The purpose of the study is the city of Baghdad, the capital of Iraq, was chosen to study the spectral reflection of the land cover and to determine the changes taking place in the areas of the main features of the city using the temporal resolution of multispectral bands of the satellite Landsat 5 and 8 for MSS and OLI sensors respectively belonging to NASA and for the period 1999-2021, and calculating the increase and decrease in the basic features of Baghdad. The main conclusions of the study were, This study from 1999 to 2021 and in two different seasons: the Spring of the growing season and Summer the dry season. When using the supervised classification method to determine the differences, the results showed remarkable changes. Where he was in 1999 Normalized Difference Vegetation Index (NDVI) 925km2 and Normalized Difference Water Index (NDWI) 75.3 km2 In the case of an increase during the growth period, while the values decreased during the period of dry to (NDVI) 390.8 km2 and (NDWI) 51.9 km2. As for Soil Adjusted Vegetation Index (SAVI) 1692.9 km2 and Normalized Difference Built up Index (NDBI) 782.1 km2 we notice a decrease in the growth period, while the values increase during the dry period to (SAVI) 2239.1 km2 and (NDBI) 1495.7 km2. In 2021 (NDVI) 242.7 km2 (NDWI) 83.4 km2 in the case of an increase during the growth period, while the values decreased during the period of dry to (NDVI) 122.2 km2 and (NDWI) 73.2 km2. As for (SAVI) 3016.3 km2 (NDBI) 1263.3 km2 we notice a decrease in the growth period, while the values increase during the dry period to (SAVI) 3702.3 km2 and (NDBI) 1882.2 km2
In this paper, we used four classification methods to classify objects and compareamong these methods, these are K Nearest Neighbor's (KNN), Stochastic Gradient Descentlearning (SGD), Logistic Regression Algorithm(LR), and Multi-Layer Perceptron (MLP). Weused MCOCO dataset for classification and detection the objects, these dataset image wererandomly divided into training and testing datasets at a ratio of 7:3, respectively. In randomlyselect training and testing dataset images, converted the color images to the gray level, thenenhancement these gray images using the histogram equalization method, resize (20 x 20) fordataset image. Principal component analysis (PCA) was used for feature extraction, andfinally apply four classification metho
... Show MoreThe complexity and variety of language included in policy and academic documents make the automatic classification of research papers based on the United Nations Sustainable Development Goals (SDGs) somewhat difficult. Using both pre-trained and contextual word embeddings to increase semantic understanding, this study presents a complete deep learning pipeline combining Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Network (CNN) architectures which aims primarily to improve the comprehensibility and accuracy of SDG text classification, thereby enabling more effective policy monitoring and research evaluation. Successful document representation via Global Vector (GloVe), Bidirectional Encoder Representations from Tra
... Show More
Arabic text classification is a challenging task because of the complex morphology of the language, the existence of different writing forms and a multitude of dialects, which can result in sparser common text representations. While transformer models such as AraBERT have obtained superior results on many Arabic NLP tasks, their high computational requirements make them difficult to deploy in environments with limited hardware resources. In some cases this can also make the model less practical for researchers working with basic computer systems. This study focuses on a more practical issue: how much accuracy a simple classifier may lose when the amount of required computation is reduced. We use a combined TF-IDF representation based on bo
... Show More