University of Twente Student Theses

Login

The recognition of hand gestures by evaluating micro-vibrations using a single wrist-worn highly sampled IMU.

Spaan, C.E (2018) The recognition of hand gestures by evaluating micro-vibrations using a single wrist-worn highly sampled IMU.

[img] PDF
15MB
Abstract:After an incidence of stroke, the motor activity of the patient can be affected. This is perceivable by the inability to complete simple hand movements. By using wearables, which are suitable for ambulatory measurements, home revalidation becomes an option. By using a highly sampled IMU implemented in a wearable device, it becomes possible to detect specific vibrations corresponding to certain hand movements. This paper is a preliminary study focused on gesture recognition and presents the answer if the information obtained by a highly sampled IMU is adequate to classify different gestures made by human subjects. This is done using data analysis and machine learning to create a model capable of gesture recognition. The confusion matrices that are extracted are discussed and future recommendations are made.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:50 technical science in general, 53 electrotechnology
Programme:Electrical Engineering BSc (56953)
Link to this item:http://purl.utwente.nl/essays/75298
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page