School of Data and Sciences (SDS)

A methodological analysis of consumption patterns and anomaly detection in prepaid and postpaid metering systems: an N-BEATS-driven predictive modeling approach

Islam, Nusaba; Debnath, Partha; Islam, Md Rakibul; Kamrul, Awon Bin; Sheakh, Md Rishat (BRAC University, 2024-10)

The introduction of the prepaid metering system has caused severe dissatisfaction among the masses, claiming that there was a noticeable spike in the bills of their monthly electricity bill. This issue was addressed in ...

Autonomous object detection dataset: a study on Bangladeshi roadways

Sakib, Kazi Sadman; Abir, Tahsinul Islam; Kareena, Shahida Sultana; Alam, Rupanti (BRAC University, 2024-10)

This research aims to enhance object detection in autonomous driving by testing the three new advanced YOLO models, namely, YOLOv5, YOLOv7, and YOLOv8, on a private dataset proposed specifically for Bangladesh. It is ...

From impersonation to authentication: techniques for identifying deep fake voices

Rabbi, B.M Saqlain; Haque, Erfanul; Huri, Humayera Shayera; Tabassum, Nuzhut (BRAC University, 2024-10)

The proliferation of fake voices has become a concerning issue, making it increasingly challenging to distinguish between authentic and fabricated audio recordings. Notable examples include the replication of the voices ...

Decentralized access control using hyperledger fabric

Hossain, Jubayer; Nabil, Mehedi Hasan; Jahin, Farhan Labib (BRAC University, 2024-10)

In traditional access control systems, all the access control mechanisms are centrally managed which is seriously vulnerable. It is susceptible to a single point of failure due to its centralized architecture. As the ...

Analysis of password security factors among E-commerce websites, news portals, and government websites

Labannya, Adhara; Baidya, Dipannita; Dipto, Nahian Hoque; Hossain, Sahadat; Das, Shantanu (BRAC University, 2024-01)

This study aims to evaluate password security practices among the top e-commerce, news portal, and different government websites in Bangladesh along with the ecommerce websites in India. Drawing from the established ...

Crop pest recognition using image processing

Ghosh, Pial; Alin, Istiak Ahmed; Chowdhury, Hasan Al Mahmud (BRAC University, 2024-10)

One of the most vital aspects of a human’s existence is food. Each food contains several nutrients which help in growth and development of the human body. It also prevents our body from various diseases. Most of the food ...

Learning the agent specific sub-optimal bound for multi-agent path finding

Prova, Ramisa Fariha; Hassan, S. M. Fuad; Sarker, Bijoya; Islam, Shariful; Ishrak, Md. Shamiul Islam Khan (BRAC University, 2024-10)

Multi-Agent Path Finding (MAPF) is a prominent challenge in robotics and artificial intelligence, encompassing the task of finding collision-free paths for multiple agents sharing a common environment. CBS, a fundamental ...

Comparative analysis of efficient deep learning models for breast cancer identification using relevant genes

Saad, Md Abu; Muqset, B. M Anjum Ul; Shopnil, Chowdhury Rifat Ahmad; Rahman, Md. Mostafizur (BRAC University, 2024-10)

Cancer remains a formidable global health challenge, with early detection critical in improving patient outcomes. In this context, applying deep learning techniques to relevant gene analysis has emerged as a promising ...

A GAN-based model for single image super-resolution on consumer-grade GPUs: comprehensive analysis and development of MSRGAN

Ahmad, Istiaq; Azam, Labib Sadman; Bhuiyan, Moinul Hossain; Mamun, Abdullah Al (BRAC University, 2024-10)

In a world where visual content plays a crucial role in anything imaginable, the need for sharper, more detailed images has never been more important. This research paper explores innovative approaches to improve the ...

Advancing legal accessibility in Bangladesh through AI-powered assistance and natural language interfaces

Hossain, Tanzir; Anawar, Md. Shakil; Islam, Ar-Rafi; Karim, Md. Adnan (BRAC University, 2024-10)

In a country where laws and regulations are as difficult to understand as the cases they govern, the path to justice is anything but straightforward. For many in Bangladesh, the legal system’s complexity acts as a ...

Optimizing CNN memory efficiency: a continual learning solution for plant stress classification

Reza, Ahmed Shakib; Zaima, Farah Ulfat; Annisa, Mysha Maliha; Sattar, Tazkera (BRAC University, 2024-10)

In nature, plants encounter a wide variety of stress-inducing elements that can create unfavorable conditions or impede their metabolic processes and hinder growth. Both biotic, living organisms, and abiotic, non-living ...

Assessing the impacts of bacteriophage coinfection on phage infectivity, host specificity, and their competence using phage cocktail

Mahzabin, Maliha; Khan, Aisha; Khan, MD. Erfan (BRAC University, 2024-09)

The MDR or Multi-drug resistant pathogens for example, Vibrio cholerae, represent an emerging serious health problem since these bacteria have natural capabilities for adaptation to environmental stresses and antibiotics. ...

Synergistic application of advanced machine learning and computer vision techniques for the detection of exoplanet and star: leveraging contrastive learning in astronomical imagery

Alif, Ashraful Kabir; Hossain, Sk Jamil; Hossain, Md Impreeaj; Antor, Shihab Shahriar; Roy, Arghya Pranto (BRAC University, 2024-11)

The detection of exoplanets through direct imaging has become increasingly feasible with the advent of modern telescopes like the James Webb Space Telescope (JWST) and its MIRI coronagraph. These instruments have ...

Tracing subtle patterns: early detection of Anorexia in social media using contextualized BERT embeddings and deep learning

Fairooz, Quazi Fariha; Khan, Tawhidur Rahman (BRAC University, 2024-10)

In a world where the usage of social media is prevalent, it is important to acknowledge the fact that these social platforms have been increasingly used to share private matters with the public eye, which may sometimes ...