ECG Identification Based on PCA and Adaboost Algorithm

被引:2
作者
Liu, Qi [1 ]
Si, Yujuan [1 ,2 ]
Li, Liangliang [1 ]
Wang, Di [1 ]
机构
[1] Jilin Univ, Coll Commun Engn, Changchun 130012, Peoples R China
[2] Jilin Univ, Zhuhai Coll, Zhuhai 519041, Peoples R China
来源
DIGITAL HUMAN MODELING AND APPLICATIONS IN HEALTH, SAFETY, ERGONOMICS AND RISK MANAGEMENT. HEALTHCARE APPLICATIONS, DHM 2019, PT II | 2019年 / 11582卷
关键词
ECG; Identification; PCA; Feature extraction; Adaboost;
D O I
10.1007/978-3-030-22219-2_4
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Electrocardiogram (ECG) is a weak electrical signal that reflects the process of heart activity, and has multiple excellent features such as uniqueness, stability, versatility, non-repeatability, easy collection and so on. As a new type of biometric authentication technology, the feature extraction and classification of ECG have become a hot research topic. However, there still exists some problems such as poor timeliness and low recognition accuracy. In order to solve these problems, in this paper, we propose an identification method based on Principal Component Analysis (PCA) and Adaboost algorithm. In this method, firstly, we remove the noise from the ECG signal and segment the ECG signal into multiple single heart beats based on detected R points. Then, PCA is used to process heart beat data to reduce feature dimension. Finally, the Adaboost algorithm is used to ensemble weak classifiers to construct a stronger classifier with higher accuracy. In order to validate the effectiveness of the proposed method, we tested our algorithm on 89 healthy subjects of the ECG-ID database. Experimental results show that the proposed method can achieve accuracy rate of 98.88% within 7 s, which demonstrates that the proposed method can provide an effective and practical way for ECG identification.
引用
收藏
页码:50 / 62
页数:13
相关论文
共 50 条
  • [41] Wireless Indoor Positioning Algorithm Based on PCA
    Li, H. L.
    Quan, W.
    Ji, G.
    Qian, Z. H.
    PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INDUSTRIAL ENGINEERING (AIIE 2015), 2015, 123 : 8 - 9
  • [42] A Parallel AES Encryption Algorithm Based on PCA
    Das, Debasis
    Misra, Rajiv
    ADVANCES IN PARALLEL, DISTRIBUTED COMPUTING, 2011, 203 : 238 - 246
  • [43] Fast Face Localisation Using AdaBoost Algorithm and Identification with Matrix Decomposition Methods
    Marciniak, Tomasz
    Drgas, Szymon
    Cetnarowicz, Damian
    MULTIMEDIA COMMUNICATIONS, SERVICES, AND SECURITY, 2011, 149 : 242 - 250
  • [44] An Improved Pruning Algorithm for ELM Based on the PCA
    Cui, Licheng
    Zhai, Huawei
    Wang, Benchao
    PROCEEDINGS OF 2017 INTERNATIONAL CONFERENCE ON ROBOTICS AND ARTIFICIAL INTELLIGENCE (ICRAI 2017), 2015, : 11 - 14
  • [45] Face Detection based on Improved Neural Network and Adaboost Algorithm
    Wang, Ziyang
    2017 INTERNATIONAL CONFERENCE ON SMART GRID AND ELECTRICAL AUTOMATION (ICSGEA), 2017, : 235 - 238
  • [46] Object Orientation Algorithm for Sequence Images Based on Adaboost Classification
    Hou, Yimin
    Jia, He
    Sun, Xiaoli
    Lun, Xiangmin
    Lan, Jianjun
    2009 ISECS INTERNATIONAL COLLOQUIUM ON COMPUTING, COMMUNICATION, CONTROL, AND MANAGEMENT, VOL IV, 2009, : 109 - +
  • [47] A noise-detection based AdaBoost algorithm for mislabeled data
    Cao, Jingjing
    Kwong, Sam
    Wang, Ran
    PATTERN RECOGNITION, 2012, 45 (12) : 4451 - 4465
  • [48] An Enhanced Biometric Score Fusion Scheme Based on the AdaBoost Algorithm
    Lin, Wei-Yang
    Yang, Chuan-Jheng
    THIRD INTERNATIONAL CONFERENCE ON INFORMATION SECURITY AND INTELLIGENT CONTROL (ISIC 2012), 2012, : 262 - 265
  • [49] An Improved Adaboost Algorithm for Imbalanced Data Based on Weighted KNN
    Li, Kewen
    Xie, Peng
    Zhai, Jiannan
    Liu, Wenying
    2017 IEEE 2ND INTERNATIONAL CONFERENCE ON BIG DATA ANALYSIS (ICBDA), 2017, : 30 - 34
  • [50] Network-based intrusion detection using Adaboost algorithm
    Hu, W
    Hu, WM
    2005 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE, PROCEEDINGS, 2005, : 712 - 717