A scalable anomaly detection framework for fleet-wide material handler assets using high-resolution sensor data, combining statistical methods and LSTM Autoencoders to detect and predict failures.
Anomaly Detection LSTM Autoencoder Predictive Maintenance Time Series Analysis Isolation Forest Fleet Analytics
Read MoreUsing time domain force sensors data, ML model assist user in deciding successive adjustments to achieve surface parallelization & thereby extracting maximum power from the TENG device
Real-time sensor data Machine Learning Classifier TENG Testing Setup Process Automation Time domain analysis
Read Morepredicting the quality of the Portuguese red wine using its chemical properties
classification model Kaggle dataset
Read MoreUsing the publically available Nasa turbofan dataset, we have estimated the RUL of an aircraft engine.
Time series analysis RUL prediction Health Index
Read More