Parameterized Data Reduction Framework of Thermal Sensing for Gait Velocity Measurements

In IoT systems, many sensing devices will periodically transmit data. However, most of the sensing data are either similar or redundant and the sensing device itself may not have effective rules standard to decide to send or not. Static rules maybe effective on specific scenario, and become ineffective when the use scenario of the sensor changes. Hence, we design an algorithm to solve the problem of data redundant for IoT devices. The algorithm iteratively separates a data region into smaller regions. In each round, it chooses a region with highest variability, and separates it into smaller regions. Finally, each region has different sizes and uses its average value to represent itself. If an area has more dynamical, diverse data, more data points will be used to present the data. In this paper, we present a method to reduce the file size of thermal sensor which can sense the temperature of a surface and outputs a two dimension gray scale image. In our evaluation result, we can reduce the file size to be 50% of JPEG format when 0:5% of distortion is allowed, and up to 93% less when 2% of distortion is allowed.