We are pleased to launch the "ElectroMyography Analysis of Human Activities - databases (EMAHA-DB)." The datasets EMAHA-DB1 to EMAHA-DB3 are developed through a SERB (science and engineering research board, Govt. of India) funded project under the core research grant scheme with grant no. CRG/2019/003801.
The data collection protocol was approved by the IIIT Sri City institutional ethics committee (No. IIITS/EC/2022/01) in accordance with the declaration of Helsinki and specific accordance with the “National Ethical Guidelines for Biomedical and Health Research involving human participants” of India. These datasets are developed with a focus on subjects from the India population. The sEMG signals are measured by a set of Noraxon Ultium wireless sEMG sensors with Ag/Agcl electrodes.
It is a novel dataset of multi-channel surface electromyography (sEMG) signals to evaluate the activities of daily living (ADL). The dataset is acquired from 25 able-bodied subjects while performing 22 activities categorized according to the functional arm activity behavioral system (FAABOS) (3 - full hand gestures, 6 - open/close office draw, 8 - grasping and holding of small office objects, 2 - flexion and extension of finger movements, 2 - writing and 1 - rest). The dataset can be analyzed for hand activity recognition classification performance.
Citation: N. K. Karnam, T. A. Chand, S. R. Dubey, and B. Gokaraju, Electromyography Analysis of Human Activities - DataBase 1 (EMAHA-DB1). Harvard Dataverse, 2023. doi: 10.7910/DVN/R6JJ4Q.
N. K. Karnam, A. C. Turlapaty, S. R. Dubey and B. Gokaraju, "EMAHA-DB1: A New Upper Limb sEMG Dataset for Classification of Activities of Daily Living," in IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-11, 2023, Art no. 4007411, doi: 10.1109/TIM.2023.3279873.
N. K. Karnam, A. C. Turlapaty, S. R. Dubey, and B. Gokaraju, EMAHA-DB1: A New Upper Limb sEMG Dataset for Classification of Activities of Daily Living. arXiv, 2023. https://doi.org/10.48550/arXiv.2301.03325
It is a new dataset of sEMG signals that correspond to experiments based on isometric and isotonic activities during weight training. Nine healthy participants aged between $18$ to $21$ years were selected on a voluntary basis. The subjects were selected based on three levels of weight training experience: a) Novice - with no prior weight training experience, b) Intermediate - with a few weeks of training and c) Trained - with at least one year of training. EMG signals are collected at two muscle sites 1) Biceps Brachii (BB) representing the upper arm activity and 2) Flexor carpi ulnaris (FCU) representing the forearm muscle activity. The activities included bicep hold and bicep curl with the right arm.
Citation: D. Kusuru, A. C. Turlapaty, and M. Thakur, Electromyography Analysis of Human Activities - DataBase 2 (EMAHA-DB2). Harvard Dataverse, 2023. doi: 10.7910/DVN/MBG5UY.
Kusuru, D., Turlapaty, A. C., & Thakur, M. (2023). Analysis of LGM Model for sEMG Signals related to Weight Training. arXiv preprint arXiv:2301.05417.
It is another dataset of sEMG signals acquired while performing 30 different sports and recreational activities. The sEMG signals were collected from 8 electrodes placed at different sites on both upper limbs. The activities included 6 cricketing actions, 4 basketball passes, 3 tennis shots, 4 ball throwing, 4 badminton shots, 3 weight training, and finally 6 recreational activities such as throwing frisbee and tennikoit ring. The main purpose of the sports data (EMAHA-DB3) is to study the role of muscle activations in various movement sequences.
Citation: D. Kusuru, A.C. Turlapaty, Electromyography Analysis of Human Activities - DataBase 3 (EMAHA-DB3), Harvard Dataverse, 2023
The focus of EMAHA-DB4 is on the ADL under different measurement conditions. A group of 10 healthy subjects without any upper limb pathologies participated in the data collection process. A total of 8 activities are performed by each subject. The measurement setup consists of a 5-channel Noraxon Ultium wireless sEMG sensor system. Representative muscle sites of the forearm are identified and self-adhesive Ag/AgCl dual electrodes are placed. In these measurements, subjects are directed to execute each activity in four different arm positions given in the list below and three different body postures given in the list 1 below. So each activity is performed in 4 × 3 = 12 different scenarios. This setup facilitates analysis of ADL in various scenarios. Specifically, it allows the examination of how a subject’s body posture and arm position impact the activity categorization.
Data links Kaggle: EMAHA DB4 Harvard Dataverse: EMAHA DB4
Vidya Sagar; Turlapaty, Anish Chand; Surya Naidu, 2023, "Electromyography Analysis of Human Activities - DataBase 4 (EMAHA-DB4)", https://doi.org/10.7910/DVN/IFPNRK, Harvard Dataverse
Related Publications
V. Sagar, A. Turlapaty and S. Naidu, "Impact of Measurement Conditions on Classification of ADL using Surface EMG Signals," 2023 International Symposium on Image and Signal Processing and Analysis (ISPA), Rome, Italy, 2023, pp. 1-6, doi: 10.1109/ISPA58351.2023.10279445.
The focus of this dataset is fatigue onset detection and estimation. Twenty-five healthy subjects with no history of upper limb pathology, including 10 males and 1 females, participated in the sEMG data collection process. The average age is 21 years. The 6 activities performed by each subject with 3 different load weights and 2 different body postures. The subjects were categorized into three levels and the number of subjects at each level are: 3 at advanced, 4 at intermediate, and 4 at beginner level. Each hand muscle activity is recorded using a 7-channel Noraxon Ultium wireless sEMG sensor setup. Seven self-adhesive Ag/AgCL dual electrodes were placed at the center of the seven most representative muscle sites of the right arm. The total duration of each session is up to one hour per subject, depending on adaptability. Each activity is performed until the subject feels fatigue. There is a rest period, which is subject-dependent, between each of the repetitions and a 30-second gap between the sessions of different activities. Each of the activities consists of two phases: (1) an action and (2) rest. However, some activities included an extra release phase. During the action phase, the subject performs the corresponding activity; during the release phase, the subject transitions from the action state to the rest state; and during the rest phase, the subject completely relaxes each of his/her muscles.
Data Links Kaggle: EMAHA DB6