The sudden COVID-19 pandemic has caused a serious global concern due to infections and mortality rates. It is a hazardous disease that has recently become the biggest crisis in the modern era. Due to the limitation of test kits and the need for screening and rapid diagnosis of patients, it is essential to perform a self-operating detection model as a fast recognition system to detect COVID-19 infection and prevent the spread among the people. In this paper, we propose a novel technique called Fast COVID-19 Detector (FCOD) to have a fast detection of COVID-19 using X-ray images. The FCOD is a deep learning model based on the Inception architecture that uses 17 depthwise separable convolution layers to detect COVID-19. Depthwise separable convolution layers decrease the computation costs, time, and they can have a reducing role in the number of parameters compared to the standard convolution layers. To evaluate FCOD, we used covid-chestxray-dataset, which contains 940 publicly available typical chest X-ray images. Our results show that FCOD can provide accuracy, F1-score, and AUC of 96%, 96%, and 0.95%, respectively in classifying COVID-19 during 0.014 s for each case. The proposed model can be employed as a supportive decision-making system to assist radiologists in clinics and hospitals to screen patients immediately.

No abstract

No abstract

No abstract

This study used the location of the average advance time (method 1) and the mean infiltration opportunity time (method 2) as the midpoint of the twopoint method for determining "power advance" and Kostiakov-Lewis infiltration parameters. Experiments were carried out in three border-irrigated fields. The results showed that calibration of the power advance equation obtained by the Elliot and Walker method had high accuracy, with an average relative error of 11.3% in the time to complete the advance phase. The root mean square deviation (d RMS ) index used by Elliot and Walker showed that method 1, with an average d RMS value of 15.7 min, has the lowest d RMS , which estimates the advance time with mean d RMS values of 5.1 and 1.8 min less than the proposed method 2 and the method of Elliot and Walker, respectively. Furthermore, using all methods, the Kostiakov-Lewis infiltration equation parameters were determined. In estimating infiltration depth, method 1 had the highest accuracy with a minimum relative error of 0%, a maximum relative error of 8.7%, and an average relative error of 3.8%. Based on both the d RMS index and the accuracy of the infiltration equation, method 1 had a higher accuracy. K E Y W O R D S average advance time, design, evaluation, infiltration opportunity, volume balance Résumé Cette étude a utilisé l'emplacement du temps moyen d'avance (méthode 1) et le temps moyen d'occasion d'infiltration (méthode 2) comme point médian de la méthode à deux points pour déterminer les paramètres d'infiltration "avance de puissance" et Kostiakov-Lewis. Des expériences ont été menées dans trois champs irrigués selon la méthode border irrigation. Les résultats ont montré que l'étalonnage de l'équation d'avance de puissance obtenue par la méthode Elliot et Walker avait une grande précision, avec une erreur relative moyenne de 11,3% dans le temps pour terminer la phase d'avance. L'indice d'écart quadratique moyen ine (d RMS ) utilisé par Elliot et Walker a montré que la * Etude du point médian d'une méthode en deux points pour prédire l'avance et l'infiltration dans l'irrigation de surface