STAD-FEBTE, a Shallow and Supervised Framework for Time Series Anomaly Detection by Automatic Feature Engineering, Balancing, and Tree-Based Ensembles: An Industrial Case Study

Computer Science

• Industrial Case 100%
• Anomaly Detection 100%
• Class Imbalance 100%
• Case Study 100%
• Sensor Measurement 100%
• Real-World Problem 50%
• Temporal Characteristic 50%
• Large Data Set 50%
• Network Architecture 50%
• Internal Network 50%
• Deep Learning Model 50%
• multi sensor 50%
• Deep Learning 50%
• Industrial System 50%
• Collected Data 50%
• Time Series Data 50%
• Sampling Frequency 50%
• Production Line 50%
• Multivariate Data 50%

Keyphrases

• Feature Tree 100%
• Automatic Feature Engineering 100%
• Class Imbalance 66%
• Categorical Features 33%
• Engineering Pipeline 33%