On Sematic Mining For GPS Track Information

In recent years the urbanization process intensified, in a short period of time population growth rapidly. This is aspects of the bearing capacity test for the city, especially in urban traffic is put forward higher request. In the field of transportation, survey is the foundation of theoretical research and technological innovation, and the resident trip information is an important survey content. Traditional survey method has a lot of defects, has been gradually cannot satisfy the large-scale, high frequency of resident trip survey requirements.Along with the rapid development of the wireless communication network and global position system (GPS) technology, huge amounts of GPS data can be collection and transmission, based on GPS of travel survey method arises at the historic moment. This method refers to the respondents with a GPS receiver, collected his trip path. Using the data mining and semantic mining technology, intelligent extraction of residents trip information implied in the GPS data. In this paper, intelligent extract trip, trip mode and trip purpose.(1) Trip identificationAdopt the classics clustering algorithm based on density, obtain track of low speed area (trajectory clustering). Match the track to the geographic information, identify stop from low speed area, and then according to the stop identified the trip.(2)Based on the fuzzy pattern recognition differentiate trip modeThe method of principal component analysis (pca) determine the characteristic variable. Corresponding characteristic variable membership function is established. Using matlab to construct the fuzzy pattern recognition model, then the model for trip mode of discrimination.(3)Based on the multiple spatial scales deduce trip purposeOn the basis of the theory of multilevel space scale, analysis GPS trajectory in the aspects of micro level. The algorithm was implemented by identifying the sub-stops from track stops, mining the semantic information of sub-stops, and quantifying the information through using the characteristic parameters of activity points (such as time, speed, corner). Additionally, the types of sub-stops activity was obtained by contrasting the characteristic parameters’value to the knowledge database based on the statistical results of a large number of data.