H2O for IoT - Jo-Fai (Joe) Chow, H2O
1 like437 views
The document outlines a presentation on H2O.ai, focusing on its applications in IoT, predictive maintenance, and anomaly detection. It includes a detailed agenda with talks on machine learning tasks, H2O’s interfaces, and the demonstration of model building techniques. Use cases, such as the SECOM dataset for predictive maintenance, are explored with steps for model evaluation and anomaly detection using deep autoencoders.
H2O for IoT - Jo-Fai (Joe) Chow, H2O
- 1. H2O for Internet of Things Jo-fai (Joe) Chow Data Scientist joe@h2o.ai @matlabulous Data Science Milan Politecnico di Milano 10th October, 2016
- 2. Agenda • First Talk (25 mins) o About H2O.ai o Demo • A Simple Classification Task • H2O’s Web Interface o Why H2O? • Our Community • Our Customers o What’s Next? • New H2O Features • Second Talk (25 mins) o H2O for IoT • Predictive Maintenance • Anomaly Detection • H2O’s R Interface • Third Talk (25 mins) o Deep Water o Demo • H2O + mxnet on GPU • H2O’s Python Interface 2
- 3. Data and Code • Please go to bit.ly/h2o_milan_1 • subfolders o iot_use_case_1 o iot_use_case_2 3
- 4. Use Case 1 Predictive Maintenance
- 5. Data for Use Case 1: SECOM 5 https://archive.ics.uci.edu/ml/datasets/SECOM
- 6. 6 We want to predict fails in the future.
- 7. The ML Problem – Pass/Fail • Inputs o 591 features • Output o Classification • -1 = pass • 1 = fail • Size: 1567 Samples 7
- 8. 8 Features (Numeric) ID (excluded from modeling)
- 9. 9 Features (Numeric) Response (Classification) -1 (Pass) or 1 (Fail)
- 10. Use Case 1: Predictive Maintenance Step 1: R Packages
- 12. Use Case 1: Predictive Maintenance Step 2: Exploratory Analysis
- 13. step_02_exploratory_analysis.R 13 Importing SECOM data Optional (different ways to import data)
- 14. step_02_exploratory_analysis.R 14 Basic exploratory analysis Convert -1 and 1 to categorical value Note: Imbalance dataset (only 104 fails)
- 15. Use H2O Flow (localhost:54321) 15
- 16. Use Case 1: Predictive Maintenance Step 3: Building & Evaluating Models
- 17. step_03_basic_models.R 17 Define features & target
- 18. step_03_basic_models.R 18 Split data with a random seed Classification 1 samples ≈ 7%
- 19. step_03_basic_models.R 19 Train H2O models with default values H2O automatically ignores Columns with constant values
- 21. Use H2O Flow (localhost:54321) 21
- 23. Advanced Procedures • Step 4 – Manual Tuning • Step 5 – Early Stopping • Step 6 – Grid Search • Step 7 – Stacking Models (“h2oEnsemble”) • Step 8 – Saving/Loading Models • Please try them out later (bit.ly/h2o_milan_1) 23
- 24. Use Case 2: Anomaly Detection
- 25. Anomaly (Outlier) Detection • Definition o Identification of items, events or observations which do not conform to an expected pattern or other items in a dataset. • Use Cases o Bank Fraud o Monitoring Manufacturing Lines o Machine Learning • Separate dataset and build different models 25Photo credit: www.dbta.com
- 26. Deep Autoencoder for Anomaly Detection • Consider the following three-layer neural network with one hidden layer and the same number of input neurons (features) as output neurons. • The loss function is the mean squared error (MSE) between the input and the output. Hence, the network is forced to learn the identity via a nonlinear, reduced representation of the original data. o e.g. High MSE = potential outliers • Such an algorithm is called a deep autoencoder. 26https://github.com/h2oai/h2o-training-book/blob/master/hands-on_training/anomaly_detection.md
- 27. MNIST Example – The Good Ones 27Samples with Low Mean Squared Error (MSE)
- 28. MNIST Example – The Bad Ones 28Samples with High Mean Squared Error (MSE)
- 29. MNIST Example – The Ugly Ones 29Samples with Highest Mean Squared Error (MSE)
- 31. use_case_2_anomaly_detection.R 31 Define your own cut-off point Build a Deep Autoencoder Look at the MSE Define cut-off Outliers identified
- 32. End of Second Talk – Thanks! 32 • Data Science Milan • Gianmario Spacagna • Politecnico di Milano • Resources o bit.ly/h2o_milan_1 o www.h2o.ai o docs.h2o.ai • Contact o joe@h2o.ai o @matlabulous o github.com/woobe