Feature Selection and Training Multilayer Perceptron Neural Networks Using Grasshopper Optimization Algorithm for Design Optimal Classifier of Big Data Sonar

Abstract

The complexity and high dimensions of big data sonar, as well as the unavoidable presence of unwanted signals such as noise, clutter, and reverberation in the environment of sonar propagation, have made the classification of big data sonar one of the most interesting and applicable topics for active researchers in this field. This paper proposes the use of the Grasshopper Optimization Algorithm (GOA) to train Multilayer Perceptron Artificial Neural Network (MLP-NN) and also to select optimal features in big data sonar (called GMLP-GOA). GMLP-GOA hybrid classifier first extracts the features of experimental sonar data using MFCC. Then, the most optimal features are selected using GOA. In the last step, MLP-NN trained with GOA is used to classify big data sonar. To evaluate the performance of GMLP-GOA, this classifier is compared with MLP-GOA, MLP-GWO, MLP-PSO, MLP-ACO, and MLP-GSA classifiers in terms of classification rate, convergence rate, local optimization avoidance power, and processing time. The results indicated that GMLP-GOA achieved a classification rate of 98.12% in a processing time of 3.14 s.

Predictive analysis of concrete slump using a stochastic search-consolidated neural network

“…Feature analysis is a popular type of statistical analysis in machine learning models [ 80 ]. A statistical technique, namely principal component analysis (PCA) [ 81 ] is employed in this section to investigate the applied dataset in terms of factor importance.…”

Identification of Damage in a Wind Turbine Blade Using Mechanical Measurements and Artificial Neural Networks

“…Indeed, AI is able to discover difficult correlations between signal and damage patterns, like ones appearing in wave propagation and ultrasound produced by distributed actuators and sensors and nondestructive evaluation (NDT), see [34][35][36][37][38][39][40][41][42]. From the many applications reported in the literature, one can mention here, for example, the aircraft icing detection and characterization problem [43], the prediction of urban gas consumption [44], the underwater backscatter recognition [45], the sonar classifier [46], the classification of marine mammals [47][48], the financial accounting information processing [49], and the biomedical application on breast cancer diagnosis [50].…”

Motion of nanovehicles on pristine and vacancy-defected silicene: implications for controlled surface motion

“…11,12 Finding their way into many fields, optimization techniques are also showing promising results to better help scientists in the field of molecular simulations. 13–16…”

“…11,12 Finding their way into many fields, optimization techniques are also showing promising results to better help scientists in the field of molecular simulations. [13][14][15][16] Controllable surface motion has been achieved through the use of external agents, such as a temperature gradient 17,18 or an electric field. 19 In this context, Lensen and Elemans 20 explored the use of scanning tunneling microscope (STM) to investigate and control the motion of molecular rotors on surfaces by performing tunneling current-time spectroscopy.…”