This paper attempts to answer the question of if it’s possible to produce a simple, quick, and accurate neural network for the use in upper-limb prosthetics. Through the implementation of convolutional and artificial neural networks and feature extraction on electromyographic data different possible architectures are examined with regards to processing time, complexity, and accuracy. It is found that the most accurate architecture is a multi-entry categorical cross entropy convolutional neural network with 100% accuracy. The issue is that it is also the slowest method requiring 9 minutes to run. The next best method found was a single-entry binary cross entropy convolutional neural network, which was able to reach an accuracy of about 95% in as little as 5 minutes. These time values, while being high for this research, are still a good deal faster than those found in some previous studies. These methods show promise in the popularization of machine learning algorithms in commercial prosthetics, which is something that is still uncommon.
","abstract_html":"<p>This paper attempts to answer the question of if it’s possible to produce a simple, quick, and accurate neural network for the use in upper-limb prosthetics. Through the implementation of convolutional and artificial neural networks and feature extraction on electromyographic data different possible architectures are examined with regards to processing time, complexity, and accuracy. It is found that the most accurate architecture is a multi-entry categorical cross entropy convolutional neural network with 100% accuracy. The issue is that it is also the slowest method requiring 9 minutes to run. The next best method found was a single-entry binary cross entropy convolutional neural network, which was able to reach an accuracy of about 95% in as little as 5 minutes. These time values, while being high for this research, are still a good deal faster than those found in some previous studies. These methods show promise in the popularization of machine learning algorithms in commercial prosthetics, which is something that is still uncommon.</p>","abstract_has_math":false,"creators":["Lavin, Maxwell"],"institution":null,"degree_name":"Master of Science in Computer Science (MSCS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Chih-Cheng Hung","Coskun Cetinkaya"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-12-15T08:00:00Z","date_published":"2019-12-15T08:00:00Z","updated_at":"2026-07-24T02:43:33Z","subjects":["Machine Learning","Neural Engineering","EMG","Neural Networks","Prosthetics","Artificial Intelligence and Robotics","Bioelectrical and Neuroengineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.kennesaw.edu/cs_etd/33","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chih-Cheng Hung","Coskun Cetinkaya"]},{"key":"dc:creator","label":"Author","values":["Lavin, Maxwell"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-12-15T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science (MSCS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning","Neural Engineering","EMG","Neural Networks","Prosthetics","Artificial Intelligence and Robotics","Bioelectrical and Neuroengineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.kennesaw.edu/cs_etd/33"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This paper attempts to answer the question of if it’s possible to produce a simple, quick, and accurate neural network for the use in upper-limb prosthetics. Through the implementation of convolutional and artificial neural networks and feature extraction on electromyographic data different possible architectures are examined with regards to processing time, complexity, and accuracy. It is found that the most accurate architecture is a multi-entry categorical cross entropy convolutional neural network with 100% accuracy. The issue is that it is also the slowest method requiring 9 minutes to run. The next best method found was a single-entry binary cross entropy convolutional neural network, which was able to reach an accuracy of about 95% in as little as 5 minutes. These time values, while being high for this research, are still a good deal faster than those found in some previous studies. These methods show promise in the popularization of machine learning algorithms in commercial prosthetics, which is something that is still uncommon.
"]},{"key":"dc:title","label":"Title","values":["Finding a Viable Neural Network Architecture for Use with Upper Limb Prosthetics"]}]}],"canonical_facts":{"dc:contributor":["Chih-Cheng Hung","Coskun Cetinkaya"],"dc:creator":["Lavin, Maxwell"],"dc:date.available":["2019-12-15T08:00:00Z"],"dc:description.abstract":["This paper attempts to answer the question of if it’s possible to produce a simple, quick, and accurate neural network for the use in upper-limb prosthetics. Through the implementation of convolutional and artificial neural networks and feature extraction on electromyographic data different possible architectures are examined with regards to processing time, complexity, and accuracy. It is found that the most accurate architecture is a multi-entry categorical cross entropy convolutional neural network with 100% accuracy. The issue is that it is also the slowest method requiring 9 minutes to run. The next best method found was a single-entry binary cross entropy convolutional neural network, which was able to reach an accuracy of about 95% in as little as 5 minutes. These time values, while being high for this research, are still a good deal faster than those found in some previous studies. These methods show promise in the popularization of machine learning algorithms in commercial prosthetics, which is something that is still uncommon.
"],"dc:identifier":["https://digitalcommons.kennesaw.edu/cs_etd/33"],"dc:subject":["Machine Learning","Neural Engineering","EMG","Neural Networks","Prosthetics","Artificial Intelligence and Robotics","Bioelectrical and Neuroengineering"],"dc:title":["Finding a Viable Neural Network Architecture for Use with Upper Limb Prosthetics"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science in Computer Science (MSCS)"]},"updated_at":"2026-07-24T02:43:33Z"}