IoT based hydroponics system using Deep Neural Networks

•Hydroponics technology has been applied in agriculture.•Lot of countries including India has been practicing hydroponics towards farming.•Good amount of research done in capturing parameters by employing sensors and controlling the hydroponics system for the growth of plant by employing IoT Technology.•Machine learning algorithm like ANN and Bayesian Network employed in hydroponics system in predicting the appropriate control action needed based on parameters gathered.•No research focused on developing an intelligent IoT based hydroponics system where intelligence deployed at the edge for controlling hydroponic environment autonomously without the need for human with better accuracy.•Solution is an Intelligent IoT based hydroponics system for Tomato plant as case study by employing Deep Neural Network which is an advancement of Artificial Neural Network.•System here captured the parameters like pH, Temperature, light intensity, humidity, Level which are monitored and accordingly analyzed by applying Deep Neural Network for predicting the appropriate control action towards controlling the hydroponic system which are classified into eight labels.•The data captured with the appropriate control action labelling are stored in cloud.•These are implemented using Arduino Microcontroller, Raspberry Pi3 and Tensor Flow as a prototype. Agriculture has the significant impact on the economy of the country. With the practice of modern farming techniques where plants can be grown without the need of soil by means of nutrient solution, Hydroponics and Aeroponics are in the rise. Now towards controlling the hydroponic plant growth, some amount of research has been done in applying machine learning algorithms like Neural Networks and Bayesian network. Internet of Things allows for Machine to Machine interaction and controlling the hydroponic system autonomously and intelligently. This work proposes to develop an intelligent IoT based hydroponic system by employing Deep Neural Networks which is first of its kind. The system so developed is intelligent enough in providing the appropriate control action for the hydroponic environment based on the multiple input parameters gathered. A prototype for Tomato plant growth as a case study was developed using Arduino, Raspberry Pi3 and Tensor Flow.