SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation

TL;DR

This paper introduces a deep learning architecture combining LSTM and Mixture Density Networks to generate synthetic sensor data that closely mimics real data, making it difficult for discriminators to distinguish between them.

Contribution

The paper presents a novel deep learning architecture for synthesizing sensor data that can pass deep discriminator tests, enhancing data privacy and utility.

Findings

Discriminator accuracy is around 50%, indicating high similarity between real and synthetic data.

The architecture effectively preserves statistical properties of the original data.

Synthetic data can potentially replace sensitive real data segments in analytics.

Abstract

Our ability to synthesize sensory data that preserves specific statistical properties of the real data has had tremendous implications on data privacy and big data analytics. The synthetic data can be used as a substitute for selective real data segments,that are sensitive to the user, thus protecting privacy and resulting in improved analytics.However, increasingly adversarial roles taken by data recipients such as mobile apps, or other cloud-based analytics services, mandate that the synthetic data, in addition to preserving statistical properties, should also be difficult to distinguish from the real data. Typically, visual inspection has been used as a test to distinguish between datasets. But more recently, sophisticated classifier models (discriminators), corresponding to a set of events, have also been employed to distinguish between synthesized and real data. The model operates on both datasets and the respective event outputs are compared for consistency. In this paper, we take a step towards generating sensory data that can pass a deep learning based discriminator model test, and make two specific contributions: first, we present a deep learning based architecture for synthesizing sensory data. This architecture comprises of a generator model, which is a stack of multiple Long-Short-Term-Memory (LSTM) networks and a Mixture Density Network. second, we use another LSTM network based discriminator model for distinguishing between the true and the synthesized data. Using a dataset of accelerometer traces, collected using smartphones of users doing their daily activities, we show that the deep learning based discriminator model can only distinguish between the real and synthesized traces with an accuracy in the neighborhood of 50%.