Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application

Abstract

Deep learning has recently been utilized with great success in a large number of diverse application domains, such as visual and face recognition, natural language processing, speech recognition, and handwriting identification. Convolutional neural networks, that belong to the deep learning models, are a subtype of artificial neural networks, which are inspired by the complex structure of the human brain and are often used for image classification tasks. One of the biggest challenges in all deep neural networks is the overfitting issue, which happens when the model performs well on the training data, but fails to make accurate predictions for the new data that is fed into the model. Several regularization methods have been introduced to prevent the overfitting problem. In the research presented in this manuscript, the overfitting challenge was tackled by selecting a proper value for the regularization parameter dropout by utilizing a swarm intelligence approach. Notwithstanding that the swarm algorithms have already been successfully applied to this domain, according to the available literature survey, their potential is still not fully investigated. Finding the optimal value of dropout is a challenging and time-consuming task if it is performed manually. Therefore, this research proposes an automated framework based on the hybridized sine cosine algorithm for tackling this major deep learning issue. The first experiment was conducted over four benchmark datasets: MNIST, CIFAR10, Semeion, and UPS, while the second experiment was performed on the brain tumor magnetic resonance imaging classification task. The obtained experimental results are compared to those generated by several similar approaches. The overall experimental results indicate that the proposed method outperforms other state-of-the-art methods included in the comparative analysis in terms of classification error and accuracy.

Artificial Neural Network Tuning by Improved Sine Cosine Algorithm for HealthCare 4.0

“…Therefore, the scientists have experimented with wide range of optimization algorithms on a variety of practical problems. Some of the most promising domains include medical diagnostics support [14,20,24,33,43], wireless sensor network tuning [4,9,12,48,57,66], stock price estimations [16], as well as intrusion detection and security domain [1,31,41,45,55,56,60,65] and plant classifying task [17].…”

Intrusion Detection by XGBoost Model Tuned by Improved Multi-verse Optimizer

“…NP-hard complexity with real world problems is common and hence the application of these algorithms is diverse. Some notable examples are artificial neural network optimization [7][8][9][10]12,14,15,19,21,26,32,36,48,53,54], wireless sensors networks (WSNs) [4,11,13,52,65,75], cryptocurrency trends estimations [44,49], finally the COVID-19 global epidemic-associated applications [22,25,64,66,[69][70][71]73], computer-conducted MRI classification and sickness determination [17,20,24,33,55], cloud-edge and fog computing and task scheduling [3,5,6,16,23,50,67], and lastly securing networks through intrusion detection [2,31,43,62,…”

Mapping Roofing with Asbestos-Containing Material by Using Remote Sensing Imagery and Machine Learning-Based Image Classification: A State-of-the-Art Review

“…Deep-learning-based (DL-based) methods and techniques have recently been rapidly used in several image processing applications [136,137]. By increasing the number of "depths" or "hidden layers" of machine learning methods, these architectures improve the performance and accuracy of the computation process [40].…”