Post graduate dissertations (Theses) of Institute of Information and Communication Technology (IICT) http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/661 2026-04-06T09:54:20Z 2026-04-06T09:54:20Z Zobair Raihan, Md. http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/7240 2026-01-21T04:53:07Z 2025-03-10T00:00:00Z

Comprehensive ensemble-based machine learning approach for DDoS detection to enhance security in software-defined network Saiful Islam, Dr. Md.; Zobair Raihan, Md.; 1017312030; 006.31/ZOB/2025 Software-Defined Networking (SDN) has emerged as a key solution for meeting the expanding demands of IT and online computing services. Its ability to offer flexible network management and cost-efficient operations has made it a preferred choice for businesses across various industries. However, SDN environments are highly susceptible to security threats, particularly Distributed Denial of Service (DDoS) attacks, which can severely impact network performance and economic stability. Addressing these security concerns is crucial to ensuring the reliability and resilience of SDN-based infrastructures. This research proposes an effective solution to detect DDoS attacks using ensemble-based machine learning. Ensemble models excel at analyzing network traffic, identifying hidden patterns, and distinguishing between benign and malicious packets. This capability helps prevent unnecessary costs incurred by users due to DDoS attacks. However, the use of black-box machine learning models in DDoS detection raises concerns about false positives (legitimate packet rejection) and false negatives (malicious packet acceptance). To address this issue, explainable AI techniques SHAP and LIME have been employed to enhance model interpretability, providing insights into the decision-making process. The CIC-DDoS-2019 dataset was utilized for model development and evaluation. Results demonstrate that the ensemble-based model outperforms non-ensemble models on the dataset. With an outstanding accuracy of 0.9999 for binary classification and 0.9627 for multi-class classification, the XGB model outperformed the others in both tests. The model's choices were interpreted using SHAP analysis, which highlighted the most significant aspects. Top contributing features in the multi-class scenario were 'Min Packet Length,' 'Fwd Packet Length Min,' 'Flow Bytes/s,' and 'Inbound.' 'Packet Length Std,' 'Destination Port,' 'Bwd Packet Length Max,' 'Bwd Packet Length Mean,' and 'Fwd PSH Flags' turned out to be the most important feature influencing the model's predictions for binary classification. Additionally, SHAP and LIME were used to explain individual model predictions, ensuring transparency in the decision-making process. This research highlights the effectiveness of ensemble-based models in DDoS detection and the importance of explainable AI in improving trust and reliability in cybersecurity applications.

2025-03-10T00:00:00Z Abeedur Rahman Khan http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/7213 2025-12-08T03:58:50Z 2025-01-14T00:00:00Z

Efficient and cost effective IOT-based watering system for home gardening Jarez Miah, Dr. Md.; Abeedur Rahman Khan; 0419311032; 004.21/ABE/2025 Urban home gardening has gained significant popularity in Bangladesh, driven by the increasing demand for fresh produce and the convenience of growing plants in residential spaces. Efficient watering is pivotal to urban gardening, particularly for indoor plants. This research focuses on the development of a cost-effective, automated watering system to address watering challenges, and aims to provide a sustainable and smart solution to improve plant growth and support the growing trend of home gardening in urban areas. The system utilizes a microcontroller, soil moisture sensors, and water level sensors to monitor and maintain optimal soil moisture levels. A water pump connected to a storage tank is controlled based on real-time data from the sensors, ensuring precise and timely watering. The integration of the Blynk IoT platform enables remote monitoring and control via a smartphone or computer, combining both convenience and accessibility for users. The system's architecture is designed to be scalable, highly adaptable, energy-efficient, and user-friendly. By incorporating affordable components such as soil moisture sensors and printed circuit boards, the project demonstrates significant cost savings yet is more efficient compared to traditional irrigation systems. The intelligent automation minimizes water wastage, prevents overflow, and ensures consistent hydration for plants, making it an ideal solution for indoor gardening. This report presents the design, implementation, and evaluation of the proposed system, highlighting its effectiveness in automating irrigation, its cost efficiency, and its potential to enhance urban gardening practices in Bangladesh. Beyond its application in individual homes, the project opens avenues for commercial use and integration into larger urban agricultural initiatives. Its scalability and modular design make it suitable for indoor plantation and community gardening projects. By addressing the unique challenges of water management in urban environments, the proposed system contributes to sustainable practices and promotes environmentally responsible urban living.

2025-01-14T00:00:00Z Ibadul Islam, Md. http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/7201 2025-12-02T07:00:15Z 2025-02-01T00:00:00Z

Design and characterization of highly negative dispersion compensating photonic crystal fiber Saiful Islam, Dr. Md.; Ibadul Islam, Md.; 1017312011; 623.6/IBA/2025 Photonic Crystal Fiber (PCF) has emerged as a revolutionary advancement in optical fiber technology, offering superior optical properties for highspeed, long-haul communication systems. The increasing demand for highspeed and long-distance optical communication necessitates effective management of different fiber impairments like dispersion, attenuation, nonlinearity, and confinement loss to mitigate signal degradation. Among these impairments, dispersion is one of the major limitations that limits the fiber efficiency including distance and bandwidth. This research focuses on the design and characterization of a highly negative dispersion compensating PCF to address chromatic dispersion issues in optical fiber communication. Besides, increased signal power causes significant system performance degradation due to nonlinear fiber effects, such as inelastic scattering and intensity dependent refractive index changes. Dispersion management is an effective technique for mitigating these nonlinear impairments, optimizing parameters like net residual dispersion (NRD) In this study, a novel PCF is proposed for dispersion compensation. The guiding characteristics of the proposed fiber are analyzed using the finite element method (FEM) with a perfectly matched layer boundary condition. The optical properties of the PCF, including chromatic dispersion, group velocity dispersion (GVD), nonlinearity, and third order dispersion (TOD), are examined over a wavelength range of 1340 nm to 1640 nm. Simulation results indicate that at an operational wavelength of 1550 nm, the proposed PCF exhibits a high negative dispersion of −2367.10 ps/(nm.km), a GVD of 3018.55 ps2/km, a third order dispersion of −574.23 ps3/km, a very low confinement loss of 0.20 dB/km and a nonlinear coefficient of 91.11 W-1km-1. The proposed PCF effectively compensates for the dispersion of standard single-mode fibers (SMFs), making it a strong candidate for long-distance, high-bit-rate optical communication applications. The study also evaluates the network implementation of the proposed dispersion compensating fiber in a long-distance optical transmission system. Performance metrics, including bit error rate (BER) and quality factor, are analyzed to demonstrate the effectiveness of the PCF based dispersion compensation strategy. The findings suggest that the proposed PCF significantly improves signal integrity by reducing pulse broadening and nonlinear impairments. Overall, the proposed design offers a promising solution for broadband dispersion compensation in wavelength division multiplexing (WDM) and dense WDM (DWDM) optical networks. The optimized PCF structure enhances transmission efficiency, and ensures robust signal propagation over extended distances. Future research will focus on experimental validation and further optimization of the proposed structure for real world optical network deployments.

2025-02-01T00:00:00Z Riad Hassan, Md. http://lib.buet.ac.bd;localhosthttp://:8080/xmlui/handle/123456789/7167 2025-08-26T07:00:59Z 2024-11-30T00:00:00Z

Novel uncertainty driven boundary refined convolution neural network for uneven medical image segmentation Mondal, Dr. Md. Rubaiyat Hossain; Riad Hassan, Md.; 0422312020; 006.32/RIA/2024 Organ segmentation has become a fundamental challenge for computer-aided intervention, diagnosis, radiation therapy, and critical robotic surgery. Automatic organ segmentation from medical images is easy for large organs with regular shape. However, it becomes challenging task due to the inconsistent shape and size of different organs. Additionally, low contrast at the organ borders, resulting from analogous tissue types, impairs the network’s capacity to accurately delineate organ contours. In this thesis, we propose an end-to-end uncertainty-driven boundary-refined segmentation network (UDBRNet) for segmenting organs from computed tomography (CT) images. This network consists of three modules. Firstly, an encoder-decoder based segmentation module generates a main and two auxiliary segmentation masks using multi-line decoders, and then, uncertainty is assessed using variations in the levels of agreement and disagreement among the masks in uncertainty determination module. Finally, both the main segmentation mask and the uncertainty information are sent to a boundary refinement module, which refines organs’ boundary residuals. The uncertainty information helps the UDBRNet’s boundary refinement module to improve the low contrast and inconsistently shaped organs’ edge refinement. Our proposed segmentation network demonstrates remarkable performance, with dice accuracies of 0.80, 0.95, 0.92, and 0.94 for Esophagus, Heart, Trachea, and Aorta respectively on the SegThor dataset. It also consistently shows superior performance, with dice accuracies of 0.71, 0.89, 0.85, 0.97, and 0.97 for Esophagus, Spinal Cord, Heart, Left-Lung, and Right-Lung respectively on the LCTSC dataset. We compare the UDBRNet performance with popular eight existing state-of-the-art segmentation methods: UNet, attentionUNet, BASNet, FC-denseNet, R2UNet, UNet++, TransUNet, and DS-TransUNet using two publicly available datasets, SegTHor and LCTSC. Results show that UDBRNet outperforms those existing methods. UDBRNet presents a promising network for more precise organ segmentation, particularly in challenging, uncertain conditions.

2024-11-30T00:00:00Z