Aydin Ayanzadeh
AI Expert VLM Specialist LLM Researcher
Ph.D. Student in Computer Science | M.S. Graduate
University of Maryland, Baltimore County
About Me
I am a Ph.D. student in Computer Science at the University of Maryland, Baltimore County, with an M.S. in Computer Science from the same institution. I have a strong focus on Computer Vision, Medical Image Analysis, and Multimodal Learning. My research interests span across developing innovative solutions for medical imaging challenges, particularly in segmentation and classification tasks.
Research Philosophy
My research is driven by the belief that artificial intelligence should serve humanity by solving real-world problems. I focus on developing accessible AI solutions that can make a meaningful impact in healthcare, environmental protection, and assistive technologies. Through interdisciplinary collaboration and cutting-edge research, I aim to bridge the gap between theoretical advances and practical applications.
Special Focus on Accessibility: I am passionate about creating inclusive technologies, particularly AI-powered navigation systems for individuals with blindness or low vision, ensuring that technological advances benefit everyone.
Research Interests
Current Focus
Accessibility AI
Developing LLM-based navigation systems for individuals with visual impairments
Environmental AI
Creating Vision-Language Models for early wildfire detection and environmental monitoring
Medical AI
Advancing deep learning techniques for medical image analysis and diagnosis
Research Approach
Collaborative
Working with interdisciplinary teams to tackle complex problems
Innovative
Exploring novel methodologies and cutting-edge technologies
Impactful
Focusing on solutions that can make a real-world difference
Mentoring
Guiding students and sharing knowledge with the community
Education
Ph.D. in Computer Science
University of Maryland, Baltimore County
GPA: 3.78/4.00
Courses: Advanced Algorithms, Knowledge Graphs, Machine Learning, Computer Vision, Data Privacy
M.S. in Computer Science
University of Maryland, Baltimore County
GPA: 3.78/4.00
Courses: Advanced Algorithms, Knowledge Graphs, Machine Learning, Computer Vision, Data Privacy
M.Sc. in Applied Informatics
Istanbul Technical University, Turkey
GPA: 3.75/4.00
Courses: Image Processing, Applied Informatics in Structural Biology, Fuzzy Logic
B.Sc. in Computer Science
University of Tabriz, Iran
GPA: 3.11/4.00
Experience
Research Experience
CORAL LAB
Dec 2022 - PresentResearcher - Advisor: Tim Oates
Baltimore, MD
- Developing a Multi-Task Network for Segmenting and Classifying Medical Images on Imbalanced Datasets
SP4CING Lab
Sept 2018 - Dec 2021Research Assistant - Co-Advisors: Behcet Ugur Toreyin and Devrim Unay
Istanbul, Turkey
- Introduced a novel auto-encoder architecture by applying the modified ResNet-18 as an encoding module
Vodafone FutureLab
May 2019 - Jan 2022Research Fellowship - Supervisor: Mehmet Basaran
Istanbul, Turkey
- Introduced Res-VGAE, a variational graph auto-encoder with residual connections
- Proposed dynamic Word2Vec to examine social structure of Vodafone customers
Tubitak 1001 (Grant #119E578)
Oct 2020 - Jan 2022Research Assistant - Supervisor: Devrim Unay
Izmir, Turkey
Project: Development of Image Processing and Machine Learning based Tools for Analysis of Phase-Contrast Optical Microscopy Time Series Images
- Perform qualitative and quantitative analysis of morphology and movement of cells from phase-contrast optical microscopy time series
- Improved cell tracking with enhanced training efficiency by designing a novel auto-encoder architecture to elevate training time, resiliency of results in the prediction step, and avoiding overfitting on segmentation and tracking tasks
Arcelik Global Co.
Dec 2019 - Dec 2020Researcher - Supervisor: Nazim Kemal Ure
Istanbul, Turkey
Project: Optimization of Multi-Task Network on Surveillance Cameras
- Proposed an optimized multi-task model compatible with edge devices and accelerated the original architecture by applying quantization in the cores of the architecture
- Accelerated the total inference time of the model from 2 fps to 18 fps
Project: Model Compression for Efficient Video Processing on Edge Devices
- Designed and developed multi-task network enterprise to perform people monitoring with surveillance cameras on edge devices
- Optimized the employed networks by quantization approach, especially with Intel OpenVINO toolkit
SiMiT Lab
Apr 2017 - June 2018Researcher (Unpaid) - Supervisor: Hazim Kemal Ekenel
Istanbul, Turkey
Project: Kaggle Dog Breeds Identification with the transfer learning approach
- Leveraged state-of-the-art models on Imagenet data sets, and employed the pre-trained model and learned weights to extract the feature from the Kaggle Dog breed identification dataset
Project: Google Cloud YouTube-8M Video Understanding Challenge
- Examined Deep Neural Networks with skip connections for Video Understanding Challenge on Kaggle
Teaching & Mentoring
Teaching Philosophy
I believe in creating an inclusive and engaging learning environment where students can develop both technical skills and critical thinking abilities. My approach combines hands-on experience with theoretical understanding, encouraging students to explore real-world applications of computer science concepts.
Teaching Experience
Computer Organization and Assembly Language Programming (CMSC 313)
Spring 2022 & Spring 2024Graduate Teaching Assistant for undergraduate computer organization course covering assembly language programming, computer architecture, and low-level system design.
Data Structures (CMSC 341)
Summer 2022Teaching Assistant for fundamental data structures course covering arrays, linked lists, stacks, queues, trees, and graphs with algorithm analysis.
Introduction to Data Science (CMSC 691)
Fall 2022 - Spring 2023Teaching Assistant for graduate-level data science course covering statistical analysis, machine learning, and data visualization techniques.
Principles of Artificial Intelligence (CMSC 671)
Fall 2023Teaching Assistant for graduate AI course covering search algorithms, knowledge representation, machine learning, and neural networks.
Mentoring & Student Guidance
Undergraduate Research
Mentoring undergraduate students in research projects related to computer vision and machine learning applications.
Technical Guidance
Providing technical support and guidance to students working on programming projects and assignments.
Career Development
Advising students on career paths in computer science, research opportunities, and graduate school applications.
Project Supervision
Supervising capstone projects and independent study courses in AI and computer vision domains.
Publications
Journal Publications
PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation
Expert Systems with Applications, vol. 213, 119040, 2023
Improved cell segmentation using deep learning in label-free optical microscopy images
Turkish Journal of Electrical Engineering and Computer Sciences, vol. 29, no. 8, pp. 2855-2868, 2021
Representation learning using graph autoencoders with residual connections
arXiv preprint arXiv:2105.00695, 2021
A New Class of Scaling Matrices for Scaled Trust Region Algorithms
arXiv preprint arXiv:1904.09209, 2019
Conference Publications
Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images
2020 28th Signal Processing and Communications Applications Conference (SIU), pp. 1-4, IEEE, 2020
Graph Embedding For Link Prediction Using Residual Variational Graph Autoencoders
2020 28th Signal Processing and Communications Applications Conference (SIU), pp. 1-4, IEEE, 2020
Cell Segmentation of 2D Phase-Contrast Microscopy Images with Deep Learning Method
2019 Medical Technologies Congress (TIPTEKNO), pp. 1-4, IEEE, 2019
Automated Segmentation of Cells in Phase Contrast Optical Microscopy Time Series Images
2019 Medical Technologies Congress (TIPTEKNO), pp. 1-4, IEEE, 2019
A Modified Ant colony Based Approach to Digital Image Edge Detection
2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI), pp. 726-729, IEEE, 2015
Gaussian Three-Dimensional kernel SVM for Edge Detection Applications
International Conference on New Research Findings in Electrical Engineering and Computer Science, Tehran, 2015
Book Chapters
Automated analysis of phase-contrast optical microscopy time-lapse images: application to wound healing and cell motility assays of breast cancer
In Diagnostic Biomedical Signal and Image Processing Applications with Deep Learning Methods, pp. 33-57, Academic Press, 2023
Preprints & Current Research
LLM-Based Indoor Navigation System for Individuals with Blindness or Low Vision
STARS Celebration Conference (2024), CMD-IT/ACM Richard Tapia Conference. (Planned submission to NeurIPS 2025/AAAI 2026)
WildfireVLM: AI-Powered Analysis for Early Wildfire Detection and Risk Assessment Using Satellite Imagery
(Planned submission to the MDP Forest Special Issue)
Journal Reviewer
AI & Machine Learning Journals
Computer Vision & Signal Processing
Note: * indicates corresponding author. For a complete list of publications and citations, please visit my Google Scholar profile.
Research Projects
Current Research
LLM-Based Indoor Navigation System for Individuals with Blindness or Low Vision
Developing an innovative indoor navigation system using Large Language Models to assist individuals with visual impairments. The system combines computer vision, natural language processing, and spatial reasoning to provide real-time navigation guidance and environmental awareness.
WildfireVLM: AI-Powered Analysis for Early Wildfire Detection and Risk Assessment
Developing a Vision-Language Model system for early wildfire detection using satellite imagery. The project focuses on creating an AI-powered solution that can analyze environmental data and provide early warning systems for wildfire prevention and management.
Completed Research
PURSUhInT: Knowledge Distillation for Efficient Deep Learning
Developed a novel approach for knowledge distillation by identifying informative hint points based on layer clustering. This method significantly improves the efficiency of knowledge transfer from large teacher models to smaller student models.
Deep Learning for Medical Image Segmentation
Developed advanced deep learning pipelines for cell segmentation in label-free optical microscopy images. The work includes both traditional CNN approaches and novel architectures for improved accuracy in medical imaging applications.
Graph Autoencoders for Representation Learning
Investigated residual connections in graph autoencoders for improved representation learning on graph-structured data. The work contributes to the field of graph neural networks and unsupervised learning.
Projects
Explore my technical implementations and software development projects
Medical Image Segmentation
Multi-task deep learning platform for automated medical image analysis with advanced handling of imbalanced datasets.
LLM Indoor Navigation System
AI-powered navigation system using GPT-4 and computer vision to assist visually impaired individuals in indoor environments.
Knowledge Distillation Framework
Novel hint-based knowledge distillation framework achieving 2.5x model compression with minimal accuracy loss.
Vision-Language Medical Models
Custom CLIP-based architecture for medical imaging with zero-shot classification and report generation capabilities.
Graph Autoencoder Framework
Advanced GNN implementation with residual connections for improved representation learning on graph-structured data.
ML Data Pipeline System
Scalable data processing pipeline handling 10TB+ daily with automated preprocessing and feature engineering.
Technical Skills
Languages
Frameworks & Libraries
Tools & Platforms
Awards & Honors
International Alumni Endowed Scholarship
University of Maryland, Baltimore County (UMBC), USA
May 2025Prestigious scholarship recognizing outstanding academic achievement and international student contributions to the UMBC community.
Research Fellowship
Vodafone FutureLab, Turkey
May 2019Competitive fellowship for advanced research in telecommunications and technology innovation.
Top 1% Ranking
Nationwide Universities Entrance Exam, Iran
Sept 2011Achieved top 1% ranking among 500,000+ students in the highly competitive national university entrance examination.
Highlighted Certificates
- AI for Medicine (3-course specialization) - deeplearning.ai on Coursera
- Deep Learning (5-course specialization) - deeplearning.ai on Coursera
- Image and Video Processing - Duke University on Coursera
Contact Me
Interested in research collaborations, academic opportunities, or discussing innovative ideas in AI and Computer Vision? I'd be happy to connect.
As a researcher in accessibility AI, this website is designed to be accessible to everyone. Press Alt + A for accessibility options.