Thesis (Bachelor of Science in Computer Science)

Browse

Author: search.filters.author.Hossain, Shahriar

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Transforming Bangladesh agriculture: AI for precision crop disease management
    (BRAC University, 2025-06) Hossain, Shahriar; Nahin, Al-Zaber; Hassan, Tasnuva; Haque, Zarif Ayman; Farin, Nusrat Jahan; Hossain, Muhammad Iqbal
    The agricultural sector encompasses a large chunk of the economy of Bangladesh as it has the necessary preconditions and factors to be suitable for agriculture. Agriculture is wholly at the whims of the environment and associated natural factors. Innovations from the time man has mastered the art of farming have allowed us to have in control some factors to ensure the desired output however there remains room for improvement and innovation especially in regards to disease detection. Currently even with a large agricultural sector, the methods for disease detection and risk management are lacking due to the inefficiencies in the system which can be very costly. To mitigate this technological innovations such as machine learning and image processing can be used to combat visible signs of disease and achieve early detection. In this paper we have explored the current options available and what can be done to make it suitable to our conditions, which ones are the best for our problem and finally we have proposed a solution we deem feasible. In our reviewed past works we have come across three models, namely Xception, VGG19 and ResNet50 which perform the best for our use cases, giving us the best results for leaf disease detection. These models have been implemented with a transfer learning approach to achieve the best results. Finally we have created a hybrid model approach combining Xception and a Vision Transformer to get the advantage of both a CNN and a Transformer to achieve the best result for our purpose.
  • Thumbnail Image
    Item
    Diabetic retinopathy detection and classification by using deep learning
    (BRAC University, 2022-01) Hossain, Shahriar; Evan, Md. Nurusshafi; Farhin, Fariya Zakir; Nabil, Mashrur Karim; Sadman, Sameen; Chakrabarty, Amitabha
    Eyes are the most sensitive part of a human being and it is one of the most challenging tasks for a computer-aided system to classify its diseases. Many visionthreatening diseases such as, Glaucoma and Diabetic Retinopathy are treated using digital fundus imaging and retinal images by the specialist at a primary level. However, a computer-aided system that can classify if the eye has a disease or not could be a handy tool for the specialists and a challenging task for computer aided system developers. A branch of machine learning which is deep learning is making a revolutionary impact on medical diagnosis using image processing and pattern recognition. Therefore, we aim to make use of some Convolutional Neural Network (CNN) architectures such as ResNet50, Inception V3, Xception, DenseNet-169 and MobileNetV3 Large to extract the features and classify if the eye has a disease or not using digital fundus photography and retinal image. For our research, we used a competition dataset available from Kaggle [1] and another dataset from IDRiD [2]. Our final dataset contained a total of 2,517 images with each stage having around 500 images in them. Upon training and testing the selected architectures, we have found that Inception V3 has an accuracy of 86.31% and 87.7% (with a lowered learning rate). Similarly for Xception, we attained 86.9% accuracy with default learning rate and 87.9% accuracy with lowered learning rate. ResNet50 gave an accuracy of 46.83%, MobileNetV3 Large gave the lowest accuracy standing at 23.81%. DenseNet-169 gave us the highest accuracy among all other models, soaring at 88.29% accuracy.
  • Thumbnail Image
    Item
    RansomListener: Ransom call sound investigation using LSTM and CNN Architectures
    (BRAC University, 2020-12) Rahman, Rafeed; Rahman, Mehfuz A; Hossain, Shahriar; Hossain, Sajid; Milon, Md.Iqbal Hossain; Akhond, Mostafijur Rahman
    Getting calls for ransoms are common phenomena in kidnapping and abduction related incidents where the life of the victim remains extremely vulnerable. These phone calls are often analyzed in real-time by law enforcement authorities to quickly identify the suspects and get crucial information for quick action. However, it is often difficult to manually analyze those phone calls due to the quality of sounds and the presence of several background noises. Even with much high-end software in their inventory, it is futile to accurately refine the incoming calls as it takes a huge amount of time to declutter the different layers of noises in the call. This paper proposes a model based on deep convolutional neural network and signal processing for automatic classification of crucial sounds in ransom related phone calls. We have proposed LSTM and 2D CNN customized models and compared their outputs with VGG16 and AlexNet. Moreover, this paper also presents a unique dataset of different sounds in terms of voices like male or female and the environmental sounds where the victim might be in which can be a probable clue for investigation purposes consisting of 17650 audio clips collected from verified online sources. Finally, the models produced very high classification accuracy with the accuracy of LSTM reaching around 93.4%.