Filtering by
- All Subjects: Electrical Engineering
- All Subjects: Transcranial Magnetic Stimulation
This thesis evaluates several sampling methods and a non-parametric approach to sample sizes required to minimize the effect of these nuisance variables on classification performance. This work specifically focused on speech analysis applications, and hence the work was done with speech features like Mel-Frequency Cepstral Coefficients (MFCC) and Filter Bank Cepstral Coefficients (FBCC). The non-parametric divergence (D_p divergence) measure was used to study the difference between different sampling schemes (Stratified and Multistage sampling) and the changes due to the sentence types in the sampling set for the process.
Transcranial magnetic stimulation (TMS) is a non-invasive brain stimulation technique used in a variety of research settings, including speech neuroscience studies. However, one of the difficulties in using TMS for speech studies is the time that it takes to localize the lip motor cortex representation on the scalp. For my project, I used MATLAB to create a software package that facilitates the localization of the ‘hotspot’ for TMS studies in a systematic, reliable manner. The software sends TMS pulses at certain locations, collects electromyography (EMG) data, and extracts motor-evoked potentials (MEPs) to help users visualize the resulting muscle activation. In this way, users can systematically find the subject’s hotspot for TMS stimulation of the motor cortex. The hotspot detection software was found to be an effective and efficient improvement on previous localization methods.