AutoEncoder for Interpolation
This paper addresses the problem of noisy and incomplete time-series sensor data for physical scientists, offering an incremental improvement over traditional interpolation methods.
This paper proposes using an AutoEncoder to simultaneously interpolate and denoise time-series sensor data. The method aims to address issues with traditional interpolation, such as lack of smoothness, poor denoising, and inaccurate derivative calculations on noisy data. A real-world example is provided to demonstrate the approach.
In physical science, sensor data are collected over time to produce timeseries data. However, depending on the real-world condition and underlying physics of the sensor, data might be noisy. Besides, the limitation of sample-time on sensors may not allow collecting data over all the timepoints, may require some form of interpolation. Interpolation may not be smooth enough, fail to denoise data, and derivative operation on noisy sensor data may be poor that do not reveal any high order dynamics. In this article, we propose to use AutoEncoder to perform interpolation that also denoise data simultaneously. A brief example using a real-world is also provided.