Performance Evaluation of Intelligent Machine Learning Models in Auditory Feedback Optimization for MCPS
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Cochlear Implant System represent a significant advancement in the domain of Medical Cyber-Physical Systems (MCPS), enabling the restoration of hearing for individuals with profound hearing loss. This research focuses on the evaluation of two distinct machine learning classifiers, Neural Network (NN) and Support Vector Machine (SVM) within the context of CIS. The study addresses the critical need to enhance user experiences, sound quality, and overall effectiveness of these systems. The research framework involves collecting medical data and preprocessing, with a particular emphasis on feature extraction from audio inputs and implant system settings. SVM, known for its robust classification capabilities, and NN, capable of capturing intricate patterns, are deployed as the primary classifiers. The study examines performance metrics, including speech intelligibility improvement, sound quality ratings, user satisfaction, and standard machine learning metrics. The evaluation reveals valuable insights into the effectiveness of SVM and NN classifiers in enhancing the Cochlear Implant System's functionality. Furthermore, ethical considerations and fairness are addressed to ensure that the evaluation is conducted with the highest standards of patient safety and user satisfaction. This research contributes to the field by offering a comprehensive evaluation of SVM and NN classifiers in a medical cyber-physical context, shedding light on their effectiveness and potential to improve the lives of CIS users. The findings and methodology have implications for medical device innovation, machine learning applications in healthcare, and the broader domain of MCPS.
Fields of Study & Subjects
Hearing Loss and Rehabilitation
Speech and Audio Processing
Artificial Intelligence in Healthcare
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 30 March 2026
- Language
- EN