基于粒子群优化的支持向量机用于直肠感知功能重建

上海交通大学学报（自然版） ›› 2014, Vol. 48 ›› Issue (02): 168-172.

基于粒子群优化的支持向量机用于直肠感知功能重建

姜恩宇1,2,昝鹏1,朱晓锦1,邵勇1

(1.上海大学机电工程与自动化学院，上海 200072； 2.上海电力学院电气工程学院，上海 200090)

收稿日期:2012-04-27 出版日期:2014-02-28 发布日期:2014-02-28
基金资助:
国家自然科学基金资助项目（31100708, 31370998）

Rectal Perception Function Rebuilding Based on Support Vector Machine Optimized by Particle Swarm Optimization

JIANG Enyu1,2,ZAN Peng1,ZHU Xiaojin1,SHAO Yong1

(1.School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, China; 2.School of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China)

Received:2012-04-27 Online:2014-02-28 Published:2014-02-28

摘要/Abstract

摘要：

针对临床上肛门失禁导致的直肠感知功能丧失，提出了一种基于粒子群优化（PSO）的支持向量机（SVM）
重建患者直肠感知功能的方法.分析人体直肠压力生理特征，将典型直肠压力收缩波形中的巨大移行性收缩（HAPC）作为产生便意的主要依据，利用小波包分析对直肠压力信号进行特征提取，通过提取的特征向量对基于SVM的直肠感知预测模型进行训练，使用PSO算法对SVM的参数进行优化，并利用训练后的模型进行便意预测，同时对比分析了参数优化后的SVM和不同核函数的SVM便意预测的准确率.实验结果表明，所提出方法切实有效，能够帮助患者重建直肠感知功能.

关键词: 支持向量机, 粒子群优化, 直肠感知, 小波包分解

Abstract:

Particle swarm optimization (PSO) optimized support vector machine (SVM) based rectal perception function rebuilding method was proposed for rectal perception loss caused by anal incontinence. By analyzing human rectum characteristics, highamplitude propagated contractions (HAPC) in rectal contractions were used to indicate an urge to defecate. Rectal pressure feature was extracted using wavelet packet analysis, taking normalized of wavelet packet coefficients mean and energy as feature vector. Rectal perception prediction model was trained based on SVM whose parameters are optimized by PSO. Then the trained model was used to predict the urge to defecate. And the prediction accuracy of the optimized and nonoptimized SVM with different kernel functions was compared. Experimental results show that the proposed method is effective in rebuilding patients’ rectal perception function.

Key words: support vector machine(SVM), particle swarm optimization(PSO), rectal perception, wavelet packet decomposition

中图分类号:

Q 811.2

姜恩宇1,2,昝鹏1,朱晓锦1,邵勇1. 基于粒子群优化的支持向量机用于直肠感知功能重建[J]. 上海交通大学学报（自然版）, 2014, 48(02): 168-172.

JIANG Enyu1,2,ZAN Peng1,ZHU Xiaojin1,SHAO Yong1. Rectal Perception Function Rebuilding Based on Support Vector Machine Optimized by Particle Swarm Optimization[J]. Journal of Shanghai Jiaotong University, 2014, 48(02): 168-172.

参考文献

［1］Barbara F, Giuseppe C, Antonio M, et al. Biofeedback treatment of fecal incontinence: Where are we, and where are we going?［J］. Word Journal of Gastroenterol, 2005, 11(31): 47714775.

［2］Jiang E, Zan P, Zhu X, et al. Rectal sensation function rebuilding based on optimal wavelet packet and support vector machine［J］. IET Science, Measurement and Technology, 2013, 7(3): 139144.

［3］Camilleri M, Bharucha A E, Lorebzo C D, et al. American neurogastroenterology and motility society consensus statement on intraluminal measurement of gastrointestinal and colonic motility in clinical practice［J］.

Neurogastroenterology and Motility, 2008, 20(12): 12691282.

［4］Meisam K, Mohammad P. An optimum algorithm in pathological voice quality assessment using waveletpacketbased features linear discriminant analysis and support vector machine［J］. Biomedical Signal Processing and Control, 2012, 7(1): 117.

［5］Serafeim P, John B, Giannis G. Subject recognition based on ground reaction force measurements of gait signals［J］. IEEE Transactions on System, Man, and Cyberneticspart B:Cybernetics, 2008, 30(6): 14761485.

［6］Chiranjib K, Prithwiraj P, Sivaji C. Waveletaided SVM tool for impulse fault identification in transformers［J］. IEEE Transactions on Power Delivery, 2006, 3(21): 12831290.

［7］Yakoub B, Farid M. Semisupervised PSOSVM regression for biophysical parameter estimation［J］. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(6): 18871895.

［8］Samar S, Magdy M. Prostate cancer spectral multi feature analysis using images［J］. IEEE Transactions on Medical Imaging, 2008, 27(4): 548556.

［9］Vahid R, Ata E, Reza G. Application of the PSOSVM model for recognition of control chart patterns［J］. ISA Transaction, 2010, 49（4）: 577586.

［10］Lin S W, Ying K C, Chen S C, et al. Particle swarm optimization for parameter determination and feature selection of support vector machines［J］. Expert Systems with Application, 2008, 35（4）: 18171824.

［11］黄标, 颜国正, 昝鹏, 等. 遥测胶囊微带天线的设计［J］.上海交通大学学报, 2007, 41(11): 18301834.

HUANG Biao, YAN Guozheng, ZAN Peng, et al. Design of the microstrip antenna for radiotelemetry capsule［J］. Journal of Shanghai Jiaotong University, 2007, 41(11): 18301834.

[1]	施裕升, 王晓科, 周宇泰, 蒋国韬, 徐天洋. 基于卡方检验与SVM的多雷达抗欺骗干扰方法[J]. 空天防御, 2022, 5(1): 108-114.
[2]	肖冉, 魏子清, 翟晓强. 基于支持向量机的办公建筑逐时能耗预测[J]. 上海交通大学学报, 2021, 55(3): 331-336.
[3]	蔡晖, 高伯阳, 祁万春, 吴熙, 谢珍建, 黄俊辉. “双碳”背景下线间潮流控制器多目标协调控制策略[J]. 上海交通大学学报, 2021, 55(12): 1608-1618.
[4]	丘文桢, 宋兴宇, 张新曙. 基于代理模型的三立柱半潜平台多目标优化[J]. 上海交通大学学报, 2021, 55(1): 11-20.
[5]	朱东, 姜萍萍, 颜国正, 王志武, 韩玎, 赵凯, 华芳芳, 姚盛健, 丁紫凡, 周泽润. 人工肛门括约肌系统便意感知重建[J]. 上海交通大学学报, 2020, 54(8): 771-777.
[6]	陶正瑞, 党嘉强, 徐锦泱, 安庆龙, 陈明, 王力, 任斐. 基于支持向量机回归的曲面零件涡流测距标定方法[J]. 上海交通大学学报, 2020, 54(7): 674-681.
[7]	徐彬彬, 洪榛, 赵磊, 俞立. 网络化倒立摆系统的偏差攻击及其检测方法[J]. 上海交通大学学报, 2020, 54(7): 697-704.
[8]	胡晓强，仲训昱，张霄力，彭侠夫，何荧. 基于支持向量机辅助的四轴陀螺两级故障诊断方法[J]. 上海交通大学学报, 2020, 54(11): 1151-1156.
[9]	王江卓,徐文聪,李建勋,贺丰收,曹兰英,缪礼锋. 基于支持向量机的雷达电子支援措施系统点迹-航迹关联算法[J]. 上海交通大学学报, 2019, 53(9): 1091-1099.
[10]	黄健，严胜刚. 未知声速下长基线系统定位修正算法[J]. 上海交通大学学报（自然版）, 2019, 53(3): 366-372.
[11]	马志宏，贡亮，林可，毛雨晗，吴伟，刘成良. 基于稻穗几何形态模式识别的在穗籽粒数估测[J]. 上海交通大学学报（自然版）, 2019, 53(2): 239-246.
[12]	李春祥，裴杨从琪，殷潇. 基于Hermite组合核EMD-WT-LSSVM的非平稳非高斯风压预测[J]. 上海交通大学学报, 2019, 53(10): 1249-1258.
[13]	王庆, 刘钊, 黄平华, 朱平. 白车身激光焊接过程的变形预测及几何补偿方法[J]. 上海交通大学学报, 2019, 53(1): 62-68.
[14]	江春冬1,2，王景玉1，杜太行1,2，郝静1,3，龙超1. 基于变分模态分解算法的单通道无线电混合信号分离[J]. 上海交通大学学报（自然版）, 2018, 52(12): 1618-1626.
[15]	李春祥,殷潇. 基于小波支持向量机的非高斯空间风压内外插预测[J]. 上海交通大学学报（自然版）, 2018, 52(11): 1516-1523.