Decision trees are mainly used to classify data and predict data classes. A spatial decision tree has been designed using Euclidean distance between objects for reflecting spatial data characteristic. Even though this...Decision trees are mainly used to classify data and predict data classes. A spatial decision tree has been designed using Euclidean distance between objects for reflecting spatial data characteristic. Even though this method explains the distance of objects in spatial dimension, it fails to represent distributions of spatial data and their relationships. But distributions of spatial data and relationships with their neighborhoods are very important in real world. This paper proposes decision tree based on spatial entropy that represents distributions of spatial data with dispersion and dissimilarity. The rate of dispersion by dissimilarity presents how related distribution of spatial data and non-spatial attributes. The experiment evaluates the accuracy and building time of decision tree as compared to previous methods and it shows that the proposed method makes efficient and scalable classification for spatial decision support.展开更多
Sensor networks consisted of low-cost, low-power, multifunctional miniature sensor devices have played an important role in our daily life. Light and humidity monitoring, seismic and animal activity detection, environ...Sensor networks consisted of low-cost, low-power, multifunctional miniature sensor devices have played an important role in our daily life. Light and humidity monitoring, seismic and animal activity detection, environment and habitat monitoring are the most common applications. However, due to the limited power supply, ordinary query methods and algorithms can not be applied on sensor networks. Queries over sensor networks should be power-aware to guarantee the maximum power savings. The minimal power consumption by avoiding the expensive communication of the redundant sensor nodes is concentrated on. A lot of work have been done to reduce the participated nodes, but none of them have considered the overlapping minimum bounded rectangle (MBR) of sensors which make them impossible to reach the optimization solution. The proposed OMSI-tree and OMR algorithm can efficiently solve this problem by executing a given query only on the sensors involved. Experiments show that there is an obvious improvement compared with TinyDB and other spatial index, adopting the proposed schema and algorithm.展开更多
文摘Decision trees are mainly used to classify data and predict data classes. A spatial decision tree has been designed using Euclidean distance between objects for reflecting spatial data characteristic. Even though this method explains the distance of objects in spatial dimension, it fails to represent distributions of spatial data and their relationships. But distributions of spatial data and relationships with their neighborhoods are very important in real world. This paper proposes decision tree based on spatial entropy that represents distributions of spatial data with dispersion and dissimilarity. The rate of dispersion by dissimilarity presents how related distribution of spatial data and non-spatial attributes. The experiment evaluates the accuracy and building time of decision tree as compared to previous methods and it shows that the proposed method makes efficient and scalable classification for spatial decision support.
基金This work is supported by the MIC ( Ministry of Information and Communication) , Korea ,under the ITRC(Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Assess-ment) .
文摘Sensor networks consisted of low-cost, low-power, multifunctional miniature sensor devices have played an important role in our daily life. Light and humidity monitoring, seismic and animal activity detection, environment and habitat monitoring are the most common applications. However, due to the limited power supply, ordinary query methods and algorithms can not be applied on sensor networks. Queries over sensor networks should be power-aware to guarantee the maximum power savings. The minimal power consumption by avoiding the expensive communication of the redundant sensor nodes is concentrated on. A lot of work have been done to reduce the participated nodes, but none of them have considered the overlapping minimum bounded rectangle (MBR) of sensors which make them impossible to reach the optimization solution. The proposed OMSI-tree and OMR algorithm can efficiently solve this problem by executing a given query only on the sensors involved. Experiments show that there is an obvious improvement compared with TinyDB and other spatial index, adopting the proposed schema and algorithm.
