Evaluation of IoT-Based Computational Intelligence Tools for DNA Sequence Analysis in Bioinformatics

TL;DR

This paper evaluates various IoT-based computational intelligence tools for DNA sequence analysis, aiming to identify the most efficient and reliable methods for handling big biological data in bioinformatics.

Contribution

It introduces a comprehensive evaluation framework using multiple analysis methods to compare IoT-based CI tools for DNA sequencing.

Findings

Fuzzy analysis identified the most accurate tools.

Entropy Shannon provided insights into data complexity.

Dempster-Shafer helped assess tool reliability.

Abstract

In contemporary age, Computational Intelligence (CI) performs an essential role in the interpretation of big biological data considering that it could provide all of the molecular biology and DNA sequencing computations. For this purpose, many researchers have attempted to implement different tools in this field and have competed aggressively. Hence, determining the best of them among the enormous number of available tools is not an easy task, selecting the one which accomplishes big data in the concise time and with no error can significantly improve the scientist's contribution in the bioinformatics field. This study uses different analysis and methods such as Fuzzy, Dempster-Shafer, Murphy and Entropy Shannon to provide the most significant and reliable evaluation of IoT-based computational intelligence tools for DNA sequence analysis. The outcomes of this study can be advantageous to the bioinformatics community, researchers and experts in big biological data.