No abstract

The Covid-19 was first appeared in 2019 in Wuhan, China. It widely and rapidly expanded all over the world. Since then, it has had a strong effect on people’s daily lives, the world economy and the public health. The fast prediction of Covid-19 can assist the medicine to choose the right treatment. In this paper, we propose a classification of Covid-19 using Models based on a Convolutional Neural Network (CNN). We propose two models to detect Covid-19. The first one uses CNN with CT or X-ray images separately. The second uses CNN with both CT and X-ray images at the same time. The used datasets contain X-ray and CT images divided into three classes which are Covid-19, Normal and Pneumonia. Each type image class has 1045 images for training and 300 for testing. All these data sets are available in Kaggle repository. In order to evaluate the proposed models, we calculate the confusion matrix, the accuracy, precision, recall and F1 score. The model that uses CNN with both X-ray and CT images of 0.99 achieves the best accuracy. We deduced that using CT images is more efficient than using X-ray images to predict Covid-19. The combination of the CT and X-ray images to detect Covid-19 is more efficient than using only CT or X-ray images. The proposed models could effectively assist the radiologists in predicting Covid-19.

The main purpose of localization in wireless sensor networks is to determine the location of the randomly collected sensors. Recently, bio-inspired localization techniques have become popular thanks to its precise and fast solution. In this paper, a recently developed meta-heuristic algorithm based on the social behavior of chickens called chicken swarm optimization (CSO) is used to solve the node localization problem. The studies that we have carried out have demonstrated the clear effect of our proposed approach by changing the characteristics of the network and the number of chickens used, as well as its ability to improve a classical approach based on CSO; and the comparison results with PSO showing the superiority of proposed approach.

No abstract