Peer-reviewed publications by Chowdhury Mohammad Abdullah on AI ethics, dialect bias in language models, HCI, and blockchain security, in reverse chronological order.
The literature presents a digitized pension system based on a consortium blockchain, with the aim of overcoming existing pension system challenges such as multiparty collaboration, manual intervention, high turnaround time, cost transparency, auditability, etc. In addition, the adoption of hyperledger fabric and the introduction of smart contracts aim to transform multi-organizational workflow into a synchronized, automated, modular, and error-free procedure.
2022
ICCIT
BloodComm: A Peer-to-Peer Blockchain-based Community for Blood Donation Network
Chowdhury Mohammad Abdullah, Minhaz Kamal, Fairuz Shaiara, and 2 more authors
In 2022 25th International Conference on Computer and Information Technology (ICCIT), Dec 2022
Blood transfusion is an integral part of the healthcare system that plays an important role in ensuring the quality of care for patients undergoing a variety of medical procedures and treatments. A large portion of this blood comes from voluntary donors. The existing blood donor management systems are unable to offer a reliable audit trail and traceability. Hence, there is a significant risk that patients may get transfusion of blood from unreliable sources. In this paper, we propose a system built on Ethereum with the goal of creating a decentralized, transparent, traceable, and secure network of blood donors. The platform uses smart contracts to facilitate peer-to-peer interactions. To encourage donors to donate blood more regularly, the system also offers rewards in the form of tokens. Our source code is available in a public Github repository1.
ICCIT
Huruf: An Application for Arabic Handwritten Character Recognition Using Deep Learning
Minhaz Kamal, Fairuz Shaiara, Chowdhury Mohammad Abdullah, and 3 more authors
In 2022 25th International Conference on Computer and Information Technology (ICCIT), Dec 2022
Handwriting Recognition has been a field of great interest in the Artificial Intelligence domain. Due to its broad use cases in real life, research has been conducted widely on it. Prominent work has been done in this field focusing mainly on Latin characters. However, the domain of Arabic handwritten character recognition is still relatively unexplored. The inherent cursive nature of the Arabic characters and variations in writing styles across individuals makes the task even more challenging. We identified some probable reasons behind this and proposed a lightweight Convolutional Neural Network based architecture for recognizing Arabic characters and digits. The proposed pipeline consists of a total 18 layers containing four layers each for convolution, pooling, batch normalization, dropout, and finally one Global average pooling and a Dense layer. Furthermore, we thoroughly investigated the different choices of hyperparameters such as choice of optimizer, kernel initializer, activation function, etc. Evaluating the proposed architecture on the publicly available ‘Arabic Handwritten Character Dataset (AHCD)’ and ‘Modified Arabic handwritten digits Database (MadBase)’ datasets, the proposed model respectively achieved an accuracy of 96.93% and 99.35% which is comparable to the state-of-the-art and makes it a suitable solution for real-life end-level applications.
Best Paper Award