Prevention of cooktop ignition using detection and multi-step machine learning algorithms.

This paper 1 1 Certain commercial products are identified in this paper in order to specify adequately the equipment used. Such identification does not imply recommendation by the National Institute of Standards and Technology, nor does it imply that this equipment is the best available for the purpose. presents a study to examine the potential use of machine learning models to build a real-time detection algorithm for prevention of kitchen cooktop fires. Sixteen sets of time-dependent sensor signals were obtained from 60 normal/ignition cooking experiments. A total of 200,000 data instances are documented and analyzed. The raw data are preprocessed. Selected features are generated for time series data focusing on real-time detection applications. Utilizing the leave-one-out cross validation method, three machine learning models are built and tested. Parametric studies are carried out to understand the diversity, volume, and tendency of the data. Given the current dataset, the detection algorithm based on Support Vector Machine (SVM) provides the most reliable prediction (with an overall accuracy of 96.9%) on pre-ignition conditions. Analyses indicate that using a multi-step approach can further improve overall prediction accuracy. The development of an accurate detection algorithm can provide reliable feedback to intercept ignition of unattended cooking and help reduce fire losses. • Time series sensor data for cooking with electric-coil and gas cooktops are presented. • Data preprocessing and feature selection for machine learning on real-time fire prevention application are discussed. • Workflow for constructing and testing machine learning models is demonstrated. • Support Vector Machine (SVM) detection algorithms can predict 96.9% of the data points with hazardous conditions. • Multi-step models can enhance data classification and improve detection accuracy. [ABSTRACT FROM AUTHOR]