Crop cultivation information system on mobile devices

Abstract

Mobile devices are used extensively by the people for communication, music, entertainment, Internet and social networking. There is a lack of applications, which can be really useful for the professionals to improve their working capabilities. Though mobile phones are used by people living in rural areas, but there are hardly any relevant applications for them to improve their productivity. In this paper, we have proposed and implemented an information system for farmers which can be operated on their mobile phones. The system is developed using Service Oriented Architecture (SOA) to process spatial data and knowledge base. The knowledge base is maintained in the form of ontologies. The system is an effort to fill the gap between farmers and agricultural experts. A farmer can provide inputs related to crops being cultivated and location specific information to get specific suggestions, alerts and recommendations to improve productivity. It will be generated using the knowledge base. Whenever a farmer observes some anomalous behavior for crops or climate, the system is able to generate recommendations based on inputs provided. We have resolved some of the queries as a part of on-going work and results are displayed on an Android based mobile devices for demonstration of the system.

IT adaptation in sugar supply chain: a study at milling level

“…116 sugar mills have already adopted this website in Uttar Pradesh and around 29 lakh farmers' details are being protected with a password protected webpage (India Governance, 2012). This concept is very useful because farmers have mobile phones and can access such technology with the telecom services in the rural and remote areas of the nations (Kumar et al, 2013b).…”

Heavy weight ontology learning using text documents

“…II. RELATED WORK Use of ontology is increasing in knowledge based systems and applications are making use of ontology where fast knowledge processing is required [9], [10], [11].The steps involved in ontology learning approaches are Natural Language Processing, Dictionary Parsing, Statistical Analysis, Machine Learning, Hierarchical Concept Clustering and Formal Concept Analysis (Lattices) or Description Logic techniques [17], [16], [14]. Data driven domain modeling techniques are classified in [3].…”