Training Swinging Door Trending Compression Algorithm for IoT devices

The communication system is essential for the devices used in IoT. Nevertheless, the consumption caused by transmitting and receiving data is a concern in many scenarios. That is due to these devices commonly having limited energy and computational capacities. Transmission of redundant or irrelevant samples frequently wastes the device’s resources. Furthermore, Storing a large amount of redundant data could consume storage space and not offer any benefit. Data Compression (DC) methods are a potential solution. DC could reduce communication usage and storage demand. This research proposes the Training Swing Door Trending (TSDT) for being implemented in IoT Devices. TSDT is a new algorithm that improves the classic Swing Door Trending (STD). They represent the data by trend lines and have a constant computational complexity. TSDT has a training step for the automatic configuration of its parameters. This article additionally presents the Compression Factor (C-Score), a new quality metric to analyze the compression results in lossy DC methods. C-Score takes as a basis the F-Score, a measure of predictive performance. The C-Score uses the Compression and Error metrics to evaluate the compression performance in Lossy Algorithms.