Open Access

ARTICLE

Machine Learning Technique to Detect Radiations in the Brain

E. Gothai^1,*, A. Baseera², P. Prabu³, K. Venkatachalam⁴, K. Saravanan⁵, S. SathishKumar⁶

1 Department of Computer Science and Engineering, Kongu Engineering College, Erode, 638060, India
2 School of Computing Science and Engineering, VIT Bhopal University, Bhopal, 466114, India
3 Department of Computer Science, CHRIST (Deemed to be University), Bangalore, 560029, India
4 Department of Computer Science and Engineering, CHRIST (Deemed to be University), Bangalore, India
5 Department of Computer Science and Engineering, Erode Sengunthar Engineering College, Thudupathi, 638057
6 Department of EEE, M.Kumarasamy College of Engineering, Karur, 639113, Tamilnadu, India

* Corresponding Author: E. Gothai. Email:

Computer Systems Science and Engineering 2022, 42(1), 149-163. https://doi.org/10.32604/csse.2022.020619

Received 31 May 2021; Accepted 19 July 2021; Issue published 02 December 2021

Abstract

The brain of humans and other organisms is affected in various ways through the electromagnetic field (EMF) radiations generated by mobile phones and cell phone towers. Morphological variations in the brain are caused by the neurological changes due to the revelation of EMF. Cellular level analysis is used to measure and detect the effect of mobile radiations, but its utilization seems very expensive, and it is a tedious process, where its analysis requires the preparation of cell suspension. In this regard, this research article proposes optimal broadcasting learning to detect changes in brain morphology due to the revelation of EMF. Here, Drosophila melanogaster acts as a specimen under the revelation of EMF. Automatic segmentation is performed for the brain to attain the microscopic images from the prejudicial geometrical characteristics that are removed to detect the effect of revelation of EMF. The geometrical characteristics of the brain image of that is microscopic segmented are analyzed. Analysis results reveal the occurrence of several prejudicial characteristics that can be processed by machine learning techniques. The important prejudicial characteristics are given to four varieties of classifiers such as naïve Bayes, artificial neural network, support vector machine, and unsystematic forest for the classification of open or nonopen microscopic image of D. melanogaster brain. The results are attained through various experimental evaluations, and the said classifiers perform well by achieving 96.44% using the prejudicial characteristics chosen by the feature selection method. The proposed system is an optimal approach that automatically identifies the effect of revelation of EMF with minimal time complexity, where the machine learning techniques produce an effective framework for image processing.

---

Keywords

---