http://ir.bdu.edu.et/handle/123456789/10166 Sat, 13 Jan 2001 06:31:53 GMT 2001-01-13T06:31:53Z http://ir.bdu.edu.et/handle/123456789/16332 SECURE AD-HOC ON-DEMAND DISTANCE VECTOR( AODV) ROUTING PROTOCOL TO PREVENT BLACKHOLE ATTACK IN MOBILE AD-HOC NETWORK ( MANET) ZEMENU, ALEM In the modern communication world, a network can be built on the fly using mobile nodes with networking capability. Such a network without any pre-existing support for communication is referred to as a Mobile Ad Hoc Network (MANET). It can be deployed in essential areas such as military and civilian environments and disaster management circumstances because of its ad hoc nature. However, with their flexibility and utility, MANETs are inherently vulnerable to a range of attacks due to their decentralized nature and lack of central oversight. Among these threats, black-hole attacks, where malicious nodes absorb and discard data packets, pose a significant risk to network reliability and security. Existing solutions for blackhole attack prevention and detection in MANETs often rely on techniques that require the cooperation of malicious nodes, such as monitoring the sequence number difference in RREP messages. However, the behavior of blackhole nodes is generally more unpredictable. Additionally, the reliance solely on sequence number differences makes the detection mechanism ineffective in identifying blackhole nodes that send legitimate-looking RREP messages. These limitations reduce the effectiveness of the proposed solutions in MANETs, where black hole nodes can use more sophisticated tactics to evade detection. This thesis addresses this critical issue by proposing an enhancement to the AODV routing protocol, utilizing the security features of the ECDSA to counter black-hole attacks. ECDSA is chosen for its robust security features and efficiency, providing strong authentication and data integrity with relatively smaller key sizes compared to other cryptographic algorithms. The integration of ECDSA into the AODV protocol ensures that only legitimate nodes, verified through digital signatures, can participate in the network. Comprehensive simulations conducted using NS-3.30 that the ECDSA-enhanced AODV protocol outperforms existing security-AODV protocols. Key performance metrics, including average throughput, PDR, E2ED, and normalized routing overhead. These enhancements validate the proposed solution's efficacy in ensuring secure and efficient routing operations within MANETs. The thesis thus presents a holistic approach to addressing critical security challenges, emphasizing authentication, authorization, confidentiality, integrity, and non-repudiation, ultimately proving the superiority of the ECDSA-enhanced AODV protocol. Keywords: Mobile Ad Hoc Network, Ad hoc On-Demand Distance Vector, Elliptic Curve Digital Signature Algorithm Sat, 27 Jul 2024 00:00:00 GMT http://ir.bdu.edu.et/handle/123456789/16332 2024-07-27T00:00:00Z http://ir.bdu.edu.et/handle/123456789/16331 REAL TIME PATH PLANNING OF UNMANNED AERIAL VEHICLE BASED ON TANGENT INTERSECTION AND TARGET GUIDANCE IN THE PRESENCE OF MOVING OBSTACLE Yosef, Jemal Path planning for unmanned aerial vehicles (UAVs) helps UAVs to efficiently avoid obstacles and arrive at their target. This article proposes a real-time path planning method based on a tangent intersection and target guidance strategy in the presence of moving obstacles to generate high-quality paths free from obstacle collision for UAVs. The elliptic tangent graph approach is used to construct two sub-paths while being guided by a target. When coming across an obstacle, one of the sub-paths is chosen using heuristic methods. The UAV follows the chosen sub-path and continuously modifies its course to avoid obstacles until the collision-free path reaches the target. This algorithm determines the UAV's escape velocity during the obstacle avoidance period using the relative velocity of the obstacle in real time. This makes it possible for the UAV to recognise and avoid any obstacles whether they are static or moving, in real time. Compared with previously developed “autonomous path planning based on tangent intersection and target guidance” algorithm, RPPATTM algorithm not only plans path for dynamic popup obstacles but also for an environment having moving obstacles. Specifically this algorithm takes less than 0.1 milliseconds to plan optimal path in dense obstacles of 100 meter by 100 meter in an obstacle of different size. Moreover RPPATTM algorithm can identify and avoid obstacles of any shape and size easily during path planning. Keyword – Elliptic tangent graph, target guidance, UAV, path planning, moving obstacle avoidance. Tue, 20 Jun 2023 00:00:00 GMT http://ir.bdu.edu.et/handle/123456789/16331 2023-06-20T00:00:00Z http://ir.bdu.edu.et/handle/123456789/16330 Tekele Zemamie Action Recognition in Ethiopia Orthodox Church Using Deep-Learning Approach Tenagne, Fikirie Atalel Human action recognition is a computer vision technique used to understand the activity of the action performed in the scene. Today, computer vision technology has become popular and is applied in various areas like surveillance systems, robot vision, satellite imaging, and others. However, using computer vision in human activity recognition is still challenging due to the dynamic movement of human motion, noise, occlusion, complex background, variable dressing style, varying illumination, and others. To overcome this and other problems, various research has been conducted, but it is still a challenging issue. In this study, we applied human action recognition techniques to interpret the meaning of Tekele Zemamie's actions in the Ethiopian Orthodox Church. Tekele Zemamie is the most frequent action held by the church choirs in the church stage ceremonies and others. To carry out the research experimental work we have prepared 900 video clip datasets. The dataset was recorded in a 2.5-meter distance using a 48MP Camera. We recorded the data at Abune Gebere Menfes Kidus church Bahir Dar Ethiopia in six action class categories. From the dataset, 80% was used for training and the remaining 20% was used to test the performance of the model. We have used skip frame selection techniques in a single video and 30 frames are selected in each video. We applied spatial, temporal, and skeleton pose feature extraction techniques. To overcome the stated problems and to develop Tekele Zemamie recognition model experimental works have been examined using BlazePose_Bi-LSTM, BlazePose_LSTM, BlazePose_SoftMax, CNN_LSTM, and CNN_Bi-LSTM deep-learning models, and we achieved 84%, 76%, 67%, 95%, and 97% recognition accuracy respectively. From the proposed models, CNN_Bi-LSTM works better than the other models. Keywords: CNN, Bi-LSTM, HPE, SKE, HAR Mon, 01 Jan 2024 00:00:00 GMT http://ir.bdu.edu.et/handle/123456789/16330 2024-01-01T00:00:00Z http://ir.bdu.edu.et/handle/123456789/16329 Performance Improvement for Verification and Identification of Automatic Fingerprint Biometrics Genet, Amde Fingerprint recognition remains crucial in modern security systems; however, challenges persist with low-quality and varied fingerprint images. This study addresses these issues by proposing an Ensemble Convolutional Neural Network-Support Vector Machine (CNN-SVM) model to enhance fingerprint recognition accuracy. Our study investigates the performance of fingerprint recognition models, focusing on preprocessing techniques and ensemble methods to mitigate these challenges. We conducted six experiments to evaluate CNN, SVM, and their ensemble combinations, both with and without preprocessing. Preprocessing steps included data augmentation, normalization, and dimensionality reduction. These experiments were performed using benchmark datasets such as the Sokoto Coventry Fingerprint Dataset (SOCOFing), leveraging a Python programming environment and Google Colab for simulation and analysis. The results demonstrate that the ensemble CNN-SVM model with preprocessing outperforms other configurations, achieving the highest accuracy of 99.73%, precision of 99.79%, recall of 99.73%, and F1 score of 99.74%. This underscores the significant impact of preprocessing and the effectiveness of the ensemble approach in fingerprint recognition tasks. The findings suggest that integrating CNN and SVM models with comprehensive preprocessing steps offers a superior method for addressing fingerprint recognition challenges, contributing to advancements in biometric security systems. Keywords: Fingerprint Recognition, Ensemble CNN-SVM, Data Augmentation, Normalization, Dimensionality Reduction. Thu, 01 Aug 2024 00:00:00 GMT http://ir.bdu.edu.et/handle/123456789/16329 2024-08-01T00:00:00Z