Browsing by Author "Sarkar, Pritom Kumar"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Advanced Solar Powered Multipurpose Agricultural Robot
    (2022) Saima, Fatema Tauze Zohora; Tabassum, Mira Tamanna; Talukder, Touhidul Islam; Hassan, Fahim; Sarkar, Pritom Kumar; Howlader, Sujan
    Agriculture is contemplated as one of the foremost principal economic exercises in Bangladesh. Its contribution to GDP is a lot and it is the third most benefaction sector to Bangladesh’s GDP. Though its subscription is decreasing for many years. It comes to12.6% in 2020 from 17% in 2010. This project bargains with the exchange and advancement of low power, low cost, and less man work robots within the agronomic approach. Agrarian automata are broadly utilized at the tunnelling, seeding, collecting stage, and developing. This robot is built to diminish the farmer’s exertion. This project’s main goal is to increase the agriculture production rate and to help the farmers. The planned Mechanical autonomy procedures are proficient for accomplishing the assignments such as seed sowing, water sprinkling, pesticide spraying, and digging the land. This system can spread seeds in 4 rackets at a single moment. A 4–7volt motor has been used in this system. This robot’s efficiency is 80% that needs a 500mA-1A current and 50rpm Motor Torque. The robot has the capacity to lift approximately 12 litters of water. This system will enlarge the fabrication rate as well as will reduce the time that is given in the production procedure. As the entire system will consume its required electrical energy from solar panels so it will be cost-effective and will contribute to the counties economy.
  • Thumbnail Image
    Item
    An efficient deep learning approach to detect various diseases using chest X-ray images
    (BRAC University, 2025-02) Hassan, Sanzana Mahrukh; Khan, Md. Anik; Hossine, Md. Abid; Lamia, Mayesha Zaman; Sarkar, Pritom Kumar; Alam, Md. Ashraful
    We propose and demonstrate an efficient deep-learning approach to classify various diseases using chest x-ray images. The proposed system comprises several steps: image acquisition, preprocessing, and classification of various diseases. The datasets include X-ray images of various diseases such as pneumonia, COVID-19, lung opacity, and normal chest images. Raw X-ray images and the dataset from Kaggle is preprocessed using image resizing and augmentation. Finally, a network-based deep learning model is applied to classify the disease. Different CNN architectures: ResNet50, ResNet101, EfficientNet, DenseNet121, and AlexNet are investigated for the classification, and the best-performing architecture is used in the model, to design a custom-made model named X Net. By incorporating certain layers from both ResNet101 and DenseNet121. The ResNet101 and DenseNet121 models gave 94% and 92% accuracy, respectively, where the rest of the models gave lower accuracy than them. Our proposed model achieves a higher accuracy of upto 96.5%.