I am an AI researcher with a Ph.D. in Electrical Engineering and Computer Science from the Gwangju Institute of Science and Technology (GIST), South Korea (2017), where I specialized in user interest modeling in social media for personalized services. From December 2021 to February 2025, I worked as a Postdoctoral Researcher in the Information Systems Technology and Design pillar at the Singapore University of Technology and Design (SUTD). My research focused on AI-driven music and audio projects, including AI music generation for video and music emotion recognition. Prior to this, I served as a Postdoctoral Researcher in the Department of Software at Korea National University of Transportation (KNUT) (June 2019–November 2021) and as a Research Scientist in the Department of Radiology at Seoul National University Hospital (SNUH) (April 2018–March 2019). During these roles, I contributed to diverse projects such as medical image segmentation and classification, fruit freshness classification, face mask detection, anomaly detection, and knowledge distillation. Beyond academia, I have a deep passion for music. I have performed as a lounge pianist and composed solo piano pieces, some of which are available on platforms like iTunes and Spotify. I have also been engaged for piano performances at various corporate and private events.

Education

• Ph.D. Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST) (Mar. 2009 - Feb. 2017)
  • Thesis: User Interest Modeling in Social Media for Personalized Services
    Advisor: Prof. Hyunju Lee; Committee: Kuk-Jin Yoon, Sung-Hee Lee, Sung Chan Jun, Xing Xie
    Formal Advisor: Prof. Kwang Mong Sim
• B.S. Computer Engineering, Changwon National University (CWNU) (Mar. 2005 - Feb. 2009)

Work Experiences

• Post-doctoral Researcher, Singapore University of Technology and Design (SUTD), Singapore (Dev. 2021 - Feb. 2025)
• Post-doctoral Researcher, Korea National University of Transportation (KNUT), South Korea (Jun. 2019 - Nov. 2021)
• Research Scientist, Seoul National University Hospital (SNUH), Seoul, South Korea (Apr. 2018 - Mar. 2019)

Honors and Awards

• Best Paper Reward (Grand Prize), Next Generation Computing Conference (2021)
• First Runner Up, Online Hackathon “AI Data for Panoramic Image of Road Environment” (2020)
• Qualcomm-GIST Innovation Award (IT Research Paper Award), School of EECS, GIST (Supported by Qualcomm) (2016)
• National Full-ride Scholarships, GIST (2009-2016)
• Student Travel Award, IEEE International Conference on Data Engineering (ICDE) (2015)
• First Runner Up, CWNU Programming Contest (2006)
• CWNU “NURI” Scholarships for Outstanding Students , CWNU, (2006-2009)

Professional Activities

• Reviewer in IJCC, ICCAIS, IJCVR, IJMTM, INRT, and PLOS One
• Teaching Assistant, Courses: Computer programming (2005), Programming Language Project (2006), Data Processing (2006) in CNU

Publications

International Journal

• Are we there yet? A brief survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges
  Jaeyong Kang, Dorien Herremans
  In arXiv:2406.08809, 2025 (Under review)
• Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model
  Jaeyong Kang, Soujanya Poria, Dorien Herremans
  In Expert Systems with Applications, 2024
• Smart Insole-Based Classification of Alzheimer’s Disease Using Few-Shot Learning Facilitated by Multi-Scale Metric Learning
  Younghoon Jeon, Jaeyong Kang, Byeong C Kim, Kun Ho Lee, Jong-In Song, Jeonghwan Gwak
  In IEEE Transactions on Consumer Electronics, 2024
• Early Alzheimer’s Disease Diagnosis using Wearable Sensors and Multilevel Gait Assessment: A Machine Learning Ensemble Approach
  Younghoon Jeon, Jaeyong Kang, Byeong C Kim, Kun Ho Lee, Jong-In Song, Jeonghwan Gwak
  In IEEE Sensors Journal, 2023
• Recurrent Autoencoder Ensembles for Brake Operating Unit Anomaly Detection on Metro Vehicles
  Jaeyong Kang, Chul-Su Kim, Jeong Won Kang, Jeonghwan Gwak
  In Computers, Materials & Continua, 2023
• Ensemble of Multi-task Deep Convolutional Neural Networks using Transfer Learning for Fruit Freshness Classification
  Jaeyong Kang, Jeonghwan Gwak
  In Multimedia Tools and Applications, 2022
• Machine learning–based detection model of early Alzheimer's disease using wearable device and gait assessment
  YoungHoon Jeon, Thi Kieu Khanh Ho, Jaeyong Kang, Byeong C Kim, Kun Ho Lee, Jong‐In Song, Jeonghwan Gwak
  In Alzheimer's & Dementia, 2021
• Anomaly Detection of the Brake Operating Unit on Metro Vehicles Using a One-Class LSTM Autoencoder
  Jaeyong Kang, Chul-Su Kim, Jeong Won Kang, Jeonghwan Gwak
  In Applied Sciences, 2021
• MRI-based Brain Tumor Classification using Ensemble of Deep Features and Machine Learning Classifiers
  Jaeyong Kang, Zahid Ullah, Jeonghwan Gwak
  In Sensors, 2021
• Ensemble Learning of Lightweight Deep Learning Models using Knowledge Distillation for Image Classification
  Jaeyong Kang, Jeonghwan Gwak
  In Mathematics, 2020
• Using Artificial Intelligence Methods for Dental Image Analysis: State-of-the-Art Reviews
  Junho Ahn, Thi Kieu Khanh Ho, Jaeyong Kang, Jeonghwan Gwak
  In Journal of Medical Imaging and Health Informatics, 2020
• Ensemble of Instance Segmentation Models for Polyp Segmentation in Colonoscopy Images
  Jaeyong Kang, Jeonghwan Gwak
  In IEEE Access, 2019
• Deep Recurrent Convolutional Networks for Inferring User Interests from Social Media
  Jaeyong Kang, HongSeok Choi, Hyunju Lee
  In Journal of Intelligent Information Systems, 2019
• Modeling User Interest in Social Media using News Media and Wikipedia
  Jaeyong Kang, Hyunju Lee
  In Information Systems, 2017
• Ontology-enhanced Agent-based Cloud Service Discovery
  Jaeyong Kang, Kwang Mong Sim
  In International Journal of Cloud Computing, 2016
• A Multiagent Brokering Protocol for Supporting Grid Resource Discovery
  Jaeyong Kang, Kwang Mong Sim
  In Applied Intelligence, 2012

International Conference

• Towards Unified Music Emotion Recognition across Dimensional and Categorical Models
  Jaeyong Kang, Dorien Herremans
  In arXiv:2502.03979, 2025 (Under review)
• A domain-knowledge-inspired music embedding space and a novel attention mechanism for symbolic music modeling
  Zixun Guo, Jaeyong Kang, Dorien Herremans
  In Proc. of the AAAI Conference on Artificial Intelligence, 2023
• COVID-19 Detection with a Semi-Supervised Adversarial Autoencoder in Chest Radiographs
  Zahid Ullah, Thi Kieu Khanh Ho, Hyunseok Lim, Jaeyong Kang, Jeonghwan Gwak
  In Proc. of the 16th Asia Pacific International Conference on Information Science and Technology (APIC-IST 2021), 2021
• A CNN-LSTM Model for Alzheimer’s Disease Multi-Class Classification using Multichannel EEG
  Thi Kieu Khanh Ho, Hyunseok Lim, Jaeyong Kang, Jong-In Song, Jeonghwan Gwak
  In Proc. of the 16th Asia Pacific International Conference on Information Science and Technology (APIC-IST 2021), 2021 2021 (Outstanding paper award).
• Feature Integration for COVID-19 Classification using Chest Radiography
  Thi Kieu Khanh Ho, Zahid Ullah, Inki Kim, Hyunseok Lim, Jaeyong Kang, Jeonghwan Gwak
  In Proc. of the 16th Asia Pacific International Conference on Information Science and Technology (APIC-IST 2021), 2021
• KD-ResUNet++: Automatic Polyp Segmentation via Self-Knowledge Distillation
  Jaeyong Kang, Jeonghwan Gwak
  In Proc. of MediaEval, 2020
• A Cloud Portal with A Cloud Service Search Engine
  Jaeyong Kang, Kwang Mong Sim
  In Proc. of the 2011 International Conference on Information and Intelligent Computing (ICIIC’11), Hong Kong, 2011
• Towards Agents and Ontology for Cloud Service Discovery
  Jaeyong Kang, Kwang Mong Sim
  In Proc. of the 2011 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC’11), Beijing, China, 2011
• Ontology and Search Engine for Cloud Computing System
  Jaeyong Kang, Kwang Mong Sim
  In Proc. of the 2011 International Conference on System Science and Engineering (ICSSE’11), Macau, China, 2011
• Cloudle: An Ontology-enhanced Cloud Service Search Engine
  Jaeyong Kang, Kwang Mong Sim
  In Proc. of the 2010 International Workshop on Cloud Information System Engineering (CISE’10), Hong Kong, 2010
• Cloudle: A Multi-criteria Cloud Service Search Engine
  Jaeyong Kang, Kwang Mong Sim
  In Proc. of the 2010 IEEE Asia-Pacific Service Computing Conference (APSCC’10), Hangzhou, China, 2010
• Cloudle : An Agent-based Cloud Search Engine that Consults a Cloud Ontology
  Jaeyong Kang, Kwang Mong Sim
  In Proc. of the 2010 International Conference on Cloud Computing and Virtualization (CCV’10), Singapore, 2010
• A Brokering Protocol for Agent-Based Grid Resource Discovery
  Jaeyong Kang, Kwang Mong Sim
  In Proc. of the 2009 International Conference on Grid and Distributed Computing (GDC’09), Jeju Island, Korea, 2009

Korean Domestic Journal

• Deep Learning-Based Brain Tumor Classification in MRI images using Ensemble of Deep Features
  Jaeyong Kang, Jeonghwan Gwak
  In Journal of The Korea Society of Computer and Information, 2021
• Embedding similarity-based anomaly detection in crowd scenes via object-centric augmentation
  Jaeyong Kang, Jeonghwan Gwak
  In Journal of The Korea Society of Computer and Information, 2021
• Adaptive Face Mask Detection System based on Scene Complexity Analysis
  Jaeyong Kang, Jeonghwan Gwak
  In Journal of The Korea Society of Computer and Information, 2021

Korean Domestic Conference

• A Crack Detection of Wooden Cultural Assets using EfficientNet model
  Jaeyong Kang, Inki Kim, Hyunseok Lim, Jeonghwan Gwak
  In Proc. of the Korea Society of Computer and Information Summer Conference, Jeju, Korea, 2021
• A Bulge Detection Model in Cultural Asset images using Ensemble of Deep Features
  Jaeyong Kang, Inki Kim, Hyunseok Lim, Jeonghwan Gwak
  In Proc. of the Korea Society of Computer and Information Summer Conference, Jeju, Korea, 2021
• An Embedding Similarity-based Model for Detecting Displacement in Cultural Asset Images
  Jaeyong Kang, Inki Kim, Hyunseok Lim, Jeonghwan Gwak
  In Proc. of the Korea Society of Computer and Information Summer Conference, Jeju, Korea, 2021
• A Displacement Detection Model in Cultural Asset Images using Object-centric Augmentation
  Jaeyong Kang, Inki Kim, Hyunseok Lim, Jeonghwan Gwak
  In Proc. of the Korea Society of Computer and Information Summer Conference, Jeju, Korea, 2021
• An Ensemble Deep Learning Model for Measuring Displacement in Cultural Asset images
  Jaeyong Kang, Inki Kim, Hyunseok Lim, Jeonghwan Gwak
  In Proc. of the Korea Society of Computer and Information Summer Conference, Jeju, Korea, 2021
• Anomaly detection performance improvement technique through weight matrix-based optical flow equalization
  Hyunseok Lim, Inki Kim, Jaeyong Kang, Jeonghwan Gwak
  In Proc. of the Korea Society of Computer and Information Summer Conference, Jeju, Korea, 2021
• Anomaly detection system using ResUNet++ based image inpainting method
  Jaeyong Kang, Hyunseok Lim, Dongwook Min, Zahid Ullah, Jeonghwan Gwak
  In Next Generation Computing Conference, Gwangju, Korea, 2021
• Embedding similarity-based crowd anomaly detection using object-centric augmentation
  Jaeyong Kang, Hyunseok Lim, Xufeng Hu, Jeonghwan Gwak
  In Next Generation Computing Conference, Gwangju, Korea, 2021 (Best Paper Award)
• Effective data preprocessing for a reconstruction model-based anomaly detection
  Jaeyong Kang, Hyunseok Lim, Inki Kim, Zahid Ullah, Jeonghwan Gwak
  In Next Generation Computing Conference, Gwangju, Korea, 2021
• Cough Detection System Using Deep Learning
  Dongwook Min, Hyunseok Lim, Thi Kieu Khanh Ho, Jaeyong Kang, Jeonghwan Gwak
  In Next Generation Computing Conference, Gwangju, Korea, 2021
• Performance Comparison of SSIM loss function applied in the GAN-based anomaly detection system
  Hyunseok Lim, Mingyu Kim, Jaeyong Kang, Jeonghwan Gwak
  In Next Generation Computing Conference, Gwangju, Korea, 2021
• Imbalanced Dataset training techniques with Hard Negative Mining and Sample Selection
  Inki Kim, Hyunseok Lim, Thi Kieu Khanh Ho, Jaeyong Kang, Jeonghwan Gwak
  In Next Generation Computing Conference, Gwangju, Korea, 2021

Patents

• Method for Modeling User Interest in Social Media
  Hyunju Lee, Jaeyong Kang
  Korean Domestic Patent, 1017679510000, 2017