C2SG Research Group

The Computing for Sustainability and Social Good (C2SG) Research Group conducts experimental research to find solutions to critical emerging problems with a focus on the development of sustainable societies, in which computing technologies interact closely with social good, while also enabling new applications. The research conducted by the group is highly interdisciplinary and involves researchers from a wide variety of fields, including computer science, biology, public health, behavioral sciences, and many more. The research that we do has several practical applications. The group works on a wide variety of issues, some of which include Deep Learning, the Internet of Things, and Cloud Computing.

Research Areas

AI, Data Science, Deep Learning

HCI, Sustainable Societies

Cloud Computing, Distributed Systems

Our Current Projects

Sustainable Livestock Management
Lumpy Skin Disease (LSD), Foot and Mouth Disease (FMD), and Infectious Bovine Keratocon-junctivitis (IBK) are some of the most common non-invasive diseases of cattle in Bangladesh. These diseases are believed to be highly contagious. To establish sustainable cities and society in the context of Bangladesh, it is important to detect the affected cattle in time and take immediate action. To do so, implementing a project idea focused on developing a novel detection system for non-invasive cattle diseases based on interviews with cattle farmers. The project aims to utilize a deep Convolutional Neural Network (CNN) with high accuracy for disease detection. Additionally, a mobile app named 'CattleSavior' will be designed and implemented, incorporating the detection system along with other necessary features to facilitate disease detection and treatment for cattle farmers. Subsequent interviews with cattle farmers will be conducted to evaluate the feedback on the mobile app's usability and effectiveness.

Eye-Tracking Paper ArXiv Link

MedIC
The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in the organ or cell region. The convolution operation possesses a restricted capability to extract visual patterns across several spatial regions of an image. The involution process, which is the inverse operation of convolution, complements this inherent lack of spatial information extraction present in convolutions. In this study, we investigate how applying a single layer of involution prior to a convolutional neural network (CNN) architecture can significantly improve classification and segmentation performance, with a comparatively negligible amount of weight parameters. We explore different tasks with this methodology including, eye-tracking data, cell images, autoencoders and similarity learning.

ArXiv Link

Efficient Multimedia Storage and Retrieval
This approach works in two sequential stages. First, the data will be uploaded to a classifier that will determine the data type and send it to the specific model for the data. Here, the images that are being uploaded are sent to our trained model for object detection, and the documents are sent for keyword extraction. Next, the extracted information is sent to Elasticsearch, which enables searching based on the contents. Because the precision of the models is so fundamental to the search’s correctness, we train our models with comprehensive datasets (Microsoft COCO Dataset for multimedia data and SemEval2017 Dataset for document data). Furthermore, we put our designed architecture to the test with a real-world implementation of an open-source OSS called OpenStack Swift. We upload images into the dataset of our implementation in various segments to find out the efficacy of our proposed model in real-life Swift object storage.

News & Gallery

We are happy to share that Dr. Jannatun Noor from C2SG Lab has been selected for the "Quality Journal Publication Award", for her scholarly works published in the top 25% (Q1) journals. This award is arranged by BRAC University, primarily awarded to the scholars of BRACU, who put their efforts into research excellence and publish their works in top journals around the world.

Members