ACM Transactions on Intelligent Systems and Technology

Includes bibliographical references.

Introduction to the Special Issue on Intelligent Trajectory Analytics: Part I -- Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graphs -- Instant Basketball Defensive Trajectory Generation -- Contrastive Trajectory Learning for Tour Recommendation -- Origin-Aware Location Prediction Based on Historical Vehicle Trajectories -- Deep Siamese Metric Learning: A Highly Scalable Approach to Searching Unordered Sets of Trajectories -- Predicting Future Locations with Semantic Trajectories -- Let Trajectories Speak Out the Traffic Bottlenecks -- Exploring the Risky Travel Area and Behavior of Car-hailing Service -- Simultaneous Past and Current Social Interaction-aware Trajectory Prediction for Multiple Intelligent Agents in Dynamic Scenes -- An Uncertainty-based Neural Network for Explainable Trajectory Segmentation -- How Members of Covert Networks Conceal the Identities of Their Leaders -- Self-Adaptive Feature Transformation Networks for Object Detection in low luminance Images -- Mining Willing-to-Pay Behavior Patterns from Payment Datasets -- Graph Neural Networks: Taxonomy, Advances, and Trends -- FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings.

[Article Title: Introduction to the Special Issue on Intelligent Trajectory Analytics: Part I/ Kai Zheng, Yong Li, Cyrus Shahabi and Hongzhi Yin, p. 1:1-1:2] Abstract: We are delighted to present this special issue on Intelligent Trajectory Analytics. Over the past decades, a broad range of techniques have been proposed for processing, managing, and mining trajectory data. It enabled and helped government agencies and businesses to better understand the mobility behavior of their citizens and customers, which is crucial for a variety of applications such as smart city and transportation, public health and safety, environmental management, and location-based services. The purpose of this special issue is to provide a forum for researchers and practitioners in academia and industry to present their latest research findings and engineering experiences in developing cutting-edge techniques for intelligent trajectory data analytics. This special issue consists of two parts. In Part 1, the guest editors selected 10 contributions that cover varying topics within this theme, ranging from car-hailing services to location predictions, from representation learning to trajectory generation.;[Article Title: Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graphs/ Yuandong Wang, Hongzhi Yin, Tong Chen, Chunyang Liu, Ben Wang, Tianyu Wo and Jie Xu, p. 2:1-2:25] Abstract: In recent years, ride-hailing services have been increasingly prevalent, as they provide huge convenience for passengers. As a fundamental problem, the timely prediction of passenger demands in different regions is vital for effective traffic flow control and route planning. As both spatial and temporal patterns are indispensable passenger demand prediction, relevant research has evolved from pure time series to graph-structured data for modeling historical passenger demand data, where a snapshot graph is constructed for each time slot by connecting region nodes via different relational edges (origin-destination relationship, geographical distance, etc.). Consequently, the spatiotemporal passenger demand records naturally carry dynamic patterns in the constructed graphs, where the edges also encode important information about the directions and volume (i.e., weights) of passenger demands between two connected regions. aspects in the graph-structure data. representation for DDW is the key to solve the prediction problem. However, existing graph-based solutions fail to simultaneously consider those three crucial aspects of dynamic, directed, and weighted graphs, leading to limited expressiveness when learning graph representations for passenger demand prediction. Therefore, we propose a novel spatiotemporal graph attention network, namely Gallat (Graph prediction with allattention) as a solution. In Gallat, by comprehensively incorporating those three intrinsic properties of dynamic directed and weighted graphs, we build three attention layers to fully capture the spatiotemporal dependencies among different regions across all historical time slots. Moreover, the model employs a subtask to conduct pretraining so that it can obtain accurate results more quickly. We evaluate the proposed model on real-world datasets, and our experimental results demonstrate that Gallat outperforms the state-of-the-art approaches.;[Article Title: Instant Basketball Defensive Trajectory Generation/ Wen-Cheng Chen, Wan-Lun Tsai, Huan-Hua Chang, Min-Chun Hu and Wei-Ta Chu, p. 3:1-3:20] Abstract: Tactic learning in virtual reality (VR) has been proven to be effective for basketball training. Endowed with the ability of generating virtual defenders in real time according to the movement of virtual offenders controlled by the user, a VR basketball training system can bring more immersive and realistic experiences for the trainee. In this article, an autoregressive generative model for instantly producing basketball defensive trajectory is introduced. We further focus on the issue of preserving the diversity of the generated trajectories. A differentiable sampling mechanism is adopted to learn the continuous Gaussian distribution of player position. Moreover, several heuristic loss functions based on the domain knowledge of basketball are designed to make the generated trajectories assemble real situations in basketball games. We compare the proposed method with the state-of-the-art works in terms of both objective and subjective manners. The objective manner compares the average position, velocity, and acceleration of the generated defensive trajectories with the real ones to evaluate the fidelity of the results. In addition, more high-level aspects such as the empty space for offender and the defensive pressure of the generated trajectory are also considered in the objective evaluation. As for the subjective manner, visual comparison questionnaires on the proposed and other methods are thoroughly conducted. The experimental results show that the proposed method can achieve better performance than previous basketball defensive trajectory generation works in terms of different evaluation metrics.;[Article Title: Contrastive Trajectory Learning for Tour Recommendation/ Fan Zhou, Pengyu Wang, Xovee Xu, Wenxin Tai and Goce Trajcevski, p. 4:1-4:25] Abstract: The main objective of Personalized Tour Recommendation (PTR) is to generate a sequence of point-of-interest (POIs) for a particular tourist, according to the user-specific constraints such as duration time, start and end points, the number of attractions planned to visit, and so on. Previous PTR solutions are based on either heuristics for solving the orienteering problem to maximize a global reward with a specified budget or approaches attempting to learn user visiting preferences and transition patterns with the stochastic process or recurrent neural networks. However, existing learning methodologies rely on historical trips to train the model and use the next visited POI as the supervised signal, which may not fully capture the coherence of preferences and thus recommend similar trips to different users, primarily due to the data sparsity problem and long-tailed distribution of POI popularity. This work presents a novel tour recommendation model by distilling knowledge and supervision signals from the trips in a self-supervised manner. We propose Contrastive Trajectory Learning for Tour Recommendation (CTLTR), which utilizes the intrinsic POI dependencies and traveling intent to discover extra knowledge and augments the sparse data via pre-training auxiliary self-supervised objectives. CTLTR provides a principled way to characterize the inherent data correlations while tackling the implicit feedback and weak supervision problems by learning robust representations applicable for tour planning. We introduce a hierarchical recurrent encoder-decoder to identify tourists' intentions and use the contrastive loss to discover subsequence semantics and their sequential patterns through maximizing the mutual information. Additionally, we observe that a data augmentation step as the preliminary of contrastive learning can solve the overfitting issue resulting from data sparsity. We conduct extensive experiments on a range of real-world datasets and demonstrate that our model can significantly improve the recommendation performance over the state-of-the-art baselines in terms of both recommendation accuracy and visiting orders.;[Article Title: Origin-Aware Location Prediction Based on Historical Vehicle Trajectories/ Meng Chen, Qingjie Liu, Weiming Huang, Teng Zhang, Yixuan Zuo and Xiaohui Yu, p. 5:1-5:18] Abstract: Next location prediction is of great importance for many location-based applications and provides essential intelligence to various businesses. In previous studies, a common approach to next location prediction is to learn the sequential transitions with massive historical trajectories based on conditional probability. Nevertheless, due to the time and space complexity, these methods (e.g., Markov models) only utilize the just passed locations to predict next locations, neglecting earlier passed locations in the trajectory. In this work, we seek to enhance the prediction performance by incorporating the travel time from all the passed locations in the query trajectory to each candidate next location.

To this end, we propose a novel prediction method, namely the Travel Time Difference Model, which exploits the difference between the shortest travel time and the actual travel time to predict next locations. Moreover, we integrate the Travel Time Difference Model with a Sequential and Temporal Predictor to yield a joint model. The joint prediction model integrates local sequential transitions, temporal regularity, and global travel time information in the trajectory for the next location prediction problem. We have conducted extensive experiments on two real-world datasets: the vehicle passage record data and the taxi trajectory data. The experimental results demonstrate significant improvements in prediction accuracy over baseline methods.;[Article Title: Deep Siamese Metric Learning: A Highly Scalable Approach to Searching Unordered Sets of Trajectories/ Christoffer L├╢ffler, Luca Reeb, Daniel Dzibela, Robert Marzilger, Nicolas Witt, Bj├╢rn M. Eskofier and Christopher Mutschler, p. 6:1-6:23] Abstract: This work proposes metric learning for fast similarity-based scene retrieval of unstructured ensembles of trajectory data from large databases. We present a novel representation learning approach using Siamese Metric Learning that approximates a distance preserving low-dimensional representation and that learns to estimate reasonable solutions to the assignment problem. To this end, we employ a Temporal Convolutional Network architecture that we extend with a gating mechanism to enable learning from sparse data, leading to solutions to the assignment problem exhibiting varying degrees of sparsity. Our experimental results on professional soccer tracking data provides insights on learned features and embeddings, as well as on generalization, sensitivity, and network architectural considerations. Our low approximation errors for learned representations and the interactive performance with retrieval times several magnitudes smaller shows that we outperform previous state of the art.;[Article Title: Predicting Future Locations with Semantic Trajectories/ Heli Sun, Xianglan Guo, Zhou Yang, Xuguang Chu, Xinwang Liu and Liang He, p. 7:1-7:20] Abstract: Location prediction has attracted much attention due to its important role in many location-based services, including taxi services, route navigation, traffic planning, and location-based advertisements. Traditional methods only use spatial-temporal trajectory data to predict where a user will go next. The divorce of semantic knowledge from the spatial-temporal one inhibits our better understanding of users' activities. Inspired by the architecture of Long Short Term Memory (LSTM), we design ST-LSTM, which draws on semantic trajectories to predict future locations. Semantic data add a new dimension to our study, increasing the accuracy of prediction. Since semantic trajectories are sparser than the spatial-temporal ones, we propose a strategic filling algorithm to solve this problem. In addition, as the prediction is based on the historical trajectories of users, the cold-start problem arises. We build a new virtual social network for users to resolve the issue. Experiments on two real-world datasets show that the performance of our method is superior to those of the baselines.;[Article Title: Let Trajectories Speak Out the Traffic Bottlenecks/ Hui Luo, Zhifeng Bao, Gao Cong, J. Shane Culpepper and Nguyen Lu Dang Khoa, p. 8:1-8:21] Abstract: Traffic bottlenecks are a set of road segments that have an unacceptable level of traffic caused by a poor balance between road capacity and traffic volume. A huge volume of trajectory data which captures realtime traffic conditions in road networks provides promising new opportunities to identify the traffic bottlenecks. In this paper, we define this problem as trajectory-driven traffic bottleneck identification: Given a road network R, a trajectory database T, find a representative set of seed edges of size K of traffic bottlenecks that influence the highest number of road segments not in the seed set. We show that this problem is NP-hard and propose a framework to find the traffic bottlenecks as follows. First, a traffic spread model is defined which represents changes in traffic volume for each road segment over time. Then, the traffic diffusion probability between two connected segments and the residual ratio of traffic volume for each segment can be computed using historical trajectory data. We then propose two different algorithmic approaches to solve the problem. The first one is a best-first algorithm BF, with an approximation ratio of 1-1/e. To further accelerate the identification process in larger datasets, we also propose a sampling-based greedy algorithm SG. Finally, comprehensive experiments using three different datasets compare and contrast various solutions, and provide insights into important efficiency and effectiveness trade-offs among the respective methods. ;[Article Title: Exploring the Risky Travel Area and Behavior of Car-hailing Service/ Hongting Niu, Hengshu Zhu, Ying Sun, Xinjiang Lu, Jing Sun, Zhiyuan Zhao, Hui Xiong and Bo Lang, p. 9:1-9:22] Abstract: Recent years have witnessed the rapid development of car-hailing services, which provide a convenient approach for connecting passengers and local drivers using their personal vehicles. At the same time, the concern on passenger safety has gradually emerged and attracted more and more attention. While car-hailing service providers have made considerable efforts on developing real-time trajectory tracking systems and alarm mechanisms, most of them only focus on providing rescue-supporting information rather than preventing potential crimes. Recently, the newly available large-scale car-hailing order data have provided an unparalleled chance for researchers to explore the risky travel area and behavior of car-hailing services, which can be used for building an intelligent crime early warning system. To this end, in this article, we propose a Risky Area and Risky Behavior Evaluation System (RARBEs) based on the real-world car-hailing order data. In RARBEs, we first mine massive multi-source urban data and train an effective area risk prediction model, which estimates area risk at the urban block level. Then, we propose a transverse and longitudinal double detection method, which estimates behavior risk based on two aspects, including fraud trajectory recognition and fraud patterns mining. In particular, we creatively propose a bipartite graph-based algorithm to model the implicit relationship between areas and behaviors, which collaboratively adjusts area risk and behavior risk estimation based on random walk regularization. Finally, extensive experiments on multi-source real-world urban data clearly validate the effectiveness and efficiency of our system.;[Article Title: Simultaneous Past and Current Social Interaction-aware Trajectory Prediction for Multiple Intelligent Agents in Dynamic Scenes/ Yanliang Zhu, Dongchun Ren, Yi Xu, Deheng Qian, Mingyu Fan, Xin Li and Huaxia Xia, p. 10:1:10:16] Abstract: Trajectory prediction of multiple agents in a crowded scene is an essential component in many applications, including intelligent monitoring, autonomous robotics, and self-driving cars. Accurate agent trajectory prediction remains a significant challenge because of the complex dynamic interactions among the agents and between them and the surrounding scene. To address the challenge, we propose a decoupled attention-based spatial-temporal modeling strategy in the proposed trajectory prediction method. The past and current interactions among agents are dynamically and adaptively summarized by two separate attention-based networks and have proven powerful in improving the prediction accuracy. Moreover, it is optional in the proposed method to make use of the road map and the plan of the ego-agent for scene-compliant and accurate predictions. The road map feature is efficiently extracted by a convolutional neural network, and the features of the ego-agent's plan is extracted by a gated recurrent network with an attention module based on the temporal characteristic.

Experiments on benchmark trajectory prediction datasets demonstrate that the proposed method is effective when the ego-agent plan and the the surrounding scene information are provided and achieves state-of-the-art performance with only the observed trajectories.;[Article Title: An Uncertainty-based Neural Network for Explainable Trajectory Segmentation/ Xin Bi, Chao Zhang, Fangtong Wang, Zhixun Liu, Xiangguo Zhao, Ye Yuan and Guoren Wang, p. 11:1-11:18] Abstract: As a variant task of time-series segmentation, trajectory segmentation is a key task in the applications of transportation pattern recognition and traffic analysis. However, segmenting trajectory is faced with challenges of implicit patterns and sparse results. Although deep neural networks have tremendous advantages in terms of high-level feature learning performance, deploying as a blackbox seriously limits the real-world applications. Providing explainable segmentations has significance for result evaluation and decision making. Thus, in this article, we address trajectory segmentation by proposing a Bayesian Encoder-Decoder Network (BED-Net) to provide accurate detection with explainability and references for the following active-learning procedures. BED-Net consists of a segmentation module based on Monte Carlo dropout and an explanation module based on uncertainty learning that provides results evaluation and visualization. Experimental results on both benchmark and real-world datasets indicate that BED-Net outperforms the rival methods and offers excellent explainability in the applications of trajectory segmentation.;[Article Title: How Members of Covert Networks Conceal the Identities of Their Leaders/ Marcin Waniek, Tomasz P. Michalak, Michael Wooldridge and Talal Rahwan, p. 12:1-12:29] Abstract: Centrality measures are the most commonly advocated social network analysis tools for identifying leaders of covert organizations. While the literature has predominantly focused on studying the effectiveness of existing centrality measures or developing new ones, we study the problem from the opposite perspective, by focusing on how a group of leaders can avoid being identified by centrality measures as key members of a covert network. More specifically, we analyze the problem of choosing a set of edges to be added to a network to decrease the leaders' ranking according to three fundamental centrality measures, namely, degree, closeness, and betweenness. We prove that this problem is NP-complete for each measure. Moreover, we study how the leaders can construct a network from scratch, designed specifically to keep them hidden from centrality measures. We identify a network structure that not only guarantees to hide the leaders to a certain extent but also allows them to spread their influence across the network.;[Article Title: Self-Adaptive Feature Transformation Networks for Object Detection in low luminance Images/ Shih-Chia Huang, Quoc-Viet Hoang and Da-Wei Jaw, p. 13:1-13:11] Abstract: Despite the recent improvement of object detection techniques, many of them fail to detect objects in low-luminance images. The blurry and dimmed nature of low-luminance images results in the extraction of vague features and failure to detect objects. In addition, many existing object detection methods are based on models trained on both sufficient- and low-luminance images, which also negatively affect the feature extraction process and detection results. In this article, we propose a framework called Self-adaptive Feature Transformation Network (SFT-Net) to effectively detect objects in low-luminance conditions. The proposed SFT-Net consists of the following three modules: (1) feature transformation module, (2) self-adaptive module, and (3) object detection module. The purpose of the feature transformation module is to enhance the extracted feature through unsupervisely learning a feature domain projection procedure. The self-adaptive module is utilized as a probabilistic module producing appropriate features either from the transformed or the original features to further boost the performance and generalization ability of the proposed framework. Finally, the object detection module is designed to accurately detect objects in both low- and sufficient- luminance images by using the appropriate features produced by the self-adaptive module. The experimental results demonstrate that the proposed SFT-Net framework significantly outperforms the state-of-the-art object detection techniques, achieving an average precision (AP) of up to 6.35 and 11.89 higher on the sufficient- and low- luminance domain, respectively. ;[Article Title: Mining Willing-to-Pay Behavior Patterns from Payment Datasets/ Yu-Ting Wen, Hui-Kuo Yang and Wen-Chih Peng, p. 14:1-14:19] Abstract: The customer base is the most valuable resource to E-commerce companies. A comprehensive understanding of customers' preferences and behavior is crucial to developing good marketing strategies, in order to achieve optimal customer lifetime values (CLVs). For example, by exploring customer behavior patterns, given a marketing plan with a limited budget, a set of potential customers is able to be identified to maximize profit. In other words, personalized campaigns at the right time and in the right place can be treated as the last stage of consumption. Moreover, effective future purchase estimation and recommendation help guide the customer to the up-selling stage. The proposed willing-to-pay prediction model (W2P) exploits the transaction data to predict customer payment behavior based on a probabilistic graphical model, which provides semantic explanation of the estimated results and deals with the sparsity of payment data from each customer. Existing work in this domain ranks the customers by their probabilities of purchase in different conditions. However, the customer with the highest purchase probability does not necessarily spend the most. Therefore, we propose a CLV maximization algorithm based on the prediction results. In addition, we improve the model by behavioral segmentation wherein we group the customers by payment behaviors to reduce the size of the offline models and enhance the accuracy for low-frequency customers. The experiment results show that our model outperforms the state-of-the-art methods in purchase behavior prediction.;[Article Title: Graph Neural Networks: Taxonomy, Advances, and Trends/ Yu Zhou, Haixia Zheng, Xin Huang, Shufeng Hao, Dengao Li and Jumin Zhao, p. 15:1-15:54] Abstract: Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-dimensional spaces according to specific tasks. Up to now, there have been several surveys on this topic. However, they usually lay emphasis on different angles so that the readers cannot see a panorama of the graph neural networks. This survey aims to overcome this limitation and provide a systematic and comprehensive review on the graph neural networks. First of all, we provide a novel taxonomy for the graph neural networks, and then refer to up to 327 relevant literatures to show the panorama of the graph neural networks. All of them are classified into the corresponding categories. In order to drive the graph neural networks into a new stage, we summarize four future research directions so as to overcome the challenges faced. It is expected that more and more scholars can understand and exploit the graph neural networks and use them in their research community.;[Article Title: FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings/ Cheng-Te Li, Cheng Hsu and Yang Zhang, p. 16:1-16:21] Abstract: Sequential recommendation (SR) learns from the temporal dynamics of user-item interactions to predict the next ones. Fairness-aware recommendation mitigates a variety of algorithmic biases in the learning of user preferences. This article aims at bringing a marriage between SR and algorithmic fairness. We propose a novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness, is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups. We propose a multi-task learning-based deep end-to-end model, FairSR, which consists of two parts. One is to learn and distill personalized sequential features from the given user and her item sequence for SR.

The other is fairness-aware preference graph embedding (FPGE). The aim of FPGE is two-fold: incorporating the knowledge of users' and items' attributes and their correlation into entity representations, and alleviating the unfair distributions of user attributes on items. Extensive experiments conducted on three datasets show FairSR can outperform state-of-the-art SR models in recommendation performance. In addition, the recommended items by FairSR also exhibit promising interaction fairness.