EMG Signal Classification with Effective Features for Diagnosis
Electromyography (EMG) signals are broadly used in various clinical or biomedical applications, prosthesis or rehabilitation devices, Muscle-Computer Interface (MCI), Evolvable Hardware Chip (EHW) development and many other applications. Electromyography
- PDF / 1,400,267 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 69 Downloads / 357 Views
Department of Computer Science, South Asian University, New Delhi, India [email protected] 2 Institute of Computer Science, Bangladesh Atomic Energy Commission, Dhaka, Bangladesh [email protected]
Abstract. Electromyography (EMG) signals are broadly used in various clinical or biomedical applications, prosthesis or rehabilitation devices, MuscleComputer Interface (MCI), Evolvable Hardware Chip (EHW) development and many other applications. Electromyography (EMG) signal records the myopathy from nonlinear subjects in both time domain and frequency domain. It becomes very difficult to classify these various statuses. In this paper, a feature extraction and classification method of healthy and myopathy EMG signals are proposed where two features have been extracted on both healthy and myopathy EMG. Mean Squared Error (MSE) has been calculated to observe which feature will give better classification result. Then SVM is used to classify the extracted results. To evaluate the proposed model, a standard dataset collected from physionet.org is used where it shows higher accuracy than the conventional methods. Keywords: Electromyography Deviation Sample Entropy
Muscle computer interface Mean Absolute
1 Introduction Electromyography signal is a type of biomedical signal which carries properties of all conventional signals and describable in terms of their amplitude, frequency, and phase. It is originated by the movement of the muscle of the body. The movement of the muscle is known as contraction and vice versa is known as relaxation. EMG signals acquire noises while traveling through various tissues and nerves. So recorded EMG signals need to be preprocessed before use. The main purpose of EMG signal classification is in clinical diagnosis and biomedical applications. Neurological and Neuromuscular diseases can also be diagnosed with the help of different EMG signals. In terms of physiological background, there are three types of EMGs- Healthy, Myopathy and Neuropathy or Amyotrophic lateral sclerosis (ALS). Neuropathy or ALS is responsible for neurological diseases and Myopathy is responsible for neuromuscular diseases. Neuropathy or ALS is a rapidly progressive and fatal neurological disease. A statistic based on USA (ALS Association 2016), revealed that approximately 6000 peoples are diagnosed in the United States. So, research on neurological diseases is © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021 J. I.-Z. Chen et al. (Eds.): ICIPCN 2020, AISC 1200, pp. 629–637, 2021. https://doi.org/10.1007/978-3-030-51859-2_57
630
A. Wadud and Md. I. H. Showrov
increasing day by day. Development in this research sector depends on the classification of different EMGs. Better features should be extracted for better classification result.
2 Related Works In 1666, Francesco Redi [1] published documentation where he informed that electricity is generated by the electric ray fish by the highly specialized muscle. In 1773, Walsh demonstrated that muscle tissu
Data Loading...
