In this article, Convolution Neural Network (CNN) is used to detect damage and no damage images form satellite imagery using different classifiers. These classifiers are well-known models that are used with CNN to detect and classify images using a specific dataset. The dataset used belongs to the Huston hurricane that caused several damages in the nearby areas. In addition, a transfer learning property is used to store the knowledge (weights) and reuse it in the next task. Moreover, each applied classifier is used to detect the images from the dataset after it is split into training, testing and validation. Keras library is used to apply the CNN algorithm with each selected classifier to detect the images. Furthermore, the performa

Correct grading of apple slices can help ensure quality and improve the marketability of the final product, which can impact the overall development of the apple slice industry post-harvest. The study intends to employ the convolutional neural network (CNN) architectures of ResNet-18 and DenseNet-201 and classical machine learning (ML) classifiers such as Wide Neural Networks (WNN), Naïve Bayes (NB), and two kernels of support vector machines (SVM) to classify apple slices into different hardness classes based on their RGB values. Our research data showed that the DenseNet-201 features classified by the SVM-Cubic kernel had the highest accuracy and lowest standard deviation (SD) among all the methods we tested, at 89.51 %  1.66 %. This

Intrusion detection system is an imperative role in increasing security and decreasing the harm of the computer security system and information system when using of network. It observes different events in a network or system to decide occurring an intrusion or not and it is used to make strategic decision, security purposes and analyzing directions. This paper describes host based intrusion detection system architecture for DDoS attack, which intelligently detects the intrusion periodically and dynamically by evaluating the intruder group respective to the present node with its neighbors. We analyze a dependable dataset named CICIDS 2017 that contains benign and DDoS attack network flows, which meets certifiable criteria and is ope

This paper proposes a new approach, of Clustering Ultrasound images using the Hybrid Filter (CUHF) to determine the gender of the fetus in the early stages. The possible advantage of CUHF, a better result can be achieved when fuzzy c-mean FCM returns incorrect clusters. The proposed approach is conducted in two steps. Firstly, a preprocessing step to decrease the noise presented in ultrasound images by applying the filters: Local Binary Pattern (LBP), median, median and discrete wavelet (DWT),(median, DWT & LBP) and (median & Laplacian) ML. Secondly, implementing Fuzzy C-Mean (FCM) for clustering the resulted images from the first step. Amongst those filters, Median & Laplace has recorded a better accuracy. Our experimental evaluation on re

Disease diagnosis with computer-aided methods has been extensively studied and applied in diagnosing and monitoring of several chronic diseases. Early detection and risk assessment of breast diseases based on clinical data is helpful for doctors to make early diagnosis and monitor the disease progression. The purpose of this study is to exploit the Convolutional Neural Network (CNN) in discriminating breast MRI scans into pathological and healthy. In this study, a fully automated and efficient deep features extraction algorithm that exploits the spatial information obtained from both T2W-TSE and STIR MRI sequences to discriminate between pathological and healthy breast MRI scans. The breast MRI scans are preprocessed prior to the feature

A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an