
    Electronic Science and Technology. 2024, 37(6):  17-28.  doi:10.16180/j.cnki.issn1007-7820.2024.06.003
    Abstract ( 107 )   HTML ( 1 )   PDF (3575KB) ( 47 )  
    Figures and Tables | References | Related Articles | Metrics

    The single-switch resonant circuit can generate high-voltage pulses using only one switch, however, when the switch is turned off at a positive resonant current, a turn-off overvoltage is generated, which damages the switch. To solve this problem, the RCD (Resistance-Capacitance-Diode) snubber circuit is paralleled with the switch or the R-D (Resistance-Diode) freewheeling branch is paralleled with the primary side of the transformer. However, under high-voltage pulse conditions, the loading characteristics and effects of the two overvoltage suppression circuits under different loads are still unclear. This study compares and analyzes the overvoltage suppression mechanism, parameter selection basis, overvoltage suppression effect and the components power loss of the two circuits. The results show that the overvoltage of the power supply switch with R-D branch is proportional to the leakage inductance current and the resistance R of the branch. If R is larger, its overvoltage coefficient is larger than that of the power supply with RCD absorption circuit. And if R is smaller, the components power loss is large. In a high-voltage pulse power supply, the capacitance of the RCD snubber circuit does not need to discharge the power. Due to the limitation of leakage inductance, when the resonant pulse circuit is short-circuited, the current is not too large to burn the switch. When driving the capacitive dielectric barrier discharge, the current can be reversed automatically to achieve zero current shutdown.

    Pulse High-Frequency Voltage Injection Method Based on Rotor Polarity Judgment Optimization
    CHEN Yibin, JIN Hai, XU Shen
    Electronic Science and Technology. 2024, 37(6):  29-35.  doi:10.16180/j.cnki.issn1007-7820.2024.06.004
    Abstract ( 171 )   HTML ( 5 )   PDF (1348KB) ( 67 )  
    Figures and Tables | References | Related Articles | Metrics

    When the permanent magnet synchronous motor operates at zero speed and low speed, the rotor position information can be accurately estimated by the pulse high-frequency injection method. The pulse high frequency injection method can not realize the rotor polarity judgment, while the traditional polarity judgment method has problems such as long response time, complex sampling and implementation process, and even polarity misjudgment. In this study, a method of judging the rotor polarity based on positive and negative voltage pulse injection is proposed. This method injects positive and negative voltage pulses into the motor, and judges the rotor polarity according to the response current peak value of the corresponding pulse. The pulse high frequency injection method combines the rotor position estimation with the polarity judgment result to obtain the accurate initial position of the rotor. This study verifies the effectiveness of the algorithm through Simulink simulation. The simulation results show that the proposed rotor polarity determination method can simplify the sampling method and algorithm complexity, reduce the response time for determining rotor polarity, and enable the pulse high-frequency injection method to accurately and quickly estimate the initial position of the rotor.

    Image Style Transfer Algorithm Based on Improved Generative Adversarial Network
    WANG Shengxiong, LIU Ruian, YAN Da
    Electronic Science and Technology. 2024, 37(6):  36-43.  doi:10.16180/j.cnki.issn1007-7820.2024.06.005
    Abstract ( 153 )   HTML ( 14 )   PDF (3584KB) ( 62 )  
    Figures and Tables | References | Related Articles | Metrics

    Image style transfer has been a research hotspot in the field of image processing, but the current style transfer models have problems such as fuzzy details of generated image, the poor color effect of style texture and excessive model parameters. An image style transfer method based on improved cycle-consistent generative adversarial network is proposed in this study. The generator network architecture is improved by adding the Ghost convolution module and the inverted residual improved module to reduce the number of model parameters and computation cost, as well as enhance the feature extraction capability of the network. And the content style loss item, the color reconstruction loss item and the map identity loss item are added to the loss function for enhancing generative capability of the model and improving the quality of generated images. The experimental results show that the proposed method has a stronger ability for style transfer, which enhances the content details and color effect of style texture from generated images effectively, improves the image quality significantly, and the model performance has also been improved well.

    Denoising Method of Cerebral Blood Oxygen Signal Based on ICEEMDAN and Sample Entropy
    CAO Yan, ZHAO Bin, XING Zhiming, JIN Zihao, DONG Xiangmei, GAO Xiumin
    Electronic Science and Technology. 2024, 37(6):  44-50.  doi:10.16180/j.cnki.issn1007-7820.2024.06.006
    Abstract ( 68 )   HTML ( 5 )   PDF (1026KB) ( 37 )  
    Figures and Tables | References | Related Articles | Metrics

    Both human physiological activity and random noise have an impact on the accuracy of cerebral blood oxygen measurement data. It is necessary to solve some noise interference encountered during signal acquisition to improve the measurement accuracy of cerebral blood oxygen detection. This study proposes a denoising method of cerebral oximetry signals by combining ICEEMDAN(Improved Complete Empirical Mode Decomposition with Adaptive Noise) and SampEn(Sample Entropy). Specifically, the modal decomposition of the cerebral blood oxygen signal is performed using ICEEMDAN to obtain the IMF components with different time complexity. The time complexity of each IMF(Intrinsic Mode Function) component is judged by the sample entropy value, and the appropriate component is selected to reconstruct the signal according to the sample entropy value of each IMF component, thus realizing the noise removal of the original signal. Experimental results show that the proposed method can effectively remove the original cerebral blood oxygen signal and realize the accuracy improvement of the collected data, thus improving the accuracy of cerebral blood oxygen detection.

    A Thirteen-Level Inverter Based on Switching Capacitor
    WU Qiang, LIU Li, LI Shengqing, DENG Na, FENG Haotian
    Electronic Science and Technology. 2024, 37(6):  51-60.  doi:10.16180/j.cnki.issn1007-7820.2024.06.007
    Abstract ( 65 )   HTML ( 1 )   PDF (4530KB) ( 45 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problems of large volume, high cost and complex structure of the existing multilevel inverter topology, a 13-level inverter based on switched capacitor is proposed. The proposed topology is composed of a DC input power supply, 3 capacitors and 14 switching devices, which realizes a 13-level output with 6 times boost. The proposed topology has lower cost and smaller volume, reduces the harmonic content of the system output, and realizes the inverter without H-bridge to reduce the voltage stress of the switch tube.The proposed inverter can achieve capacitor voltage self-balancing without any auxiliary method, which simplifies the complexity of control. The superiority of the proposed topology is verified by comparison with other traditional multilevel inverters. Simulation and experimental results verification on the simulation and prototype platform prove that the inverter has good performance in both steady and dynamic conditions.

    Multi-Path Parallel Multi-Scale Feature Reuse for Remote Sensing Image Super-Resolution
    ZHAO Xu, HU Demin
    Electronic Science and Technology. 2024, 37(6):  61-68.  doi:10.16180/j.cnki.issn1007-7820.2024.06.008
    Abstract ( 105 )   HTML ( 9 )   PDF (1288KB) ( 62 )  
    Figures and Tables | References | Related Articles | Metrics

    Objects in remote sensing images are small in size, unevenly distributed, and highly coupled. In view of the current situation that the feature extraction information of remote sensing image super-resolution models is single and underutilized, this study proposes a multi-path parallel multi-scale feature reuse network model to improve performance of image reconstruction. The model fuses feature information extracted from multiple network residual blocks using a structure of local feature cascade and global feature fusion, where each residual block is serially connected by two multi-scale convolutional units. The multi-scale convolution units construct multiple branches to extract image features in parallel through cross-fusion of feature information. At the same time, short skip connections are introduced to strengthen feature reuse between different branches, and long skip connections are introduced to strengthen feature fusion at different depths of the network. When the amplification factor is 4, the peak signal-to-noise ratios of the model on the two test sets are 29.653 1 dB and 29.037 4 dB respectively, and they are significantly improved compared with the test results of other models. Therefore, the proposed model has a good effect on super-resolution reconstruction of remote sensing images.

    An Online Condition Monitoring Method of Electrical Equipment Based on Multiple Change Points and Template Matching
    JIA Can, QI Jinpeng, YUAN Ao, XUE Yuxin, DAI Li
    Electronic Science and Technology. 2024, 37(6):  69-76.  doi:10.16180/j.cnki.issn1007-7820.2024.06.009
    Abstract ( 86 )   HTML ( 4 )   PDF (5739KB) ( 37 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problems such as slow processing speed and low accuracy of condition monitoring technology for electrical equipment at this stage, an online status monitoring method of electrical equipment based on the multi-change point detection technology and template matching strategy is proposed. Based on the buffer model and the sliding window model, this method uses the TSTKS(Ternary Search Tree and Kolmogorov-Smirnov) algorithm to form the feature vector of the window dimension and the buffer dimension. The running state matching and status switching time positioning of the electrical equipment are realized by template matching of the two dimensions. Simulation experiments results of the household refrigerator show that the proposed method has the advantages of fast detection speed and high accuracy, and can provide a reference for the state monitoring field of electrical equipment.

    A Fast Classification Online Detection Method Based on Multi-Threshold Template
    XUE Yuxin, QI Jinpeng, JIA Can, YUAN Ao, HUANG Lina
    Electronic Science and Technology. 2024, 37(6):  77-83.  doi:10.16180/j.cnki.issn1007-7820.2024.06.010
    Abstract ( 87 )   HTML ( 3 )   PDF (2019KB) ( 37 )  
    Figures and Tables | References | Related Articles | Metrics

    The traditional off-line data analysis method has many shortcomings in processing the data with high immediacy and large flow, while the online detection model can meet the real-time requirements of data flow analysis. This study proposes an online detection method based on the multi-threshold template. The proposed method combines TSTKS(Ternary Search Tree and Kolmogorov-Smirnov) algorithm for online detection, and updates the window length based on the mutation point density to improve the mutation point detection accuracy. Self-learning, matching and classification of time series data are realized by equal grading strategy, so as to detect and predict the status of large-scale lesion data. The experimental results of simulation experiment and lesion data show that the proposed method has the advantages of high efficiency and accurate classification, which provides a new method for the rapid classification of large-scale time series data.

    A Classification Method of Time Series Pathological Data Segments Based on Deep Learning
    YUAN Ao, QI Jinpeng, JIA Can, XUE Yuxin, GUO Yangyang
    Electronic Science and Technology. 2024, 37(6):  84-91.  doi:10.16180/j.cnki.issn1007-7820.2024.06.011
    Abstract ( 103 )   HTML ( 5 )   PDF (3328KB) ( 50 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problems of low detection accuracy and slow detection speed in the analysis of large-scale time-series medical data, this study proposes a time-series pathological data segment method based on deep learning. On the basis of TSTKS(Ternary Search Trees and modified Kolmogorov-Smirnov) algorithm and sliding window theory, this method can realize fast and accurate classification of pathological data segments using deep learning technology. Based on the results of classification of pathological data segments by the proposed method, the dynamic adjustment of sliding window size is realized. Through the analysis of real epileptic EEG(Electroencephalogram) signals, the experimental results show that the proposed classification method of pathological data segment and the sliding window dynamic adjustment mechanism based on this classification method have the advantages of fast detection speed and high accuracy, which can provide a new choice for the rapid analysis of large-scale time series data.

    Research on AES and ECC Algorithm Image Encryption Based on FPGA
    FANG Yingli, FANG Yuming
    Electronic Science and Technology. 2024, 37(6):  92-97.  doi:10.16180/j.cnki.issn1007-7820.2024.06.012
    Abstract ( 173 )   HTML ( 18 )   PDF (2019KB) ( 48 )  
    Figures and Tables | References | Related Articles | Metrics

    With the increasing use of digital images, it is essential to protect confidential image data from unauthorized access. In view of the security problems of digital image in the fields of communication, storage and transmission, this study proposes a digital envelope technology encryption scheme with high security and high speed based on the advantages of symmetric algorithm model and asymmetric algorithm model. This method is based on AES(Advanced Encryption Standard) and ECC(Elliptic Curve Cryptography), and optimized ECC hardware architecture is used for symmetric key sharing to enhance the security of the key. The traditional AES is optimized by adding pseudo-random numbers, using column shift instead of column obfuscation, and three-dimensional S-box box to maintain the Shannon diffusion and obfuscation principle while reducing the time complexity. This study the digital image encryption simulation and performance test of AES algorithm are carried out on FPGA(Field Programmable Gate Array). The test results show that the proposed encryption scheme has the advantages of rapidity, high security and effectiveness, and can better achieve image encryption.

    Research Progress in Network Security Situation Awareness Models
    FANG Xiang
    Electronic Science and Technology. 2024, 37(6):  98-102.  doi:10.16180/j.cnki.issn1007-7820.2024.06.013
    Abstract ( 204 )   HTML ( 5 )   PDF (596KB) ( 61 )  
    References | Related Articles | Metrics

    In response to the increasing number and forms of network attacks, different types and names of network security situational awareness models have received widespread attention and research from the academic community. In the context of the rapid popularization of information technology, hardware system, software vulnerabilities, and security vulnerabilities in daily application operations have led to an increasing number of ways and means of network attacks. However, a single type of network security monitoring and analysis tool is no longer suitable for the current development of network technology. By reviewing the research history and current status of network security situational awareness technology, this article summarizes and analyzes the theoretical development and engineering applications of situational awareness models, and discusses the shortcomings and deficiencies in relevant technical solutions. It also looks forward to the future research directions of network security situational awareness models.

Download

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
Address:
P.O.Box 375,2 Taibai Road(South),Xi'an 710071,China
Tel/Fax:0086-029-88202440
Website:http://www.dianzikeji.org
E-mail:dzkj@mail.xidian.edu.cn
Unit Price:$20.00