检索结果-内蒙古大学图书馆

Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2024年第8期36卷 3783-3800页

作者： Deng, Jinliang Chen, Xiusi Jiang, Renhe Yin, Du Yang, Yi Song, Xuan Tsang, Ivor W. Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen 518055 Guangdong Peoples R China Univ Technol Sydney Australian Artificial Intelligence Inst Sydney NSW 2007 Australia Univ Calif Los Angeles Los Angeles CA 90095 USA Univ Tokyo Ctr Spatial Informat Sci Bunkyo Ku Tokyo 1138654 Japan Univ New South Wales Dept Comp Sci & Engn Sydney NSW 2052 Australia Tencent WXG Shenzhen 510310 Guangdong Peoples R China Southern Univ Sci & Technol SUSTech SUSTech UTokyo Joint Res Ctr Super Smart City Dept Comp Sci & Engn Shenzhen 518055 Guangdong Peoples R China ASTAR Ctr Frontier AI Res Singapore 138632 Singapore

Multivariate time-series (MTS) forecasting is a paramount and fundamental problem in many real-world applications. The core issue in MTS forecasting is how to effectively model complex spatial-temporal patterns. In this paper, we develop a adaptive, interpretable and scalable forecasting framework, which seeks to individually model each component of the spatial-temporal patterns. We name this framework SCNN, as an acronym of Structured Component-based Neural Network. SCNN works with a pre-defined generative process of MTS, which arithmetically characterizes the latent structure of the spatial-temporal patterns. In line with its reverse process, SCNN decouples MTS data into structured and heterogeneous components and then respectively extrapolates the evolution of these components, the dynamics of which are more traceable and predictable than the original MTS. Extensive experiments are conducted to demonstrate that SCNN can achieve superior performance over state-of-the-art models on three real-world datasets. Additionally, we examine SCNN with different configurations and perform in-depth analyses of the properties of SCNN.

关键词： Time series analysis Forecasting Adaptation models Convolution Predictive models Deep learning Transformers disentanglement spatial-temporal data mining time series forecasting

来源：评论

学校读者我要写书评

暂无评论

TrajBERT: BERT-Based Trajectory Recovery With spatial-temporal Refinement for Implicit Sparse Trajectories

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第5期23卷 4849-4860页

作者： Si, Junjun Yang, Jin Xiang, Yang Wang, Hanqiu Li, Li Zhang, Rongqing Tu, Bo Chen, Xiangqun Peking Univ Sch Software & Microelect Beijing 100871 Peoples R China Hezhixin Shandong Big Data Technol Co Ltd Jinan 250001 Peoples R China Tongji Univ Shanghai 200092 Peoples R China Beijing Informat Sci & Technol Univ Beijing 100192 Peoples R China

In the realm of human mobility data analysis, a multitude of constraints result in the publication of sparse, non-uniform implicit trajectories without explicit location information, such as coordinates. Researchers have dedicated substantial efforts towards trajectory recovery, aiming to densify trajectories and gain a more comprehensive understanding of human mobility. However, existing trajectory recovery methods focus on explicit trajectories, and require extensive historical data to capture users' mobility patterns. Nevertheless, implicit trajectories are usually more sparse than explicit trajectories. Addressing these challenges, we propose TrajBERT, an innovative BERT-based trajectory recovery method with spatial-temporal refinement. TrajBERT employs the Transformer encoder to learn mobility patterns bi-directionally and enhances the predictions by cross-stage temporal refinement. Subsequently, we design an output layer with global spatial refinement with a novel spatial-temporal aware loss function. To evaluate the performance of TrajBERT, we conduct a series of experiments on real-world datasets. Remarkably, TrajBERT yields at least 8.2% performance improvement compared to the state-of-the-art trajectory recovery approachs. Furthermore, TrajBERT successfully mitigates the cold start problem commonly experienced with new users lacking historical trajectories. It also shows superior robustness when faced with extremely sparse trajectories, thus demonstrating its potential as a practical tool in the field of human mobility analysis.

关键词： Trajectory recovery trajectory reconstruction trajectory mining spatial-temporal data mining

来源：评论

学校读者我要写书评

暂无评论

MG-TAR: Multi-View Graph Convolutional Networks for Traffic Accident Risk Prediction

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第4期24卷 3779-3794页

作者： Trirat, Patara Yoon, Susik Lee, Jae-Gil Korea Adv Inst Sci & Technol Sch Comp Daejeon South Korea UIUC Dept Comp Sci Urbana IL 61801 USA

Due to the continuing colossal socio-economic losses caused by traffic accidents, it is of prime importance to precisely forecast the traffic accident risk to reduce future accidents. In this paper, we use dangerous driving statistics from driving log data and multi-graph learning to enhance predictive performance. We first conduct geographical and temporal correlation analyses to quantify the relationship between dangerous driving and actual accidents. Then, to learn various dependencies between districts besides the traditional adjacency matrix, we simultaneously model both static and dynamic graphs representing the spatio-temporal contextual relationships with heterogeneous environmental data, including the dangerous driving behavior. A graph is generated for each type of the relationships. Ultimately, we propose an end-to-end framework, called MG-TAR, to effectively learn the association of multiple graphs for accident risk prediction by adopting multi-view graph neural networks with a multi-attention module. Thorough experiments on ten real-world datasets show that, compared with state-of-the-art methods, MG-TAR reduces the error of predicting the accident risk by up to 23% and improves the accuracy of predicting the most dangerous areas by up to 27%.

关键词： Accidents Correlation Predictive models Roads Forecasting Context modeling Behavioral sciences Traffic accident risk prediction spatial-temporal data mining dangerous driving behavior graph neural networks intelligent transportation system

来源：评论

学校读者我要写书评

暂无评论

Representation learning and Graph Convolutional Networks for short-term vehicle trajectory prediction

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2024年 637卷

作者： Xu, Xinpeng Yang, Chen Wu, Weiguo Xi'an Jiaotong Univ Sch Comp Sci & Technol Xian 710049 Peoples R China East China Res Inst Comp Technol Shanghai 201818 Peoples R China Beijing Univ Posts & Telecommun Sch Comp Sci & Technol Beijing 100876 Peoples R China

Trajectory prediction is an important topic in intelligent transportation research. This study considers in-depth, the diversity and complexity of spatial-temporal trajectory, proposes a feature extraction method based on representation learning, and further designs and implements a short -term spatial-temporal vehicle trajectory prediction model on this basis. First, we propose a feature representation method aiming at the potential preference features of spatial-temporal vehicle trajectory space, so as to accurately represent the vehicle preference features. Second, considering the complexity of the topology of the road Network of vehicles and the fact that (Graph Convolutional Network, GCN) can learn the node features of the network structure, a feature extraction method based on GCN is proposed, which achieves the goal of vectorizing the road Network structure into a low-dimensional dense vector. Finally, a feature fusion method is proposed to comprehensively predict trajectory. Experiments show that this model not only effectively and comprehensively represent the trajectory features, but also synthesize the spatial features, temporal features and trajectory preference features, and finally obtains improved prediction results.

关键词： Vehicle trajectory prediction Intelligent transportation spatial-temporal data mining Representation learning Graph Convolutional Network

来源：评论

学校读者我要写书评

暂无评论

Towards hour-level crime prediction: A neural attentive framework with spatial-temporal-categorical fusion

引用

NEUROCOMPUTING 2022年第0期486卷 286-297页

作者： Liang, Weichao Wang, Youquan Tao, Haicheng Cao, Jie Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China Nanjing Univ Finance & Econ Jiangsu Prov Key Lab E Business Nanjing Peoples R China

As one of the most complex social problems around the world, crime may bring the risk of dying or losing property to the public if not handled properly. Crime prediction which aims at predicting crime incidents before they happen is of great importance to fight against crime. Previous studies are concerned primarily with day-level crime prediction and have certain limitations on modeling complex spatial-temporal-cate gorical dependency contained in the criminal activities as well as utilizing external factors to facilitate the forecast. In this paper, we develop a novel Neural Attentive framework for Hour-level Crime prediction (NAHC) to cope with these challenges. Specifically, we first adopt the priori knowledge-based data enhancement strategy to alleviate the zero-inflated issue raised in hour-level settings. Then, multi graph convolutional networks are applied to capture spatial dependency from different aspects. After that, we integrate gated recurrent units with a temporal attention mechanism to jointly address temporal dependency and capture time-sensitive external factors. A categorical attention mechanism is proposed for dealing with categorical dependency and finally a fully connected network is utilized to generate the final prediction results. Extensive experiments on two real-world crime datasets demonstrate the effectiveness of our framework over the state-of-the-art comparing methods.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Crime prediction spatial-temporal data mining Deep learning Urban computing

来源：评论

学校读者我要写书评

暂无评论

Uncovering cabdrivers' behavior patterns from their digital traces

引用

COMPUTERS ENVIRONMENT AND URBAN SYSTEMS 2010年第6期34卷 541-548页

作者： Liu, Liang Andris, Clio Ratti, Carlo MIT Dept Urban Planning & Studies Cambridge MA 02139 USA

Recognizing high-level human behavior and decisions from their digital traces are critical issues in pervasive computing systems. In this paper, we develop a novel methodology to reveal cabdrivers' operation patterns by analyzing their continuous digital traces. For the first time, we systematically study large scale cabdrivers' behavior in a real and complex city context through their daily digital traces. We identify a set of valuable features, which are simple and effective to classify cabdrivers, delineate cabdrivers' operation patterns and compare the different cabdrivers' behavior. The methodology and steps could spatially and temporally quantify, visualize, and examine different cabdrivers' operation patterns. Drivers were categorized into top drivers and ordinary drivers by their daily income. We use the daily operations of 3000 cabdrivers in over 48 million of trips and 240 million kilometers to uncover: (1) spatial selection behavior, (2) context-aware spatio-temporal operation behavior, (3) route choice behavior, and (4) operation tactics. Though we focused on cabdriver operation patterns analysis from their digital traces, the methodology is a general empirical and analytical methodology for any GPS-like trace analysis. Our work demonstrates the great potential to utilize the massive pervasive data sets to understand human behavior and high-level intelligence. Published by Elsevier Ltd.

关键词： Cabdriver Operation behavior Mobility pattern GPS spatial-temporal data mining Pervasive computing

来源：评论

学校读者我要写书评

暂无评论

On the discovery of spatial-temporal fluctuating patterns

引用

INTERNATIONAL JOURNAL OF data SCIENCE AND ANALYTICS 2019年第1期8卷 57-75页

作者： Teng, Shan-Yun Ou, Cheng-Kuan Chuang, Kun-Ta Natl Cheng Kung Univ Dept Comp Sci & Informat Engn Tainan Taiwan

In this paper, we explore a new mining paradigm, called spatial-temporal fluctuating patterns (abbreviated as STFs), to discover potentially fluctuating and useful feature sets from the spatial-temporal data. These feature sets have some properties which are variant as time advances. Once STFs are discovered, we can find the turning points of patterns, which enables anomaly detection and transformation discovery over time. For example, the discovery of STFs can possibly figure out the phenomenon of virus variation during the epidemic outbreak, further providing the government with clues for the epidemic control. Therefore, we develop a union-based mining with the downward-closure structure to speed up the spatial-temporal mining process and dynamically compute fluctuating patterns. As shown in our experimental studies, the proposed framework can efficiently discover STFs on a real epidemic disease dataset, showing its prominent advantages to be utilized in real applications.

关键词： Fluctuating patterns spatial-temporal data mining Significant fluctuation

来源：评论

学校读者我要写书评

暂无评论

Understanding Places Exploration and Visitation via Human Mobility mining

引用

INTERNATIONAL JOURNAL OF INTELLIGENT INFORMATION TECHNOLOGIES 2024年第1期20卷 1页

作者： Shad, Shafqat Usman, Muhammad Kumar, Chandan Afzal, Hadiqa Univeristy Montevallo Montevallo AL 35115 USA Verizon Wireless Waltham MA 02451 USA Iowa State Univ Iowa City IA USA

spatial-temporal data is widely available because of advancement in location acquisition technologies (GPS, GSM, Wifi, etc.) over past decades. This spatial-temporal data can easily be used to leverage user's trajectories, history, and habits to develop location-based services (LBS). But to leverage user's history based on location is bit challenging, in this paper we used the user's GPS log data to discover trajectories and analyze different life patterns over it. We proposed that a human spends 80% of his life on known places or safe places. We converted GPS patterns into visitation locations, converted them into daily and periodic trends and analyzed them over time to prove our assumption. We used the GPS data collected by Microsoft Research Asia, this data has 182 users with 73 users with their mode of movement information i.e., Taxi, Walk, Train etc.

关键词： Mobility mining Habit mining Pattern mining Location Based Services spatial-temporal data mining

来源：评论

学校读者我要写书评

暂无评论

spatial-temporal Convolutional Graph Attention Networks for Citywide Traffic Flow Forecasting 20

Spatial-Temporal Convolutional Graph Attention Networks for ...

引用

29th ACM International Conference on Information and Knowledge Management (CIKM)

作者： Zhang, Xiyue Huang, Chao Xu, Yong Xia, Lianghao South China Univ Technol Guangzhou Peoples R China JD Finance Amer Corp Mountain View CA USA Peng Cheng Lab Shenzhen Peoples R China

ISBN: (纸本)9781450368599

Traffic flow prediction plays an important role in many spatial-temporal data applications, e.g., traffic management and urban planning. Various deep learning techniques are developed to model the traffic dynamic patterns with different neural network architectures, such as attention mechanism, recurrent neural network. However, two important challenges have yet to be well addressed: (i) Most of these methods solely focus on local spatial dependencies and ignore the global inter-region dependencies in terms of traffic distributions;(ii) It is important to capture channel-aware semantics when performing spatial-temporal information aggregation. To address these challenges, we propose a new traffic prediction framework-spatial-temporal Convolutional Graph Attention Network (ST-CGA), to enable the traffic prediction with the modeling of region dependencies, from locally to globally in a comprehensive manner. In our ST-CGA framework, we first develop a hierarchical attention networks with a graph-based neural architecture, to capture both the multi-level temporal relations and cross-region traffic dependencies. Furthermore, a region-wise spatial relation encoder is proposed to supercharge ST-CGA mapping spatial and temporal signals into different representation subspaces, with channel-aware recalibration residual network. Extensive experiments on four real-world datasets demonstrate that ST-CGA achieve substantial gains over many state-of-the-art baselines.

关键词： spatial-temporal data mining Graph Attention Networks Traffic flow Forecasting Urban Computing

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Dependence Learning with Meteorological Context for Transportation Demand Prediction 17th

Spatiotemporal Dependence Learning with Meteorological Conte...

引用

17th International Conference on Knowledge Science, Engineering and Management (KSEM)

作者： Dong, Wenxin Zhang, Zili Deng, Huangyao Zhang, Chi Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China

ISBN: (纸本)9789819754915;9789819754922

As the demand for transportation increases, accurate transportation demand prediction becomes beneficial for the government in allocating transportation resources. However, predicting transportation demand presents challenges due to various uncertainty factors, such as weather, holidays, and traffic conditions, leading to complex spatiotemporal dependencies in the data. Recent studies applied deep learning methods to this task and achieved promising results, but challenges persist. The impact of weather is usually overlooked in previous researches. There is also a lack of consideration for capturing the dynamic change of spatial relationships in cities promptly. In this paper, an Attentionbased Dynamic Layer-wise Graph Convolution Network (ADLGCN) is proposed to address these issues. Specifically, a cross-attention mechanism based on weather and transportation demand data is presented to quantify the impact of weather on transportation demand. Additionally, a multi-graph convolutional structure is proposed to focus on capturing real-time spatial relationships. A temporal attention mechanism based on multiple historical periods is introduced to capture temporal dependencies in transportation demand. Finally, extensive experiments demonstrate that our model outperforms the state-of-the-art method, with an average improvement in MAE metrics of 4.45% on two real-world datasets.

关键词： Traffic prediction spatial-temporal data mining Attention Graph convolution Time series

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：