home >  
Meet Faculty
meet
Sarun Gulyanon
February 19, 2025
Yan Trostin
Meet
Sarun Gulyanon

Expertise:

Computer Vision | Machine Learning | Biomedical Imaging | Data Science

Pronouns
he/him
Fun Fact
I was a member of a band called FEN (Face Eye Nice), where I was the keyboardist.
Courses
  •  AIC-301 SYMBOLIC AI
  •  18-793 IMAGE AND VIDEO PROCESSING
  •  18-900/41-900 RESEARCH, ENTREPRENEURSHIP and INNOVATION

When it comes to teaching, nothing is more fulfilling than watching young people succeed, grow, and achieve their goals. I’m deeply committed to fostering a community of AI and technology enthusiasts and helping them reach their full potential. For me, learning is not just about gaining knowledge but also about sharing it and exploring new frontiers together.

My passion for technology and computer science began with participating in Olympiad inInformatics camps, where I honed my programming skills and gained opportunities to explore computer science further.

During my undergraduate studies at the University of Edinburgh, I had the privilege of taking a computer vision course with Prof. Bob Fisher, whose teaching inspired me to delve deeper into this fascinating field. Building on my interest in bioinformatics, I decided to pursue a PhD focusing on neuron morphology analysis—including reconstruction, centerline extraction, segmentation, and multi-modal comparison—under the guidance of Dr. Gavriil Tsechpenakis.

After earning my PhD, I spent six years at Thammasat University, teaching courses ranging from Python programming and linear algebra to machine learning and computer vision. I was part of the Data Science and Innovation program, which focuses on applying data science to social sciences. While I enjoyed this role, my true research passion lies in computer vision and biomedical imaging, which ultimately led me to CMKL University.

My passion for computer vision has only deepened over time. With AI driving innovation, computer vision has evolved from a standalone discipline into one that thrives on integration, such as with multimodal models that combine diverse data types to uncover new insights. The rapid pace of AI research brings endless opportunities, new directions, and ground breaking applications. It’s an incredibly exciting time to be part of this field!

Education
  • Ph.D. in Computer Science, Purdue University, May 2018
    PhD Dissertation: "Model and Appearance Based Analysis of Neuronal Morphology from Different Microscopy Imaging Modalities"
  • M.S. in Computer and Information Science, Purdue University, May 2016
  • B.Sc. in Computer Science, University of Edinburgh, Jul 20134th Year Project: Machine Learning Tools for Cardio Vascular Data Analysis
Current Research
  • Healthcare: I am working on predictive models and causal machine learning to assess the risk of child violence. My research involves using machine learning to predict instances of child violence and conducting factor analysis to inform policies aimed at prevention.
  • Signal processing: In collaboration with Western Digital Storage Technologies (Thailand) Ltd., I am developing machine learning models to analyze signals from Raman and FTIR spectra. The goal is to automate the classification of material types for contamination analysis in hard disk drives.
  • Applied Data Science: In collaboration with BTS Group Holdings PCL, I am building a price elasticity model to simulate how pricing adjustments impact ridership behavior and demand.
Selected Publications
  • S. Gulyanon et al., “Denoising Raman Spectra Using Autoencoder for Improved Analysis of Contamination in HDD,”  in IEEE Access, 2024, DOI: 10.1109/ACCESS.2024.3441824.
  • He L.; Gulyanon, S.; Skanata, M.M.; Karagyozov, D.; Heckscher, E.S.; Krieg, M.;Tsechpenakis, G.; Gershow, M.; Tracey, W.D., Jr., “Direction selectivity in Drosophila proprioceptors requires the mechanosensory channel TMC,” Current Biology, 29(6):945-956.e3, 2019. DOI: 10.1016/j.cub.2019.02.025.