Conference proceeding
Synthetic Sensor Data Generation for Health Applications: A Supervised Deep Learning Approach
2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Vol.2018, pp.1164-1167
07/2018
Handle:
https://hdl.handle.net/2376/100393
PMID: 30440598
Abstract
Recent advancements in mobile devices, data analysis, and wearable sensors render the capability of in-place health monitoring. Supervised machine learning algorithms, the core intelligence of these systems, learn from labeled training data. However, labeling vast amount of data is time-consuming and expensive. Moreover, sensor data often contains personal information that a user may not be comfortable sharing. Therefore, there is a strong need to develop methods for generating realistic labeled sensor data. In this paper, we propose a supervised generative adversarial network architecture that learns from feedback from both a discriminator and a classifier in order to create synthetic sensor data. We demonstrate the effectiveness of the architecture on a publicly available human activity dataset. We show that our generator learns to output diverse samples that are similar but not identical to the training data.
Metrics
11 Record Views
Details
- Title
- Synthetic Sensor Data Generation for Health Applications: A Supervised Deep Learning Approach
- Creators
- Skyler Norgaard - Dept. of Comput. Sci., Kalamazoo Coll., Kalamazoo, MI, USARamyar Saeedi - Dept. of Comput. Sci., Kalamazoo Coll., Kalamazoo, MI, USAKeyvan Sasani - Dept. of Comput. Sci., Kalamazoo Coll., Kalamazoo, MI, USAAssefaw H Gebremedhin - Dept. of Comput. Sci., Kalamazoo Coll., Kalamazoo, MI, USA
- Publication Details
- 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Vol.2018, pp.1164-1167
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Publisher
- IEEE
- Identifiers
- 99900546699301842
- Language
- English
- Resource Type
- Conference proceeding