sEMG for Basic Hand movements

Donated on 11/17/2014

The sEMG for Basic Hand movements includes 2 databases of surface electromyographic signals of 6 hand movements using Delsys' EMG System. Healthy subjects conducted six daily life grasps.

Dataset Characteristics

Time-Series

Subject Area

Health and Medicine

Associated Tasks

Classification

Feature Type

Real

# Instances

3000

# Features

2500

Dataset Information

Additional Information

Instrumentation: The data were collected at a sampling rate of 500 Hz, using as a programming kernel the National Instrument’s (NI) Labview. The signals were band-pass filtered using a Butterworth Band Pass filter with low and high cutoff at 15Hz and 500Hz respectively and a notch filter at 50Hz to eliminate line interference artifacts. The hardware that was used was an NI analog/digital conversion card NI USB- 009, mounted on a PC. The signal was taken from two Differential EMG Sensors and the signals were transmitted to a 2-channel EMG system by Delsys Bagnoli™ Handheld EMG Systems. Protocol: The experiments consisted of freely and repeatedly grasping of different items, which were essential to conduct the hand movements. The speed and force were intentionally left to the subject’s will. There were two forearm surface EMG electrodes Flexor Capri Ulnaris and Extensor Capri Radialis, Longus and Brevis) held in place by elastic bands and the reference electrode in the middle, in order to gather information about the muscle activation. The subjects were asked to perform repeatedly the following six movements, which can be considered as daily hand grasps: a) Spherical: for holding spherical tools b) Tip: for holding small tools c) Palmar: for grasping with palm facing the object d) Lateral: for holding thin, flat objects e) Cylindrical: for holding cylindrical tools f) Hook: for supporting a heavy load An illustrative photo is included in the data folder. Two different databases are included: 1) 5 healthy subjects (two males and three females) of the same age approximately (20 to 22-year-old) conducted the six grasps for 30 times each. The measured time is 6 sec. There is a mat file available for every subject. 2) 1 healthy subject (male, 22-year-old) conducted the six grasps for 100 times each for 3 consecutive days. The measured time is 5 sec. There is a mat file available for every day.

Has Missing Values?

No

Variable Information

Data Format: The format of each mat file is the following: • The data per grasp and per channel are in separate table with an obvious naming. {Spherical --> (spher_ch1, spher_ch2), Tip --> (tip_ch1, tip_ch2), Palmar --> (palm_ch1, palm_ch2), Lateral --> (lat_ch1, lat_ch2), Cylindrical --> (cyl_ch1, cyl_ch2), Hook --> (hook_ch1, hook_ch2)} • Each row of these tables has the whole signal per trial. The signal value is measured in Voltage. In summary, in each subject, there will be a mat file with 12 matrixes, in which matrix there will be 30 (trials) rows and 3000 (points of the signal) columns for database 1 (or 100 rows and 2500 columns for database 2).

Reviews

There are no reviews for this dataset yet.

Login to Write a Review
Download
0 citations
5097 views

Creators

Christos Sapsanis

Anthony Tzes

G. Georgoulas

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy