Cancer Classification Analysis for Microarray Gene Expression Data by Integrating Wavelet Transform and Visual Analysis

Cancer classification using microarray gene expression data has received high interest because of its capability of performing cancer diagnosis computationally. However, researchers often faced difficulty in analyzing the data to achieve an accurate cancer diagnosis due to the size and noise issues in the microarray gene expression data. Therefore, it is important to perform feature extraction procedure to enhance the performance in cancer diagnosis. In this study, an approach is proposed by integrating wavelet-based feature extraction and visual analysis for cancer classification. Feature extraction is performed with wavelet transform and validates with a statistical test to determine only statistically valuable features. Visual analysis is also conducted to inspect not only the distribution of features but also the patterns of the cancer data. With cancer datasets, the performances of three machine learning (ML) algorithms for cancer classification are measured to show the effectiveness of the approach. From the performance evaluation study, we found that our approach has an ability to classifying cancers accurately.