Integrating Numerical and Quantitative Techniques for Analysis of Large-Scale Biological data using Hyper-heuristic Algorithm
Prachi Vijayeeta1, M. N. Das2, B. S. P. Mishra3
1Prachi Vijayeeta, School of Computer Engineering, Kalinga Institute of Industrial Technology, [Deemed To Be University], Bhubaneswar.
2M. N. Das, School of Computer Engineering, Kalinga Institute of Industrial Technology, [Deemed To Be University], Bhubaneswar.
3B. S. P. Mishra. School of Computer Engineering, Kalinga Institute of Industrial Technology, [Deemed To Be University], Bhubaneswar.
Manuscript received on May 02, 2020. | Revised Manuscript received on May 21, 2020. | Manuscript published on May 30, 2020. | PP: 2752-2762 | Volume-9 Issue-1, May 2020. | Retrieval Number: A3025059120/2020©BEIESP | DOI: 10.35940/ijrte.A3025.059120
Open Access | Ethics and Policies | Cite | Mendeley
© 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: A major thrust in the field of computational intelligence is the ability to comprehend and interpret intelligence in combination with several research disciplines of computer science, biology, statistics, and cognitive science. The emergence of bio informatics is a two-fold manifestation of advance biology along with data mining and statistical learning that attempts to analyse and interpret a large collection of medical data. It aims at exploring facts about unknown patterns. This paper aims at providing a model that numerically analyses the existence of carcinomas in the genomic data sequence. Attempts have been taken to optimise the highly contributing factors using recent nature inspired algorithms like Emperor Penguin Optimization Algorithm (EPOA) and Chaotic Artificial Algae Optimization(CAAO). These algorithms are gaining popularity as they are capable of exploring global optimum instead of local optimum. The performance of these algorithms are judged by implementing it in seven benchmark datasets. To ensure a good potential of these new algorithms, we have made a comparative study with the capability of other indigenous optimization algorithms like PSO etc.
Keywords: Optimization, microarray datasets, support vector machines, k-fold validations.
Scope of the Article: Numerical Modelling of Structures