Publisher
University of Tennessee at Chattanooga
Place of Publication
Chattanooga (Tenn.)
Abstract
Prosthetic hands have become increasingly prevalent in recent years, providing individuals with missing or impaired limbs the ability to perform various daily tasks. However, the lack of proper sensory feedback in these devices can make it difficult for users to control the movement of the prosthetic hand. To address this issue, researchers have explored using inertial measurement unit (IMU) data to predict the grasping of the prosthetic hand. The ultimate goal of our work is to develop an optimized system that can accurately and seamlessly convert IMU data into visual prosthetic hand movements. In this study, we used the machine learning technique based on IMU data to distinguish two different prosthetic hand grasps named cylindrical and hook. In order to recognize grasps, we proposed a Deep ANN and achieved a high level of accuracy.
Document Type
posters
Language
English
Rights
http://rightsstatements.org/vocab/InC/1.0/
License
http://creativecommons.org/licenses/by/4.0/
Recommended Citation
Ghaffar Nia, Nafiseh and Kaplanoglu, Erkan, "Towards Prediction of Prosthetics Hand Orientation for Different Grasps Using Machine Learning Algorithm". ReSEARCH Dialogues Conference proceedings. https://scholar.utc.edu/research-dialogues/2023/proceedings/1.
Towards Prediction of Prosthetics Hand Orientation for Different Grasps Using Machine Learning Algorithm
Prosthetic hands have become increasingly prevalent in recent years, providing individuals with missing or impaired limbs the ability to perform various daily tasks. However, the lack of proper sensory feedback in these devices can make it difficult for users to control the movement of the prosthetic hand. To address this issue, researchers have explored using inertial measurement unit (IMU) data to predict the grasping of the prosthetic hand. The ultimate goal of our work is to develop an optimized system that can accurately and seamlessly convert IMU data into visual prosthetic hand movements. In this study, we used the machine learning technique based on IMU data to distinguish two different prosthetic hand grasps named cylindrical and hook. In order to recognize grasps, we proposed a Deep ANN and achieved a high level of accuracy.