Abstract:

The productivity of dairy farms is a key element which is studied at Animal Science faculties. The proposed online platform analyzes using Elasticsearch and with the help of faculty students the acquired data from various Romanian dairy farms that are stored in the MongoDB NoSQL database. When new data is added by the Animal Science students, a new document is added inside the MongoDB collection and the characteristics used for matching are indexed inside Elasticsearch. Regular expressions are provided by professors and are utilized for extracting the relevant information. While performing the crawling, the features regarding the productivity parameters like milk quantity, fat and protein content, compound feed consumption are found using XPath in order to determine the relationships between the features. The important characteristics are detected by creating a document term matrix based on term frequency-inverse document frequency. The matching is done according to the characteristics by using the weighted terms according to the matrix. After the matching is done, the students, as well as the farms have access to the best case situation with the highest productivity which is suggested based on the previous analyzed cases. The farmers collaborate and they improve the existent knowledge base of the system after being approved by Animal Science faculty experts, as well as they can learn how to manage better their dairy farm according to the automatic assignment which is done for determining the best suited features. After a period of time, feedback comes from the farmers based on the implemented solution and the students, as well as the expert can use it for learning. The shift to the online platform has improved the management of healthcare records, while the automatic productivity recommendation aims to enhance the productivity of dairy farms, as well as the farmers, the students and the animal science experts learn from the previous successfully tested cases.

Keywords:

Learning analytics, Ontology, Semantical matching, Collaborative learning, Community building.