A computational model for ubiquitous intelligent services in indoor agriculture

Abstract

The application of ubiquitous computing has increased in recent years, especially due to the development of technologies such as mobile computing, accurate sensors and specific protocols for an IoT. One of the trends in this research area is the use of context awareness. In agriculture, the context can be related to the environment, for example, the conditions found inside a greenhouse. Recently a series of studies proposed the use of sensors to monitor the production or the use of cameras to obtain crop information, providing data, reminders and alerts to farmers. This paper proposes a computational model for Indoor Agriculture called IndoorPlant that uses the contexts history analysis to provide intelligent services such as predict the productivity, indicate the problems that the crop may suffer, give suggestions for improvements in the parameters in the greenhouse, among others. IndoorPlant was tested on cucumber prediction using simulated data that was approved by three farmers with more than 10 years of experience each. The results obtained in the prediction of cucumber, with a coefficient of determination (R2) of 0.9912 for root mean square error (RMSE) of 8,06 units of cucumber.