Speech-Based Parkinson's Prediction Using Ranked Syntactic Combinations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting Parkinson's disease through speech analysis are not sufficiently accurate and efficient, particularly in processing and analyzing audio data to determine the presence of the disease.
Innovation Solution
A Parkinson's disease prediction apparatus and method that utilizes a deep neural network model to analyze audio data, extracts syntactic combinations, and optimizes preprocessing conditions to enhance the accuracy of disease prediction by ranking and selecting high-performing syntactic combinations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing speech analysis methods are used to predict Parkinson's disease, then the prediction can be performed, but the accuracy is not sufficient
Solution Approach 1:
The patent applies parameter changes by systematically varying preprocessing conditions (noise reduction, feature extraction parameters, data normalization) and syntactic combination parameters (n-gram orders, combination types) to optimize the prediction model. This allows the system to identify the most effective parameter settings for accurate Parkinson's disease prediction from speech data.
Solution Approach 2:
The patent segments the speech analysis process into multiple independent components: audio preprocessing, feature extraction, syntactic combination generation, and prediction modeling. By dividing the complex analysis into separable stages, the system can optimize each component independently and combine them to achieve high overall accuracy.
2Measurement precision
If multiple preprocessing conditions and syntactic combinations are verified to improve accuracy, then the prediction accuracy improves, but the processing time and complexity increase
Solution Approach 1:
The patent performs preliminary action by pre-verifying and ranking multiple preprocessing conditions and syntactic combinations before actual prediction. The system pre-processes training data with various conditions, evaluates their effectiveness, and stores the optimal configurations. This allows rapid deployment without re-verification during actual prediction tasks.
Solution Approach 2:
The system efficiently manages the parameter verification process by systematically testing different preprocessing parameters and syntactic combination parameters, then selecting the optimal set based on verification results. This structured approach to parameter optimization balances thoroughness with computational efficiency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided are a Parkinson's disease prediction apparatus and a Parkinson's disease prediction method. The Parkinson's disease prediction method is performed by a processor of the Parkinson's disease prediction apparatus and includes extracting a syntactic combination from audio data including a speaker's speech result, verifying accuracy of a Parkinson's disease prediction model by changing conditions for preprocessing the audio data and the syntactic combination, determining a syntactic combination ranked in a high rank as audio data for Parkinson's disease prediction, based on a result of verifying the accuracy of the Parkinson's disease prediction model, and inputting, to the Parkinson's disease prediction model, a speaker's speech result corresponding to the audio data for the Parkinson's disease prediction and obtaining a Parkinson's disease prediction result for the speaker as an output of the Parkinson's disease prediction model.