The alteration of surrounding rock is an important prospecting indicator in mineral exploration, but some important minerals are unclassified or misclassified when using hyperspectral remote sensing mineral recognition. A method for mineral recognition mapping was proposed. In this method, a decision tree discrimination rule was established based on the classification and regression tree data-mining algorithm and the absorption characteristics of field-measured spectra. Compared with spectral angle mapping and mixture-tuned matched filtering (MTMF), this method is shown to be efficient for mineral recognition mapping using hyperspectral images; its accuracy is 85.06%, which is greater than that of the MTMF method (83.91%). The advantages of the proposed method comprise the reduction of errors caused by the setting of the artificial threshold for mineral mapping and the lesser degree of difficulty in its training. Furthermore, the hierarchy structure of the decision tree in this method reflects the recognition process clearly, and the rule nodes are closely related to the spectra of the minerals; therefore, the advantage of this method is the interpretability of the results and the process. This method could be used for mineral recognition and classification using hyperspectral images.
New technologies and automated systems (such as multi-sensor systems) allow us to collect and store a large amount of
spatial data in a quite efficient and inexpensive way. Especially, the advent of remote sensing and GIS has great
enhanced our capabilities to capture spatial data. However raw data are seldom useful without some kind of processing,
it needs more powerful technologies to deal with the databases. Therefore, spatial data fusion and data mining have been
used in this domain. They can improve the efficiency and accuracy of spatial information utilization. In this paper, we
focused on how to fusion spatial data for decision making by learning Bayesian networks. A review is presented on
spatial data fusion. We propose a method of spatial data fusion based on Bayesian networks, which is optimized by using
the theory of Particle Swarm Optimization (PSO). And then we showed a case study for spatial data fusion based on the
approach. The experimental results are given to illustrate the practical feasibility of the proposed technique. Eventually,
we conclude with a summary and a statement of future work.
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.
KEYWORDS: Data mining, Data modeling, Databases, Soil science, Knowledge discovery, Data hiding, Systems modeling, Medical imaging, Evolutionary algorithms, Remote sensing
Spatial data mining is a process of discovering interesting, novel, and potentially useful information or knowledge hidden in spatial data sets. It involves different techniques and different methods from various areas of research. A Bayesian network is a graphical model that encodes causal probabilistic relationships among variables of interest, which has a powerful ability for representing and reasoning and provides an effective way to spatial data mining. In this paper we give an introduction to Bayesian networks, and discuss using Bayesian networks for spatial data mining. We propose a framework of spatial data mining based on Bayesian networks. Then we show a case study and use the experimental results to validate the practical viability of the proposed approach to spatial data mining. Finally, the paper gives a summary and some remarks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.