Tasnim Ferdous is a Senior Lecturer at BRAC University. She earned her Masters in Electrical and Computer Engineering from Oregon State University (2016), receiving the Laurel Award for Outstanding Academic Performance, and her B.Sc. in Electrical and Electronic Engineering from AIUB (2012).

Her research combines biomedical signal processing, machine learning, and computational neuroscience. She focuses on non-invasive neurotechnology to improve cognitive performance and mental well-being. Her current work includes EEG-based neurofeedback for memory consolidation and automated sleep stage classification using adaptive deep learning models.

Tasnim previously worked as an Electrical Engineer at Electro Scientific Industries (ESI), USA) and as a faculty member at Northern University Bangladesh. She now mentors students and leads initiatives to advance neurofeedback, BCI, and sleep research at BRAC University.

Beside working, she loves to sketch and frame beautiful sights on paper. She also spends time reading on various topics, hiking within the woods and trying out different recipes.

Google Scholar
ORCID

1. Computational Neuroscience/ Brain Computer Interface(BCI)
   Neuroinformatics and Digital health
   Biomedical Signal processing.
   Sensor electronics, Machine Learning and Deep learning applications

Open Positions

I am looking for motivated undergraduate or master’s students to join my research on AI, Cognitive Neuroscience, and Computer Vision.

How to Apply

Send your CV + project interest to: tasnim.ferdous@bracu.ac.bd


ONGOING
Neuroadaptive Gamified Cognitive Training with BCI and Memory Palace Techniques 
This research develops a smart, gamified training system that improves attention, memory, and fatigue management. It combines brain signals (EEG), eye tracking, and user performance to understand a person’s cognitive state in real time.

The system adapts tasks based on the user’s attention and fatigue levels and uses memory palace techniques to support better learning. Machine learning models classify mental states and help personalize the training experience for improved cognitive performance.
-Team members: Ms. Tasnim Ferdous

Transfer Learning for Sleep Quality Monitoring using EEG 
This ongoing work extends the model to improve generalization across datasets using transfer learning. The goal is to develop a robust system for sleep stage classification and sleep quality monitoring that can adapt to new data with limited training, enabling practical real-world deployment.

Team: Ms. Tasnim Ferdous, Naveed Mahmood

Adaptive Multimodal Gesture-Based Interface for Visually Impaired Users 
This work focuses on a multimodal interaction system that enables visually impaired users to control mobile devices through hand gestures. It integrates webcam-based vision with wearable sEMG signals for reliable gesture detection.

The system uses AI models to recognize user intent in real time and provides audio and haptic feedback for interaction. By adapting to user behavior, it aims to improve accessibility and enable independent device control beyond voice-based interfaces.

Team: Ms. Tasnim Ferdous, Mostakim Mahmud Mugdhha, Dr. Khalilur Rahman

COMPLETED
1. Explainable Deep Learning for EEG-Based Sleep Stage Classification (IEEEXplorer)
This work focuses on improving the interpretability of attention-based deep learning models for EEG-based sleep stage classification. Explainable AI (XAI) technique (GradCam) was applied to highlight the most relevant EEG features influencing model decisions, making the system more transparent and reliable.

Team: Ms. Tasnim Ferdous, Naveed Mahmood, Dr. Aniqua Nusrat Zereen

2. Machine learning on PPG based automated Sleep stage classification (IEEEXplorer | IEEEXplorer )
-Team members: Ms. Tasnim Ferdous, Dr. Aniqua Nusrat Zereen, Reshad Ul Karim, Abrar Samin, Sammam Mahdi, Himika Tasnim