An Immune-Inspired Approach for Breast Cancer Classification

Abstract : Many pattern recognition and machine learning methods have been used in cancer diagnosis. The Artificial Immune System (AIS) is a novel computational intelligence technique. Designed by the principles of the natural immune system, it is able of learning, memorize and perform pattern recognition. The AIS's are used in various domains as intrusion detection, robotics, illnesses diagnostic, data mining, etc. This paper presents a new immune inspired idea based on median filtering for cloning, and applied for benign/malignant breast cancer classification. The classifier was tested on Wisconsin Diagnostic Breast Cancer Database using classification accuracy, sensitivity ans specificity, and was found to be very competitive when compared to other classifiers.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01054936
Contributor : Frédéric Davesne <>
Submitted on : Sunday, August 10, 2014 - 4:42:23 PM
Last modification on : Monday, October 28, 2019 - 10:50:21 AM

Identifiers

Collections

Citation

Rima Daoudi, Khalifa Djemal, Abdelkader Benyettou. An Immune-Inspired Approach for Breast Cancer Classification. 14th International Conference on Engineering Applications of Neural Networks (EANN 2013), Sep 2013, Halkidiki, Greece. pp.273--281, ⟨10.1007/978-3-642-41013-0_28⟩. ⟨hal-01054936⟩

Share

Metrics

Record views

113