A Novel Approach for Breast Cancer Data Classification Using Deep Forest Network
| Autor: | Debabrata Singh, Bishnupriya Panda, Sipra Sahoo, Shrabanee Swagatika |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Artificial neural network
business.industry Computer science Data classification Pattern recognition medicine.disease Uncorrelated ComputingMethodologies_PATTERNRECOGNITION Breast cancer Classifier (linguistics) Principal component analysis medicine Artificial intelligence Breast cancer classification business Curse of dimensionality |
| Zdroj: | Smart Innovation, Systems and Technologies ISBN: 9789811562013 |
| DOI: | 10.1007/978-981-15-6202-0_31 |
| Popis: | This work presents a deep forest network-based breast cancer classification system. Post application of principal component analysis (PCA) on the dataset reduced the dimensionality of data from nine dimensions to four dimensions to keep most uncorrelated features. Subsequent application of tenfold cross-validated deep forest-based classifier resulted in improved prediction accuracy. The proposed model is compared with contemporary neural network systems. The proposed model outperforms the contemporary neural network model with substantial prediction accuracy of 99.11%. The major contribution of this work is development and application of deep forest model for breast cancer classification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|