International Journal of Electrical and Electronics Research (IJEER) Open Access | Rapid and quality publishing Research Article | Volume 10, Issue 4 | Pages 822-825 | e-ISSN: 2347-470X 822 Website: www.ijeer.forexjournal.co.in SEMG Signals Identification Using DT and LR Classifier ░ ABSTRACT- In the recent era of technology, biomedical signals have been attracted lots of attention regarding the development of rehabilitation robotic technology. The surface electromyography (SEMG) signals are the fabulous signals utilized in the field of robotics. In this context, SEMG signals have been acquired by twenty-five right-hand dominated healthy human subjects to discriminate the various hand gestures. The placement of SEMG electrodes has been done according to the predefined acupressure point of required hand movements. After the SEMG signal acquisition, pre-processing and noise rejection have been performed. The de-noising and four levels of SEMG signal decomposition have been accomplished by discrete wavelet transform (DWT). In this article, the third and fourth-level detail coefficients have been utilized for time-scale feature extractions. The performance of ten time-scale features has been evaluated and compared to each other with the three-fold cross-validation technique by using a Decision Tree (DT) and Linear Regression (LR) classifier. The results demonstrated that the DT classifier classification accuracy was found superior to the LR classifier. By using the DT classifier technique 96.3% accuracy has been achieved, with all combined features as a feature vector. Keywords: DT classifier, discrete wavelet transform, LR classifier, SEMG signals. ░ 1. INTRODUCTION The human body movement depends on the body structure, which needs very essential information about the human body structure [1], [2]. The smallest functional unit to characterize the neural controlling of the contraction process of muscles is known as a motor unit. It consists of a cell body, axon, dendrites, and muscle fibers [3]. The main objective of studying the SEMG signals is to discriminate between various muscle movements into classes by MUAP during contractions [4]. These signals are detected and recorded using the surface electrodes which are placed adjacent to the skin superimposed on the muscles acupressure point [5]. The signal is generated during the contraction of the electrical activity of muscle fibers and the generated SEMG signals contain some useful feature which can be analyzed by the way of applying Wavelet Transform (WT) and other powerful techniques like Empirical Mode Decomposition (EMD) for multifunctional myoelectric control [6]. The SEMG signal plays a vital role in both engineering and medical applications. SEMG is related to the muscle activation function by critically analyzing the electrical signal which is generated by the muscular contraction and flexion [7], [8]. The muscular contraction can be divided into two types such as voluntary and involuntary. As a result of this contraction, muscle potential is generated in the form of the SEMG signal [9]. So, SEMG signals contained the intentional information of movement performed by the subject [10]. SEMG is the study of the signals generated by muscles. The forearm muscles play a significant role in controlling hand motion [11], [12]. In similar ways, different programmed actions of any robotic arm which can include supination/pronation, opening/closing the hand, extended index, pincer, and a rest position; the muscles of interest are chosen from the desired biceps, triceps, thumb, and wrist movements. The remaining section of this paper is arranged as follows: In Section II, describes the data acquisition as well as the feature extraction process by the DWT technique. Section III shows the proposed experimental results obtained from MATLAB © 20. Finally, the concluded results are given in Section IV. ░ 2. MATERIALS AND METHODS 2.1 Data Recording and Pre-processing The EMG data has been acquired by six different hand movements with the different age groups of 18 to 24 years of 25 subjects. Two channels of passive non-invasive electrodes which have been connected to the Myotrace 400 hardware device are utilized for SEMG data acquisition. The placement of all electrodes has been done by standard Myotrace 400 manual information [13]. Due to the non-invasive characteristic of surface electrodes, the deployment of various surface electrodes has been widely adopted in various engineering as well as medical application-based studies. One advantage of this electrode is the ease of handling moreover it can only explore the surface muscles [14]. But this kind of electrode cannot identify the deeper muscles which can be easily detected SEMG Signals Identification Using DT And LR Classifier by Wavelet-Based Features Yogendra Narayan 1 , Meet Kumari 2 and Rajeev Ranjan 3 1,2,3 Department of Electronics and Communication Engineering, Chandigarh University, Mohali, India, 1 yogendranarayan.cse@cumail.in, 2 meetkumari08@yahoo.in, 3 rajeev.e9518@cumail.in *Correspondence: Yogendra Narayan; yogendranarayan.cse@cumail.in ARTICLE INFORMATION Author(s): Yogendra Narayan, Meet Kumari and Rajeev Ranjan; Received: 15/06/2022; Accepted: 29/09/2022; Published: 18/10/2022; e-ISSN: 2347-470X; Paper Id: IJEER-RDEC3750; Citation: 10.37391/IJEER.100410 Webpage-link: https://ijeer.forexjournal.co.in/archive/volume-10/ijeer-100410.html Publisher’s Note: FOREX Publication stays neutral with regard to Jurisdictional claims in Published maps and institutional affiliations.