| Abstract [eng] |
Thesis „Voice signal decomposition for Parkinson‘s disease detection“ goal of this research is the robust detection of Parkinson’s disease by acoustic analysis of sustained voice recordings. Application of signal decomposition into intrinsic mode functions (IMFs) is investigated as a novel type of audio features and a custom solution for decision-level fusion, employing statistical functionals to compress decisions from all IMFs. Similar research analysis was made. Analysis was based on the selected criteria and it was decided whether it was worthwhile to do a research with selected methodologies. Proposed audio features are perceptual linear predictive cepstral coefficients (PLPCCs) estimated on the extracted components from one or several equally-spaced windows of audio signal. Decompositions used are empirical mode decomposition (EMD) and variational mode decomposition (VMD). Random forest (RF) is used as a base detector as well as meta learner for decision-level fusion. Cost of log-likelihood ratio (Cllr) and equal error rate (EER) were used to measure goodness-of-detection. During the experiment, 1134 voice recordings database was used, which content consisted of healthy and sick patients with different genders and sustainable vowel /a/ pronunciation. Baseline solution using PLPCCs from all frames was compared to several types of decision-level fusion (EMD, VMD, and EMD + VMD) using 1–3 windows of various sizes (10 – 100 ms). Decomposition-based PLPCCs and EMD + VMD fusion from three 30 ms sized windows resulted in detection performance with an average EER of 6.5 % and clearly outperformed the baseline solution of decomposition-less PLPCCs, having EER of 32.9 %. Variable importance from meta RF found both decompositions as useful and variance-related statistics of base RF decisions as the most important. System prototype was designed and was created to share and put to the test the research results. Prototype system was created according to described product definition, system limitations, functional and non-functional requirements, hierarchy chart, technical specifications, the logical architecture, the business logic, use Case diagram, the user interface and user's Manual. The conclusions describe what has been done and additional notes or note patterns. |
