Novel ABC based training algorithm for ovarian cancer detection using neural network

Artificial Bee Colony (ABC) is one of the most popular and successful swarm intelligence based algorithm which imitates the food search behavior of the honey bees. Various researchers have used this algorithm for optimization tasks including the training of neural networks for prediction and classification problems. In this manuscript, we have proposed a novel Error guided Artificial Bee Colony (EABC) algorithm which is based on the operators of ABC. The EABC is evaluated on real world problem of neural network training and EABC trained neural network is used for the detection of ovarian cancer from the mass spectrometry data of the blood samples. From the results, it has been observed that EABC exhibits a considerably better performance in finding the optimized neuron weights of the neural network when compared against other training algorithms.