Hybrid GA-PCA Feature Selection Approach for Inertial Human Activity Recognition

被引:0
|
作者
El-Maaty, Aymara M. Abo [1 ]
Wassal, Amr G. [1 ]
机构
[1] Cairo Univ, Comp Engn Dept, Gizah 12613, Egypt
关键词
Time-Series; Human Activity Recognition; Feature Selection; Evolutionary Algorithm; Genetic Algorithm; GENETIC ALGORITHMS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Genetic algorithms is used as a wrapper feature selection technique in many research studies. In this paper we investigate GA capabilities in selecting the best set of time-series features for human activity recognition application. We propose a hybrid GA-PCA approach, where GA is used to select a subset of N features from 561 features, then PCA is used to reduce the subset into M orthogonal features. Experimental results show the ability of GA to eliminate low performance features without affecting the classification accuracy.
引用
收藏
页码:1027 / 1032
页数:6
相关论文
共 50 条
  • [1] A GA-PCA approach for power sector performance ranking based on machine productivity
    Ebrahimipour, V.
    Azadeh, A.
    Rezaie, K.
    Suzuki, K.
    [J]. APPLIED MATHEMATICS AND COMPUTATION, 2007, 186 (02) : 1205 - 1215
  • [2] Evaluation of Feature Selection on Human Activity Recognition
    Mazaar, Hussein
    Emary, Eid
    Onsi, Hoda
    [J]. 2015 IEEE SEVENTH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND INFORMATION SYSTEMS (ICICIS), 2015, : 591 - 599
  • [3] PCA Feature Selection For recognition of chatter gestation
    Shao Qiang
    Feng Chang-jian
    Kang Jing
    [J]. MEASUREMENT TECHNOLOGY AND ITS APPLICATION, PTS 1 AND 2, 2013, 239-240 : 434 - 437
  • [4] A GA based hierarchical feature selection approach for handwritten word recognition
    Malakar, Samir
    Ghosh, Manosij
    Bhowmik, Showmik
    Sarkar, Ram
    Nasipuri, Mita
    [J]. NEURAL COMPUTING & APPLICATIONS, 2020, 32 (07): : 2533 - 2552
  • [5] A GA based hierarchical feature selection approach for handwritten word recognition
    Samir Malakar
    Manosij Ghosh
    Showmik Bhowmik
    Ram Sarkar
    Mita Nasipuri
    [J]. Neural Computing and Applications, 2020, 32 : 2533 - 2552
  • [6] A Feature Selection and Classification Method for Activity Recognition Based on an Inertial Sensing Unit
    Fan, Shurui
    Jia, Yating
    Jia, Congyue
    [J]. INFORMATION, 2019, 10 (10)
  • [7] Hybrid Feature Selection Approach for Arabic Named Entity Recognition
    Shahine, Miran
    Sakre, Mohamed
    [J]. COMPUTATIONAL LINGUISTICS AND INTELLIGENT TEXT PROCESSING, (CICLING 2016), PT I, 2018, 9623 : 452 - 464
  • [8] AN ONLINE FEATURE SELECTION ARCHITECTURE FOR HUMAN ACTIVITY RECOGNITION
    Karagiannaki, Katerina
    Panousopoulou, Athanasia
    Tsakalides, Panagiotis
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 2522 - 2526
  • [9] A Benchmark Study on Feature Selection for Human Activity Recognition
    Karagiannaki, Katerina
    Panousopoulou, Athanasia
    Tsakalides, Panagiotis
    [J]. UBICOMP'16 ADJUNCT: PROCEEDINGS OF THE 2016 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING, 2016, : 105 - 108
  • [10] Enhanced Human Activity Recognition Using Wearable Sensors via a Hybrid Feature Selection Method
    Fan, Changjun
    Gao, Fei
    [J]. SENSORS, 2021, 21 (19)