Al-Razi University Journal of Computer Science and Technology

Artificial Intelligence for Analyzing Decadal Land Changes in Sana’s- Yemen From 1980 to 2020 Using Remote Sensing & GIS

2024-07-28T12:06:39+00:00

Managing natural resources has become crucial due to rapid population growth, weather changes, and disasters. LULC maps are essential for planning and managing resources, but developing countries such as Yemen lack such studies and sufficient interest in this field. The problem of this study is to find solutions in studying the management of natural resources that lead to making appropriate decisions for the advancement of the economic situation and the management of agricultural, industrial, and population lands. The objectives of this research are: 1. To determine land changes in Sana'a city from 1980 to 2020. 2. To create a database for Land Use & Land Cover (LULC) classification of Sana'a city from 1980 to 2020. It has used remote sensing and GIS technology with Landsat images from 1980,1990,2000, 2010, and 2020 with the best classifier from the machine learning technique object-based classifier as Random Forest (RF) algorithm, affiliated to technologies Artificial intelligence (AI) technique. The research determined the changes in land in Sana'a over these decades. The findings demonstrated that in Sana'a before 2010, urban area density increased, and in 2010, it decreased. Sana'a's urban area density increased in 2020. The built-up area changed, with percentages of 12.17% in 1980, 34.24 in 1990, 40.15% in 2000, 30.94% in 2010, and 44.74% in 2020. The average classification accuracy was 99.88%. Recommendations for sustainable urban growth in Sana'a include enforcing policies to protect agricultural lands, promoting eco-friendly practices, studying socio-economic factors of urban expansion, training local planners, and educating the public on sustainable land use. This research recommends that the following studies find solutions for better resource management to enhance economic conditions and manage lands effectively.

PPIPAE: Protecting Personal Information from Phishing Attacks in E-commerce: Review paper

2024-07-28T12:06:39+00:00

After the widespread spread of the Internet, which now covers all parts of the world, and with the emergence of electronic commerce, most people prefer to buy and sell their products on the Internet. All commercial and banking transactions have shifted from the traditional method to the digital method, making electronic phishing crimes a center of attraction for attackers and violating privacy in the digital space. Phishing is one of the methods used by attackers to obtain personal information by deceiving users by using fake websites similar to legitimate websites or through fake URLs and transferring the user to a scammers’ website for various purposes such as obtaining sensitive personal data or bank accounts and passwords. There are many types of phishing but in this scientific paper, we only aim to review the most important techniques used to detect phishing attacks, whether by forging web pages and URLs or through deceptive emails Which is the main points of the discussion of this paper. We also discuss the most important deception methods used by fraudsters on people.

Keywords: E-Commerce, URLs, Phishing attacks, Fake web pages, Spam messages.

Early Diagnosis of Multiclass Skin Lesions Using Hybrid Models Based on Fused Features

2024-07-28T12:06:39+00:00

Skin lesions (SL) are among the most serious types of skin diseases. Melanoma is considered a serious type of skin lesion. The incidence of melanoma increases annually, which poses a health risk. Life threatening. Dermoscopy is one of the best techniques that reveals invisible internal structures and helps detect types of SL. The SL are similar in the early stages, which poses a challenge to distinguish between them by manual diagnosis. Therefore, artificial intelligence (AI) techniques address deficiencies through manual diagnosis. In this study, two strategies were developed to analyze dermoscopic images for early diagnosis of SL. The images were optimized for ISIC 2018 and the Active Contour Algorithm (ACA) was applied to extract regions of interest (ROI) and isolate them from healthy areas. The ROI was fed to two strategies separately. The first strategy received the ROI and was fed to the Gray-Level Co-occurrence Matrix (GLCM), Local Binary Patterns (LBP) and Fuzzy Color Histogram (FCH) algorithms to extract features. They were combined into feature vectors. The fused features were fed to the Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers to classify them with high accuracy. The second strategy received the ROI and fed it to the ResNet18 model to extract the deep features and classify them with great efficiency using ANN and SVM. ANN-ResNet18 achieved promising results, reaching an AUC of 84.73%, sensitivity of 87.74%, accuracy of 93.8%, precision of 82.9%, and specificity of 98.47%.

SURVEY: SECURING IPV6 NEIGHBOR DISCOVERY PROTOCOL

2024-07-28T12:06:39+00:00

: IPv6 Neighbor Discovery Protocol (NDP) is essential to facilitate communication between local network nodes. However, NDP is vulnerable to various attacks that can disrupt network communication and facilitate malicious activities. This study attempts to identify the major security vulnerabilities to NDP and assess available methods to improve its security. We conducted a systematic literature review to analyze the benefits and limitations of mechanisms such as Cryptographically Generated Addresses (CGA), Secure Neighbor Discovery (SEND), and Attestation-based Neighbor Discovery. Our findings show that these mechanisms significantly reduce the impact of Neighbor Discovery attacks. We recommend an attack detection mechanism to address spoofing of Neighbor Solicitation (NS) and Neighbor Advertisement (NA) messages to improve NDP security in IPv6 networks. These insights can help network administrators and protocol designers implement effective defenses against NDP attacks, thereby enhancing the stability and security of IPv6 deployments. Our research contributes to ongoing efforts to improve IPv6 network reliability by investigating the protocol's structure, the role of ICMPv6, associated security concerns, and potential security solutions.

Survey of Cross-Layering Technique in Wireless Sensor Networks (WSNs)

2024-07-28T12:06:39+00:00

Wireless Sensor Networks (WSNs) have gained significant attention in recent years due to their vast applications in various fields such as environmental monitoring, healthcare, and industrial automation. However, WSNs face several challenges, including energy efficiency, latency, and reliability. Trade-off issues persist in the study results even after a great deal of research, approaches, and studies have been conducted in the subject of enhancing the quality of service in wireless sensor networks. In WSNs, cross-layer technology proved effective in meeting the demands of applications while also meeting quality of service standards. Cross-layer design has emerged as a promising approach to address these challenges by integrating and optimizing different layers of the OSI model. This survey provides a comprehensive overview of cross-layer design in WSNs, highlighting recent advancements, challenges, and future directions.