Article
Computer Science, Information Systems
Tao Jia, Chenxi Cai, Xin Li, Xi Luo, Yuanyu Zhang, Xuesong Yu
Summary: This study proposes a methodological framework to detect dynamical communities in multilayer spatial interaction networks and examine their spatiotemporal patterns. By using random walks to merge network layers, the Leiden technique to derive dynamical communities, and exploratory analytic methods to examine spatiotemporal patterns, the study demonstrates the effectiveness of the methods in detecting cohesive and comparable dynamical communities, clustering patterns, and the life courses and interactions of these communities. The study also shows the applicability of the methods in analyzing mixed land use patterns and providing decision-making support for sustainable urban management.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2022)
Article
Computer Science, Information Systems
Xiao Pan, Lei Wu, Fenjie Long, Ang Ma
Summary: With the increasing popularity of mobile devices and social networks, a large amount of trajectory data has been accumulated. This data contains valuable information such as spatiality, time series, and other external descriptive attributes. Personalized trajectory recommendation is crucial for users to quickly find routes that meet their travel needs. Existing methods typically provide the same route recommendations to different users for a given origin and destination. However, user behavior preferences can be learned from their historical trajectories with multiple attributes. In this paper, we propose two novel personalized trajectory recommendation methods based on user behavior probability learning. These methods transform the recommendation problem into a shortest path problem and utilize Bayesian probability models. Experimental results on real datasets demonstrate the effectiveness of our proposed methods.
FRONTIERS OF COMPUTER SCIENCE
(2022)
Article
Engineering, Electrical & Electronic
Yabo Li, Haijun Zhang, Keping Long, Chunxiao Jiang, Mohsen Guizani
Summary: This paper investigates the use of replacing base stations with unmanned aerial vehicles for communication, proposing a joint resource allocation and UAV trajectory optimization algorithm to maximize total energy efficiency. The algorithm is validated through numerical results, demonstrating its rationality.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Maryam Shakeri, Hyerim Park, Ikbeom Jeon, Abolghasem Sadeghi-Niaraki, Woontack Woo
Summary: This paper proposes a personalized recommendation method for augmented reality (AR) contents based on real-time user behavior model to solve the cold-start problem for new users. The experiment results demonstrate that the proposed method brings noticeable improvements in enhancing the personalized experience of the AR tour system and outperforms the conventional method in terms of recommendation performance.
Article
Engineering, Aerospace
Judith Rosenow, Gong Chen, Hartmut Fricke, Xiaoqian Sun, Yanjun Wang
Summary: Air traffic trajectory optimization is a complex problem that involves considerations of operational, economical, environmental, political, and social factors, which vary across continents and may change during a single flight. Analysis of historical flight track data from China and Europe reveals significant differences in routing structure, leading to efforts to optimize reference trajectories for increased efficiency of continental air traffic flows.
Article
Computer Science, Artificial Intelligence
Zhuo Li, Keyou You, Jian Sun, Gang Wang
Summary: This article focuses on the problem of trajectory planning for an autonomous vehicle in the context of field exploration. Unlike previous research that aims to maximize information about spatial fields, this work considers efficient exploration of spatiotemporal fields with unknown distributions, while respecting a cumulative information constraint. A reinforcement learning algorithm is proposed to learn a continuous planning policy, and simulations show that it outperforms the commonly-used coverage planning method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Geography, Physical
Naixia Mou, Qi Jiang, Lingxian Zhang, Jiqiang Niu, Yunhao Zheng, Yanci Wang, Tengfei Yang
Summary: This study proposes a personalized recurrent neural network (P-RecN) for tourist route recommendation. By mining the semantic information of historical trajectory data and capturing the sequence travel patterns of tourists, the model can better understand the travel patterns of tourists, improving recommendation accuracy and ranking ability.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2022)
Article
Computer Science, Artificial Intelligence
Bangchao Deng, Dingqi Yang, Bingqing Qu, Benjamin Fankhauser, Philippe Cudre-Mauroux
Summary: This paper introduces a general RNN architecture called Flashback++ for modeling sparse user mobility trajectories. By leveraging rich spatiotemporal contexts to search past hidden states and optimally combining them through a re-weighting mechanism, the architecture significantly improves the robustness and performance of the models.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Yabo Li, Haijun Zhang, Keping Long
Summary: This study proposes a NOMA scenario based on dual UAVs to maximize secrecy energy efficiency through optimizing communication resources, UAV trajectories, and artificial noise. By applying matching-swapping method and upper/lower bound transformation, the joint optimization problem is effectively solved.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Green & Sustainable Science & Technology
Byron Quito, Maria de la Cruz del Rio-Rama, Jose Alvarez-Garcia, Festus Victor Bekun
Summary: The increase in consumption and resource use linked to human activity poses risks to energy security and sustainability, leading to a global restructuring of policy agendas to integrate environmental well-being through channels such as energy efficiency (EE). This study aims to analyze the relationship between energy efficiency, renewable energy, and financial development. Using a spatial econometrics model, the research finds spatial autocorrelation of EE among European countries and observes that the use of renewable energies promotes EE in neighboring economies. On the other hand, financial development has both positive and negative effects on EE, with the institutional component showing a positive impact and the stock market component showing a negative impact. The findings highlight the importance of renewable energy use in improving EE and the need for policy makers to develop mechanisms for greener and more sustainable development while encouraging efficient energy use.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2023)
Article
Computer Science, Information Systems
Saeed Taghizadeh, Abel Elekes, Martin Schaeler, Klemens Boehm
Summary: This paper addresses the meaningfulness of similarity in deep trajectory representations, proposing a methodology based on experiments. By comparing t2vec to classical models in terms of robustness and semantics of similarity, it concludes that combining t2vec with classical models may be the best way to identify similar trajectories.
INFORMATION SYSTEMS
(2021)
Article
Engineering, Aerospace
Dejian Zhang, Jian Zhang, Zhigang Jiao, Qingjie Ni, Qiuping Guo
Summary: Based on the lift-to-drag ratio, this paper proposes a novel correction efficiency coefficient model for the trajectory optimization of a two-dimensional trajectory correction projectile. The research indicates that a smaller correction efficiency coefficient leads to a stronger correction ability. By optimizing the trajectory and canard geometry, the projectile can accurately hit the target and effectively eliminate lateral trajectory swing. The research results provide references for the design of trajectory and canard geometry.
Article
Public, Environmental & Occupational Health
Ling Shan, Yuehua Jiang, Cuicui Liu, Jing Zhang, Guanghong Zhang, Xufeng Cui
Summary: The coordinated relationship between urban population-land spatial patterns and ecological efficiency is important for resource utilization, environmental protection, and sustainable development. This study reveals that the matching degree of urban population-land spatial patterns has increased, but the overall level is still low. The ecological efficiency shows a radial distribution with higher values in the middle and lower values in the periphery, conflicting with the spatial patterns. The study provides a new framework for urban environmental assessment and planning decision-making.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Automation & Control Systems
Bidan Huang, Yiming Yang, Ya-Yen Tsai, Guang-Zhong Yang
Summary: This article introduces a robotic system for manufacturing personalized medical stent graft implants based on a modular design, which utilizes real-time 3D vision, multirobot collaboration, and personalization to guide robots to adapt to different implant geometry. The system can efficiently generate collision-free paths and is generalizable to different stent graft designs.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Si Liu, Renda Bao, Defa Zhu, Shaofei Huang, Qiong Yan, Liang Lin, Chao Dong
Summary: This paper proposes a novel method called Personalized Spatial-aware Affine Modulation (PSAM) to address the problem of fine-grained face editing. The method utilizes personalized and spatial-aware modulation of intermediate features to modify face attributes according to users' preference.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Theory & Methods
Lu Chen, Yunjun Gao, Xuan Song, Zheng Li, Yifan Zhu, Xiaoye Miao, Christian S. Jensen
Summary: With the increasing digitization of processes, the amount of available data, known as big data, is exploding. Volume, velocity, and variety are the three main challenges in enabling value creation from big data. Metric spaces provide an ideal solution for addressing variety as they can incorporate any data equipped with a distance notion satisfying the triangle inequality. Indexing techniques for metric data have been proposed to accelerate search in metric spaces, yet the existing surveys are limited and a comprehensive empirical study is yet to be reported. This article aims to offer a comprehensive survey of existing metric indexes supporting exact similarity search, provide complexity analyses of index construction, and offer empirical comparison of query processing performance. The importance of empirical studies in evaluating metric indexing performance is highlighted, as performance can depend heavily on pruning and validation effectiveness and data distribution.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Information Systems
Pengfei Jin, Lu Chen, Yunjun Gao, Xueqin Chang, Zhanyu Liu, Shu Shen, Christian S. Jensen
Summary: Geo-social networks provide opportunities for marketing and promotion of geo-located services. By maximizing the influence of bichromatic reverse kNearest Neighbors, an optimal set of points of interest (POIs) can be identified that are both geo-textually and socially relevant to social influencers. This functionality is useful in various real-life applications, including social advertising, viral marketing, and personalized POI recommendation.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Mengxuan Zhang, Lei Li, Goce Trajcevski, Andreas Zufle, Xiaofang Zhou
Summary: This paper discusses the challenges and methods for shortest path computation in frequently evolving small-world networks. By adopting Parallel Shortest-distance Labeling (PSL) as the construction method for 2-hop labeling and designing update mechanisms, the query efficiency and index maintenance effectiveness are improved.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Editorial Material
Computer Science, Artificial Intelligence
Shuo Shang, Jianbing Shen, Ji-Rong Wen, Panos Kalnis
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Yunyi Li, Yongjing Hao, Pengpeng Zhao, Guanfeng Liu, Yanchi Liu, Victor S. Sheng, Xiaofang Zhou
Summary: This article proposes an Edge-Enhanced Global Disentangled Graph Neural Network (EGD-GNN) model to capture the relation information between items for global item representation and local user intention learning. Experimental results show that our model can achieve a significant improvement over state-of-the-art baselines and effectively distinguish item features.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2023)
Article
Computer Science, Artificial Intelligence
Dingming Wu, Erjia Xiao, Yi Zhu, Christian S. S. Jensen, Kezhong Lu
Summary: This study proposes a new way of accessing information in event-based social networking (EBSN) that combines pull and push functionalities, allowing users to conduct ad-hoc searches for events and receive partner recommendations.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yu Yang, Hongzhi Yin, Jiannong Cao, Tong Chen, Quoc Viet Hung Nguyen, Xiaofang Zhou, Lei Chen
Summary: Dynamic graphs are graphs whose structure changes over time. Existing approaches only consider dynamic graphs as a sequence of changes in vertex connections, ignoring the asynchronous nature of the dynamics where the evolution of each local structure starts at different times and lasts for various durations. To address this, we propose a novel representation of dynamic graphs as temporal edge sequences associated with joining time of vertices (ToV) and timespan of edges (ToE). We also introduce a time-aware Transformer to embed the dynamic connections and ToEs into learned vertex representations, along with encoding time-sensitive information. Our approach outperforms the state-of-the-art in various graph mining tasks and is efficient for embedding large-scale dynamic graphs.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yan Zhao, Jiaxin Liu, Yunchuan Li, Dalin Zhang, Christian S. Jensen, Kai Zheng
Summary: This paper proposes a novel preference-aware group task assignment framework for spatial crowdsourcing, which includes two components: Mutual Information-based Preference Modeling and Preference-aware Group Task Assignment. The framework learns group preferences using mutual information and weights group members adaptively. It also employs tree decomposition to assign tasks to appropriate worker groups, prioritizing more interested groups.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yongjing Hao, Tingting Zhang, Pengpeng Zhao, Yanchi Liu, Victor S. Sheng, Jiajie Xu, Guanfeng Liu, Xiaofang Zhou
Summary: Sequential recommendation has become crucial in various Internet applications. Existing methods overlook the transition patterns between the features of items, while our proposed model enhances recommendation performance through learning feature-level and item-level sequences.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Mohsen Saaki, Saeid Hosseini, Sana Rahmani, Mohammad Reza Kangavari, Wen Hua, Xiaofang Zhou
Summary: This study highlights the importance of finding suitable individuals to answer questions using short content and identifies the challenges involved. The authors propose a novel embedding approach and recommendation system to overcome these challenges, and provide experimental results to demonstrate its effectiveness.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Shanshan Feng, Lisi Chen, Kaiqi Zhao, Wei Wei, Xuemeng Song, Shuo Shang, Panos Kalnis, Ling Shao
Summary: Graph embedding aims to learn low-dimensional node representations to preserve original graph structures. Most existing graph embedding models fail to effectively preserve complex patterns, such as hierarchical structures, in Euclidean spaces. To address this, we propose a novel Rotated Lorentzian Embedding (ROLE) model that can capture hierarchical structures and model asymmetric proximity using rotation transformations. Experimental results on real-world directed graph datasets demonstrate that ROLE consistently outperforms various state-of-the-art embedding models, especially in the task of node recommendation.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yao Tian, Tingyun Yan, Xi Zhao, Kai Huang, Xiaofang Zhou
Summary: This paper proposes a novel indexing approach called LIMS, which uses data clustering, pivot-based data transformation techniques, and learned indexes to support efficient similarity query processing in metric spaces. LIMS partitions the underlying data into clusters with relatively uniform data distribution and utilizes a small number of pivots for data redistribution. Similar data are mapped into compact regions with totally ordinal mapped values. Machine learning models approximate the position of each data record on disk, and efficient algorithms are designed for range queries, nearest neighbor queries, and index maintenance with dynamic updates.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yan Zhao, Kai Zheng, Yunchuan Li, Jinfu Xia, Bin Yang, Torben Bach Pedersen, Rui Mao, Christian S. Jensen, Xiaofang Zhou
Summary: In spatial crowdsourcing, mobile users are involved in spatio-temporal tasks that require travel to specific locations. The task assignment in spatial crowdsourcing is a challenging problem that needs to be addressed to maximize profits. This study introduces a profit-driven task assignment problem and proposes various algorithms, including an optimal algorithm based on tree decomposition and greedy algorithms based on random tuning optimization. Additionally, a heuristic algorithm based on ant colony optimization is provided to balance effectiveness and efficiency. Extensive experiments using real and synthetic data are conducted to evaluate the proposed methods.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Theory & Methods
Huan Li, Hua Lu, Christian S. Jensen, Bo Tang, Muhammad Aamir Cheema
Summary: This survey focuses on the data quality issues in the Internet of Things (IoT), providing insights and analysis on major dimensions, technologies, trends, and open issues related to spatially referenced IoT data. It aims to offer valuable references for practitioners developing IoT-enabled applications and researchers conducting IoT data quality research.
ACM COMPUTING SURVEYS
(2023)