Real-Time ABR Signal Classification Using Machine Learning Techniques: A LabVIEW-Based Implementation

Auditory Brainstem Response (ABR) testing is a cornerstone of auditory and neurological diagnostics, providing objective evaluation of auditory pathways. Despite its widespread clinical use, traditional manual ABR signal classification methods are time-consuming, prone to human error, and dependent on highly skilled personnel. This study proposes a framework for ABR signal classification leveraging advanced machine learning techniques integrated within the LabVIEW environment. By combining Discrete Wavelet Transform (DWT) based feature extraction with machine learning models---Support Vector Machines (SVM), Logistic Regression, and Artificial Neural Networks (ANN)---the proposed system achieves up to 95.42% classification accuracy. The hardware-software architecture, utilizing National Instruments (NI) myRIO for embedded processing, provides automated signal acquisition and classification capabilities. This automated system significantly enhances diagnostic efficiency, reduces reliance on manual interpretation, and provides scalable solutions adaptable to diverse clinical and research needs. These findings underscore the transformative potential of machine learning in ABR diagnostics, paving the way for improved early detection of auditory and cognitive disorders.