About Me
Hello! I am Tahsin. I am a PhD student in the department of ECE, University of Florida. I am working under Professor Navid Asadi in the FICS lab. I am currently working on physical assurance for AI and package security. My research interests are deep learning, computer vision and hardware security.
I graduated in Electrical and Electronic Engineering from Bangladesh University of Engineering and Technology (BUET) in 2017. After graduation, I worked as Machine Learning Engineer in Semion Limited and AI Samurai, served as an RA in the MHealth Lab, Department of Biomedical Engineering, BUET and mentored several undergraduate students in their thesis and research works.
I love to read science-fiction books, write short stories, watch movies.
Research Interests
- Machine Learning
- Deep Learning
- Computer Vision
- Sequence Modeling
- Natural Language Processing
Educations
PhD in Electrical and Electronics Engineering, 2021
University of FloridaMSc in Electrical and Electronics Engineering, 2019
Bangladesh University of Engineering and TechnologyBSc in Electrical and Electronics Engineering, 2017
Bangladesh University of Engineering and TechnologyMajor Publications
- Md Mahfuz Al Hasan, Mohammad Tahsin Mostafiz, Thomas An Lee, Jake Julia, Nidish Vashistha, Shayan Taheri, Navid Asadi Zanjani, " EVHA: Explainable Vision System for Hardware Testing and Assurance - An Overview", ACM Journal on Emerging Technologies in Computing Systems
- Tahsin Mostafiz, Dr. Khalid Ashraf, " Pathology Extraction from Chest X-Ray Radiology Reports: A Performance Study", arXiv 1812.02305
- Tahsin Mostafiz, Ismat Jarin, Dr. Shaikh A. Fattah and Dr. Celia Shahnaz, "Retinal Blood Vessel Segmentation using Residual Block Incorporated U-Net Architecture and Fuzzy Inference System", 2018 4th IEEE WIECON-ECE Conference
- A. Mitra, T. Mostafiz, R. Ur Rashid, "Photoplay: An Android Application to Stimulate Children’s Cognitive Development", 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC)
Selected Projects
-
- RadAssist, A Web Based Tool for Brain Hemorrhage Detection and Localization
I worked on developing the backend deep learning model for the web based tool RadAssist. It assists doctors in detecting and localizing abnormalities and hemorrhage from brain CT scan images. A survey tool as well is added to this web app too. This project abstract has been accepted at the SIIM 2020 Conference! Congratulations to everyone who worked, guided and supported us.
- An Inference Tool for SemRad, a Teleradiology Solution Software
A complete teleradiology solution that incorporates deep learning models to detect chest abnormalities. The framework is JavaFX and SQL is at backend. This was a professional project. I designed an inference tool for abnormality detection and localization in Chest X-Rays Based on MobileNet Algorithm. This was later integrated into the software.
- Class Activation Mapping(CAM) for SemRad, a Teleradiology Solution Software
A complete teleradiology solution that incorporates deep learning models to detect chest abnormalities. The framework is JavaFX and SQL is at backend. This was a professional project. I designed a Class Activation Mapping tool based on this paper for localization of abnormalities in Chest X-Rays. This was later integrated into the software.
- Retinal Vessel segmentation using Autoencoder
This was performed on DRIVE dataset, using Unet based architecture with residual blocks. It was part of a research work which later got accepted in 4th IEEE WIECON-ECE Conference 2018. Details are in the Publications
- Pathology Extraction from Chest X-Ray Radiological Reports
Using the NER method described here, I created a model that can extract pathology terms from EHR reports. This is an ongoing research project
- Development of a Hardware for the Measurement of THD in Power System
I developed a device using Raspeberry Pi, Arduino and Transformer that can measure total harmonic distortion(THD) present in the power system. This was a part of our undergrad thesis.
- PhotoPlay, An android app for children
This app was designed to help children stimulate their cognitive development. It uses an inception v3 model as it's backbone, pretrained on ImageNet dataset and fine-tuned on additional data. It was part of a research work which later got accepted in 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC). Details are in the Publications section.
- Differential Diagnoses, an Amazon Alexa skill
This Alexa skill can speak out all differential diagnoses for user fed symptoms. It has a comprehensive list of 1700 differential diagnoses and their corresponding mapping to symptoms. Development of this skill is still in progress.
- Identification of Risk Factors for Heart Disease in Diabetic Patients
Using bidirectional LSTM and CRF based entity recognition model, risk factors were detected for heart diseases in diabetic patients. The dataset was from i2b2. This was a professional project.
- semDDX, an Android app
This is an android app that helps to 1) easily navigate the vast landscape of differential diagnoses 2) learn DD easily for medical students 3) normalize and standardize communication between physicians. The app is available at Google Play Store.
- Gate Level Design, Cell Layout, and Simulation of 10-bit Priority Encoder.
This was the final project for VLSI II Laboratory. This was an academic project.
- Gate level design and simulation of an 8-bit Microprocessor (Modified SAP)
This was the final project for Microprocessor and Interfacing Laboratory. This was an academic project.
- Interface and Gaming Console Design for A Computer and An Android Game.
A 2-D Car racing game for PC and Android devices (Phone, Tablet, Smart TV etc.) with external control system and an user friendly gaming interface was designed. Detail explanation and demo are available here on Youtube.This was an academic project for Control System Lab.
- Home Security System Via Push Message Service
Arduino along with GSM module, LCD panel, proximity and sonar sensors were used for this project. This was an academic project for Communication I Lab.
- Gate level design and simulation of a 4-bit Arithmetic Logic Unit
This was the final project for Digital Electronics Laboratory. This was an academic project.
- An Oscilloscope for the Measurement of Current and Voltage.
This was the final project for Measurement and Instrumentation Laboratory. I made a 2 channel oscilloscope that can simultaneously measure and plot voltage and current values on a Graphical User Interface designed by me. It was also the last undergrad project I worked on.
- SONAR Controlled Flappy Bird
The infamous Flappy Bird could be played by waving hand in this project. Arduino along with SONAR sensor were used for this project. A demo is available here on Youtube.
- Home Automation System
This was a group project. We made a home automation system that had electric fans and lights as test loads and an android app was built to control the loads from a distance. This prototype used bluetooth to connect.
- RadAssist, A Web Based Tool for Brain Hemorrhage Detection and Localization