コンピュータサイエンスとシステム生物学のジャーナル

Data Adaptive Rule-based Classification System for Alzheimer Classification

Abstract

Mohit Jain, Prerna Dua, Sumeet Dua and Walter J Lukiw

Microarrays have already produced huge amounts of valuable genetic data that is challenging to analyse due to its high dimensionality and complexity. An inherent problem with the microarray data which is characteristic of diseases such as Alzheimer’s is that they face computational complexity due to the sparseness of the points within the data, which affect both the accuracy and the efficiency of supervised learning methods. This paper proposes a data-adaptive rule-based classification system for Alzheimer’s disease classification that generates relevant rules by finding adaptive partitions using gradient-based partitioning of the data. The adaptive partitions are generated from the histogram by analyzing Tuple Tests following which efficient and relevant rules are discovered that assist in classifying the new data correctly. The proposed approach has been compared with other rule-based and machine learning classifiers, and detailed results and discussion of the experiments are presented to demonstrate comparative analysis and the efficacy of the results.