EXTRACT: Strong Examples from Weakly-Labeled Sensor Data
This addresses the problem of interpreting sensor data for applications in wearables and IoT, offering a practical solution for event extraction with minimal prior knowledge.
The paper tackles the challenge of extracting high-level events from low-level sensor data by introducing a technique that automatically identifies real-world events using only rough temporal estimates, achieving up to 96% precision and recall for events like human actions and spoken words.
Thanks to the rise of wearable and connected devices, sensor-generated time series comprise a large and growing fraction of the world's data. Unfortunately, extracting value from this data can be challenging, since sensors report low-level signals (e.g., acceleration), not the high-level events that are typically of interest (e.g., gestures). We introduce a technique to bridge this gap by automatically extracting examples of real-world events in low-level data, given only a rough estimate of when these events have taken place. By identifying sets of features that repeat in the same temporal arrangement, we isolate examples of such diverse events as human actions, power consumption patterns, and spoken words with up to 96% precision and recall. Our method is fast enough to run in real time and assumes only minimal knowledge of which variables are relevant or the lengths of events. Our evaluation uses numerous publicly available datasets and over 1 million samples of manually labeled sensor data.