Hybrid Intuitionistic Fuzzy Fused Quantum Particle Swarm Intelligence for the Prediction of Dyslexia
J. Loveline Zeema1, D. Francis Xavier Christopher2

1J. Loveline Zeema, Research Scholar School of Computer Studies Rathnavel Subramaniam College of Arts and Science Sulur, Coimbatore (Tamilnadu), India.
2Dr. D.Francis Xavier Christopher, Director, School of Computer StudiesRathnavel Subramaniam College of Arts and Science Sulur, Coimbatore (Tamilnadu), India

Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 166-171 | Volume-8 Issue-7, May 2019 | Retrieval Number: F5080048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Discovering the presence of dyslexia among the children needs proper analysis in earlier childhood days. The method used for diagnosing such disability is often done by making children to solve non-writing based graphical test. Depending on their performance specialist score these test, and identify whether the children suffer from dyslexia or not. Controversy in an assignment of scoring by experts exploits uncertainty in the dyslexic dataset, which has been recently accredited as a new challenge in the field of cognitive computing. The uncertainty in the diagnosis of dyslexia is intensified due to certain symptoms that are well-matched with multiple disorders. In this paper to overwhelm the vagueness, uncertainty, impreciseness in datasets, an intelligent intuitionistic fuzzy with quantum particle swarm optimization is fused in the artificial neural network is developed. This model tackles the issue of uncertainty by introducing the degree of hesitation which well defines the instances with multiple class labels. The quantum mechanism of particle swarm optimization makes the ANN in an intelligent manner by inferring the knowledge about the weight assigned among hidden nodes in a parallel manner. The simulation results prove the performance of this proposed QPSO-IFANN model which greatly assists the parents to discover the symptoms of dyslexia and recommend them to take their children to a psychologist for an individual checkup.
Keyword: Dyslexia, Uncertainty, Vagueness, Artificial Neural Network, Intuitionistic Fuzzy, Quantum Particle Swarm Optimization and Indeterminacy.
Scope of the Article: Regression and Prediction.