Practical Processing of Mobile Sensor Data for Continual Deep Learning Predictions
This work addresses the challenge of applying machine learning to mobile phone sensor data by reducing the need for resource-intensive feature engineering, which is incremental as it builds on existing deep learning methods.
The paper tackles the problem of processing mobile sensor data for continual deep learning predictions by proposing a practical approach that includes data cleaning, normalization, and classification with a recurrent neural network, resulting in a 40% performance increase (AUC of 0.702) compared to a random baseline in a case study with 279 participants.
We present a practical approach for processing mobile sensor time series data for continual deep learning predictions. The approach comprises data cleaning, normalization, capping, time-based compression, and finally classification with a recurrent neural network. We demonstrate the effectiveness of the approach in a case study with 279 participants. On the basis of sparse sensor events, the network continually predicts whether the participants would attend to a notification within 10 minutes. Compared to a random baseline, the classifier achieves a 40% performance increase (AUC of 0.702) on a withheld test set. This approach allows to forgo resource-intensive, domain-specific, error-prone feature engineering, which may drastically increase the applicability of machine learning to mobile phone sensor data.