added a research item
Regionalization attempts to group units into a few subsets to partition the entire area. The results represent the underlying spatial structure and facilitate decision-making. Massive amounts of trajectories produced in the urban space provide a new opportunity for regionalization from human mobility. This paper proposes and applies a novel regionalization method to cluster similar areal units and visualize the spatial structure by considering all trajectories in an area into a word embedding model. In this model, nodes in a trajectory are regarded as words in a sentence, and nodes can be clustered in the feature space. The result depicts the underlying socio-economic structure at multiple spatial scales. To our knowledge, this is the first regionalization method from trajectories with natural language processing technology. A case study of mobile phone trajectory data in Beijing is used to validate our method, and then we evaluate its performance by predicting the next location of an individual’s trajectory. The case study indicates that the method is fast, flexible and scalable to large trajectory datasets, and moreover, represents the structure of trajectory more effectively.
A neighbourhood is a shared space for spatial interaction. The vibrancy of a neighbourhood represents a synergy between the people, activities and values in a place, which increases community vitality and spurs economic opportunity. It can be investigated both qualitatively and quantitatively. However, there are technical challenges involved in accurately charting vibrancy. With the recent advances in communication technology and the prevalence of location-aware devices such as mobile phones, individual trajectories can be collected and analysed on a large scale. In previous research, the weights of the vibrancies corresponding to different trajectories are not differentiated. In this study, an improved PageRank algorithm using a weighted bipartite graph is proposed to measure the vibrancy of an urban neighbourhood from a different perspective, which highlights the differences between vibrancies arising from different types of citizens. This method connects the land much more closely with human activities and provides a new perspective on, and guidance for, urban resource allocation and urban planning.
Given the abundant quantities of big spatiotemporal geographic data that are available, interactions among spatial entities can now be extracted from various perspectives. This research investigates the spatial interactions within the metropolis of Beijing quantitatively. Two methods of quantifying the interactions are proposed. These interactions can be calculated from either individual trajectories extracted from mobile phone records or the co-occurrence of the toponyms of administrative units mentioned in online news items. By fitting these two types of data with a gravity model and comparing the results, we determine that the distance decay effect exists in both data sets, and this effect is more obvious in the interactions computed from the human trajectories. The spatial interactions and connections quantified from the two data sources display greater numbers of mutual patterns in the central urban areas, whereas more diversity is observed in the suburban areas. We conclude that the choice of assumptions as to which data can adequately represent spatial interactions significantly affects the results; therefore, rigorous examination of specific problems is needed to redefine the problems in a more specific way.
The advanced technologies in location-based services and telecom have yield large volumes of trajectory data. Understanding these data effectively requires intuitive yet accurate visual analysis. The visual analysis of massive trajectory data is challenged by the numerous interactions among different locations, which cause massive clutter. This paper presents a new methodology for visual analysis by integrating algebraic multigrid (AMG) method in data aggregation. The non-parametric method helps to build a multi-layer node representation from a graph which is extracted from trajectory data. The comparison with AMG and other methods shows that AMG method is more advanced in both the spatial representation and the importance of nodes. The new method is tested with real-world dataset of cell-phone signalling records in Beijing. The results show that our method is suitable for processing and creating abstraction of massive trajectory dataset, revealing inherent patterns and creating intuitive and vivid flow maps.