⌘+K

Pulse Explore Communities Researchers Journals

Home Communities Explore

June 11, 2026Transactions of the Korean Society of Mechanical Engineers B

Development of a Memory-Efficient AI-based Anomaly Detection Algorithm for Semiconductor Thermal Process

Junho Hwang Sunuwe Kim Sangwook Park

View at Publisher

Ask AI

Bookmark

Share

Key Points

The aim is to develop a simple, memory-efficient anomaly detection algorithm for semiconductor thermal processes.
Developed an AI-based algorithm using multiple sensors for anomaly detection.
Optimized the algorithm to use only 27K parameters with fast performance.
Achieved a learning time of under 10 ms per epoch.
Attained an average F1 score of 91.67% for anomaly detection.
Utilized significantly fewer parameters compared to existing algorithms.
Demonstrated a viable solution for real-world semiconductor applications.

Implication

Develops a simple anomaly detection algorithm in semiconductors, suggesting improved performance with fewer resources.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Hwang et al. (2026) studied this question.

synapsesocial.com/papers/6a2cf34dfaef96ed7f055cb8 https://doi.org/10.3795/ksme-b.2026.50.6.295

View at Publisher

Ask AI

Bookmark

Share

Keep reading

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Autoencoder-based detector for distinguishing process anomaly and sensor failure2024 · 11 citations
2Research on Quality Anomaly Detection and Early Warning of Semiconductor Chip Manufacturing Process Based on Machine Learning2025
3Unsupervised Learning-Based Clustering Algorithm for Potential Outlier Detection in Semiconductor Manufacturing ProcessOriginal Research · 2026
4Topology-based Lightweight Anomaly Detection via Functional Patch Decomposition in Industrial Control SystemsOriginal Research · 2026
5The Nano Paradox: AI and Machine Learning in Predicting Semiconductor DegradationOriginal Research · 2026

AI-Powered Predictive Analytics for Semiconductor Manufacturing: Case Studies and Industry Applications2024
Memory-Augmented Prediction with Cross-Iteration Alignment for Anomaly Signal Detection in the Integrated Test of Aerospace Products2026
Constrained Dynamic Time Warping and Polyline Distance for Anomaly Detection in Semiconductor Manufacturing2026
Centrifugal Pump Design Using Computational Fluid Dynamics: Effects of Impeller Blade Length and Thickness on Centrifugal Pump PerformanceTransactions of the Korean Society of Mechanical Engineers B · 2026
Enhancing the Performance of Graphene Oxide-based Hydrovoltaic Generators via Phosphoric Acid IncorportationTransactions of the Korean Society of Mechanical Engineers B · 2026

TMore from Transactions of the Korean Society of Mechanical Engineers B