About Me
Hello, I’m Amir!
In my PhD, I apply these methods primarily to clinical data (e.g., EEG, imaging), where I develop end-to-end pipelines for representation learning, model evaluation, and software tools used by researchers and clinicians. In parallel, I’ve worked on computer vision and generative modeling problems in industry, including image quality assessment and generative restoration during my ML internship at Dassault Systèmes.
My core interests are model robustness, interpretability, and deployment-aware ML especially for vision, generative models, and multimodal systems. I enjoy translating research ideas into usable software and collaborating across research and engineering teams.
personal information
- Full Name
- Amir Hossein Daraie
- D.o.b.
- 13th September 2000
- address
- 318 Hackerman Hall, Johns Hopkins University, 3400 North Charles Street, Baltimore MD 21218
- adaraie1 [at] jhu.edu / daraieamirh [at] gmail.com
- phone
- +1 (443) 388 4810
languages
English
Professional
Persian
Native
German
Intermediate
Professional Skills
- Deep learning
- Designing and training neural network models
- Computer Vision
- Extracting information from visual data
- Explainable AI (XAI)
- Interpreting and justifying model decisions
- Signal processing
- Cleaning, analyzing, transforming raw signals
Professional Skills
Python
CVML
C/C++
Computer Graphics
Prototyping
Control Theory and Signal Processing
work experience
2022 - Present
Johns Hopkins University School of Medicine
Ph.D. Student at Johns Hopkins
In my primary project, I developed a diagnostic system for seizure localization using intracranial EEG, combining dynamical network models and spectral entropy without supervised training. The method achieved 97.43% sensitivity and 92.48% precision over 1,000+ hours of patient data and provided objective, data-driven support for clinical decision-making.
Summer 2025
Dassault Systèmes
R&D Software Engineer Intern
Moreover, spend some time to built and evaluated generative models (VAEs, GANs, and diffusion-based approaches) for image restoration and outpainting tasks, and trained CNN- and ViT-based architectures on large image datasets.
2014 - 2019
RoboCup Federation
Engineer and team leader
Developed software and hardware for autonomous rescue robots, programmed and implemented navigation algorithms, and mentored over 10 students in programming and PCB design.
Education
2022 - Present
Johns Hopkins University
Ph.D. in Biomedical EngineeringAdvisors: Dr. Sridevi V. Sarma, Dr. Adam S. Charles, Dr. Joon Yi-Kang (MD)
Area of research: Epilepsy monitoring and treatment
2022 - Present
Johns Hopkins University
Double masters degree in BME & Applied Mathematics and StatisticsArea of focus: Statistics and Statistical Learning
2018 - 2022
Amirkabir University of Technology
Bachelors degree in Biomedical EngineeringMinor in Electrical Engineering
GPA: 3.8/4
Clients
References
During Amir’s period in Donders Sleep and Memory Lab from July to October 2021, Amir gained extensive experience in wearable sleep sensor technology and big sleep EEG data analysis. He played a crucial role in developing a real-time controller for a sleep EEG wearable, demonstrating exceptional talent, motivation, and learning abilities. Amir quickly mastered necessary sleep research skills, asked insightful questions, and maintained a positive, proactive attitude. He exhibited outstanding independent thinking, problem-solving skills, and the ability to meet deadlines under high workload conditions. Despite the challenges of the pandemic, Amir’s enthusiasm, teamwork, and effective communication made him an invaluable asset to our lab. I highly recommend him and believe he will be a valuable addition to any academic environment.
Interests
Blog
For those who are interested in latest trends in graphic and industrial design may be found useful and intersting to read my Blog. I am writing daily posts which includes freebies and giveaways as well. I would be glad to any comment and will appreciate your questions and feedback.