With the development and acceleration of urbanization, urban metro traffic is gradually growing up to a large network, and the structure of topology between stations becomes more complex, which makes it increasingly difficult to capture the spatial dependency. The vertical and horizontal interlacing of multiple lines makes the stations distributed topologically, and the traditional graph convolution is implemented on the adjacency matrix generated based on a priori knowledge, which cannot reflect the actual spatial dependence between stations. To address these problems, this paper proposes an adaptive graph convolutional network model (Adapt-GCN), which replaces the fixed adjacency matrix obtained from a priori knowledge in the traditional GCN with a trainable adaptive adjacency matrix. This can not only effectively adjust the weights of correlations between adjacent stations, but also adaptively capture the spatial dependencies between non-adjacent stations. This paper uses the Shanghai Metro dataset to verify the effectiveness of the model in improving prediction accuracy and reducing training time.
18 September 2024 in IEEE Transactions on Intelligent Transportation Systems
Traffic flow forecasting is challenging due to the intricate spatio-temporal correlations in traffic patterns. Previous works captured spatial dependencies based on graph neural networks and used fixed graph construction methods to characterize spatial relationships, which limits the ability of models to capture dynamic and long-range spatial dependencies. Meanwhile, prior studies did not consider the issue of a large number of redundant parameters in traffic prediction models, which not only increases the storage cost of the model but also reduces its generalization ability. To address the above challenges, we propose a Dynamic Spatial Transformer for Traffic Forecasting with Low-Rank Tensor Compression (DSFormer-LRTC). Specifically, we constructed a global spatial Transformer to capture remote spatial dependencies, and a distance-based mask matrix is used in local spatial Transformer to enhance the adjacent spatial influence. To reduce the complexity of the model, the model adopts a design that separates temporal and spatial. Meanwhile, we introduce low-rank tensor decomposition to reconstruct the parameter matrix in Transformer module to compress the proposed model. Experimental results show that DSFormer-LRTC achieves state-of-the-art performance on four real-world datasets. The experimental analysis of attention matrix also proves that the model can learn dynamic and distant spatial features. Finally, the compressed model parameters reduce the original parameter size by two-thirds, while significantly outperforming the baseline model in terms of computational efficiency.
Wireless local area network (WLAN) fingerprint-based localization has become the most attractive and popular approach for indoor localization. However, the primary concern for its practical implementation is the laborious manual effort of calibrating sufficient location-labeled fingerprints. The Semi-supervised extreme learning machine (SELM) performs well in reducing calibration effort. Traditional SELM methods only use Received signal strength (RSS) information to construct the neighbor graph and ignores location information, which helps recognizing prior information for manifold alignments. We propose Composite SELM (CSELM) method by using both RSS signals and location information to construct composite graph. Besides, the issue of unlabeled RSS data quality has not been solved. We propose a novel approach called Composite semisupervised extreme learning machine with unlabeled RSS Quality estimation (CSELM-QE) that takes into account the quality of unlabeled RSS data and combines the composite neighbor graph, which considers location information in the semi-supervised extreme learning machine. Experimental results show that the CSELM-QE could construct a precise localization model, reduce the calibration effort for radio map construction and improve localization accuracy. Our quality estimation method can be applied to other methods that need to retain high quality unlabeled Received signal strength data to improve model accuracy.
31 January 2021 in KSII Transactions on Internet and Information Systems
To reduce the risk of traffic congestion to residents and the urban transportation system, this paper extracted frequently congested areas and major trunk roads based on the GPS (global positioning system) data of cabs and TPI (traffic performance index) data and identified traffic patterns and main trunk roads in the traffic grid, so as to analyze the evolution of traffic congestion and make effective suggestions. The results can not only enable travelers to effectively avoid peak periods and congested sections but also support the managers to optimize urban planning and implement efficient traffic management methods. The research process of this study is as follows: firstly, the research object area was divided into different grids based on one-week taxi GPS data and the distribution characteristics of taxi operations in Qingdao. Secondly, the two-dimensional grid traffic attribute information is constructed using the following two indicators: number of vehicles and the average speed of passenger trajectory. Then, the congestion discriminant model based on the three-dimensional traffic attribute information was established according to the variation rules of the number of position point in the grid. Finally, the TPI data was applied to compare and evaluate the identification results of the above two models to identify frequently congested grids and main trunk roads. The case analysis showed that the result of grid’s congestion status identification considering three-dimensional traffic attribute information (25.198%) was better than that of grid congestion state considering two-dimensional traffic attribute information (23.997%).