Detection and classification of brain tumor using Artificial Neural Network from EEG Images
Journal Title: International Journal of Science Engineering and Advance Technology - Year 2013, Vol 1, Issue 7
Abstract
Brain tumor is an abnormal intracranial growth caused by cells reproducing themselves in an uncontrolled manner. Curing cancer has been a major goal of medical researchers for decades. The early detection of cancer can be helpful in curing the disease completely. In this paper we propose an ANN base approach to identify brain tumor from electroencephalogram (EEG) signals. It mainly consists of three stages; they are pre-processing, feature extraction and classification. The preprocessing involves resizing so that the further processing is easier. Feature Extraction involves extracting the features. The classification stage involves Artificial Neural network. Raw EEG signals are valuable in brain tumor diagnosis. On this basis, a brain tumor identification system is developed to analyze those features to judge whether brain tumor is present or not.
Authors and Affiliations
Shashi Kiran. S| Assistant Professor, JNN College of Engineering, Shimoga, Karnataka, India E-mail: shashisurya81@gmail.com, Liyakathunisa| Assistant Professor, Sri Jayachamarajendra College of Engineering, Mysore, Karnataka, India E-mail: dr.liyakath@yahoo.com
Keywords
Related Articles
- EP ID EP16241
- DOI -
- Views 407
- Downloads 16
Eco-Physiological Studies On Fox Sagar Lake With Reference To Water Quality
The present paper deals with the ecological studies on Fox Sagar lake with reference to pollution. For this purpose both physicochemical and biological parameters were analysed. Fox Sagar lake is famous for its natura...
New Multilevel Inverter Topology for Direct GridIntegration of Renewable Energy Systems
Owing to the fact that we are getting into quick development in innovation, strong state semiconductors have prompted the improvement of medium-voltage control converters which could deflect the requirement for high...
Secure Broker-Less Publish/Subscribe Systems Using Identity-Based Encryption
publish–subscribe is a messaging pattern where senders of messages, called publishers, do not program the messages to be sent directly to specific receivers, called subscribers. provisioning of basic security mechan...
CONVERGENCE OF ITERATIVE NEWTON’S METHOD FOR THE SOLUTION NUMERICAL EQUATIONS
this paper an Iterative Newton’s method for the solution of simple and multiple roots of an equation f(x)=0 is given and it is proved that this method has second order convergence.
An Innovative Self-assurance Methodology for Challenging AI Problems in graphical passwords
Numerous security primitives depend on hard numerical issues. Utilizing hard AI issues for security is rising as an energizing new worldview, however has been under-investigated. In this paper, we show another securi...