Cancer remains a global health challenge, with various types such as lung, breast, and colon cancer posing significant threats. Timely and accurate diagnosis is crucial for effective treatment and improved survival rates. Genetic research offers promising avenues in the fight against cancer, as identifying gene mutations and expression levels enables the development of targeted therapies and a deeper understanding of disease subtypes and progression. This study investigates a novel hybrid method aimed at improving the accuracy and efficiency of cancer diagnosis and classification. By combining Discrete Cosine Transformation (DCT) and Univariate Feature Selection (UFS) methods, the feature selection process is optimized for the dataset. The extracted features are then rigorously tested using established classifiers to assess their effectiveness in cancer classification. The proposed method's performance was evaluated using eight distinct datasets, and metrics such as MF1, K-score, and sensitivity were calculated and compared with various methods in the literature. Empirical evidence demonstrates that the proposed method outperforms others on 5 out of 8 datasets in terms of both accuracy and computational efficiency. The presented method represents a reliable tool for cancer diagnosis and classification.
Cancer Microarray data Discrete cosine transform Univariate feature selection Genomic data analysis
Cancer remains a global health challenge, with various types such as lung, breast, and colon cancer posing significant threats. Timely and accurate diagnosis is crucial for effective treatment and improved survival rates. Genetic research offers promising avenues in the fight against cancer, as identifying gene mutations and expression levels enables the development of targeted therapies and a deeper understanding of disease subtypes and progression. This study investigates a novel hybrid method aimed at improving the accuracy and efficiency of cancer diagnosis and classification. By combining Discrete Cosine Transformation (DCT) and Univariate Feature Selection (UFS) methods, the feature selection process is optimized for the dataset. The extracted features are then rigorously tested using established classifiers to assess their effectiveness in cancer classification. The proposed method's performance was evaluated using eight distinct datasets, and metrics such as MF1, K-score, and sensitivity were calculated and compared with various methods in the literature. Empirical evidence demonstrates that the proposed method outperforms others on 5 out of 8 datasets in terms of both accuracy and computational efficiency. The presented method represents a reliable tool for cancer diagnosis and classification.
Cancer Microarray data Discrete cosine transform Univariate feature selection Genomic data analysis
Primary Language | English |
---|---|
Subjects | Biomedical Engineering (Other), Electrical Engineering (Other) |
Journal Section | Research Articles |
Authors | |
Publication Date | July 15, 2024 |
Submission Date | May 30, 2024 |
Acceptance Date | July 1, 2024 |
Published in Issue | Year 2024 |