As the number of vehicles grows in urban cities, planning vehicle routes to avoid congestion and decrease commuting time is important. In this paper, we study the shortest path problem (SPP) withmultiplesource-destination pairs, namely MSD-SPP, to minimize the average travel time of all routing paths. The asynchronous setting in MSD-SPP, i.e., vehicles may not simultaneously complete routing actions, makes it challenging for cooperative route planning among multiple agents and leads to ineffective route planning. To tackle this issue, in this paper, we propose a two-stage framework of inter-region and intra-region route planning by dividing an entire road network into multiple sub-graph regions. Next, the proposed asyn-MARL model allows efficient asynchronous multi-agent learning by three key techniques. Firstly, the model adopts a low-dimensional global state to implicitly represent the high-dimensional joint observations and actions of multi-agents. Secondly, by a novel trajectory collection mechanism, the model can decrease the redundancy in training trajectories. Additionally, with a novel actor network, the model facilitates the cooperation among vehicles towards the same or close destinations, and a reachability graph can prevent infinite loops in routing paths. On both synthetic and real road networks, the evaluation result demonstrates that asyn-MARL outperforms state-of-the-art planning approaches.

The constrained shortest path ($\mathtt {CSP}$) problem has wide applications in travel path planning, mobile video broadcasting and network routing. Existing works do not work well on large dynamic graphs and suffer from either ineffectiveness or low scalability issues. To overcome these issues, in this paper, we propose an efficient and effective solution framework, namely$\mathtt {CSP\_{G}S}$. The solution framework includes two key components: (1) the techniques to decompose a large$\mathtt {CSP}$instance into multiple small sub-instances and (2) the developed learning model$\mathtt {CSP\_{D}QN}$to solve small$\mathtt {CSP}$instances. The evaluation result on real road network graphs indicates that our approach$\mathtt {CSP\_{G}S}$performs well on large dynamic graphs by rather high quality and reasonable running time, and particularly adapt to significant graph changes even with broken edges. To the best of our knowledge, this is the first learning-based model to well solve the$\mathtt {CSP}$problem on large dynamic graphs.

Multivariate time series forecasting has wide applications such as traffic flow prediction, supermarket commodity demand forecasting and etc., and a large number of forecasting models have been developed. Given these models, a natural question has been raised: what theoretical limits of forecasting accuracy can these models achieve? Recent works of urban human mobility prediction have made progress on the maximum predictability that any algorithm can achieve. However, existing approaches on maximum predictability on the multivariate time series fully ignore the interrelationship between multiple variables. In this article, we propose a methodology to measure the upper limit of predictability for multivariate time series with multivariate constraint relations. The key of the proposed methodology is a novel entropy, named Multivariate Constraint Sample Entropy (McSE), to incorporate the multivariate constraint relations for better predictability. We conduct a systematic evaluation over eight datasets and compare existing methods with our proposed predictability and find that we get a higher predictability. We also find that the forecasting algorithms that capture the multivariate constraint relation information, such as GNN, can achieve higher accuracy, confirming the importance of multivariate constraint relations for predictability.

How to perform human mobility simulation and generate massive and high-quality individual mobility trajectories is an important and challenging research problem. Existing works generate mobility trajectories, suffering from the issues of missing either macro- or micro-scopic mobility. In this paper, we develop a mobile trajectory generation framework to simulate human mobility. This framework attempts to simulate both macro-and micro-scopic human mobility by incorporating both macro-and micro-scopic models. Our very initial results demonstrate the possibility to generate dense mobile trajectory exhibiting reasonable macro- and micro-scopic human mobility.

The shortest path problem (SPP) in graph theory has wide applications in daily travels, transportation and network routing. Existing works do not work well on large dynamic graphs and suffer from either low scalability or gealization issue. To overcome these issues, in this paper, we propose an efficient and effective learning framework, namely SPP-GS, to solve the SPP problem on large dynamic graph. The key components of SPP- GS include the techniques to decompose a large SPP instance into multiple small instance and the developed GCN-DQN model to solve small SPP instances. The evaluation result on 7 real road network graphs indicates that our approach SPP-GS performs well on large dynamic graphs by rather high quality and reasonable running time.

This work proposes a novel approach for multiple time series forecasting. At first, multi-way delay embedding transform (MDT) is employed to represent time series as low-rank block Hankel tensors (BHT). Then, the higher-order tensors are projected to compressed core tensors by applying Tucker decomposition. At the same time, the generalized tensor Autoregressive Integrated Moving Average (ARIMA) is explicitly used on consecutive core tensors to predict future samples. In this manner, the proposed approach tactically incorporates the unique advantages of MDT tensorization (to exploit mutual correlations) and tensor ARIMA coupled with low-rank Tucker decomposition into a unified framework. This framework exploits the low-rank structure of block Hankel tensors in the embedded space and captures the intrinsic correlations among multiple TS, which thus can improve the forecasting results, especially for multiple short time series. Experiments conducted on three public datasets and two industrial datasets verify that the proposed BHT-ARIMA effectively improves forecasting accuracy and reduces computational cost compared with the state-of-the-art methods.

Multivariate time series forecasting has wide applications such as traffic flow prediction, supermarket commodity demand forecasting and etc. In literature, Due to the complex temporal patterns and inter-dependencies among multivariate time series, a large number of forecasting models have been developed. However, one question still remains unclear: how these models perform on a certain forecasting task, and there is lack of comprehensive performance comparison of these models on different tasks. To this end, in this paper, we conduct a systematic evaluation of eight representative forecasting models over eight multivariate time series datasets, and have the following findings: 1) When the datasets exhibit strong periodic patterns, deep learning models perform best. Otherwise on the datasets in a non-periodic manner, the statistical models such as ARIMA perform best. 2) For the long term prediction involving a high horizon value, the direct prediction strategy could lead to lower errors than the recursive one, but at the cost of higher training time. 3) For the multivariate time series explicitly involving graphic inter-dependencies among the multivariates, e.g., the road network topology in the spatio-temporal time series of traffic volumes in multiple routes, the Graph Convolution Network can incorporate the graphic inter-dependencies into their forecasting models for smaller prediction errors.

Images can not only display contents themselves, but also convey emotions, e.g., excitement, sadness. Affective image classification is useful and hot in many fields such as computer vision and multimedia. Current researches usually consider the relationship model between images and emotions as a black box. They extract the traditional discursive visual features such as SIFT and wavelet textures, and use them directly upon various classification algorithms. However, these visual features are not interpretable, and people cannot know why such a set of features induce a particular emotion. And due to the highly subjective nature of images, the classification accuracies on these visual features are not satisfactory for a long time. We propose the interpretable aesthetic features to describe images inspired by art theories, which are intuitive, discriminative and easily understandable. Affective image classification based on these features can achieve higher accuracy, compared with the state-of-the-art. Specifically, the features can also intuitively explain why an image tends to convey a certain emotion. We also develop an emotion guided image gallery to demonstrate the proposed feature collection.