Biomedical Engineering and Bioengineering Commons^™

Multi-Classifier Fusion Strategy For Activity And Intent Recognition Of Torso Movements, Abhijit Kadrolkar

Doctoral Dissertations

As assistive, wearable robotic devices are being developed to physically assist their users, it has become crucial to develop safe, reliable methods to coordinate the device with the intentions and motions of the wearer. This dissertation investigates the recognition of user intent during flexion and extension of the human torso in the sagittal plane to be used for control of an assistive exoskeleton for the human torso. A multi-sensor intent recognition approach is developed that combines information from surface electromyogram (sEMG) signals from the user’s muscles and inertial sensors mounted on the user’s body. Intent recognition is implemented by following …

Markerless Radiostereogammetry Of The Shoulder Joint In Humans: Comparisons Of Scapulohumeral Kinematics Between Individuals With Healthy And Supraspinatus-Impaired Shoulders, Ashley N. Hannon

Electronic Thesis and Dissertation Repository

The purpose of this collection of studies was to further develop the knowledge of shoulder motion in order to better understand joint function through direct measurement of 3D scapulohumeral joint kinematics using a technique of high accuracy. Markerless, bi-planar fluoroscopic radiostereometric analysis using a generic shoulder model was developed in this thesis, reducing the amount of radiation exposure to subjects. The studies compared kinematic data of the scapulohumeral joint in six degrees of freedom with a precise, in-vivo measuring technique. Data were collected on young and older healthy individuals, individuals with a torn supraspinatus and post-surgical intervention.

Although this generic …

A New Technique To Improve The Operation Of Prosthetic Limbs During Muscle Fatigue, H. Albunashee, G. Rasool, K. Iqbal, G. White

Journal of the Arkansas Academy of Science

Prosthetic limbs hold a promise to renew the quality of life for the amputee. Neural commands are decoded via a classifier to generate control signals for the prosthetic devices. In the literature, many challenges and limitations have been identified that affect the prosthesis operation. One such drawback is muscle fatigue which degrades the surface electromyogram (sEMG) signals, and consequently, the performance of the deployed classification algorithm declines from 90% to 50% of average accuracy. We used a new technique using the Linear Discrimination Analysis (LDA) algorithm and the muscle synergy-based task discrimination (MSD) algorithm to improve the classification accuracy. In …