Due to the unreliability of wired communications and the risks of controlling the process of transmitting data besides the complications that affecting data protection and the high costs of systems infrastructure, led to use wireless communications instead of wires media, but these networks are vulnerable towards illegal attacks. The side effects of these attacks are modifying data or penetrate the security system and discover its weaknesses, which leads to great material losses. These risks and difficulties led to the reluctance of wires communications and propose intelligent techniques and robust encryption algorithms for preventing data transmitted over wireless networks to keep it safe from cyber security attacks. So, there is a persistent need for providing intelligent techniques and robust algorithms to preserve conveyed information using wireless network. This paper introduces scenario for proposing intelligent technique to increase data reliability and provides a new way to improve high level of protection besides reduces infrastructure cost. The proposed system relies on two models, where the first model based on producing a knowledge base of risk rules while the aim of the second module is a risk assessment outcomes and encryption process according to attacks type. In this system, reducing risks levels based on renewable rules whereas a novel security system established on non-periodic keys with unsystematic operations using fuzzy system. We concluded that the proposed system has the ability to protect the transmitted data, increases its reliability and reduce the potential risks. MATLAB Toolkit 2014 then Weka open source package was used in encryption and data mining for the proposed system.

The primary objective of this paper is to improve a biometric authentication and classification model using the ear as a distinct part of the face since it is unchanged with time and unaffected by facial expressions. The proposed model is a new scenario for enhancing ear recognition accuracy via modifying the AdaBoost algorithm to optimize adaptive learning. To overcome the limitation of image illumination, occlusion, and problems of image registration, the Scale-invariant feature transform technique was used to extract features. Various consecutive phases were used to improve classification accuracy. These phases are image acquisition, preprocessing, filtering, smoothing, and feature extraction. To assess the proposed system's performance. method, the classification accuracy has been compared using different types of classifiers. These classifiers are Naïve Bayesian, KNN, J48, and SVM. The range of the identification accuracy for all the processed databases using the proposed scenario is between (%93.8- %97.8). The system was executed using MATHLAB R2017, 2.10 GHz processor, and 4 GB RAM.

Malaria is a contagious disease that infects many people each year. It is diagnosed in the laboratory using an expert and thorough examination of healthy and si Malaria is a contagious disease that infects many people each year. It is diagnosed in the laboratory using an expert and thorough examination of healthy and si

In the past two decades, the rapid growth of demand for wireless data communications has become evident due to the unreliability of wired data communications, which has become inadequate due to high costs and management monitoring of its security problems. Furthermore, such data may be intercepted when transmitted via wire connections with a negative attack and its contents changed with illegal modification. Therefore, due to these circumstances, there is an urgent need to protect data and achieve a wireless local area network (WLAN) for transmission. Data protection is therefore required through the design and implementation of a rigid algorithm that reduces the risk of hacking into wireless networks and prevents hackers from finding inevitable vulnerabilities in the data protection system. This research paper introduces a new technology to protect data from potential risks and provides a new “type” of encryption algorithms that minimizes these risks. This technology relies on the adoption of renewable rules proposed as production bases based on ambiguous logic to accomplish the construction of an intelligent data analysis system and move forward with appropriate protection decisions. The targeted packets for the local area network were captured and analyzed using open source software “WIRESHARK”. Unsupervised learning classifier was used to monitor the network and detect the malicious intruders. The flow data have been collected and features are extracted and analyzed to examine the transmitted packets which were classified and ranked to have a specific cluster. Minimizing and comprising risk taking in consideration the imprecise data which was achieved via fuzzy rules. The results were discussed and concluded that potential risks could be minimized by the production rules that control the proposed data for the transferred encryption system. MATLAB 2014 toolkit based on a laptop with an Intel I3 processor and 4GB RAM was used.

Automated fingerprint recognition and authentication have been widely used in biometrics applications and as a personal identity tool due to their dependability and unique characteristics. The person's fingerprint must be authentic and not altered or forged to be used to verify that person's identity. It is more difficult to determine whether a fingerprint is real /authenticated. The presented work aims to design two models based on a convolutional neural network (CNN) with the ability to detect whether the fingerprints are authenticated or not. The proposed methodology includes two levels: the first involves forgery detection of fingerprints. Whereas the second level exam ines fingerprint identification. Furthermore, a reliable deep learning technique that includes Transfer Learning (TL) and building the architecture of CNN from scratch was utilized to diagnose and identify fingerprints for 100 persons using the SOCO dataset. Thus, the results recorded higher accuracy at 98.69% and 99.08% sensitivity of forgery detection. Furthermore, it achieved an optimal rate for matching fingerprints and outperformed other TL models (VGG16, VGG19, ResNet50) and related works. For this reason, it could be considered a successful model for Biometric fingerprint authentication and forgery detection.

Email types sorting is one of the most important tasks in current information systems with the purpose to improve the security of messages, allowing for their sorting into different types. This paper aims at studying the Convolution Neural Network and Long Short-Term Memory (CNN-LSTM), Convolution Neural Network and Gated Recurrent Unit (CNN-GRU) and Long Short-Term Memory (LSTM) deep learning models for the classification of emails into categories such as “Normal”, “Fraudulent”, “Harassment” and “Suspicious”. The architecture of each model is discussed and the results of the models’ performance by testing on labelled emails are presented. Evaluation outcomes show substantial gains in precision and throughput to conventional approaches hence inferring to the efficiency of these proposed models for automated email filtration and content evaluation. Last but not the least, the performance of the classification algorithms is evaluated with the help of parameters like Accuracy, precision, recall and F1-Score. From the experiment, the models found out that CNN-LSTM, together with the Term Frequency and Inverse Document Frequency (TF-IDF) feature extraction yielded the highest accuracy. The accuracy, precision, recall and f1-score values are 99. 348%, 99. 5%, 99. 3%, and 99. 2%, respectively.