engleski

Predicting Low-Cost Gas Sensor Readings From Transients Using Long Short-Term Memory Neural Networks

With the everyday growth of the Internet of Things (IoT), the number of connected sensor devices increases as well, where each sensor consumes energy while being constantly online. During that time, they collect large amounts of data in short intervals leading to the collection of redundant and perhaps irrelevant data. Moreover, being commonly battery powered, sensor batteries need to be frequently replaced or recharged. The former requires smarter and less frequent data collection, while the latter being complementary to the former requires putting them to sleep while not being used in order to save energy. The focus of this article is low-cost gas sensors as they need to preheat for several minutes to reliably collect gas concentration. However, instead of waiting for a sensor to heat up, a transient, i.e., a data trend that the sensor collects while heating up is analyzed. It is shown that long short-term memory (LSTM) neural network can be used to learn and later predict the actual gas level from a part of the transient. This way, instead of being constantly online or fully preheating, the sensor needs to be turned on for only 20 s and then sleep for 120 s. With high accuracy, our approach decreases energy consumption by up to 85% compared to a system where sensors are constantly online, and more than 50% compared to a system where a sensor collects actual values instead of a part of the transient.

IoT, artificial neural networks, prediction algorithms, transient analysis

nije evidentirano