Enhanced deep convolutional neural network for malarial parasite classification

Abstract

The standard method for examining malarial disease is performed through the examination of blood smears under the microscope for parasite-infected red blood cells and this is done by qualified technicians. The inadequacy of this traditional method is enhanced using advanced computer vision and deep learning methods to automatically classify the malarial parasite from the microscope’s blood smear image as infected or uninfected. The primary challenge lies in the classification of malarial parasitizes from blood smear data which decide the overall accuracy. The proposed work uses a deep convolutional neural network (DCNN) to detect the malarial parasitizes from smear blood cell images. The primary focus of the work is to (i) compare the validation loss and accuracy by tuning the hyper-parameters in order to classify the images and (ii) compute the Kappa Coefficient and Matthew’s correlation coefficient. The efficiency of the proposed model is analyzed by comparing the optimizers (Adam and Adagrad) at various epochs. The overall accuracy of the proposed DCNN model reached 98.9% compared to the existing state-of-the-art models by focusing on hyper-parameter tuning.

KEYWORDS:

• Malaria
• computer vision
• deep learning
• convolutional neural networks
• hyper-parameters
• classification

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

M. Suriya

Ms. M. Suriya, working as an Assistant Professor in the Department of Computer Science and Engineering at KPR Institute of Engineering and Technology, Coimbatore. She has received her B.E in Information Technology from Avinashilingam University, Coimbatore in 2008 and Master's in Computer Science and Engineering from Anna University of Technology, Coimbatore in 2010. She is pursuing Ph.D. in Information and Communication under Anna University, Chennai. She has about 9 years of teaching experience and her areas of interest include Artificial Intelligence, Big Data and Wireless Communication. She has authored more than 25 research papers in refereed International Journals and IEEE conferences and has published 1 book and 8 book chapters with reputed publishers like Springer. She has obtained one patent and is serving as a reviewer for more that 6 peer journals like Inderscience, Taylor and Francis, MONET, IGI etc. She is certified NVIDIA DLI Ambassador for ‘Fundamentals of Computer Vision.’

V. Chandran

Mr. V. Chandran is working as an Assistant Professor in the Department of Electronics and Communication Engineering at KPR Institute of Engineering and Technology, Coimbatore. He is pursuing his Doctoral degree in the area of Artificial Intelligence at Anna University, Chennai. He completed his Master of Engineering in VLSI Design from Government College of Technology, Coimbatore and his Bachelor's degree in Electronics and Communication Engineering in VeltechMultitech Dr. Rangarajan Dr. Sakunthala Engineering College, Chennai. He is having 2 years of teaching experience from Bannari Amman Institute of Technology, Sathyamangalam. He published 8 research papers in both National and International journals (4 Scopus indexed) and presented 10 papers in conferences. He has qualified in GATE 2015 and received fellowship to pursue his Masters. He received an honor from NVIDIA as a University ambassador certified DLI instructor for Deep Learning.

M. G. Sumithra

Dr. M. G. Sumithra is working as Professor and Head in the Department of Electronics and Communication Engineering at KPR Institute of Engineering and Technology, Coimbatore. She has received her B.E. degree in Electronics and Communication Engineering from Government College of Engineering, Salem, India in 1994, she obtained her M.E. Degree in Medical Electronics from College of Engineering, Gundy, Anna University Chennai, India in 2001 and received Ph.D. (Information and Communication Engineering) Anna University Chennai, India in 2011. She has 24 Yrs and 8 Months of teaching experience. Her areas of interest include Signal/Image Processing, Biomedical Engineering, wireless Communications and Artificial intelligence. She has published 66 technical papers in refereed journals, 3 book chapters and 129 research papers in national and International conferences in India and 5 in abroad. In addition, she has published 3 book chapters and she is NVIDIA Deep learning Institute certified Instructor for ‘Computer vision’.