Hello, I'm

Xijia Zhao

Ph.D. Student in Electrical & Computer Engineering

Case Western Reserve University

About Me

I am a third-year Ph.D. student in Electrical and Computer Engineering at Case Western Reserve University. My research focuses on scalable machine learning methods (e.g., self-supervised learning, continual learning), efficient on-device learning, and large-scale model applications in time-series.

Work Experience

National Science Foundation I-Corps

Feb 2025 – May 2025
  • Served as the entrepreneurial lead for the commercialization of our edge-device product
  • Conducted customer discovery, market validation, and business model development

General Motors

Jan 2024 – Aug 2024
  • Developed ML models based on ViT and CNN for in-line anomaly detection in GM's battery welding
  • Investigated large-scale ML models for in-line smart manufacturing applications

University of Kentucky

Sep 2021 – Jun 2022
  • Built a cost-effective system for machine data acquisition and analysis, including an edge device capable of neural network inference for time-series and model updates

Projects

Edge-Device for Intelligent IoT Monitoring

On-Board Continual Learning

Designed a custom edge-device board integrating sensors and a microprocessor for real-time IoT monitoring. The system supports optimized on-board machine learning model training and adaptation, enabling continual learning directly at the edge level without full cloud dependency.

Edge Computing Continual Learning IoT Embedded ML

Self-Supervised Learning for Welding Image Analysis

Multi-Level Contrastive Learning

Developed multi-level contrastive learning methods (MOCO and DINO variants) for GM's large-scale welding image dataset. The proposed multi-scale paradigm improved representation quality and transfer performance across defect classification tasks.

Self-Supervised Learning Computer Vision MOCO DINO

Publications

2026

Sotubadi, S.V., A. Hosseinzadeh, H. Ghassemi-Armaki, M.M. Pour, J. Ma, X. Zhao, J.T. Bracey, B.E. Carlson, and P.E. Wang

"Harnessing unlabeled plant data and labeled lab data for enhanced quality prediction in laser welding"

Journal of Manufacturing Processes, 157, pp. 1015–1034.

2025

Zhao, X., H. Ghassemi-Armaki, B. Carlson, and P. Wang

"Unleashing the Power of Unlabeled Plant Data: A Hierarchical Contrastive Learning Framework for Dynamic Manufacturing Process Monitoring"

Journal of Manufacturing Systems, 83, pp. 483–493.

2025

Wang, P., H. Ghassemi-Armaki, M. Pour, Zhao, X., J. Ma, K. Sattari, and B. Carlson

"Applicable and Generalizable Machine Learning for Intelligent Welding in Automotive Manufacturing"

Welding in the World, pp. 1–36.

2025

York, E., Zhao, X., H. Ghassemi-Armaki, B. Carlson, and P. Wang

"Transfer Learning-Enhanced Transformer for Virtual Process Sensing in Resistance Spot Welding"

Manufacturing Letters, 45, pp. 13–16.

2024

Zhao, X. and P. Wang

"A Deployable Edge Computing Solution for Machine Condition Monitoring"

2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). Glasgow, United Kingdom, pp. 1–6.

2024

Zhao, X., J. Kershaw, M. Pour, J. Ma, H. Ghassemi-Armaki, B. Carlson, and P. Wang

"Efficient and Generalizable Machine Learning for Inline Defect Detection in Battery Laser Welding"

International Conference on Precision Engineering. Sendai, Japan.

Education

Ph.D.

Electrical and Computer Engineering

Case Western Reserve University

2024 – Present

B.S.

Electrical Engineering

University of Kentucky

2021 – 2024

B.S.

Electrical Engineering

Beijing University of Technology

2019 – 2023

Skills

AI & Machine Learning

Self-Supervised Learning Continual Learning Computer Vision LLM Fine-tuning On-Device ML

Programming

Python C C++ ARM Assembly

Tools & Platforms

AWS Embedded Systems LaTeX Cloud Deployment

Languages & Interests

English Mandarin Basketball Guitar Saxophone