ABSTRACT
In the medical diagnosis such as WBC (white blood cell), the scattergram images show the relationships between neutrophils, eosinophils, basophils, lymphocytes, and monocytes cells in the blood. For COVID-19 detection, the distributions of these cells differ in healthy and COVID-19 patients. This study proposes a hybrid CNN model for COVID-19 detection using scatter images obtained from WBC sub (differential-DIFF) parameters instead of CT or X-Ray scans. As a data set, the scattergram images of 335 COVID-19 suspects without chronic disease, collected from the biochemistry department of Elazig Fethi Sekin City Hospital, are examined. At first, the data augmentation is performed by applying HSV(Hue, Saturation, Value) and CIE-1931(Commission Internationale de l'éclairage) conversions. Thus, three different image large sets are obtained as a result of raw, CIE-1931, and HSV conversions. Secondly, feature extraction is applied by giving these images as separate inputs to the CNN model. Finally, the ReliefF feature extraction algorithm is applied to determine the most dominant features in feature vectors and to determine the features that maximize classification accuracy. The obtaining feature vector is classified with high-performance SVM in binary classification. The overall accuracy is 95.2%, and the F1-Score is 94.1%. The results show that the method can successfully detect COVID -19 disease using scattergram images and is an alternative to CT and X-Ray scans.
ABSTRACT
This paper aims to update the exposure to flood risk in a catchment area of the Community of Madrid (Spain) linked to primary sector activities, albeit affected by the urban expansion of the capital. This research starts with the updating of the flood inventory, encompassing episodes documented between 1629 and 2020. The inadequate occupation of the territory means that floods continue to cause significant damage nowadays. It is worth highlighting the two recent floods (2019) that occurred just 15 days apart and caused serious damage to several towns in the basin. The areas at risk of flooding are obtained from the National Floodplain Mapping System, and the maximum and minimum floodable volume in the sector of the Tajuña River basin with the highest exposure to flooding has been calculated. The Sentinel 2 image in false colour (RGB bands 11-2-3, 11-8-3 and 12-11-8) and its transformation to colour properties (Intensity, Hue and Saturation) has made it possible to determine the extension of the riparian vegetation and the irrigated crops located in the alluvial plain. The SPOT 6 image with higher spatial resolution has allowed us to update the mapping of buildings located in areas at risk of flooding. Finally, based on cadastral data, a detailed cartography of built-up areas in areas at risk of flooding is provided. They affect buildings built mainly between the 1960s and 1990s, although the most recent buildings are built on agricultural land in the alluvial plain, even though current regulations prevent the occupation of these lands.