Tarik Reza Toha

Ph.D. Student

UNC Computer Science

Chapel Hill, NC 27514

Email: ttoha12@cs.unc.edu

Research Interests
  1. RF Sensing
  2. Computer Vision
  3. Machine Learning

Hello! I am Tarik Reza Toha, a second-year Ph.D. student in Computer Science at the University of North Carolina at Chapel Hill, advised by Prof. Shahriar Nirjon. My research focuses on developing intelligent RF sensing systems by integrating computer vision and machine learning techniques.

Previously, I was a Lecturer in the Department of Textile Machinery Design and Maintenance at the Bangladesh University of Textiles. I earned both my Bachelor's and Master's degrees in Computer Science and Engineering from the Bangladesh University of Engineering and Technology, where I conducted my thesis work under the supervision of Prof. A. B. M. Alim Al Islam.

Educational Background

University of North Carolina at Chapel Hill
  • Ph.D. in Computer Science, August 2023 - Present
    • - Supervisor: Prof. Shahriar Nirjon
Bangladesh University of Engineering and Technology
  • M.Sc. in Computer Science and Engineering, October 2017 - September 2021
    • - Thesis: Vehicle Detection in Road Networks having Unstructured Traffic using Limited Computational Resources
    • - Supervisor: Prof. A. B. M. Alim Al Islam
  • B.Sc. in Computer Science and Engineering, February 2013 - September 2017
    • - Thesis: Energy-Efficient Parallel Computing Considering Both Computational and Cooling Power Consumption
    • - Supervisor: Prof. A. B. M. Alim Al Islam

Research Experience

University of North Carolina at Chapel Hill
  • Graduate Research Assistant, August 2023 - Present
    • - mmWave Anomaly Detection: Running
    • - Stationary People Counting: EWSN 2025
Bangladesh University of Engineering and Technology
  • Graduate Research Assistant, October 2017 - September 2021
    • - Embedded Object Detection: ICDM 2021
    • - Dense Crowd Localization: ASOC 2022
  • Undergraduate Research Assistant, August 2016 - September 2017
    • - Green MapReduce Clusters: ICC 2018, TPDS 2021

Teaching Experience

University of North Carolina at Chapel Hill
  • Graduate Teaching Assistant, August 2023 - Present
    • - Mobile Computing Systems: Android, iOS
    • - Files and Databases: SQLite, Python
Bangladesh University of Textiles
  • Lecturer, December 2018 - Present
    • - Programming Languages: C, MATLAB, Python
    • - Database and Information Systems: MySQL, Laravel
    • - Embedded Systems and IoT: Arduino, NodeMCU
    • - Data Analytics: Python, Machine Learning

Selected Projects

RF Sensing
  1. mmWave Anomaly Detection: Developed mmAnomaly, a multimodal framework that fuses mmWave radar sensing with camera-derived visual context to enhance anomaly detection. The system integrates visual feature extraction, generative modeling for cross-modal signal synthesis, and foundation-model-based accurate detection and localization.
    Skills: Multimodal Sensing, Generative Models, Vision-Language Models, Foundation Models, PyTorch
  2. Stationary People Counting: Counting people with mmWave radar in stationary and densely packed scenarios poses challenges due to the minimal motion cues. mmCounter was developed to detect breathing signals, analyze spatial distributions, and estimate occupancy using a foundation model.
    Skills: mmWave Sensing, Signal Processing, Foundation Models, Vision Transformer, PyTorch
  3. Privacy-Preserving Human Activity Recognition: Developed WiHAR, a camera-free system for recognizing human activities in privacy-sensitive environments using WiFi Channel State Information (CSI). The system generates Power Delay Profiles from CSI amplitude data and classifies activities using a foundation model.
    Skills: WiFi CSI Sensing, Signal Processing, Foundation Models, Vision Transformer, PyTorch
Computer Vision
  1. Embedded Object Detection: Object detection in embedded systems necessitates a balance between speed and accuracy under resource constraints. Developed DhakaNet, a deep learning architecture that optimizes YOLOv5 by reducing computational overhead and incorporating a multi-scale attention mechanism, enabling efficient and accurate inference on edge devices.
    Skills: Foundation Models, YOLOv5, PyTorch, Raspberry Pi, Laravel, MySQL
  2. Dense Crowd Localization: Dense crowd scenarios, such as the Hajj pilgrimage, pose challenges including occlusion, perspective distortion, and extreme density. Designed LC-Net, a deep learning model leveraging residual layers to mitigate vanishing gradients and dilated convolutions to preserve spatial resolution for accurate individual localization.
    Skills: CNN, Data Augmentation, Keras, AWS, Raspberry Pi, Laravel, MySQL
Machine Learning
  1. Green MapReduce Clusters: High energy consumption, particularly for cooling, is a major challenge in large-scale MapReduce clusters. Developed GMC, a machine learning-based solution that predicts energy usage of incoming jobs and dynamically optimizes the number of machines to improve energy efficiency without sacrificing performance.
    Skills: Distributed Systems, Machine Learning, Hadoop, SimGrid, WEKA, R, Arduino, Java, MySQL
Miscellaneous
  1. Heart Tracker: Built a standalone heart rate monitor using Atmega328P and MAX30102 sensor that captures IR signals, computes BPM, and plots real-time data on a 128×64 OLED—no PC required.
    Skills: Arduino, Heart Rate Sensor, OLED Display
  2. SnapStory: Built an Android app that generates illustrated micro-stories from photos using a Large Vision-Language Model via the Gemini API. The app captures an image, generates a story, segments it into sentences, and visualizes each sentence with AI-generated illustrations.
    Skills: Android Development, Gemini API
  3. Fast 2048 OCR: Built a fast OCR module to extract 4 × 4 board states from 2048 game screenshots using OpenCV and Tesseract OCR, served via FastAPI for real-time integration with an LLM gaming agent.
    Skills: Python, OpenCV, Tesseract OCR, FastAPI, JavaScript
  4. Bluetooth Messaging App: Developed macOS (BlueClient) and iOS (BlueApp) applications for Bluetooth Low Energy (BLE) messaging. Implemented a custom GATT service on macOS as the peripheral and an iOS central client for managing connection, subscription, and two-way data exchange.
    Skills: iOS Development, macOS Development, Bluetooth Low Energy
  5. Secured Messaging App: Integrated an AES-GCM encryption module with native C++ padding (via JNI) into a commercial XMPP-based Android instant messaging app to enhance secure message handling and transmission.
    Skills: Android Development, Cybersecurity, C++

Selected Publications

Conference Papers
  1. T. R. Toha, S.-J. L. Lu, and S. Nirjon, "mmCounter: Static People Counting in Dense Indoor Scenarios Using mmWave Radar," International Conference on Embedded Wireless Systems and Networks (EWSN). Leuven, Belgium: ACM, September 2025, accepted.
  2. M. H. R. Bhuiyan, I. M. Arafat, M. Rahaman, T. R. Toha, and S. M. M. Alam, "Devising a Vibration-Based Fault Detection System for Textile Machinery," in Proceedings of the 19th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous). Pittsburgh, USA: Springer, November 2022, pp. 3–20. [Online]. Available: https://doi.org/10.1007/978-3-031-34776-4_1
  3. T. R. Toha, M. Rahaman, S. I. Salim, M. Hossain, A. M. Sadri, and A. B. M. A. A. Islam, "DhakaNet: Unstructured Vehicle Detection using Limited Computational Resources," in Proceedings of the 21st IEEE International Conference on Data Mining (ICDM). Auckland, New Zealand: IEEE, December 2021, pp. 1367–1372. [Online]. Available: https://doi.org/10.1109/ICDM51629.2021.00172
  4. T. R. Toha, M. M. R. Lunar, A. S. M. Rizvi, N. Nurain, and A. B. M. A. A. Islam, "GMC: Greening MapReduce Clusters Considering both Computational Energy and Cooling Energy," in Proceedings of the 52nd IEEE International Conference on Communications (ICC). Kansas City, MO, USA: IEEE, May 2018, pp. 1–6. [Online]. Available: https://doi.org/10.1109/ICC.2018.8422113
  5. T. R. Toha, S. Estyak, T. A. Khan, T. Chakraborty, and A. B. M. A. A. Islam, "Sparse Mat: A Tale of Devising A Low-Cost Directional System for Pedestrian Counting," in Proceedings of the 3rd International Conference on Networking, Systems and Security (NSysS). Dhaka, Bangladesh: IEEE, January 2017, pp. 21–29. [Online]. Available: https://doi.org/10.1109/NSysS.2017.7885796 [Best Paper Award]
  6. T. R. Toha, M. M. Uddin, M. N. Reza, M. A. A. Maruf, A. Chakraborty, and A. B. M. A. A. Islam, "Towards Making an Anonymous and One-Stop Online Reporting System for Third-World Countries," in Proceedings of the 7th Annual Symposium on Computing for Development (DEV). Nairobi, Kenya: ACM, November 2016, pp. 24:1–24:4. [Online]. Available: https://doi.org/10.1145/3001913.3006633
Journal Papers
  1. A. D. Gupta, Z. Sadek, M. S. Hossain, T. R. Toha, A. Mondol, S. U. Habiba, and S. M. M. Alam, "An Approach to Automatic Fault Detection in Four-Point System for Knitted Fabric With Our Benchmark Dataset ISL-Knit," Heliyon, vol. 10, no. 17, p. E35931, September 2024. [Online]. Available: https://doi.org/10.1016/j.heliyon.2024.e35931 [Scopus: Q1]
  2. M. M. Mushfiq, T. R. Toha, S. I. Salim, A. Mostak, M. Rahaman, N. A. Al-Nabhan, A. M. Sadri, and A. B. M. A. A. Islam, "To Lane or Not to Lane? – Comparing On-Road Experiences in Developing and Developed Countries Using a New Simulator RoadBird," IEEE Transactions on Intelligent Transportation Systems (TITS), vol. 25, no. 8, pp. 8486–8498, June 2024. [Online]. Available: https://doi.org/10.1109/TITS.2024.3406731 [Scopus: Q1]
  3. T. R. Toha, N. A. Al-Nabhan, S. I. Salim, M. Rahaman, U. Kamal, and A. B. M. A. A. Islam, "LC-Net: Localized Counting Network for Extremely Dense Crowds," Applied Soft Computing Journal (ASOC), Elsevier, vol. 123, p. 108930, July 2022. [Online]. Available: https://doi.org/10.1016/j.asoc.2022.108930 [Scopus: Q1]
  4. T. R. Toha, A. S. M. Rizvi, J. Noor, M. A. Adnan, and A. B. M. A. A. Islam, "Towards Greening MapReduce Clusters Considering both Computation Energy and Cooling Energy," IEEE Transactions on Parallel and Distributed Systems (TPDS), vol. 32, no. 4, pp. 931–942, April 2021. [Online]. Available: https://doi.org/10.1109/TPDS.2020.3029724 [Scopus: Q1]