Donghyun Park

About

Donghyun Park is a leading researcher in edge computing, real-time fault detection, and intelligent monitoring systems for smart manufacturing. His most influential work, "LiReD: A Light-Weight Real-Time Fault Detection System for Edge Computing Using LSTM Recurrent Neural Networks" (2018, 167 citations), addresses a critical challenge in Industry 4.0: enabling accurate, low-latency fault detection without overwhelming cloud infrastructure. By designing a lightweight LSTM-based model optimized for edge devices, Park demonstrated that complex neural networks could operate efficiently on resource-constrained hardware, making real-time anomaly detection practical for smart factories. This contribution has been widely recognized for bridging the gap between deep learning accuracy and edge deployment feasibility. Park's research continues to advance the intersection of embedded systems, machine learning, and industrial automation, with his work cited by researchers developing fault-tolerant cyber-physical systems. His achievements highlight a commitment to creating scalable, real-time solutions that reduce reliance on centralized cloud computing, positioning him as a key innovator in the edge AI and smart manufacturing domains.

Research Focus

Key Achievements

Top Papers

1. 1
   LiReD: A Light-Weight Real-Time Fault Detection System for Edge Computing Using LSTM Recurrent Neural Networks

   167 citations · 2018

Key Collaborators

Contact & Links