A new deep concolutional neural network model for classification of Covid-19 related human development level

The measures taken during the pandemic have had lasting effects on people's lives. On the other hand it has led national and multilateral institutions to develop new directions and methods of human development capability. Because, this pandemic become a systemic human development crisis affecting health, the economy, education, social life and accumulated gains. This study shows how the relationship of the Human Development Index (HDI), which has combined effects on health, education and the economy, should be considered in the context of pandemic factors. First, the COVID-19 data of the countries taken from a public and reliable source were extracted and made into an acceptable structure. Then, statistical feature selection was applied to determine which variables are closely related to HDI and to enable the Deep Convolutional Neural Network (DCNN) model to give more accurate results. Continuous Wavelet Transform (CWT) and scalogram methods are used for time series data visualization. Three different images of each country are merged into a single image, permeating each other for ease of processing. These images were made available for the input of the ResNet-50 network, a pre-trained DCNN model, by undergoing various preprocessing processes. After the training and validation processes, the feature vectors in the fc1000 layer of the network were drawn and given to the Support Vector Machine Classifier (SVMC) input. Specificity (88.2%), sensitivity (96.5%), precision (99.9%), F1 Score (94.9%) and Matthews Correlation Coefficient (MCC) (85.9%) total performance metrics were achieved. In addition, a study was conducted to determine the relationship between COVID-19 and the human development index using the hyperparameter classifier based on Bayesian optimization. The study was conducted using the AlexNet network that is one of the DCNN model. Then, specificity (96%), sensitivity (72%), precision (92%), Accuracy (85%), and F1 score (80%) metrics were achieved.