Anomaly detection and analysis by a gradient boosting trees and neural network ensemble model

Autor:	Tanaka Hisanori, Takayuki Nishimura
Rok vydání:	2020
Předmět:	Variable (computer science) Boosting (machine learning) Ensemble forecasting Artificial neural network business.industry Computer science Semiconductor device modeling Pattern recognition Anomaly detection Artificial intelligence Construct (python library) Gradient boosting business
Zdroj:	2020 International Symposium on Semiconductor Manufacturing (ISSM).
DOI:	10.1109/issm51728.2020.9377494
Popis:	In this paper, we describe a method for predicting product characteristics, its evaluation results, and application examples. Process equipment data is selected as an explanatory variable. By using an ensemble of gradient boosting trees and neural networks, we were able to construct a prediction model with higher accuracy than the conventional model. In addition, anomaly detection and analysis based on this prediction model are discussed.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::69b949d6df4b90ebc3755c4288d15796 https://doi.org/10.1109/issm51728.2020.9377494 Zobrazit plný text záznamu