Ontologies provide a shared and common understanding of a domain that can be communicated between people and across application systems. An ontology for a certain domain can be created from scratch or by merging existing ontologies in the same domain. Establishing ontology from scratch is hard and expensive. Multiple ontologies of different systems for the same domain may be dissimilar, thus, various parties with different ontologies do not fully understand each other in spite of these ontologies are for the same domain. To solve this problem, it is necessary to integrate these ontologies. Integrated ontology, should be consistent and has no redundancy. This work presents a semi-automated system for building an integrated ontology by matching and merging existing ontologies. The proposed system has been applied on the agricultural domain for Faba Bean crop to get a dynamic integrated ontology, it can be applied also on all crops whatever field crops or horticulture crops. Source ontologies in the proposed system have been implemented in XML language. CommonKADS Methodology has been used in building the target ontology. CommonKADS Methodology deals with the following kinds of entities: Concepts, properties, and values. The proposed system proposed a technique to solve the matching and merging problems by using a multi-matching technique to find the correspondences between entities in the source ontologies and merging technique which deals with concepts, properties, values and hierarchical classifications. The outcome of the proposed system is an integrated ontology in hierarchical classification of the concepts .
A chatbot is an application of artificial intelligence in natural language processing and speech recognition. It is a computer program that imitates humans in making conversations with other people. Chatbots that specialize in a single topic, such as agriculture, are known as domain-specific chatbots. In this paper, we present a dataset for farmer intents. Intent identification is the first step in building a chatbot. The dataset includes five intents (pest or disease identification, irrigation, fertilization, weed identification, and plantation date). The length of the dataset is 720 records. We applied a Multi-Layers Perceptron (MLP) for intent classification. We tried different numbers of neurons per hidden layer and compared between increasing the number of neurons with the fixed number of epochs. The result shows that as the number of neurons in the hidden layers increases, the introduced MLP achieves high accuracy in a small number of epochs. MLP achieves 97% accuracy on the introduced dataset when the number of neurons in each hidden layer is 256 and the number of epochs is 10.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.