EMAHA-DB1: A New Upper Limb sEMG Dataset for Classification of Activities of Daily Living

• Published in: IEEE transactions on instrumentation and measurement Vol. 72; pp. 1 - 11
• Main Authors: Karnam, Naveen Kumar, Turlapaty, Anish Chand, Dubey, Shiv Ram, Gokaraju, Balakrishna
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Activities of daily living; Activities of daily living (ADL); Activity recognition; Artificial neural networks; Classification; Classification algorithms; Classifiers; Cross correlation; Data collection; dataset and benchmark; Datasets; Deep learning; Discriminant analysis; Electromyography; features; Fingers; Frequency domain analysis; Grasping; Hand (anatomy); Kernel functions; Machine learning; Muscles; Polynomials; Prostheses; Robotics; Signal analysis; Sociology; State of the art; Statistics; Support vector machines; surface electromyography (sEMG); Time domain analysis
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2023.3279873

In this article, we present electromyography analysis of human activity-database 1 (EMAHA-DB1), a novel dataset of multichannel surface electromyography (sEMG) signals to evaluate the activities of daily living (ADL). The dataset is acquired from 25 non-disabled subjects while performing 22 activities categorized according to functional arm activity behavioral observation system (FAABOS) (three-full hand gestures, six-open/close office draw, eight-grasping and holding of small office objects, two-flexion and extension of finger movements, two-writing and one-rest). The sEMG data is measured by a set of five Noraxon Ultium wireless sEMG sensors with Ag/Agcl electrodes placed on a human hand. The dataset is analyzed for hand activity recognition classification performance. The classification is performed using six state-of-the-art machine learning classifiers, including random forest (RF), fine <inline-formula> <tex-math notation="LaTeX">K </tex-math></inline-formula>-nearest neighbor (KNN), ensemble KNN (sKNN), linear discriminant analysis (LDA), support vector machines (SVMs), and a hybrid deep learning architecture of convolutional neural network (CNN) and bidirectional-long short term memory (Bi-LSTM) layers. In the classical methods, ten combinations of time domain and frequency domain feature sets are analyzed. The state-of-the-art classification accuracy on five FAABOS categories is 83.21% by using the SVM classifier with the third order polynomial kernel using energy feature and auto regressive feature set ensemble. The classification accuracy on 22 class hand activities is 75.39% by the same SVM classifier with the log moments in the frequency domain (LMF) feature, modified LMF, time domain statistical (TDS) feature, spectral band powers (SBPs), channel cross correlation and local binary patterns (LBPs) set ensemble. The analysis depicts the technical challenges addressed by the dataset. The developed dataset can be used as a benchmark for various classification methods as well as for sEMG signal analysis corresponding to ADL and for the development of prosthetics and other wearable robotics.