Jiejun Huang

Development of a campus information navigation system based on GIS

Using GIS and other spatial information technology to build digital campus is an effective way to achieve intelligent management of the campus. According to the actual situation of Wuhan University of Technology, the framework of GIS-based navigation intelligent system for Wuhan University of Technology (WHUT) is proposed. The development and implementation of GIS-based campus information navigation system is presented from data collection, database design, system implementation and other aspects. The system realizes some functions such as education management, information inquiry, service guide, virtual campus navigation and decision making etc. Eventually, it draws a conclusion and prospects the future of campus GIS.

Development of a Data Mining Application for Agriculture Based on Bayesian Networks

Data mining is a process by which the data can be analyzed so as to generate useful knowledge. It aims to use existing data to invent new facts and to uncover new relationships previously unknown even to experts. Bayesian network is a powerful tool for dealing with uncertainties, and has a widespread use in the area of data mining. In this paper, we focus on development of a data mining application for agriculture based on Bayesian networks. Let features (or objects) as variables or the nodes in Bayesian network, let directed edges present the relationships between features, and the relevancy intensity can be regarded as confidence between the variables. Accordingly, it can find the relationships in the agricultural data by learning a Bayesian network. After defining the domain variables and data preparation, we construct a model for agricultural application based on Bayesian network learning method. The experimental results indicate that the proposed method is feasible and efficient, and it is a promising approach for data mining in agricultural data.

An approach based on Decision Tree to agricultural land grading

Land resources assessment is the premise and basis for the sustainable utilization of land resources. As a classification technology, Decision Tree has already been applied wildly in the area of information classification. This paper firstly introduces the fundamental theory and characteristics of Decision tree as well as its learning process. Then Iterative Dichotomiser 3 (ID3) algorithm and Decision tree pruning algorithm are combined to construct the Decision tree for agricultural land grading with a good result. The sampling and testing result shows that the accuracy in this case reaches as high as 86%. It can be easily concluded that Decision tree is an effective way for the agriculture land grading.

Rough set for quantitative analysis of characteristic information in metallogenic prediction

Purpose – The purpose of this paper is to extract the characterized mineralization information from large numbers of data obtained from geologic exploration based on rough set; analyze the inherent relation between mineral information genes and metallogenic probability, and offer the scientific basis for target prediction.Design/methodology/approach – Mineral information includes all kinds of relative metallogenic information. In order to extract comprehensive metallogenic prediction information, it is necessary to filter initial observation information to emphasize the factors that are most advantageous to metallogenic prognosis. Rough set can delete irrespective or unimportant attributes on the premises of no information missing and no classification ability changing, without supplementary information or prior knowledge, which has important theoretic and practical value for metallogenic prognosis.Findings – The association and importance of geological information referring to prospecting are found out t...

Study on spatial knowledge representation and reasoning based on Bayesian networks

Spatial information plays an essential role on the progress of science and technology, and has a profound impact on economic growth and society progress in the twenty-first century. Spatial knowledge representation and reasoning are very important for us to utilize spatial information. In this paper, a review is presented on spatial knowledge representation and reasoning. And then we propose a method of spatial knowledge representation and reasoning based on Bayesian networks. We focused on how to represent spatial relationship, spatial objects and spatial features by using Bayesian networks. Let spatial features (or spatial objects, spatial relationships) as variables or the nodes in Bayesian network, let directed edges present the relationships between spatial features, and the relevancy intensity can be regarded as confidence between the variables (the same as probability parameter in Bayesian network). Accordingly, the problem of spatial knowledge representation will be changed to the problem of learning Bayesian networks. The experimental results are given to verify the practical feasibility of the proposed methodology. Eventually, we conclude with a summary and a statement of future work.