Brain Image Classification Using Discretization and Feature Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current brain image classification methods based on machine learning fail to consider the correlation between data distribution characteristics and attributes, leading to high computational complexity, high storage requirements, and low classification accuracy and efficiency.
Innovation Solution
A brain image classification method that involves discretizing the data into training, validation, and test sets, constructing a multi-objective function to optimize discretization, and using feature selection and reduction to improve classification accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If feature extraction is performed on original brain image data using machine learning, then classification can be achieved, but computational complexity and storage requirements increase
Solution Approach 1:
The patent segments the continuous brain image data into discrete intervals using discretization algorithms. This segmentation transforms the original continuous data space into multiple discrete segments, reducing the complexity of subsequent classification while preserving essential data characteristics for accurate classification
Solution Approach 2:
The patent changes the parameter representation of brain image data from continuous values to discrete interval labels. This parameter transformation simplifies the data structure and reduces computational complexity while maintaining the ability to achieve accurate classification through the discretization process
2Reliability
If feature extraction is performed on original brain image data, then classification can be achieved, but storage requirements increase
Solution Approach 1:
The patent extracts essential information from the original brain image data by discretizing it into interval-based representations. This extraction process retains the most important classification-relevant features while discarding redundant information, thereby reducing storage requirements while maintaining classification accuracy
3Reliability
If traditional machine learning classification is used on original brain image data, then classification results can be obtained, but processing efficiency is low
Solution Approach 1:
The patent performs preliminary discretization processing on the brain image data before classification. This preliminary action of dividing continuous data into discrete intervals simplifies the subsequent classification task, enabling faster processing while maintaining accurate classification results
4Productivity
If data discretization is performed to reduce complexity, then computational efficiency improves, but information loss may occur
Solution Approach 1:
The patent carefully transforms the parameter representation from continuous to discrete values through optimized discretization algorithms. This parameter change is designed to reduce computational complexity while preserving the essential information needed for accurate classification by determining optimal interval boundaries
Data Source
AI summary
The present invention discloses a brain image classification method based on discretized data, includes: dividing an original brain image dataset into an original training set, an original validation set, and an original test set; constructing a multi-objective function including an information loss before and after dataset discretization, a classification error rate, and a discrete data complexity, and obtaining a discretization scheme; discretizing the original training set, the original validation set and the original test set according to the discretization scheme; performing feature selection on a discrete training set and a discrete validation set, and performing feature reduction on the discrete training set, and a discrete test set using the feature selection result to obtain a reduced discrete training set and a reduced discrete test set; and training a classifier using the reduced discrete training set to classify the reduced discrete test set, to obtain a brain image data classification result.