How do we choose the appropriate deep learning method for our case? A systematic literature review

Abstract

Abstract In the era of technology 4.0, there are many problems in multiple sectors of life that are difficult for humans to solve, ranging from issues in the education quality performance system, difficulties in disease diagnosis, problems in manufacturing systems, construction, food grading, quality control, Etc. Various efforts have been made to solve these problems, from the conventional method of manually retrieving data to obtain the best solution to using a big data-based approach with deep learning. Deep learning has successfully solved problems in various sectors, proving that using big data on deep learning algorithms gives significant results. This systematic review aims to review the studies that have been carried out on applying deep learning to solve or help problems in various sectors. This systematic review shows an overview of deep learning neural networks created in the completion process, the differences in the artificial intelligent methods used, and the advantages and disadvantages of deep learning in various models. It identifies challenges and recommendations for the future. The methods used in this systematic review include search strategies, selecting literature studies, and managing and extracting data. Based on the systematic review results, we know that Convolutional Neural Network (CNN) is the most widely used model for this deep learning algorithm to recognize the feature, along with the image-based data transformation strategy. Finally, deep learning has become very popular because it can transform various data types to get the desired result.