To address the limitations of existing methods for dynamic vehicle routing problems, including exponential growth in solving time as problem size increases, susceptibility to local optima, and difficulty in handling stochastic demands and changes, we propose an online deep reinforcement learning algorithm for solving dynamic vehicle routing problems with time windows. First, we establish a partially observable Markov decision process (POMDP) model based on the time sequence of customer deliveries by the fleet. This model describes the interaction between the agent and the dynamic environment. Second, we propose a network model based on the Transformer architecture with multi-head attention to represent the policy and value function networks. Additionally, an actor-critic algorithm with a greedy baseline is designed to train the neural networks. Once trained, the network model can provide end-to-end solutions for dynamic vehicle routing problems and adjust planned routes online based on dynamic changes in problem conditions. Experiments demonstrate that the proposed method outperforms advanced meta-heuristic algorithms and deep reinforcement learning algorithms in both solution speed and quality, indicating that this method can efficiently achieve online optimization for dynamic vehicle routing problems with time windows.

Demand-responsive customized bus (DRCB) provides a new direction for the transformation of the traditional bus industry. However, most existing DRCB path planning strategies adopt heuristic algorithms and often fall short in terms of solution accuracy and computational efficiency, making them inadequate for practical application. Therefore, this paper proposes a path planning strategy that combines Dijkstra's algorithm with Q-learning. First, Dijkstra's algorithm is used to calculate the shortest path between any two nodes in the transportation network. Then, based on the results, the Q-learning algorithm is employed to explore the shortest path passing through multiple target nodes. Finally, experimental validation is conducted. The results demonstrate that Dijkstra's algorithm can enhance the speed and accuracy of the Q-learning algorithm in solving DRCB path planning problem.

Traffic prediction is important for Intelligent Transport System, and it is also the basis of many practical applications. However, traffic data are often highly non-linear and have complex spatio-temporal relationships, making this task challenging. In this paper, a new deep learning framework, Weighted Graph Convolutional Long Short-term Memory Network (WGCN-LSTM), is proposed for urban traffic flow prediction. The model combines the advantages of graph convolutional networks (GCN) and Long short-term memory networks (LSTM) to capture both spatial and temporal features in traffic flow data. WGCN-LSTM can reflect the actual network topology more accurately by weighting the road length and traffic flow. The experimental results show that WGCN-LSTM has higher prediction accuracy than other baseline models on two real traffic flow data sets, which verifies the effectiveness and applicability of this method in complex traffic prediction tasks.

The outbreak of coronavirus disease (COVID-19) has swept across more than 180 countries and territories since late January 2020. As a worldwide emergency response, governments have implemented various measures and policies, such as self-quarantine, travel restrictions, work from home, and regional lockdown, to control the spread of the epidemic. These countermeasures seek to restrict human mobility because COVID-19 is a highly contagious disease that is spread by human-to-human transmission. Medical experts and policymakers have expressed the urgency to effectively evaluate the outcome of human restriction policies with the aid of big data and information technology. Thus, based on big human mobility data and city POI data, an interactive visual analytics system called Epidemic Mobility (EpiMob) was designed in this study. The system interactively simulates the changes in human mobility and infection status in response to the implementation of a certain restriction policy or a combination of policies (e.g., regional lockdown, telecommuting, screening). Users can conveniently designate the spatial and temporal ranges for different mobility restriction policies. Then, the results reflecting the infection situation under different policies are dynamically displayed and can be flexibly compared and analyzed in depth. Multiple case studies consisting of interviews with domain experts were conducted in the largest metropolitan area of Japan (i.e., Greater Tokyo Area) to demonstrate that the system can provide insight into the effects of different human mobility restriction policies for epidemic control, through measurements and comparisons.

This paper considers the problem of inferring actual count of mobility dynamics in regional fine-grained scenarios given only few labeled GPS flow data (labeled here means GPS flow data with actual count of moving dynamics). This problem is challenging due to low-labeled GPS data and unseen scenarios. The existing research usually use residential census data or sensors' data in large area as reference ground truth to scale GPS flow to match the real count, which is further limited to apply in more fine-grained areas. In this paper, we extend the connection between few pairs of GPS flow and real count to unseen scenarios by inferring the relation of count estimation only based on GPS flow. Two cross attention modules are further utilized. The first one is to learn more discriminative features of unlabeled GPS flow from labeled GPS flow while the second one is to learn the coefficients to estimate the real count by measuring the similarity between GPS flows. Extensive experiments on two real-world large datasets show our method is a simple, effective framework, and outperforms the other approaches.

Predicting the density and flow of the crowd or traffic at a citywide level becomes possible by using the big data and cutting-edge AI technologies. It has been a very significant research topic with high social impact, which can be widely applied to emergency management, traffic regulation, and urban planning. In particular, by meshing a large urban area to a number of fine-grained mesh-grids, citywide crowd and traffic information in a continuous time period can be represented with 4D tensor (Timestep, Height, Width, Channel). Based on this idea, a series of methods have been proposed to address grid-based prediction for citywide crowd and traffic. In this study, we revisit the density and in-out flow prediction problem and publish a new aggregated human mobility dataset generated from a real-world smartphone application. Comparing with the existing ones, our dataset holds several advantages including large mesh-grid number, fine-grained mesh size, and high user sample. Towards this large-scale crowd dataset, we propose a novel deep learning model called DeepCrowd by designing pyramid architectures and high-dimensional attention mechanism based on Convolutional LSTM. Lastly, thorough and comprehensive performance evaluations are conducted to demonstrate the superiority of the proposed DeepCrowd comparing to multiple state-of-the-art methods.

With the rapid development of the Intelligent Transportation System (ITS), accurate traffic forecasting has emerged as a critical challenge. The key bottleneck lies in capturing the intricate spatio-temporal traffic patterns. In recent years, numerous neural networks with complicated architectures have been proposed to address this issue. However, the advancements in network architectures have encountered diminishing performance gains. In this study, we present a novel component called spatio-temporal adaptive embedding that can yield outstanding results with vanilla transformers. Our proposed Spatio-Temporal Adaptive Embedding transformer (STAEformer) achieves state-of-the-art performance on five real-world traffic forecasting datasets. Further experiments demonstrate that spatio-temporal adaptive embedding plays a crucial role in traffic forecasting by effectively capturing intrinsic spatio-temporal relations and chronological information in traffic time series.

Traffic forecasting as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the spatio-temporal heterogeneity and non-stationarity implied in the traffic stream, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (i.e., METR-LA and PEMS-BAY) and a new large-scale traffic speed dataset called EXPY-TKY that covers 1843 expressway road links in Tokyo. Our model outperformed the state-of-the-arts on all three datasets. Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle the road links and time slots with different patterns and be robustly adaptive to any anomalous traffic situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

A core component of the Intelligent Transportation System (ITS) is road network, which forms the most basic transport infrastructure, and becomes widely applied in many traffic applications. In most traffic models, the spatial representation of road network is learned only through static graph connection while dynamic driver preference and traffic conditions in the real world are ignored. Therefore, in this paper, a novel trajectory-based road network representation is proposed. By mining vehicle trajectories, our proposed method can learn dynamic route choice through embeddings of each road in a next-hop prediction model. Then road correlations are calculated by the embeddings to build a latent correlation graph that can be applied in various traffic-related applications. Extensive experiment results prove the effectiveness and rationality of our proposed approach.

Spatio-temporal modeling as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the underlying heterogeneity and non-stationarity implied in the graph streams, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (METR-LA and PEMS-BAY) and a large-scale spatio-temporal dataset that contains a variaty of non-stationary phenomena. Our model outperformed the state-of-the-arts to a large degree on all three datasets (over 27% MAE and 34% RMSE). Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle locations and time slots with different patterns and be robustly adaptive to different anomalous situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

Event crowd management has been a significant research topic with high social impact. When some big events happen such as an earthquake, typhoon, and national festival, crowd management becomes the first priority for governments (e.g., police) and public service operators (e.g., subway/bus operator) to protect people’s safety or maintain the operation of public infrastructures. However, under such event situations, human behavior will become very different from daily routines, which makes prediction of crowd dynamics at big events become highly challenging, especially at a citywide level. Therefore in this study, we aim to extract the “deep” trend only from the current momentary observations and generate an accurate prediction for the trend in the short future, which is considered to be an effective way to deal with the event situations. Motivated by these, we build an online system called DeepUrbanEvent, which can iteratively take citywide crowd dynamics from the current one hour as input and report the prediction results for the next one hour as output. A novel deep learning architecture built with recurrent neural networks is designed to effectively model these highly complex sequential data in an analogous manner to video prediction tasks. Experimental results demonstrate the superior performance of our proposed methodology to the existing approaches. Lastly, we apply our prototype system to multiple big real-world events and show that it is highly deployable as an online crowd management system.

Traffic state prediction is essential in Intelligent Transportation Systems for surveillance, management, and daily commuting. For developing high-accuracy prediction models, real-world traffic state datasets are necessary for training model parameters and evaluating prediction results. However, limited by the existing traffic collection devices, most of the current open datasets for traffic state prediction cannot obtain accurate traffic flow information. In contrast, some datasets directly use detection devices in freeway systems, so they cannot reflect complex urban traffic states. Therefore, a dataset from advanced devices that can record the flow from point to point on an urban road network attracts more attention and drives the progress of research on traffic state prediction models. To deal with the above issues, we introduce a Suburban Traffic Flow dataset using Geomagnetic sensors, or STF-G dataset, constructed for traffic flow prediction. The STF-G dataset consists of 2.5 billion vehicle driving scenarios and 319 corresponding geomagnetic sensors. The data was collected over 20 months and processed with two regional road graphs. We also do the Benchmark experiments in STF-G for analyzing and evaluating the performance of graph neural network models in traffic flow prediction and compare them to the other datasets with the same baseline.

Citywide crowd prediction can be of great importance for emergency management, traffic regulation, and urban planning. By meshing a large urban area to a number of fine-grained mesh-grids as illustrated in Fig. 1 , citywide crowd in a continuous time period can be represented with a four-dimensional tensor ${\mathbb{R}^{Timestep{\text{ }}p \times {\text{ }}Height{\text{ }} \times {\text{ }}Width{\text{ }} \times {\text{ }}Channel{\text{ }}}}$ in an analogous manner to video data, where each Timestep can be seen as one video frame, Height , Width is two-dimensional index for mesh-grids, and each Channel stores an aggregated scalar value for each mesh-grid. Specifically, given historical observations of crowd density and in-out flow x d = d 1 ,…,d t , xf = f 1 ,…, f t at timestamp t , we aim to build prediction models for the next-step density and in-out flow y d = d t +1, yf = f t +1, where y d means how many people will be in each mesh-grid at the next timestamp, and yf means how many people will flow into or out from each mesh-grid in next time interval. Al-though many deep models [1] – [6] have been proposed to address such tasks, their actual effects are still not well validated on large-scale and high-quality datasets. The datasets used in most of the works so far are originally generated based on taxi or bicycle trip data, which don’t cover and reflect the citywide crowd density and flow. Thus, we first publish new crowd flow data called BousaiTYO and BousaiOSA [7] . These new datasets are created using the GPS log data collected from a popular smartphone app of Yahoo! Japan Corporation, which can well reflect the real-world crowd flow in Tokyo and Osaka. As shown by Table 1 , our dataset has: (1) larger spatial area; (2) finer mesh size; (3) higher user sample.

COVID-19 has spread worldwide, and over 140 million people have been confirmed infected, over 3 million people have died, and the numbers are still increasing dramatically. The consensus has been reached by scientists that COVID-19 can be transmitted in an airborne way, and human-to-human transmission is the primary cause of the fast spread of COVID-19. Thus, mobility should be restricted to control the epidemic, and many governments worldwide have succeeded in curbing the spread by means of control policies like city lockdowns. Against this background, we propose a novel fine-grained transmission model based on realworld human mobility data and develop a platform that helps the researcher or governors to explore the possibility of future development of the epidemic spreading and simulate the outcomes of human mobility and the epidemic state under different epidemic control policies. The proposed platform can also support users to determine potential contacts, discover regions with high infectious risks, and assess the individual infectious risk. The multi-functional platform aims at helping the users to evaluate the effectiveness of a regional lockdown policy and facilitate the process of screening and more accurately targeting the potential virus carriers.

Every day, people are using search engines for different purposes such as research, shopping, or entertainment. Among the behaviors of search engine users, we are particularly interested in search-and-go behavior, which intuitively corresponds to a simple but challenging question, i.e., will users go where they search? Accurately estimating such behavior can be of great importance for Internet companies to recommend point-of-interest (POI), advertisement, and route, as well as for governments and public service operators like metro companies to conduct traffic monitoring, crowd management, and transportation scheduling. Therefore, in this study, we first collect search log data and GPS log data with linked and consistent user ID from Yahoo! Japan portal application installed in millions of smart-phones and tablets. Then we propose a framework including a complete data-processing procedure and an end-to-end deep learning model to predict whether a user will check-in the searched place or not. Specifically, as users’ daily activities are considered to have high correlation with their travel, eating, and recreation decision in the future (i.e., go or not), Deep Spatial–Temporal Interaction Network (DeepSTIN) is elaborately designed to automatically learn the sophisticated spatiotemporal interactions between mobility data and search query data. Experimental results based on the standard metrics demonstrate that our proposed framework can achieve satisfactory performances on multiple real-world search scenarios.

Knowing "what is happening" and "what will happen" of the mobility in a city is the building block of a data-driven smart city system. In recent years, mobility digital twin that makes a virtual replication of human mobility and predicting or simulating the fine-grained movements of the subjects in a virtual space at a metropolitan scale in near real-time has shown its great potential in modern urban intelligent systems. However, few studies have provided practical solutions. The main difficulties are four-folds: 1) the daily variation of human mobility is hard to model and predict; 2) the transportation network enforces a complex constraints on human mobility; 3) generating a rational fine-grained human trajectory is challenging for existing machine learning models; and 4) making a fine-grained prediction incurs high computational costs, which is challenging for an online system. Bearing these difficulties in mind, in this paper we propose a two-stage human mobility predictor that stratifies the coarse and fine-grained level predictions. In the first stage, to encode the daily variation of human mobility at a metropolitan level, we automatically extract citywide mobility trends as crowd contexts and predict long-term and long-distance movements at a coarse level. In the second stage, the coarse predictions are resolved to a fine-grained level via a probabilistic trajectory retrieval method, which offloads most of the heavy computations to the offline phase. We tested our method using a real-world mobile phone GPS dataset in the Kanto area in Japan, and achieved good prediction accuracy and a time efficiency of about 2 min in predicting future 1h movements of about 220K mobile phone users on a single machine to support more higher-level analysis of mobility prediction.

Rapidly developing location acquisition technologies provide a powerful tool for understanding and predicting human mobility in cities, which is very significant for urban planning, traffic regulation, and emergency management. However, with the existing methodologies, it is still difficult to accurately predict millions of peoples’ mobility in a large urban area such as Tokyo, Shanghai, and Hong Kong, especially when collected data used for model training are often limited to a small portion of the total population. Obviously, human activities in city are closely linked with point-of-interest (POI) information, which can reflect the semantic meaning of human mobility. This motivates us to fuse human mobility data and city POI data to improve the prediction performance with limited training data, but current fusion technologies can hardly handle these two heterogeneous data. Therefore, we propose a unique POI-embedding mechanism, that aggregates the regional POIs by categories to generate an artificial POI-image for each urban grid and enriches each trajectory snippet to a four-dimensional tensor in an analogous manner to a short video. Then, we design a deep learning architecture combining CNN with LSTM to simultaneously capture both the spatiotemporal and geographical information from the enriched trajectories. Furthermore, transfer learning is employed to transfer mobility knowledge from one city to another, so that we can fully utilize other cities’ data to train a stronger model for the target city with only limited data available. Finally, we achieve satisfactory performance of human mobility prediction at the citywide level using a limited amount of trajectories as training data, which has been validated over five urban areas of different types and scales.

With the rapid development of the modern city, technologies of smart cities are indispensable for solving urban problems. Medical services are one of the key areas related to the lives of urban residents. In particular, how to effectively manage the human resources of a hospital is a complex and challenging problem to improve treatment capabilities. Due to the grievous shortage of medical personnel, hospitals have to make quality schedules to improve the efficiency of the hospital and the utilization rate of human resources. Although there have been a large number of researches on hospital staff scheduling, few people also consider future patient population forecasts, doctor scheduling and hospital structure. These factors are very important in the hospital staff scheduling problem. Concerning this, this paper establishes an optimization system combining a two-layer mixed-integer linear programming and an extended prophet model for the hospital personnel scheduling. The model considers factors such as weather, disease types, number of patients, room resources, doctor resources, working hours, etc., and can quickly obtain a timetable with complex constraints. Finally, the convergence and the practicability of the model has been verified with real data from a hospital in China.