This study investigated the application and enhancement of Non-Invasive Brain-Computer Interfaces (NI-BCIs), focused on enhancing the efficiency and effectiveness of this technology for individuals with severe physical limitations. The core research goal was to improve current limitations associated with wires, noise, and invasive procedures often associated with BCI technology. The key discussed solution involves developing an optimized Encoder/Decoder (E/D) pair using machine learning techniques, particularly those borrowed from Generative Adversarial Networks (GAN) and other Deep Neural Networks, to minimize data transmission and ensure robustness against data degradation. The study highlighted the crucial role of machine learning in self-adjusting and isolating essential data for accurate and efficient classification. The research design involved training this E/D pair to unlock applications of NI EEG BCIs, such as speech synthesis and seamless control of mobile devices. This research successfully trained the E/D pair with a compression ratio of 500 to 75 data points. With parallel processing, this paper successfully processed and transmitted 36 channels of EEG data without data loss at 97% accuracy in 0.0752s. By successfully developing a robust E/D pair, the study aims to revolutionize BCI technology, paving the way for more intuitive interfaces and significantly improving the quality of life for locked-in individuals. This research thus contributes to advancements in NI-BCIs, harnessing machine learning to address current limitations and unlock new possibilities for this critical technology.
","abstract_html":"<p>This study investigated the application and enhancement of Non-Invasive Brain-Computer Interfaces (NI-BCIs), focused on enhancing the efficiency and effectiveness of this technology for individuals with severe physical limitations. The core research goal was to improve current limitations associated with wires, noise, and invasive procedures often associated with BCI technology. The key discussed solution involves developing an optimized Encoder/Decoder (E/D) pair using machine learning techniques, particularly those borrowed from Generative Adversarial Networks (GAN) and other Deep Neural Networks, to minimize data transmission and ensure robustness against data degradation. The study highlighted the crucial role of machine learning in self-adjusting and isolating essential data for accurate and efficient classification. The research design involved training this E/D pair to unlock applications of NI EEG BCIs, such as speech synthesis and seamless control of mobile devices. This research successfully trained the E/D pair with a compression ratio of 500 to 75 data points. With parallel processing, this paper successfully processed and transmitted 36 channels of EEG data without data loss at 97% accuracy in 0.0752s. By successfully developing a robust E/D pair, the study aims to revolutionize BCI technology, paving the way for more intuitive interfaces and significantly improving the quality of life for locked-in individuals. This research thus contributes to advancements in NI-BCIs, harnessing machine learning to address current limitations and unlock new possibilities for this critical technology.</p>","abstract_has_math":false,"creators":["Fanfan, Ernst"],"institution":null,"degree_name":"Master of Science in Computer Science (MSCS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Adrian Randolph","Jose Garrido"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-07-15T07:00:00Z","date_published":"2023-07-15T07:00:00Z","updated_at":"2026-07-24T02:44:06Z","subjects":["Brain Computer Interface","Bluetooth","Machine Learning","Generative Adversarial Network","Neuroscience","Neuro Information System","Transmission Protocol","Artificial Intelligence and Robotics","Management Information Systems"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.kennesaw.edu/cs_etd/57","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Adrian Randolph","Jose Garrido"]},{"key":"dc:creator","label":"Author","values":["Fanfan, Ernst"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2023-07-15T07:00:00Z"]},{"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":["Brain Computer Interface","Bluetooth","Machine Learning","Generative Adversarial Network","Neuroscience","Neuro Information System","Transmission Protocol","Artificial Intelligence and Robotics","Management Information Systems"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.kennesaw.edu/cs_etd/57"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This study investigated the application and enhancement of Non-Invasive Brain-Computer Interfaces (NI-BCIs), focused on enhancing the efficiency and effectiveness of this technology for individuals with severe physical limitations. The core research goal was to improve current limitations associated with wires, noise, and invasive procedures often associated with BCI technology. The key discussed solution involves developing an optimized Encoder/Decoder (E/D) pair using machine learning techniques, particularly those borrowed from Generative Adversarial Networks (GAN) and other Deep Neural Networks, to minimize data transmission and ensure robustness against data degradation. The study highlighted the crucial role of machine learning in self-adjusting and isolating essential data for accurate and efficient classification. The research design involved training this E/D pair to unlock applications of NI EEG BCIs, such as speech synthesis and seamless control of mobile devices. This research successfully trained the E/D pair with a compression ratio of 500 to 75 data points. With parallel processing, this paper successfully processed and transmitted 36 channels of EEG data without data loss at 97% accuracy in 0.0752s. By successfully developing a robust E/D pair, the study aims to revolutionize BCI technology, paving the way for more intuitive interfaces and significantly improving the quality of life for locked-in individuals. This research thus contributes to advancements in NI-BCIs, harnessing machine learning to address current limitations and unlock new possibilities for this critical technology.
"]},{"key":"dc:title","label":"Title","values":["Using Machine Learning Techniques to Model Encoder/Decoder Pair for Non-invasive Electroencephalographic Wireless Signal Transmission"]}]}],"canonical_facts":{"dc:contributor":["Adrian Randolph","Jose Garrido"],"dc:creator":["Fanfan, Ernst"],"dc:date.available":["2023-07-15T07:00:00Z"],"dc:description.abstract":["This study investigated the application and enhancement of Non-Invasive Brain-Computer Interfaces (NI-BCIs), focused on enhancing the efficiency and effectiveness of this technology for individuals with severe physical limitations. The core research goal was to improve current limitations associated with wires, noise, and invasive procedures often associated with BCI technology. The key discussed solution involves developing an optimized Encoder/Decoder (E/D) pair using machine learning techniques, particularly those borrowed from Generative Adversarial Networks (GAN) and other Deep Neural Networks, to minimize data transmission and ensure robustness against data degradation. The study highlighted the crucial role of machine learning in self-adjusting and isolating essential data for accurate and efficient classification. The research design involved training this E/D pair to unlock applications of NI EEG BCIs, such as speech synthesis and seamless control of mobile devices. This research successfully trained the E/D pair with a compression ratio of 500 to 75 data points. With parallel processing, this paper successfully processed and transmitted 36 channels of EEG data without data loss at 97% accuracy in 0.0752s. By successfully developing a robust E/D pair, the study aims to revolutionize BCI technology, paving the way for more intuitive interfaces and significantly improving the quality of life for locked-in individuals. This research thus contributes to advancements in NI-BCIs, harnessing machine learning to address current limitations and unlock new possibilities for this critical technology.
"],"dc:identifier":["https://digitalcommons.kennesaw.edu/cs_etd/57"],"dc:subject":["Brain Computer Interface","Bluetooth","Machine Learning","Generative Adversarial Network","Neuroscience","Neuro Information System","Transmission Protocol","Artificial Intelligence and Robotics","Management Information Systems"],"dc:title":["Using Machine Learning Techniques to Model Encoder/Decoder Pair for Non-invasive Electroencephalographic Wireless Signal Transmission"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science in Computer Science (MSCS)"]},"updated_at":"2026-07-24T02:44:06Z"}