Results in Engineering (Mar 2023)

Codon-mRNA prediction using deep optimal neurocomputing technique (DLSTM-DSN-WOA) and multivariate analysis

  • Zena A. Kadhuim,
  • Samaher Al-Janabi

Journal volume & issue
Vol. 17
p. 100847

Abstract

Read online

Based on the principle that the upgrading of any nation begins by raising the level of performance of its institutions that serve the community, including the Ministry of Healthcare and given the development in the field of technology, and the growing need to save the life of persons from different types of diseuses and determined the proteins that increase or prevent any diseuses, so it is found that the world has tended in recent years to intelligent data analysis techniques spatially deep neurocomputing in healthcare fields to predict high quality results in short time. The paper presents model to Codon-mRNA Prediction using Deep Optimal Neurocomputing Technique (DLSTM-DSN-WOA) and Multivariate Analysis. That model consists of five basic stages: The first stage is the process of collecting and preparing the data to make it in suitable form for the decision-making stage and included several steps, including the processing of missing values and condign the target, the second stage involved develop optimization algorithms called Whale Optimization Algorithm (WOA) to build optimal structure to one of the deep neurocomputing network (i.e., long short-term memory (LSTM)). That tool select after deep analysis achieve on optimization algorithms include PSO, BOA, WOA, COA, and FA; this analysis focus on determined for points: the main programming steps, main parameters, advantages, and disadvantages for each algorithm. . The WOA used to find the best structure of deep neurocomputing technique called LSTM that choose to develop after campier among multi techniques (i.e., Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Bi-Directional Long Short-Term Memory (BiLSTM), and AlexNet, GoogleNet). That campier perform based on the programing steps and main parameters affect in each algorithm, because WOA as algorithm having many advantages and characteristics. The proposed model appears as pragmatic intelligent data analysis model for reduce the computation and time of handle huge real data.

Keywords