Project Report

Browse

Search Results

Now showing 1 - 10 of 3755
  • No Thumbnail Available
    Item
    Reasoning Over Context in Bangla: A Generative QA Approach to Factoid Understanding Using LLM
    (Daffodil International University, 2025-01-14) Rana, Md. Masud
    This paper presents the development of a Bangla Question Answering (QA) system using advanced transformer-based models to tackle the complexities of Bangla language processing. Specifically, it compares the performance of BanglaT5, a model fine-tuned for Bangla, with mT5, a multilingual variant of the T5 model. Both models were evaluated on a dataset of over 7,500 Bangla news articles, focusing on factoid-based question answering. The results show that BanglaT5 outperforms mT5 on key metrics such as ROUGE, BLEU, Character Error Rate (CER), and Word Error Rate (WER), showcasing its superior ability to handle Bangla’s unique linguistic features like morphology and syntax. BanglaT5 achieved a ROUGE-1 F1 score of 0.6979, Exact Match Accuracy of 0.49, and CER of 0.4054, demonstrating its ability to generate accurate, contextual answers. In contrast, mT5’s performance was much lower, with an Exact Match Accuracy of 0.0008 and WER of 0.9996. This comparison highlights the importance of fine-tuning models for specific languages like Bangla, emphasizing the limitations of multilingual models in tasks requiring deep linguistic understanding. The system developed in this research offers a scalable solution for Bangla QA, with potential applications in education, public services, and digital literacy, contributing to the growing field of Bangla NLP. Future work will focus on deploying the model in real time, expanding the dataset, and exploring multimodal capabilities to increase its use in real-world applications.
  • No Thumbnail Available
    Item
    Ideation of Depression and Suicide Using Machine Learning Techniques
    (Daffodil International University, 2025-01-14) Rihan, Aspy
    Depression has emerged as a major mental health challenge globally, with a noticeable rise in prevalence in Bangladesh, particularly accompanied by increasing suicidal tendencies. This study investigates the underlying causes of depression and presents a machine learning-based approach for its early detection. Unemployment, family pressure, work stress, and social isolation were identified as key contributing factors. This issue was addressed using several supervised machine learning models, including Nave Bayes, Support Vector Machine (SVM), Logistic Regression (LR), Random Forest, Linear Discriminant Analysis (LDA), AdaBoost, Decision Tree, and k-Nearest Neighbor (k-NN). A comprehensive dataset related to mental health and depression symptoms was used to train and test these models. Statistical Machine Learning has shown to be the most accurate and consistent method while Logistic Regression provided the most consistent and balanced performance. Naïve Bayes had good recall capabilities, and AdaBoost had robust performance across a variety of metrics. Additionally, Random Forest and k-NN provided reliable results, while Decision Tree and LDA did not produce any interpretable yet effective results. This study confirms the potential of machine learning techniques for the accurate detection of depression and related mental health issues. It will be important to enhance model explanation, reduce algorithmic bias, integrate diverse data sources, and adhere to ethical principles like privacy protection and informed consent for future research. In resource-constrained regions like Bangladesh, AI-driven mental health tools are especially important for enabling timely diagnosis and support.
  • No Thumbnail Available
    Item
    Identifying The Authenticity of Images Using Deep Learning Techniques
    (Daffodil International University, 2025-01-14) Mondal, Sourav Kumar
    The rapid development of generative artificial intelligence has produced a wave of hyper-realistic deepfakes, posing existential challenges for authenticity verification to occur in digital media. This study proposes a deep learning architecture for the binary classification of AI-generated and real images as a reaction to a growing need for credible detection techniques. We comparatively evaluate four various architectures: ResNetRS50, MobileNetV2, EfficientNetB0, and a specially designed CNN with integrated Gabor filters and attention mechanisms. All models were trained and evaluated on an equalized, high-quality dataset under the same experimental conditions to provide serious benchmarking. While MobileNetV2 and EfficientNetB0 achieved higher peak validation accuracies of 99.29% and 99.81% respectively, ResNetRS50 was the most powerful and most generalized model. Its robust convergence behavior, high interpretability, and resistance to overfitting— particularly under extended training durations and high-density data—make it the top choice even at a slightly lower peak accuracy of 97.24%. Extended testing using classification reports, confusion matrices, and performance curves supports this conclusion further. A web interface was also established to demonstrate real-time deployment capability, showing that the model is usable in practical applications. The proposed method not only elevates the state of AI image forensics but also serves as a basis for large-scale and trustworthy content verification systems in the face of rising synthetic media.
  • No Thumbnail Available
    Item
    Fruit Quality Classification using Deep Learning and Explainable AI
    (Daffodil International University, 2025-01-14) Annafi, Abdun Nafi; Muhtasim, Tasnuva
    Fruit quality classification is a critical task in agriculture and food industries to ensure standardization and market value. This study evaluates the performance of VGG19, MobileNetV2, ResNet50, custom CNN and BiLSTM for fruit classification using deep learning. A dataset of 3,758 images across seven fruit classes was used for training and evaluation. Among the tested models, MobileNetV2 achieved the highest accuracy (99.48%), making it the most suitable for real-world applications due to its efficiency. LIME (Local Interpretable Model-Agnostic Explanations) was employed to interpret model predictions, verifying that fruit characteristics like color, shape, and texture were key factors in classification decisions. The study highlights dataset imbalance and lighting variations as primary challenges. Future improvements include dataset expansion, hyperparameter optimization, and real-time deployment of the best-performing model. This research provides insights into selecting optimal deep learning models for automated fruit classification, contributing to precision agriculture and quality assurance in food industries.
  • No Thumbnail Available
    Item
    Detection and Classification Process of Banana Leaf Diseases Using Convolutional Neural Networks (CNNs
    (Daffodil International University, 2025-05-12) Rahman, Md. Hizbur
    Finding and treating banana leaf diseases early helps farmers grow more crops and lose less. This matters most in places where bananas are a main food and income source. This thesis shows a new way to find and sort banana leaf diseases using a smart computer model. The model uses parts from two strong deep learning tools—Vision Transformer and ResNet50. It also uses an attention method to boost accuracy. The dataset, called BananaLSD, has leaf images from four groups: Cordana, Healthy, Pestalotiopsis, and Sigatoka. Before training the model, the images were cleaned and changed to help it learn better. Several models were tested, including pre-trained ResNet50, Vision Transformer, and a new hybrid CNN model. We used accuracy, F1- score, and confusion matrices to see how well they worked. The hybrid model with attention did the best. It had the highest accuracy and F1-score when sorting the diseases. This shows that using hybrid CNN models can help farmers spot crop problems sooner. It can also lead to better farming and less waste. The thesis also looks at how using AI in farming affects people, money, and the planet. The goal is to support fair, smart, and lasting ways to grow food. These findings show how tech can help solve real farming problems, like disease and food supply.
  • No Thumbnail Available
    Item
    Paddy Variety Detecting System using Image Recognition
    (Daffodil International University, 2025-01-12) Mollah, Abid Hasan; Mostafa, Md. Fahmid Bin
    The purpose of this research is to develop an advanced automated system for classifying the paddy varieties, based on the image classifying procedure, deep learning techniques, specifically, Convolutional Neural Networks (CNNs), combined with high-resolution images of the eight major rice varieties present in Bangladesh. The motivation can be found in the disadvantages of manual classification techniques, including labor-intensive, error-prone, and cumbersome to apply in rural settings on a large scale. By employing the features at the advanced level of CNNs, this project introduces an AI-based approach to the identification of varieties of rice as: BRRI Dhan 25, BRRI Dhan 28, BRRI Dhan 29, BRRI Dhan 89, BRRI Dhan The methodology required the generation of a dataset, the manipulation of pictures, the application of data augmentation methods and the training of various CNN models such as DenseNet121, VGG16 and MobileNet. The assessment of the performance of the models was performed on the base of accuracy, precision, recall, and F1-score as the criteria, and DenseNet121 turned out prominently among the options. The system has been developed so that it increases the rice variety identification accuracy and time and presents a real alternative solution for farmers, researchers, and policy makers which supports the development of digital agriculture. The next stage for development will be focused on the use of this model within mobile applications to provide real-time support to agricultural practices.
  • No Thumbnail Available
    Item
    Acute Lymphoblastic Leukaemia Detection using Deep Learning ( ViT)
    (Daffodil International University, 2025-01-14) Haque, Khandaker Rezoanul
    Significant advancements in machine learning have been made in disease detection within the medical field; however, challenges remain—particularly in achieving high accuracy and minimizing false positives. Recently, Vision Transformer (ViT) technology, originally developed for visual tasks, has demonstrated promising potential in enhancing detection performance. Motivated by this, our study implemented ViT to detect Acute Lymphoblastic Leukemia (ALL), achieving a remarkable accuracy of 99.35%. This means that out of every 100 disease-related images, our model accurately identified the diseased blood cells approximately 99 times. We utilized a publicly available ALL dataset that includes all four stages of the disease. The importance of this work is underscored by the severe health risks posed by ALL, especially in children. Furthermore, our research highlights the potential of precisely identifying early-stage cancer cases. What distinguishes our approach is the application of machine learning—specifically ViT—to automatically detect and classify cancer, offering a substantial improvement over traditional ALL detection methods, which are often time-consuming and prone to human error. Looking ahead, we aim to develop dedicated hardware to support medical professionals in the rapid and accurate identification of ALL symptoms and affected blood cells. This fusion of data science and medicine holds significant promise for addressing a wide range of medical challenges, including ALL.
  • No Thumbnail Available
    Item
    Bangla News Headline Generation
    (Daffodil International University, 2025-01-14) Rifat, Mahmudul Hasan
    This project presents a comparative study on Bangla news headline generation using two transformer-based models: the multilingual mT5 and the monolingual BT5-base. Aimed at addressing the scarcity of effective headline generation tools for low- resource languages like Bangla, the study evaluates both models on a curated dataset using standard performance metrics. While both models demonstrated stable training behavior, BT5-base exhibited faster convergence and lower validation loss, indicating more efficient learning. Evaluation results reveal a stark contrast in output quality: BT5-base achieved a ROUGE-1 F1 score of over 56% and a ROUGE- 2 score of 45.92%, significantly outperforming mT5, whose scores remained below 3% across all ROUGE metrics. Furthermore, BT5-base attained a 21.33% exact match rate and showed markedly lower Character Error Rate (CER) and Word Error Rate (WER), highlighting its superior ability to produce semantically and lexically aligned headlines. These results affirm the effectiveness of domain-specific pretraining, as the Bangla-focused BT5-base consistently delivered more fluent, accurate, and culturally appropriate headlines than the multilingual mT5 model. The findings underscore the value of monolingual transformer models for text generation in underrepresented languages and contribute a practical foundation for future advancements in Bangla NLP applications.
  • No Thumbnail Available
    Item
    Curative Care Management system for Diabetes Patient
    (Daffodil International University, 2025-01-13) Rafi, Tanveer Hasan
    The Curative Care Management system is a web based platform which is specified for diabetics patients. This system gives personalized health portal, AI based Diet plan, blog page to seek knowledge about diabetes and their issues. This system also gives a individual database to patients to maintain their early prescription and medication and documents also. A patients can make a appointment by filling up some basic questions. Doctors also prescribe a patients very easily. Patients and doctors are record their information and prescription etc. There are many health care management app or websites are available in the market. But there is no specified platform for diabetics patients. This curative care managements system is a platform which is specified for diabetes patients. This system is developed by many programming languages like HTML , CSS , Java script , react JS, PHP, MySql, pocket Base etc. My primary aim to create a website which is very user friendly for diabetes patients and they should manage their early diabetes by using my system. They should save their clinical records for a long time and the could make a appointment for specialist doctor easly.
  • No Thumbnail Available
    Item
    Multi-Model Deep Learning Approach for Monkeypox Detection: Evaluating Base and Enhanced CNN Architectures
    (Daffodil International University, 2025-01-14) Yousuf, Mahmud Kabir
    Global reemergence of monkeypox has underlined the urgency of rapid, specific and scalable diagnostic solutions. PurposeThis study investigates the possible use of deep learning techniques for automated classification of monkeypox from skin lesion images in a cohort of suspected and confirmed monkeypox patients. The study evaluates five known architecture of Convolutional Neural Networks (CNN)- VGG16, InceptionV3, MobileNet, Xception, and ResNet50 on a dataset of 998 images labelled with monkeypox, chickenpox, measles and normal. Implemented each model in a base and hybrid form, hybrid version improved by attention mechanisms and noise regularization, improves focus on lesions and encourages generalization. Evaluation Metrics for Performance Accuracy, Precision, Recall and F1- score Among all the tested models, the hybrid MobileNet and InceptionV3 models had the highest accuracies of 97% and 96%, respectively, and stable performance in classification. Hybrid versions of other models like Xception and VGG16 also performed very well. On the other hand, the ResNet50 hybrid model performed poorly, suggesting the difficulties adapting that architecture for this problem. The findings from this study corroborates that hybrid deep learning models are immensely beneficial for improving the accuracy and robustness of monkeypox classification from images. Thus, these results highlight the promise of AI-mediated diagnostic tools to address early detection and outbreak management, especially in resource- scarce settings. Research coming down the pipeline will identity suitable prospects for data expansion, transformer architectures, and integrating multimodal clinical data to ultimately yield a more reliable and clinically- applicable diagnostic.