The process of gentrification changes the composition and character of urban neighbourhoods in cities worldwide. Amenities such as art galleries, designer boutiques, fine dining, and specialty cafés interact with most gentrification processes and could act as indicators for measuring gentrification. Previous literature has explored the role of amenities in gentrification, and some have found distinctive amenity landscapes in different spatial contexts. However, there is a lack of a more generalized approach for identifying gentrification-related amenities across different regions. This study proposed a machine learning-based framework to identify localized gentrification amenities. Specifically, amenities were represented by Points of Interest (POIs) and matched to the North American Industry Classification System (NAICS), an industry classification system commonly used in amenity-related studies. Bridging POI categories and the NAICS hierarchy enables a dialog between big data and conventional statistical data. Then, given typical gentrification neighborhoods in an area, featured amenities can be identified via a supervised gradient boosting method. The framework was applied to Shenzhen, a major Chinese city. Results showed that Shenzhen has a distinct amenity landscape in its gentrified neighborhoods; for example, bubble tea beverage shops were recognized as a dominant amenity, as opposed to the cafés in many Western cities, as well as financial institutions, digital electronics, and car-related amenities. The proposed machine learning-based framework not only provides a generalized approach to identifying gentrification-related amenities in different regions, but also enables dynamic and fine-grained tracking of gentrification on the basis of big data.

DBSCAN, a density-based clustering algorithm, has been widely used in pattern recognition and data mining. However, under large-scale streaming data scenarios, it suffers heavy computational cost because it examines distances between each points multiple times, especially in traffic applications which usually require calculating road network shortest distance instead of Euclidean distance. Therefore, the performance of DBSCAN for real-time clustering analyses is has become a bottleneck in such applications. Focusing on fast identifying traffic-related events, this paper utilizes linear feature to improve the efficiency of clustering by introducing linear referencing system (LRS). LRS has long been used in managing linear features, which could simplify shortest-path computation into 1-dimensional relative distance calculation, thus can significantly reduce computational complexity and cost, and meet the real-time analysis requirement of streaming data. Using vehicle GPS trajectory as an example, this study designs a LRS and its associated dynamic segmentation method for identifying traffic congestions. Experiment results proved the flexibility and efficiency of the proposed LRS-based clustering approach in identifying traffic congestions.

Although mixed use is an emerging strategy that has been widely accepted in urban planning for promoting neighbourhood vibrancy, there is no consensus on how to quantitatively measure the mix and the effects of mixed use on neighbourhood vibrancy. Shannon entropy, the most commonly used diversity measurement in assessing mixed use, has been found to be inadequate in measuring the multifaceted, multidimensional characteristics of mixed use. And lack of data also makes it difficult to find the relationship between mixed use and neighbourhood vibrancy. However, the recent availability of new sources including mobile phone data and Point of Interest (POI) data have made it possible to develop new indices of mixed use and neighbourhood vibrancy to analyse their relationships. Taking advantage of these emerging new data sources, this study used the numbers of mobile phone users in a 24-hour period as a proxy of neighbourhood vibrancy and used POIs from a navigation database to develop a series of mixed-use indicators that can better reflect the multifaceted, multidimensional characteristics of mixed-use neighbourhoods. The Hill numbers, a unified form of diversity measurement used in ecological literature that includes richness, entropy, and the Simpson index, are used to measure the degrees of mixed use. Using such fine-grained data sets and the Hill numbers allowed us to obtain better insights into the relationship between mixed use and neighbourhood vibrancy. Four models varying in POI measurements that reflect different dimensions of mixed use were presented. The results showed that either POI density or entropy can explain approximately 1% of neighbourhood vibrancy, while POI richness contributes significantly in improving neighbourhood vibrancy. The results also revealed that the entropy has limitations as a measure for representing mixed use and demonstrated the necessity of adopting a set of more appropriate measurements for mixed use. Increasing the number of POIs has limited power to improve neighbourhood vibrancy compared with encouraging the mixing of complementary POIs. These exploratory findings may be useful for adjusting mixed-use assessments and to help guide urban planning and neighbourhood design.

Mp-matching floating car data is a fundamental task in traffic surveillance, traffic anomaly detection, and urban dynamic analysis. This study proposes a parallel map-matching approach to process streaming large volume floating car data. Considering the connectivity of a transportation network, the matching candidates are limited with a coarse spatial grid. A distance filter and a direction filter are combined to reduce the number of matching candidates. The trajectory between consecutive nodes is recovered with a shortest path list. The shortest path list in memory was developed to reduce the computation and speed up the matching process. A non-relational distributed database parallelizes the map-matching procedure. The performance of the presented approach was tested with large volume floating car data in Wuhan, China. It demonstrates that this method achieves 90.62% correct map-matching results. This efficiency could fulfill the needs of real-time traffic monitoring, and will benefit trajectory analysis.