Weather Classification using Fusion Of Convolutional Neural Networks and Traditional Classification Methods

Abstract

The weather phenomenon is very important in routine lives. The weather prediction, road electronic monitoring, traffic communication, capping inversion (CAP), afforestation, and the adjustment of the environmental issues are important factors to many decisions. Weather images classification may help in decision support systems. There are traditional and intelligent ways that can sufficiently achieve weather image classification. Traditional methods enhance the classification accuracy and the usability of weather phenomena. Researchers approve that machine learning has achieved better accuracies based on deep learning neural networks. This paper compares three different intelligent models by using a weather image dataset. The first model uses a convolution neural network (CNN) to classify five categories of weather images. The second model uses a fusion of convolution neural network and Decision Tree (DT). The third one uses a fusion of CNN and Support Vector Machine (SVM). The three models are applied to the collected dataset from Github and Kaggle. The study has achieved 92%, 93%, and 94% for CNN, CNN+DT, and CNN+SVM respectively. The Proposed methods have achieved high recognition accuracies for weather forecasting.

Classification of Weather Phenomenon with a New Deep Learning Method Based on Transfer Learning

“…Weyn [18]. Weather images are classified in different ways for traffic communication, afforestation, and regulation of environmental problems [19]. CNN based methods and machine learning based methods have been used together to obtain high accuracy performance results.…”

Automatic Dialect identification of Spoken Arabic Speech using Deep Neural Networks

“…Classification approaches have been used in several research fields to resolve different problems. For example, they have been used for weather forecasting [10], scene and image classification in computer vision [11,12,13] and protein classification in bioinformatics [14]. For the purpose of dialect identification, each dialect was handled as a separate class and then apply the classification approach.…”