The prediction of travel times is challenging because of the sparseness of real-time traffic data and the intrinsic uncertainty of travel on congested urban road networks. We propose a new gradient–boosted regression tree method to accurately predict travel times. This model accounts for spatiotemporal correlations extracted from historical and real-time traffic data for adjacent and target links. This method can deliver high prediction accuracy by combining simple regression trees with poor performance. It corrects the error found in existing models for improved prediction accuracy. Our spatiotemporal gradient–boosted regression tree model was verified in experiments. The training data were obtained from big data reflecting historic traffic conditions collected by probe vehicles in Wuhan from January to May 2014. Real-time data were extracted from 11 weeks of GPS records collected in Wuhan from 5 May 2014 to 20 July 2014. Based on these data, we predicted link travel time for the period from 21 July 2014 to 25 July 2014. Experiments showed that our proposed spatiotemporal gradient–boosted regression tree model obtained better results than gradient boosting, random forest, or autoregressive integrated moving average approaches. Furthermore, these results indicate the advantages of our model for urban link travel time prediction.

An accurate estimation of missing data in traffic flow is crucial in urban planning, intelligent transportation, economic geography, and other fields. Thus, improving the data quality of traffic flow is a necessary step in data modeling. Most existing studies use data-driven models to determine spatiotemporal patterns in traffic flow data and fill in the missing information automatically. However, simple data-driven models have unsatisfactory results for describing complex patterns in traffic flow and filling in missing data. This study treated the complex patterns in traffic flow as integrating multiple simple patterns and proposed a hybrid missing data imputation framework called ST-PTD. We used a specific time-series analysis to mine periodic patterns and proposed a novel matrix decomposition method to describe the trend of the traffic flow data. Furthermore, we fused the periodic and trend characteristics of the missing data using a novel dendritic neural network. We applied the framework in actual traffic flow data sets collected in Wuhan, China. The results showed that the ST-PTD framework outperformed the eight existing baselines in terms of imputation accuracy.

Most studies of spatial colocation patterns of crime and land-use features in geographical information science and environmental criminology employ global measures, potentially obscuring spatial inhomogeneity. This study investigated the relationships of three types of crime with 22 types of land-use in Wuhan, China. First, global colocation patterns were examined. Then, local colocation patterns were examined based on the recently-proposed local colocation quotient, followed by a detailed comparison of the results. Different types of crimes were encouraged or discouraged by different types of land-use features with varying intensity, and the local colocation patterns demonstrated spatial inhomogeneity.

Spatio-temporal Bayesian modeling, a method based on regional statistics, is widely used in epidemiological studies. Using Bayesian theory, this study builds a spatio-temporal Bayesian model specific to urban crime to analyze its spatio-temporal patterns and determine any developing trends. The associated covariates and their changes are also analyzed. The model is then used to analyze data regarding burglaries that occurred in Wuhan City in China from January to August 2013. Of the diverse socio-economic variables associated with crime rate, including population, the number of local internet bars, hotels, shopping centers, unemployment rate, and residential zones, this study finds that the burglary crime rate is significantly correlated with the average resident population per community and number of local internet bars. This finding provides a scientific reference for urban safety protection.

Taxi trajectories reflect human mobility over a road network. Pick-up and drop-off locations in different time periods represent origins and destinations of trips, respectively, demonstrating the spatiotemporal characteristics of human behavior. Each trip can be viewed as a displacement in the random walk model, and the distribution of extracted trips shows a distance decay effect. To identify the spatial similarity of trips at a finer scale, this paper investigates the distribution of trips through topic modeling techniques. Firstly, trip origins and trip destinations were identified from raw GPS data. Then, different trips were given semantic information, i.e., link identification numbers with a semantic enrichment process. Each taxi trajectory was composed of a series of trip destinations corresponding to the same taxi. Subsequently, each taxi trajectory was analogous to a document consisting of different words, and all taxi’s trajectories could be regarded as document corpora, enabling a semantic analysis of massive trip destinations. Finally, we obtained different trip destination topics reflecting the spatial similarity and regional property of human mobility through LDA topic model training. The effectiveness of this approach was illustrated by a case study using a large dataset of taxi trajectories collected from 2 to 8 June 2014 in Wuhan, China.

With the rapid development of indoor localization in recent years; signals of opportunity have become a reliable and convenient source for indoor localization. The mobile device cannot only capture images of the indoor environment in real-time, but can also obtain one or more different types of signals of opportunity as well. Based on this, we design a convolutional neural network (CNN) model that concatenates features of image data and signals of opportunity for localization by using indoor scene datasets and simulating the situation of indoor location probability. Using the method of transfer learning on the Inception V3 network model feature information is added to assist in scene recognition. The experimental result shows that, for two different experiment sceneries, the accuracies of the prediction results are 97.0% and 96.6% using the proposed model, compared to 69.0% and 81.2% by the method of overlapping positioning information and the base map, and compared to 73.3% and 77.7% by using the fine-tuned Inception V3 model. The accuracy of indoor scene recognition is improved; in particular, the error rate at the spatial connection of different scenes is decreased, and the recognition rate of similar scenes is increased.