It is meaningful to analyze urban spatial structure by identifying urban subcenters, and many methods of doing so have been proposed in the published literature. Although these methods are widely applied, they exhibit obvious shortcomings that limit their further application. Therefore, it is of great value to propose a new urban subcenter identification method that can overcome these shortcomings. In this paper, we propose the density contour tree (DCT) method for detecting urban polycentric structures and their spatial distributions. Conceptually, this method is based on an analogy between urban spatial structure and terrain. The point-of-interest (POI) density is visualized as a continuous mathematical surface representing the urban terrain. Peaks represent the regions of the most frequent human activity, valleys represent regions with small population densities in the city, and slopes represent spatial changes in urban land-use intensity. Using this method, we have detected the urban “polycentric” structure of Beijing and determined the corresponding spatial relationships. In addition, several important properties of the urban centers have been identified. For example, Beijing has a typical urban polycentric structure with an urban center area accounting for 5.9% of the total urban area, and most of the urban centers in Beijing serve comprehensive functions. In general, the method and the results can serve as references for the later research on analyzing urban structure.

Chinese address element segmentation is a basic and key step in geocoding technology, and the segmentation results directly affect the accuracy and certainty of geocoding. However, due to the lack of obvious word boundaries in Chinese text, the grammatical and semantic features of Chinese text are complicated. Coupled with the diversity and complexity in Chinese address expressions, the segmentation of Chinese address elements is a substantial challenge. Therefore, this paper proposes a method of Chinese address element segmentation based on a bidirectional gated recurrent unit (Bi-GRU) neural network. This method uses the Bi-GRU neural network to generate tag features based on Chinese word segmentation and then uses the Viterbi algorithm to perform tag inference to achieve the segmentation of Chinese address elements. The neural network model is trained and verified based on the point of interest (POI) address data and partial directory data from the Baidu map of Beijing. The results show that the method is superior to previous neural network models in terms of segmentation performance and efficiency.

Urban nighttime leisure spaces (UNLSs), important urban sites of nighttime economic activity, have created enormous economic and social benefits. Both the physical features (e.g., location, shape, and area) and the social functions (e.g., commercial streets, office buildings, and entertainment venues) of UNLSs are important in UNLS mapping. However, most studies rely solely on census data or nighttime light (NTL) images to map the physical features of UNLSs, which limits UNLS mapping, and few studies perform UNLS mapping from a social function perspective. Point-of-interest (POI) data, which can reflect social activity functions, are needed. As a result, a novel methodological UNLS mapping framework, that integrates NTL images and POI data is required. Consequently, we first extracted high-NTL intensity and high-POI density areas from composite data as areas with high nightlife activity levels. Then, the POI data were analyzed to identify the social functions of leisure spaces revealing that nighttime leisure activities are not abundant in Beijing overall, the total UNLS area in Beijing is 31.08 km², which accounts for only 0.2% of the total area of Beijing. In addition, the nightlife activities in the central urban area are more abundant than those in the suburbs. The main urban area has the largest UNLS area. Compared with the nightlife landmarks in Beijing established by the government, our results provide more details on the spatial pattern of nighttime leisure activities throughout the city. Our study aims to provide new insights into how multisource data can be leveraged for UNLS mapping to enable researchers to broaden their study scope. This investigation can also help government departments better understand the local nightlife situation to rationally formulate planning and adjustment measures.

Air pollution is a growing problem and poses a challenge to people’s healthy lives. Accurate prediction of air pollutant concentrations is considered the key to air pollution warning and management. In this paper, a novel PM_2.5 concentration prediction model, CBAM-CNN-Bi LSTM, is constructed by deep learning techniques based on the principles related to spatial big data. This model consists of the convolutional block attention module (CBAM), the convolutional neural network (CNN), and the bi-directional long short-term memory neural network (Bi LSTM). CBAM is applied to the extraction of feature relationships between pollutant data and meteorological data and assists in deeply obtaining the spatial distribution characteristics of PM_2.5 concentrations. As the output layer, Bi LSTM obtains the variation pattern of PM_2.5 concentrations from spatial data, overcomes the problem of long-term dependence on PM_2.5 concentrations, and achieves the task of accurately forecasting PM_2.5 concentrations at multiple sites. Based on real datasets, we perform an experimental evaluation and the results show that, in comparison to other models, CBAM-CNN-Bi LSTM improves the accuracy of PM_2.5 concentration prediction. For the prediction tasks from 1 to 12 h, our proposed prediction model performs well. For the 13 to 48 h prediction task, the CBAM-CNN-Bi LSTM also achieves satisfactory results.

A combination of genetic algorithm and particle swarm optimization (PSO) for vehicle routing problems with time windows (VRPTW) is proposed in this paper. The improvements of the proposed algorithm include: using the particle real number encoding method to decode the route to alleviate the computation burden, applying a linear decreasing function based on the number of the iterations to provide balance between global and local exploration abilities, and integrating with the crossover operator of genetic algorithm to avoid the premature convergence and the local minimum. The experimental results show that the proposed algorithm is not only more efficient and competitive with other published results but can also obtain more optimal solutions for solving the VRPTW issue. One new well-known solution for this benchmark problem is also outlined in the following.

Landmark visual salience (characterized by features that contrast with their surroundings and visual peculiarities) and semantic salience (characterized by features with unusual or important meaning and content in the environment) are two important factors that affect an individual’s visual attention during wayfinding. However, empirical evidence regarding which factor dominates visual guidance during indoor wayfinding is rare, especially in real-world environments. In this study, we assumed that semantic salience dominates the guidance of visual attention, which means that semantic salience will correlate with participants’ fixations more significantly than visual salience. Notably, in previous studies, semantic salience was shown to guide visual attention in static images or familiar scenes in a laboratory environment. To validate this assumption, first, we collected the eye movement data of 22 participants as they found their way through a building. We then computed the landmark visual and semantic salience using computer vision models and questionnaires, respectively. Finally, we conducted correlation tests to verify our assumption. The results failed to validate our assumption and show that the role of salience in visual guidance in a real-world wayfinding process is different from the role of salience in perceiving static images or scenes in a laboratory. Visual salience dominates visual attention during indoor wayfinding, but the roles of salience in visual guidance are mixed across different landmark classes and tasks. The results provide new evidence for understanding how pedestrians visually interpret landmark information during real-world indoor wayfinding.