Surface electromyography based explainable Artificial Intelligence fusion framework for feature selection of hand gesture recognition

被引:6
作者
Gehlot, Naveen [1 ]
Jena, Ashutosh [1 ]
Vijayvargiya, Ankit [2 ,3 ]
Kumar, Rajesh [1 ]
机构
[1] Malaviya Natl Inst Technol, Dept Elect Engn, Jaipur 302017, India
[2] Dublin City Univ, Insight Sci Fdn Ireland Res Ctr Data Analyt, Sch Human & Hlth Performance, Dublin D09V209, Ireland
[3] Swami Keshvanand Inst Technol Management & Gramoth, Dept Elect Engn, Jaipur 302017, India
关键词
Hand gesture recognition; Surface electromyography; Feature selection; Fusion framework; Explainable Artificial Intelligence; Machine learning; SEMG SIGNAL; CLASSIFICATION;
D O I
10.1016/j.engappai.2024.109119
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Over the past decade, the utilization of machine learning (ML) models for recognizing hand gestures from surface electromyography (sEMG) signals has been in demand for the control of prosthetics. Such real-time control demands swift responses and efficient models. The model's efficiency heavily relies on selecting optimal handcrafted features. As the number of acquisition channels increases, the complexity of handcrafted features escalates the computational burden and necessitates the reduction of irrelevant or noisy features to enhance model efficiency. This study proposes an eXplainable Artificial Intelligence (XAI) fusion-based feature selection framework for sEMG-based hand gesture recognition (HGR). The proposed framework comprises two stages. Firstly, it combines three feature selection methods: filter, wrapper, and embedded. Secondly, it employs SHAPbased explainability for ML models to select relevant features. The first stage of feature selection retains ten relevant features, followed by a fine selection of 50% of features in the second stage. The performance of the proposed framework is compared with three baseline models. It shows that the proposed model performs better than other baseline models in terms of accuracy, precision, recall, f-score, and computational time. The proposed XAI fusion framework achieves an average classification accuracy of 80.75% with the Extra Tree classifier, with a computational time of 3.47 ms. Furthermore, to assess its robustness against baseline models, evaluation is conducted using a publicly available dataset, revealing superior performance compared to other baselines.
引用
收藏
页数:12
相关论文
共 63 条
[1]   Evaluation of surface EMG-based recognition algorithms for decoding hand movements [J].
Abbaspour, Sara ;
Linden, Maria ;
Gholamhosseini, Hamid ;
Naber, Autumn ;
Ortiz-Catalan, Max .
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2020, 58 (01) :83-100
[2]   k-best feature selection and ranking via stochastic approximation [J].
Akman, David V. ;
Malekipirbazari, Milad ;
Yenice, Zeren D. ;
Yeo, Anders ;
Adhikari, Niranjan ;
Wong, Yong Kai ;
Abbasi, Babak ;
Gumus, Alev Taskin .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 213
[3]   Shapley-based feature augmentation [J].
Antwarg, Liat ;
Galed, Chen ;
Shimoni, Nathaniel ;
Rokach, Lior ;
Shapira, Bracha .
INFORMATION FUSION, 2023, 96 :92-102
[4]  
Arican E, 2022, ROM J INF SCI TECH, V25, P338
[5]   Fast wrapper feature subset selection in high-dimensional datasets by means of filter re-ranking [J].
Bermejo, Pablo ;
de la Ossa, Luis ;
Gamez, Jose A. ;
Puerta, Jose M. .
KNOWLEDGE-BASED SYSTEMS, 2012, 25 (01) :35-44
[6]   An interpretable feature selection method integrating ensemble models for chiller fault diagnosis [J].
Bi, Jian ;
Wang, Hua ;
Hua, Mei ;
Yan, Ke .
JOURNAL OF BUILDING ENGINEERING, 2024, 87
[7]  
Biswas S., 2016, International Journal of Applied Evolutionary Computation (IJAEC), V7, P28, DOI [DOI 10.4018/IJAEC.2016100102, 10.4018/ijaec.2016100102, 10.4018/IJAEC.2016100102]
[8]   Improvement of K-means Cluster Quality by Post Processing Resulted Clusters [J].
Borlea, Ioan-Daniel ;
Precup, Radu-Emil ;
Borlea, Alexandra-Bianca .
8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND QUANTITATIVE MANAGEMENT (ITQM 2020 & 2021): DEVELOPING GLOBAL DIGITAL ECONOMY AFTER COVID-19, 2022, 199 :63-70
[9]   Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning [J].
Cote-Allard, Ulysse ;
Fall, Cheikh Latyr ;
Drouin, Alexandre ;
Campeau-Lecours, Alexandre ;
Gosselin, Clement ;
Glette, Kyrre ;
Laviolette, Francois ;
Gosselin, Benoit .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2019, 27 (04) :760-771
[10]  
Cristianini N., 2000, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods