Publications

 Whaiduzzaman, M., Barros, A., Chanda, M., Barman, S., Sultana, T., Rahman, M.S., Roy, S. and Fidge, C., 2022. “A review of emerging technologies for IoT-based smart cities”. Sensors, 22(23), p.9271.
This paper examines smart cities' concepts, applications, and challenges, focusing on IoT, machine learning, and blockchain for enhanced operations. It highlights IoT ecosystems, security, and emerging technologies to build resilient, future-ready cities. 

Uddin, M.A., Talukder, M.A., Uzzaman, M.S., Debnath, C., Chanda, M., Paul, S., Islam, M.M., Khraisat, A., Alazab, A. and Aryal, S., 2024. “Deep learning-based human activity recognition using CNN, ConvLSTM, and LRCN”. International Journal of Cognitive Computing in Engineering.

This paper presents a deep learning approach to human activity recognition (HAR) using CNN, ConvLSTM, and LRCN models. CNN achieved the highest accuracy (99.58% on UCF50, 92.70% on HMDB51), showcasing its potential for applications in healthcare, assisted living, and public safety. 

Chanda, M., Rahman, S. and Sarker, M.M., 2022. “Impact of Internet Connectivity on Education System in Bangladesh during Covid-19”. International Journal of Advanced Networking and Applications, 13(4), pp.5063-5068.

This paper examines the rise of internet usage in Bangladesh's education sector, especially during the COVID-19 pandemic. Based on a survey of 260 participants, it highlights students' perspectives on online classes, key challenges, and provides recommendations for policymakers and educators.

Chanda, M., Mazumder, O. and Patwary, M.F.K., 2023, December. “Smoker Recognition from Lung X-ray Images using ML”. In 2023 26th International Conference on Computer and Information Technology (ICCIT) (pp. 1-6). IEEE.

This study proposes a novel CNN-based system to detect smoking status from lung X-ray images with 91.50% accuracy, 92% precision, and 91% recall. Using a dataset divided into smokers and non-smokers, the system offers real-time, high-sensitivity detection. It has potential applications in hospitals, police or army recruitment, and university admissions.

Moumita Chanda, Olive Mazumder, Md. Fazlul Karim Patwary. “Is VGG-19 Road Segmentation Method better than the Customized UNET Method?” Accepted in 3rd 2024 IEEE World Conference on Applied Intelligence and Computing (AIC 2024).

This paper explores road segmentation techniques for self-driving cars, focusing on lane detection and object recognition. We compare the VGG-19 and UNET models, finding that VGG-19 achieves 40% accuracy and 93% precision in detecting complex road structures. The study contributes to advancing semantic segmentation for autonomous driving.

Wahida Ferdose Urmi, Mohammed Nasir Uddin, Md Ashraf Uddin, Md. Alamin Talukder, Md. Rahat Hasan, Souvik Paul, Moumita Chanda, John Ayoade, Ansam Khraisat, Rakib Hossen, Faisal Imran. “A stacked ensemble approach to detect cyber attacks based on feature selection techniques”. 

This study evaluates feature selection techniques (RFE, MI, LFS) and proposes a stacked ensemble classification approach for Cyber-Attack Detection Systems. The results show RFE achieved up to 100% accuracy, significantly improving detection performance on CICIDS2017 and NSL-KDD datasets, enhancing cybersecurity.

Chanda, Moumita, Olive Mazumder, Souvik Paul, and Tawfikur Rahman. "Brain–computer interfaces for security and authentication." Artificial Intelligence Applications for Brain–Computer Interfaces (2025): 205-225.

This study investigates the synergistic uses of AI in BCI, such as how AI algorithms help to extract features, recognize patterns, improve security, and secure data transmission in BCI systems. Therefore, the purpose of this research study is to evaluate, from an engineering perspective, the perspectives and the nature of the first level of research on the risks and opportunities of BCI in the safety and security industries. Also, after the systematic review, we can propose a systematic approach toward the BCI technology.