Recent years have witnessed a great development in the use of deep learning in the applied fields in general, including the improvement of remote sensing. Satellite imagery classification has played a prominent role in various development processes. This paper presents a new improvement in automatic urban classification using One Dimension Convolutional Neural Network (1DCNN) architecture. The suggested approach has three enhancement processes. First, select training boxes for different classes and create many pixels with variable class signatures. This makes the training process dependent on the broadband of signature for the classes. Second, modified 1D convolution was used to re-encode pixel values to increase distinguish power. Third, adding a new median filter layer at the end of network architecture to remove pixels like noise to make the resulting map smoother. An image of Greater Cairo is used and the different urban classes are defined within it. The proposed method was compared to other methods based on pixels. The proposed method proved to be numerically and visually superior. International Journal of Intelligent Computing and Information Sciences https://ijicis.journals.ekb.eg/ 2 N. Laban et al.

The weather phenomenon is very important in routine lives. The weather prediction, road electronic monitoring, traffic communication, capping inversion (CAP), afforestation, and the adjustment of the environmental issues are important factors to many decisions. Weather images classification may help in decision support systems. There are traditional and intelligent ways that can sufficiently achieve weather image classification. Traditional methods enhance the classification accuracy and the usability of weather phenomena. Researchers approve that machine learning has achieved better accuracies based on deep learning neural networks. This paper compares three different intelligent models by using a weather image dataset. The first model uses a convolution neural network (CNN) to classify five categories of weather images. The second model uses a fusion of convolution neural network and Decision Tree (DT). The third one uses a fusion of CNN and Support Vector Machine (SVM). The three models are applied to the collected dataset from Github and Kaggle. The study has achieved 92%, 93%, and 94% for CNN, CNN+DT, and CNN+SVM respectively. The Proposed methods have achieved high recognition accuracies for weather forecasting.

Data security is one of the most important sciences nowadays. There is a huge amount of data transferred over the internet each moment and this data should be secured. Steganography is a type data security techniques that is used to hide the secret message into a cover object. Image steganography is the technique that hides an image in another image. This paper proposed a technique that depends on Lower-Upper (LU) decomposition. In the proposed technique LU decomposition is applied for both cover and secret images. The proposed method was tested using some gray and color images. The proposed technique achieved high results with reference to Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Normalized Cross-Correlation (NCC). The PSNR for the cover image is ranging from 36 to 44 dB. The similarity between the secret image and the extracted image is 100% and the NCC is 1.

In recent time, the most applied classification method for hyperspectral images is based on the supervised deep learning approach. The hyperspectral images require special handling while it consists of hundreds of bands / channels. In this article, the experiments are conducted using one of the widespread deep learning models, Convolutional Neural Networks (CNNs), specifically, Csutom Spectral CNN architecture (CSCNN). The introduced network is based on the data reduction and data normalization. It firstly ommits the unnecessary data channels and retains the meaningful ones. Then, it passes the remaining data through the CNN layers (convolutional, rectified linear unit, fully connected, dropout,…etc) until reaches the classification layer. The experiments are applied on four benchmarcks [hyperspectral datasets], namely, Salinas-A, Kenndy Space Center (KSC), Indian Pines (IP), and Pavia University (Pavia-U). The proposed model achieved an overall accuracy more than 99.50 %. In last, a comparison versus the state of the art is also introduced.