[1]赵旭阳,张延彬,王忠勇,等.基于SVM的声磁标签检测系统设计及其FPGA实现[J].郑州大学学报(工学版),2021,42(3):13-18.[doi:10.13705/j.issn.1671-6833.2021.03.003]
　Zhao Xuyang,Zhang Yanbin,Wang Zhongyong,et al.Design of Acoustic Magnetic Label Detection System Based on SVM and FPGA Implementation[J].Journal of Zhengzhou University (Engineering Science),2021,42(3):13-18.[doi:10.13705/j.issn.1671-6833.2021.03.003]
点击复制

基于SVM的声磁标签检测系统设计及其FPGA实现()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
42
期数:
2021年3期
页码:
13-18
栏目:
出版日期:
2021-05-10

文章信息/Info

Title:
Design of Acoustic Magnetic Label Detection System Based on SVM and FPGA Implementation
作者:
赵旭阳, 张延彬, 王忠勇, 陈明亮
郑州大学 信息工程学院，河南 郑州 450001
Author(s):
Zhao Xuyang; Zhang Yanbin; Wang Zhongyong; Chen Mingliang
School of Information Engineering, Zhengzhou University, Zhengzhou 450001, China
关键词:
Keywords:
EAS;  acoustic magnetic;  support vector machine;  FFT;  FPGA
DOI:
10.13705/j.issn.1671-6833.2021.03.003
文献标志码:
A
摘要:
针对强电磁干扰环境下,传统声磁EAS系统存在检测距离近,误报(漏报率高等缺点,提出了一种基于支持向量机,SVM的声磁EAS系统,并以芯片作为实现平台)通过快速傅里叶变换, FFT法提取标签(噪声信号频域特征,将其作为SVM算法训练样本)SVM训练模型对数据帧做有标签和无标签二分类,训练部分在MATLAB上进行分类计算部分在FPGA内部实现,采用三级并行计算结构,算法用时小于0.5MZ测试结果表明:有干扰环境下,硬标签最远检测距离可达1.45m,识别率最高可达99.4%软标签最远检测距离可达0.75m,识别率最高可达 98.9%)与传统声磁EAS系统相比,检测距离明显增大,识别率提高)该系统为复杂环境下EAS系统的稳定运行提供了一种解决方案)
Abstract:
In strong electromagnetic interference environment, traditional acoustic magnetic EAS system has some shortcomes, such as short detection distance, high rate of false alarm and miss alarm. In order to solve these problems, an acoustic magnetic EAS system based on support vector machine (SVM) is proposed. The algorithm is implemented on FPGA chip. The fast Fourier transform (FFT) method is used to extract the frequency characteristics of tag and noise signals, which are used as the training samples of SVM algorithm. SVM algorithm classifies data frames into labeled and unlabeled ones, and the training part is implemented in MATLAB. The classification calculation part is implemented in FPGA, which adopts three-level parallel computing structure, and the algorithm time is less than 0.5 ms. The test results showed that: Under the interference environment, the longest detection distance of hard tag can reach 1.45 m, and the recognition rate can reach 99.4%. The longest detection distance of soft tag can reach 0.75 m, and the recognition rate can reach 98.9%. Compared with the traditional acoustic magnetic EAS system, this system can significantly increase the detection distance, improve the recognition rate, and provide a solution for the stable operation of EAS system in complex environment.

参考文献/References:

[1] 姚江敏,王忠勇,张延彬,等.基于DSP的声磁EAS系统设计[J].电声技术,2013,37(5):62-65.

[2] 方元,刘太君,谢晋雄,等.基于伪随机序列的射频EAS检测技术[J].数据通信,2019(1):24-27.
[3] 康雪娟,马文华,林钰人.基于ARM Cortex-M3的声磁商品电子防盗系统设计[J].计算机测量与控制,2016,24(10):263-266.
[4] 都伊林.声磁防盗系统的识别原理及应用[J].电子科技,2007(7):79-82.
[5] 王焱. 基于FPGA的一体式射频EAS检测器设计与实现[D].郑州:郑州大学,2016.
[6] 滕士雷.58KHZ声磁防盗系统原理研究[J].计量与测试技术,2017,44(12):35-37,40.
[7] ANGUITA D,BONI A,RIDELLA S. A digital architecture for support vector machines: theory, algorithm, and FPGA implementation[J]. IEEE transactions on neural networks,2003,14(5):993-1009.
[8] BOUJELBEN O, BAHOURA M. Efficient FPGA-based architecture of an automatic wheeze detector using a combination of MFCC and SVM algorithms[J]. Journal of systems architecture,2018,88:54-64.
[9] WISNIEWSKI R,BAZYDLO G, SZCZ SNIAK P. SVM algorithm oriented for implementation in a low-cost Xilinx FPGA [J]. Integration,2019,64:163-172.
[10]刘涵，王博，尹嵩，等．一种基于FPGA的新的SVM 硬件实现方法［J］．仪器仪表学报，2010,31（10）：2235-2241.
[11]王华忠，俞金寿．核函数方法及其模型选择［J］．江南大学学报，2006（4）：500-504．
[12]胡福平，徐美华，沈华明．SVM的并行计算结构研究及FPGA实现［J］．微电子学与计算机，2018,35（6）：79-83.
[13]王梅．一种改进的核函数参数选择方法［D］．西安：西安科技大学，2011．
[14]周志华．机器学习［M］．北京：清华大学出版社，2016:121-146.

相似文献/References:

[1]程健,安鸿波,郭一楠,等.一种区域知识引导的船舶吃水线动态识别算法[J].郑州大学学报(工学版),2021,42(3):47.[doi:10.13705/j.issn.1671-6833.2021.03.008]
　Cheng Jian,An Hongbo,Guo Yinan,et al.Dynamic Identification of Ship Waterline Image Area Based on Knowledge Guidance[J].Journal of Zhengzhou University (Engineering Science),2021,42(3):47.[doi:10.13705/j.issn.1671-6833.2021.03.008]

更新日期/Last Update: 2021-06-24