Forecasting traffic flow and speed in the urban is important for many applications, ranging from the intelligent navigation of map applications to congestion relief of city management systems. Therefore, mining the complex spatio-temporal correlations in the traffic data to accurately predict traffic is essential for the community. However, previous studies that combined the graph convolution network or self-attention mechanism with deep time series models (e.g., the recurrent neural network) can only capture spatial dependencies in each time slot and temporal dependencies in each sensor, ignoring the spatial and temporal correlations across different time slots and sensors. Besides, the state-of-the-art Transformer architecture used in previous methods is insensitive to local spatio-temporal contexts, which is hard to suit with traffic forecasting. To solve the above two issues, we propose a novel deep learning model for traffic forecasting, named Locality-aware spatio-temporal joint Transformer (Lastjormer), which elaborately designs a spatio-temporal joint attention in the Transformer architecture to capture all dynamic dependencies in the traffic data. Specifically, our model utilizes the dot-product self-attention on sensors across many time slots to extract correlations among them and introduces the linear and convolution self-attention mechanism to reduce the computation needs and incorporate local spatio-temporal information. Experiments on three real-world traffic datasets, England, METR-LA, and PEMS-BAY, demonstrate that our Lastjormer achieves state-of-the-art performances on a variety of challenging traffic forecasting benchmarks.
24 April 2020 in IEEE Transactions on Intelligent Transportation Systems
In recent years, with the rapid development of public transportation, the ways people travel has become more diversified and complicated. Transportation mode detection, as a significant branch of human activity recognition (HAR), is of great importance in analyzing human travel patterns, traffic prediction and planning. Though many works have been devoted to transportation mode detection, there remains challenge for accurate and robust transportation pattern identification. In this paper, we propose a residual and LSTM recurrent networks-based transportation mode detection algorithm using multiple light-weight sensors integrated in commodity smartphones. Feature representation learning is adopted separately on multiple preprocessed sensor data using deep residual and LSTM network, which can enhance the identification accuracy and support one or more sensors. Residual units are introduced to accelerate the learning speed and enhance the accuracy of transportation mode detection. Furthermore, we also leverage the attention model to learn the significance of different features and different timesteps to enhance the recognition accuracy. Extensive experimental results on three datasets indicate that using our proposed model can achieve the best recognition accuracy for eight transportation modes including being stationary, walking, running, cycling, taking a car, taking a bus, taking a subway and taking a train, which outperforms other benchmark algorithms.
With the rapid development of mobile Internet techniques, using the sensor-rich smartphones to sense various contexts attracts much attention, such as transportation mode recognition. The transportation mode information can help to improve urban planning, traffic management and journey planning. Though much work has been done on the transportation mode recognition using classic machine learning algorithms, the performance of these methods is not reasonable and heavily relies on the effectiveness of handcrafted features. In this paper, we leverage the strong representation ability of deep learning method and present a deep-learning-based algorithm for transportation mode recognition, namely CL-TRANSMODE, which is capable of accurately detecting multiple transportation modes. The algorithm first uses a convolutional neural network (CNN) to learn appropriate and robust feature representations for transportation modes recognition. Then, an LSTM network performs a further learning of the temporal dependencies characteristics on the feature vectors of CNN output. To further enhance the accuracy of transportation mode recognition, several artificial segments and peak features are extracted from the raw sensor measurements. These features characterize the transportation modes over a much long period of time (minutes or hours). By combining the CNN-extracted features and handcrafted features, our proposed CL-TRANSMODE transportation mode recognition algorithm can accurately differentiate eight transportation modes, i.e., walking, running, bicycling, driving a car, riding a bus, taking a metro, taking a train, or being stationary. Extensive experiments on both the SHL and HTC datasets demonstrate that use our proposed CL-TRANSMODE transportation mode recognition algorithm which outperforms the state-of-the-art comparative algorithms. On the SHL dataset, which contain barometric data, the accuracy using the CL-TRANSMODE algorithm can reaches 98.1%.
1 February 2022 in IEEE Transactions on Intelligent Transportation Systems
Travel Time Estimation (TTE) is indispensable in intelligent transportation system (ITS). It is significant to achieve the fine-grained Trajectory-based Travel Time Estimation (TTTE) for multi-city scenarios, namely to accurately estimate travel time of the given trajectory for multiple city scenarios. However, it faces great challenges due to complex factors including dynamic temporal dependencies and fine-grained spatial dependencies. To tackle these challenges, we propose a meta learning based framework, MetaTTE, to continuously provide accurate travel time estimation over time by leveraging well-designed deep neural network model called DED, which consists of Data preprocessing module and Encoder-Decoder network module. By introducing meta learning techniques, the generalization ability of MetaTTE is enhanced using small amount of examples, which opens up new opportunities to increase the potential of achieving consistent performance on TTTE when traffic conditions and road networks change over time in the future. The DED model adopts an encoder-decoder network to capture fine-grained spatial and temporal representations. Extensive experiments on two real-world datasets are conducted to confirm that our MetaTTE outperforms nine state-of-art baselines, and improve 29.35% and 25.93% accuracy than the best baseline on Chengdu and Porto datasets, respectively.
Traffic forecasting belongs to intelligent transportation systems and is helpful for public property and life safety. Therefore, to forecast traffic accurately, researchers pay great attention to dealing with complex problems by mining intricate spatial and temporal dependencies of the traffic. However, some challenges still hold back traffic forecasting: 1) Most studies mainly focus on modeling correlations of traffic time series of close distances on the road network and ignore correlations of remote but similar traffic time series; 2) Previous static graph-based methods failed to reflect the dynamic changed spatial relations of multiple time series in the evolving traffic system. To tackle the above issues, we design a new dynamic multigraph spatio-temporal convolution network (DMGSTCN) in this article, which utilizes the gated causal convolution with the dynamic multigraph convolution network (DMGCN) to simultaneously extract spatial and temporal information. Specifically, DMGCN uses not only distance-based graphs but also structure-based graphs to obtain spatial information from nearby and remote but similar traffic time series, respectively. Moreover, to dynamically model spatial correlations, DMGCN first splits neighbors of each traffic time series into different regions according to relative position relationships. Then DMGCN assigns different weights to different regions at different time slices. Empirical evaluations on four traffic forecasting benchmarks reveal that DMGSTCN outperforms existing methods.
10 February 2022 in International Journal of Intelligent Systems