Seulgi Kim
Papers
1
Total Citations
167
H-Index
1
About
Seulgi Kim is a leading researcher in edge computing, artificial intelligence, and intelligent fault detection systems. Her most influential work, "LiReD: A Light-Weight Real-Time Fault Detection System for Edge Computing Using LSTM Recurrent Neural Networks" (167 citations), introduced a groundbreaking approach to real-time machine monitoring in smart factories. By deploying lightweight LSTM-based neural networks directly on edge devices, Kim solved the critical challenge of processing massive sensor data without relying on cloud servers, dramatically reducing latency and computing resource requirements. This innovation enables continuous, real-time fault analysis in industrial environments where immediate detection is essential for preventing equipment failures and production downtime. Kim's contributions bridge the gap between advanced deep learning techniques and practical edge computing constraints, making her work highly cited by researchers in industrial IoT, predictive maintenance, and embedded AI systems. Her research continues to shape the development of efficient, real-time monitoring solutions that balance accuracy with computational efficiency, establishing her as a key figure in the evolution of smart manufacturing and edge intelligence.
Research Focus
Key Achievements
Top Papers
- 1