2023

Browse

Filters

202352

Settings

Search Results

Now showing 1 - 10 of 52
  • Thumbnail Image
    Item
    A peer to peer blockchain based approach for blood donation community
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Kamal, Minhaz; Abdullah, Chowdhury Mohammad; Shaiara, Fairuz
  • Thumbnail Image
    Item
    PPoS: An Optimized Consensus Protocol for IoT Devices
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Anan, Tasnim Ferdous; Mahi, Abdullah Ibne Masud; Arnob, Tausif Khan
  • Thumbnail Image
    Item
    Medical Image Synthesis using Generative Adversarial Network
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Risha, Antara; Islam, Shaira Saiyara; Tahsin, Anika
  • Thumbnail Image
    Item
    Real time Gaze Tracking in Remote Proctoring: A Study of Appearance-based Gaze Estimation
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Onim, Nafiul; Shahid, Mirza Sadaf; Quayes, Muhammad Rafsan
    Our thesis aims to address the critical issue of academic dishonesty in online examinations by proposing a proctoring system that integrates eye gaze tracking technology for the detection of suspicious behavior. The study begins by discussing the existing challenges of current ex amination systems and identifying the problems that need to be addressed. It emphasizes the necessity for a more advanced proctoring system with gaze tracking capabilities to effectively deter attempts at academic dishonesty. The research is divided into two main parts: the selec tion of an appropriate model and the incorporation of proctoring functionalities. Two models were chosen for evaluation, namely iTracker, which was pre-trained on the GazeCapture dataset, and L2cs-net, which we trained on the MPIIFaceGaze dataset. The findings from these exper iments indicate that L2cs-net outperforms iTracker in terms of accuracy, speed, and latency but only when supplied with the processing power of a GPU, without one iTracker is better. Regarding the proctoring system aspect, it is noted that most of the existing research is com mercially driven, with limited academic contributions. To optimize the proctoring system for online exams, we recognize the significant value of examinees’ eye gaze and define important regions on and off the screen through calibration using “magic pixels”. Moreover, we attribute cheating criteria using a formulated equation that takes into account factors such as Count, Frequency, Duration, and Regression. Two potential approaches for the proctoring system, namely Thresholding and Machine Learning (ML), are considered. However, our focus lies on the development of a thresholding-based approach. Overall, this thesis presents a comprehensive exploration of academic dishonesty in online examinations, proposes a proctoring system using eye gaze tracking technology, and compares the performance of different models and method ologies. The findings contribute to the advancement of proctoring systems and provide insights for the development of more effective measures against academic dishonesty.
  • Thumbnail Image
    Item
    A Diverse and Explainable Multi-hop QA Dataset for Bengali Language
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Intiser, Md. Aseer; Islam, Mohammad Munimul; Salehin, Md. Reyanus
    Bengali is a resource-scare language with a scarcity of quality data sets both in single and multi-hp question answering. In an approach to fill that gap, we want to take a little step by generating a reading comprehension based open-domain multi-hop question answering which will be explainable and diverse. We will generate about 100 passages from news and Wikipedia articles and 500 question-answer pairs. We will maintain the diversity in selecting domains of contexts and also in generating questions and answers. Our data set will be explainable in generating the answer to a given question by providing supporting facts and showing the reasoning chain
  • Thumbnail Image
    Item
    Evaluation of User Experience of Bangladesh E-government Services: A Student’s Perspective
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Imtiaz, Nafiz; Rahman, Ibtid; Robe, Md. Adnan Rahman
    With the government striving to make the country digitally driven, the Bangladesh Na tional Digital Architecture (BNDA) framework was made to ensure improved and more user-friendly services. The e-services of the Bangladesh Government have already im plemented the BNDA framework. The usability of those services is a prime concern to be able to reach a large number of users. Although previous studies on the usability of government websites were made, no significant research from the user experience per spective has been done on the newly designed e-service websites. This research aims to evaluate the User Experience(UX) of two e-service websites namely, Railway Ser vice and Surokkha-Vaccine Management System of the Bangladesh Government from the students’ perspective. As students are a majority part of the user base of these e-services both directly and indirectly, it is crucial to know about their user experi ence. The study uses the widely recognized Jakob Nielsen’s 10 Usability Principles for user interface design for Heuristic Evaluation (HE) and User Experience Questionnaire (UEQ) questionnaire for the evaluation of user experience. The findings prove that the user experience of the e-services is still not meeting the UX standards. Specifically, the novelty factor needs more improvement than the rest of the factors as their results are mostly below average or less according to the gathered data. The data gathered from this research can be used to make e-service websites that give a more user-friendly ex perience by following UX standards
  • Thumbnail Image
    Item
    Joint Position-based Anomaly Detection using Graph Convolution Network
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Haque, Md. Wasiul; Siddique, Mohammed Afzal; Saju, Md. Hasan
  • Thumbnail Image
    Item
    Attack and Anomaly Detection in IoT Devices using Federated Learning
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-04-30) Adib, Mosabbir Sadman; Raf, Moshiur; Pranto, MD Jabear Hossain
    There has been a lot of focus from governments, universities, and businesses in recent years on the intersection of cybersecurity and machine learning (ML) for the Internet of Things (IoT). The Internet of Things (IoT) can be made more secure and efficient in the future through the groundbreaking concept of federated cybersecurity (FC). This new idea has the ability to efficiently identify security problems, implement countermeasures, and contain them within the IoT network infrastructure. Cybersecurity goals are met through the federation of a shared and learned model among several actors. Protecting the insecure IoT environment requires privacy-aware ML models like federated learning (FL).
  • Thumbnail Image
    Item
    An Ensemble Method for Cancer Classification and Identification of Cancer-Specific Genes from Genomic Data
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Rizwan, Siana; Tabassum, Farzana; Islam, Sabrina
    Classifying cancer using gene expression can be an important tool for under standing the specific characteristics of a patient’s cancer and for guiding the most appropriate treatment approach. By identifying the specific genes that are involved in the development and progression of a particular cancer, it may be possible to tailor treatment to target those genes and improve outcomes for the patient. In addition, by understanding the genetic makeup of a patient’s cancer, it may be possible to identify clinical trials or targeted therapies that may be more effective for that patient. Here, in our study, we worked with the TCGA Pan Cancer dataset where we used the RNA-seq data for analyzing the gene expres sions. The dataset comprises 33 types of cancer. Our study mainly focuses on implementing an explainable AI-based panCancer classification approach using gene expression analysis. The goal is to accurately detect the type of cancer in in dividuals within a short time. We employed seven classifier algorithms- Logistic Regression, SVM, XGBoost, Random Forest, MLP, 1-D CNN, and TabNet. To enhance the performance of the models, we utilized feature selection techniques such as Lasso, SelectFromModel, Select-K-Best, and ElasticNet. SelectFrom Model with 500 features yielded the best performance. We applied ensemble methods of probability averaging and max voting, with probability averaging achieving the highest accuracy of 96.60%. Validation of the selected features’ contribution and comparison with gene sets from DESeq2 analysis confirmed their significance and relevance. This approach provides insights into cancer specific molecular mechanisms and pathways. Overall, our study demonstrates the effectiveness of feature selection in reducing dimensionality while maintain ing predictive power and biological relevance
  • Thumbnail Image
    Item
    Exploring The Effect of Code Coverage And Maintainability for Identifying Software Testability
    (Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Abrar, Md. Fahim; Alam, Muntasir Bin
    The ability of code to reveal its flaws, especially during automated testing, is known as software testability. The program being tested must be able to with stand testing. The coverage of the test data provided by a specific test data generation algorithm, on the other hand, is what determines whether a test will be successful. To clarify whether and how software testability affects test coverage. However little empirical evidence has been presented. In this article, we suggest a technique to clarify this issue. The testability of programs is determined using a variety of source code metrics, and our suggested framework builds machine learn ing models using the coverage of Software Under Test (SUT) provided by various automatically generated test suites.The cost of additional testing is decreased be cause the resulting models can anticipate the code coverage offered by a particular test data generation algorithm before the algorithm is even run.To measure the testability of source code, a concrete proxy called predicted coverage is used. The correlation between code coverage and maintainability is crucial in assessing the testability of software, as high code coverage combined with well-maintained code facilitates the creation of comprehensive test cases and ensures thorough testing of critical paths and edge cases.