Dissertations/Theses - Institute of Information and Communication Technology
Browse
232 results
Search Results
Item An automated walking guide to assist way-finding and situation awareness for the visually impaired(Institute of Information and Communication Technology (IICT), BUET, 2024-10-19) Sheezanul Hassan; Liakot Ali, Dr. Md.Safe and independent mobility is one of the major daily challenges faced by the visually impaired. To navigate a new area safely, they need to know the location of obstacles and other things in their path. They struggle with object detection and obstacle avoidance, making it challenging to navigate new or unfamiliar situations and be aware of obstacles and their relative positions. However, establishing secure and safe mobility and pathfinding for the visually impaired is a critical issue in their life that must be solved accurately and efficiently. Recognizing currency is another severe problem for them because different notes in our country have similar colors, surfaces and sizes causing major problems for the visually impaired. Object recognition alone may not be sufficient to assist visually impaired individuals effectively. Incorporating lateral position identification can provide users with a sense of spatial orientation within their environment, enabling them to navigate paths toward recognized objects more accurately. In this thesis, a system is proposed to assist visually impaired individuals by identifying both navigation objects and their corresponding lateral positions, and recognizing Bangladeshi currency. This system aims to serve as a comprehensive walking guide, offering benefits for both indoor and outdoor navigation. By enhancing spatial awareness and providing critical information about their surroundings, this system will enable visually impaired users to make informed decisions regarding their movements and actions; thereby, improving their independence and quality of life. The system utilizes EfficientNet, a Convolutional Neural Network architecture for Machine Learning to design a model for currency and navigation objects that can recognize fifteen classes of objects for assisting the visually impaired. The architecture also applies computational logic to the model to identify lateral positions of the navigation objects; and thus conceptualizing a system that can act as a walking guide for visually impaired people aiding navigation and awareness. The model proposed in the system has been evaluated with real-world objects to assess the performance of the proposed method. The experimental analysis demonstrates that the system achieves notable Accuracy, Precision, Recall, and F1 scores, highlighting its prospective relevance and effectiveness in the field.Item Generation of novel mashup data and detection of categorical web attacks(Department of IICT, BUET, 2025-02-19) Shakil Ahammad; Asiful Mustafa, Dr. HossenInformation security is a dynamic combination of technology between what we have and whatever we can. The study of information security is all about data because of the polymorphic nature of cyber-attacking signatures. Utilizing critical data, such as at- tacking signatures, is a primitive component of designing green cyberspace. Designing sustainable cyberspace by planning different critical systems utilizing machine learn- ing and Red Teaming concepts is important to protecting digital assets in the globally connected world. A heterogeneous source of IOC data can be an excellent source for designing a minified version of SIEM, and this research has made a paradigm about m-SEIM components. To design this m-SEIM, a few premium enterprise Dynamic Application Security Testing (DAST) tools, like Acunetix-360, Qualys WAS module, Burpsuite Enterprise edition, Nessus, etc, have been used to collect web-attack signa- tures. These tools are considered a great source of attacks in the cyber security in- dustry. As a plan for the cost-effective cyberspace design concept, this work describes how the data of the attacking side can be re-engineered using machine learning tech- niques. From these, heterogeneous sources of attacking signatures are considered Novel Mashup Data (NMD). As part of the optimistic model-finding approach of this research on the novel mashup cyber-attacking data, the success ratio of the attacking and be- nign data is 99.67% on CNN. In comparison, the Lagrangian Support Vector Machine (LSVM), Logistic Regression, and Recurrent Neural Network (RNN) models success ratio has been observed respectively 99.63%, 99.38% and 99.37%. In this work, four types of web attacks, e.g., Path-Traversal, OS Commanding, SQLi, and XSS, are con- sidered to be detected through machine learning. A supervised machine learning model Convolutional Neural Network (CNN) has been trained, and the success ratio has been observed at 98.55% on the collected data. However, the collected data is not equally sampled due to the limitation of the cyber-attacking signatures. The trained model is deployed with the web server to calculate the run-time threats of the operand message. Open-source Kali Linux tools are utilized to check the model’s performance for data poisoning attack detection and classification purposes. In this phase of the performance measures, we have observed the success of Path Traversal, OS Commanding, SQLi, and XSS attack classification success, respectively 91.78%, 53.52%, 95.2%, and 89.18%.Item An efficient CNN-based regression model for noise prediction in color images(Institute of Information and Communication Technology (IICT), BUET, 2025-04-07) Nasima Islam Bithi; Miah, Dr. Md JarezThe presence of noise in digital images remains a critical barrier to high-fidelity visual representation, compromising both perceptual quality and the accuracy of downstream image analysis. Among various noise types, Gaussian and Poisson noise stemming from electronic sensor imperfections and photon-counting variability, respectively pose significant challenges. Accurate estimation of these noise levels is essential for improving computer vision tasks such as denoising, super-resolution, segmentation, and object detection. However, existing approaches often struggle under high-noise conditions, mixed-noise scenarios, and color image contexts. To address these limitations, we introduce two deep regression models: NoiseNet and NoiseNetV2, designed with noise-specific feature extraction and attention mechanisms to enhance performance across diverse noise types and datasets. Evaluated on datasets including Flickr30k, COCO, CelebA, and DIV2K, the proposed NoiseNet model achieved state-of-the-art results. For Gaussian noise, it recorded the Mean Absolute Error (MAE) of 0.0038, a Root Mean Squared Error (RMSE) of 0.0052, and an R² score of 0.9910, outperforming the best-performing baseline DenseNet121 by margins of ~2.7× lower MAE, ~2.5× lower RMSE, and ~1.05× higher R² score. For Poisson noise, NoiseNet achieved an MAE of 0.0547, RMSE of 0.0763, and R² of 0.9922, representing improvements of ~ 4× lower MAE, ~3.7× lower RMSE, and ~1.1× higher R² score compared to the best-performing baseline ResNet50. The model also outperformed classical techniques like BM3D and Scikit-learn in both low- and high-noise scenarios. Furthermore, NoiseNetV2, an enhanced variant incorporating an attention mechanism, delivered even stronger results under mixed noise conditions. For Gaussian noise, it reached an MAE of 0.0078, R² of 0.9682, and RMSE of 0.0103; for Poisson noise, it obtained an MAE of 0.2759, R² of 0.8106, and RMSE of 0.3763, outperforming both NoiseNet and all other baseline models for mixed noise. These findings confirm the proposed models’ strong generalization and practical utility in fields such as medical imaging, autonomous driving, remote sensing, and surveillance, enabling precise noise estimation for advanced image restoration and real-time vision systems.Item Comprehensive ensemble-based machine learning approach for DDoS detection to enhance security in software-defined network(Institute of Information and Communication Technology (IICT), BUET, 2025-03-10) Zobair Raihan, Md.; Saiful Islam, Dr. Md.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.Item Efficient and cost effective IOT-based watering system for home gardening(Institute of Information and Communication Technology (IICT), BUET, 2025-01-14) Abeedur Rahman Khan; Jarez Miah, Dr. Md.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.Item Design and characterization of highly negative dispersion compensating photonic crystal fiber(Institute of Information and Communication Technology (IICT), BUET, 2025-02-01) Ibadul Islam, Md.; Saiful Islam, Dr. Md.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.Item Novel uncertainty driven boundary refined convolution neural network for uneven medical image segmentation(Institute of Information and Communication Technology (IICT), BUET, 2024-11-30) Riad Hassan, Md.; Mondal, Dr. Md. Rubaiyat HossainOrgan 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.Item Development of multiple server monitoring and administration system(Institute of Information and Communication Technology (IICT), BUET, 2019-12-14) Arshad Ali, Md.; Ali, Dr. Md. LiakotIn this era of Information and Communication Technology (ICT), Data centre is a part and parcel of any IT driven business and entrepreneurship. There needs to maintain a number of servers and networks for twenty four hours to keep the business alive and for smooth operation and better customer services. So administration and monitoring all those servers and devices are very important. Server is basically a blend of hardware and software. It has lots of data and information stored in it. There can be additional services which are not limited to hosting services, messaging, contact, chat services, etc. Usually all these services needs to keep always running which are very vital to administer and monitor. Efficient monitoring and administration service can facilitate and accelerate cloud based servers, or physical server’s performance, which is deadly need for any Business. This project presents the development of very effective and time-appropriate server monitoring and Administration software application. System architecture, dataflow diagram, use case diagram, ERD diagram and flowchart of the operation of the software are presented in the report. Front end of this application has been developed using Microsoft dot net tools and back end is by oracle database. Servers that needs to be monitored and administered need to be registered with the system. The system is capable of pulling data from the registered servers having different variations and versions of OS. The concerned person having access to the system can view all the necessary parameters in a single page using the dash-board feature of the system. The system is able to alter the system admin if any parameter crosses the thresh hold value. He will be notified by SMS as well as email and can take immediate action if it is needed. The software application is scalable, secured and very helpful for the system admin working a datacenter.Item Image-based deep learning architecture for indoor fire and smoke detection(2024-12-07) Sozol, Md. Shafak Shahriar; Mondal, Dr. Md. Rubaiyat HossainFire incidents are becoming more frequent in both indoor and outdoor settings. To ensure the safety and security of indoor property, it is essential to have an effective fire detection method. Traditional detection techniques often depend on smoke, heat, or fire sensors. Deep learning models have outperformed traditional color features-based fire and smoke detectors by reducing false alarm rates and extending the detection range. Most deep learning models approach fire and smoke recognition as a classification task and neglect the region proposals. Deep learning-based object detectors have superseded them by incorporating these proposals and providing significant accuracy as well as lower false positive rates. However, existing object detectors fall short of improved accuracy in indoor settings and real-time detection, considering fire and smoke dynamics. This study aims to overcome these challenges by developing FireNet-D5 model for effective fire and smoke detection in indoor settings. The FireNet-D5 model integrates a Squeeze and Excitation (SE) attention module at the backbone and a multi-feature fusion BiFPN module at the neck and adds color filtering with NMS to the pre-processing stage. Later, the model was optimized by a genetic algorithm to determine the optimal hyperparameter settings. To cover all prospective indoor scenarios, a novel medium-scale indoor fire and smoke (ISFire) dataset is developed. It consists of four classes (i.e., Blue Fire, Black Smoke, Yellow-Orange Fire, and White-Gray Smoke), with manual annotation. There are 7,322 images in the dataset. An explainable AI method, Grad-CAM, is used to provide visual explanations of model predictions, ensuring interpretability and transparency. Finally, for a fair evaluation, seven benchmark object detection models are re-implemented, along with the proposed model (FireNet-D5), and trained them on the ISFire dataset. In addition, a statistical metric, "Cohen's d", is applied to test the practical significance and consistency of the models' outcome. The experimental results indicated that FireNet-D5 improved the baseline network's [email protected] by 3.0%, reduced the model parameters by 2.7%, and showed a 32% comparative difference based on Cohen's d effect size. Ultimately, this research lays the foundation for future developments in reliable indoor fire detection technology.