Abstract
With the growing adoption of the Internet of Things (IoT) technology in the agricultural sector, smart devices are becoming more prevalent. The availability of new, timely, and precise data offers a great opportunity to develop advanced analytical models. Therefore, the platform used to deliver new developments to the final user is a key enabler for adopting IoT technology. This work presents a generic design of a software platform based on the cloud and implemented using microservices to facilitate the use of predictive or prescriptive analytics under different IoT scenarios. Several technologies are combined to comply with the essential features—scalability, portability, interoperability, and usability—that the platform must consider to assist decision-making in agricultural 4.0 contexts. The platform is prepared to integrate new sensor devices, perform data operations, integrate several data sources, transfer complex statistical model developments seamlessly, and provide a user-friendly graphical interface. The proposed software architecture is implemented with open-source technologies and validated in a smart farming scenario. The growth of a batch of pigs at the fattening stage is estimated from the data provided by a level sensor installed in the silo that stores the feed from which the animals are fed. With this application, we demonstrate how farmers can monitor the weight distribution and receive alarms when high deviations happen.
Highlights
In an Internet of Things (IoT) scenario there are sensors that can share their data through the Internet and interoperate with cloud platforms, see Figure 1
The cloud platform is the key to manage the different requirements of IoT scenarios such as huge volumes of heterogeneous data, security, interoperability, and scalability by providing the on-demand computing resources such as networks, databases, servers, storage, and others through the Internet thanks to its cloud computing infrastructure
Once the point reading is cleaned, the accumulated weekly consumption is estimated. This estimated consumption based on the sensor readings is compared with a theoretical accumulated feed consumption which is computed according to technical parameters that reflects usual patterns of the farm and the breed of animals that hosts. These parameters are provided by the user and are the average daily gain (ADG), the expected feed conversion rate (FCR), and the age
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. The automatic acquisition of data, which is part of the datafication and digitization process, is undertaken in many sectors given that sensors are becoming cheaper and more energy-efficient [7] The value of such data is directly related to the use given. With the aim to increase the value of the data collected, data scientists in the fields of Operational Research, Artificial Intelligence, or Statistics are developing advanced modeling techniques These techniques may rely at some points in solving intensive computational processes regarding CPU (central processing unit) and memory, such as when solving optimization models or training neural networks. To increase the data value, statistical models are integrated in order to estimate the feed intake and the growth of a batch of pigs.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
