arXiv subjects

Lijun Sun

Publications and source records attributed to Lijun Sun.

105 records · Page 6Linked to original sources

arXiv2021

Bayesian Temporal Factorization for Multidimensional Time Series Prediction

Large-scale and multidimensional spatiotemporal data sets are becoming ubiquitous in many real-world applications such as monitoring urban traffic and air quality. Making predictions on these time series has become a critical challenge due to not only the large-scale and high-dimensional nature but also the considerable amount of missing data. In this paper, we propose a Bayesian temporal factorization (BTF) framework for modeling multidimensional time series -- in particular spatiotemporal data -- in the presence of missing values. By integrating low-rank matrix/tensor factorization and vector autoregressive (VAR) process into a single probabilistic graphical model, this framework can characterize both global and local consistencies in large-scale time series data. The graphical model allows us to effectively perform probabilistic predictions and produce uncertainty estimates without imputing those missing values. We develop efficient Gibbs sampling algorithms for model inference and model updating for real-time prediction and test the proposed BTF framework on several real-world spatiotemporal data sets for both missing data imputation and multi-step rolling prediction tasks. The numerical experiments demonstrate the superiority of the proposed BTF approaches over existing state-of-the-art methods.

stat.ML↗

arXiv2020

Inductive Graph Neural Networks for Spatiotemporal Kriging

Time series forecasting and spatiotemporal kriging are the two most important tasks in spatiotemporal data analysis. Recent research on graph neural networks has made substantial progress in time series forecasting, while little attention has been paid to the kriging problem -- recovering signals for unsampled locations/sensors. Most existing scalable kriging methods (e.g., matrix/tensor completion) are transductive, and thus full retraining is required when we have a new sensor to interpolate. In this paper, we develop an Inductive Graph Neural Network Kriging (IGNNK) model to recover data for unsampled sensors on a network/graph structure. To generalize the effect of distance and reachability, we generate random subgraphs as samples and reconstruct the corresponding adjacency matrix for each sample. By reconstructing all signals on each sample subgraph, IGNNK can effectively learn the spatial message passing mechanism. Empirical results on several real-world spatiotemporal datasets demonstrate the effectiveness of our model. In addition, we also find that the learned model can be successfully transferred to the same type of kriging tasks on an unseen dataset. Our results show that: 1) GNN is an efficient and effective tool for spatial kriging; 2) inductive GNNs can be trained using dynamic adjacency matrices; 3) a trained model can be transferred to new graph structures and 4) IGNNK can be used to generate virtual sensors.

cs.LG↗

arXiv2020

The replacement system of the JUNO liquid scintillator pilot experiment at Daya Bay

The Jiangmen Underground Neutrino Observatory (JUNO), a multi-purpose neutrino experiment, will use 20 kt liquid scintillator (LS). To achieve the physics goal of determining the neutrino mass ordering, 3$\%$ energy resolution at 1 MeV is required. This puts strict requirements on the LS light yield and the transparency. Four LS purification steps have been designed and mid-scale plants have been built at Daya Bay. To examine the performance of the purified LS and find the optimized LS composition, the purified LS was injected to the antineutrino detector 1 in the experimental hall 1 (EH1-AD1) of the Daya Bay neutrino experiment. To pump out the original gadolinium loaded LS and fill the new LS, a LS replacement system has been built in EH1 in 2017. By replacing the Gd-LS with purified water, then replacing the water with purified LS, the replacement system successfully achieved the designed goal. Subsequently, the fluorescence and the wavelength shifter were added to higher concentrations via the replacement system. The data taken at various LS compositions helped JUNO determine the final LS cocktail. Details of the design, the construction, and the operation of the replacement system are reported in this paper.

physics.ins-det↗

arXiv2020

Industrial Topics in Urban Labor System

Categorization is an essential component for us to understand the world for ourselves and to communicate it collectively. It is therefore important to recognize that classification system are not necessarily static, especially for economic systems, and even more so in urban areas where most innovation takes place and is implemented. Out-of-date classification systems would potentially limit further understanding of the current economy because things constantly change. Here, we develop an occupation-based classification system for the US labor economy, called industrial topics, that satisfy adaptability and representability. By leveraging the distributions of occupations across the US urban areas, we identify industrial topics - clusters of occupations based on their co-existence pattern. Industrial topics indicate the mechanisms under the systematic allocation of different occupations. Considering the densely connected occupations as an industrial topic, our approach characterizes regional economies by their topical composition. Unlike the existing survey-based top-down approach, our method provides timely information about the underlying structure of the regional economy, which is critical for policymakers and business leaders, especially in our fast-changing economy.

cs.SI↗

arXiv2020

Incremental Bayesian tensor learning for structural monitoring data imputation and response forecasting

There has been increased interest in missing sensor data imputation, which is ubiquitous in the field of structural health monitoring (SHM) due to discontinuous sensing caused by sensor malfunction. To address this fundamental issue, this paper presents an incremental Bayesian tensor learning method for reconstruction of spatiotemporal missing data in SHM and forecasting of structural response. In particular, a spatiotemporal tensor is first constructed followed by Bayesian tensor factorization that extracts latent features for missing data imputation. To enable structural response forecasting based on incomplete sensing data, the tensor decomposition is further integrated with vector autoregression in an incremental learning scheme. The performance of the proposed approach is validated on continuous field-sensing data (including strain and temperature records) of a concrete bridge, based on the assumption that strain time histories are highly correlated to temperature recordings. The results indicate that the proposed probabilistic tensor learning approach is accurate and robust even in the presence of large rates of random missing, structured missing and their combination. The effect of rank selection on the imputation and prediction performance is also investigated. The results show that a better estimation accuracy can be achieved with a higher rank for random missing whereas a lower rank for structured missing.

cs.LG↗

arXiv2020

Low-Rank Autoregressive Tensor Completion for Multivariate Time Series Forecasting

Time series prediction has been a long-standing research topic and an essential application in many domains. Modern time series collected from sensor networks (e.g., energy consumption and traffic flow) are often large-scale and incomplete with considerable corruption and missing values, making it difficult to perform accurate predictions. In this paper, we propose a low-rank autoregressive tensor completion (LATC) framework to model multivariate time series data. The key of LATC is to transform the original multivariate time series matrix (e.g., sensor$\times$time point) to a third-order tensor structure (e.g., sensor$\times$time of day$\times$day) by introducing an additional temporal dimension, which allows us to model the inherent rhythms and seasonality of time series as global patterns. With the tensor structure, we can transform the time series prediction and missing data imputation problems into a universal low-rank tensor completion problem. Besides minimizing tensor rank, we also integrate a novel autoregressive norm on the original matrix representation into the objective function. The two components serve different roles. The low-rank structure allows us to effectively capture the global consistency and trends across all the three dimensions (i.e., similarity among sensors, similarity of different days, and current time v.s. the same time of historical days). The autoregressive norm can better model the local temporal trends. Our numerical experiments on three real-world data sets demonstrate the superiority of the integration of global and local trends in LATC in both missing data imputation and rolling prediction tasks.

stat.ML↗

arXiv2020

A Nonconvex Low-Rank Tensor Completion Model for Spatiotemporal Traffic Data Imputation

Sparsity and missing data problems are very common in spatiotemporal traffic data collected from various sensing systems. Making accurate imputation is critical to many applications in intelligent transportation systems. In this paper, we formulate the missing data imputation problem in spatiotemporal traffic data in a low-rank tensor completion (LRTC) framework and define a novel truncated nuclear norm (TNN) on traffic tensors of location$\times$day$\times$time of day. In particular, we introduce an universal rate parameter to control the degree of truncation on all tensor modes in the proposed LRTC-TNN model, and this allows us to better characterize the hidden patterns in spatiotemporal traffic data. Based on the framework of the Alternating Direction Method of Multipliers (ADMM), we present an efficient algorithm to obtain the optimal solution for each variable. We conduct numerical experiments on four spatiotemporal traffic data sets, and our results show that the proposed LRTC-TNN model outperforms many state-of-the-art imputation models with missing rates/patterns. Moreover, the proposed model also outperforms other baseline models in extreme missing scenarios.

stat.ML↗

arXiv2020

Efficient Motion Planning for Automated Lane Change based on Imitation Learning and Mixed-Integer Optimization

Intelligent motion planning is one of the core components in automated vehicles, which has received extensive interests. Traditional motion planning methods suffer from several drawbacks in terms of optimality, efficiency and generalization capability. Sampling based methods cannot guarantee the optimality of the generated trajectories. Whereas the optimization-based methods are not able to perform motion planning in real-time, and limited by the simplified formalization. In this work, we propose a learning-based approach to handle those shortcomings. Mixed Integer Quadratic Problem based optimization (MIQP) is used to generate the optimal lane-change trajectories which served as the training dataset for learning-based action generation algorithms. A hierarchical supervised learning model is devised to make the fast lane-change decision. Numerous experiments have been conducted to evaluate the optimality, efficiency, and generalization capability of the proposed approach. The experimental results indicate that the proposed model outperforms several commonly used motion planning baselines.

cs.RO↗

arXiv2020

Routine pattern discovery and anomaly detection in individual travel behavior

Discovering patterns and detecting anomalies in individual travel behavior is a crucial problem in both research and practice. In this paper, we address this problem by building a probabilistic framework to model individual spatiotemporal travel behavior data (e.g., trip records and trajectory data). We develop a two-dimensional latent Dirichlet allocation (LDA) model to characterize the generative mechanism of spatiotemporal trip records of each traveler. This model introduces two separate factor matrices for the spatial dimension and the temporal dimension, respectively, and use a two-dimensional core structure at the individual level to effectively model the joint interactions and complex dependencies. This model can efficiently summarize travel behavior patterns on both spatial and temporal dimensions from very sparse trip sequences in an unsupervised way. In this way, complex travel behavior can be modeled as a mixture of representative and interpretable spatiotemporal patterns. By applying the trained model on future/unseen spatiotemporal records of a traveler, we can detect her behavior anomalies by scoring those observations using perplexity. We demonstrate the effectiveness of the proposed modeling framework on a real-world license plate recognition (LPR) data set. The results confirm the advantage of statistical learning methods in modeling sparse individual travel behavior data. This type of pattern discovery and anomaly detection applications can provide useful insights for traffic monitoring, law enforcement, and individual travel behavior profiling.

cs.SI↗

arXiv2020

Scaling of contact networks for epidemic spreading in urban transit systems

Improved mobility not only contributes to more intensive human activities but also facilitates the spread of communicable disease, thus constituting a major threat to billions of urban commuters. In this study, we present a multi-city investigation of communicable diseases percolating among metro travelers. We use smart card data from three megacities in China to construct individual-level contact networks, based on which the spread of disease is modeled and studied. We observe that, though differing in urban forms, network layouts, and mobility patterns, the metro systems of the three cities share similar contact network structures. This motivates us to develop a universal generation model that captures the distributions of the number of contacts as well as the contact duration among individual travelers. This model explains how the structural properties of the metro contact network are associated with the risk level of communicable diseases. Our results highlight the vulnerability of urban mass transit systems during disease outbreaks and suggest important planning and operation strategies for mitigating the risk of communicable diseases.

physics.soc-ph↗

arXiv2017

Small cities face greater impact from automation

The city has proven to be the most successful form of human agglomeration and provides wide employment opportunities for its dwellers. As advances in robotics and artificial intelligence revive concerns about the impact of automation on jobs, a question looms: How will automation affect employment in cities? Here, we provide a comparative picture of the impact of automation across U.S. urban areas. Small cities will undertake greater adjustments, such as worker displacement and job content substitutions. We demonstrate that large cities exhibit increased occupational and skill specialization due to increased abundance of managerial and technical professions. These occupations are not easily automatable, and, thus, reduce the potential impact of automation in large cities. Our results pass several robustness checks including potential errors in the estimation of occupational automation and sub-sampling of occupations. Our study provides the first empirical law connecting two societal forces: urban agglomeration and automation's impact on employment.

cs.CY↗

arXiv2016

The laboratory measurement of radioactivity purification for Pb212 in liquid scintillator

The liquid scintillator (LS) has been widely utilized in the past, running and future neutrino experiments, and requirement to the LS radio-purity is higher and higher. The water extraction is a powerful method to remove soluble radioactive nuclei, and a mini-extraction station has been constructed. To evaluate the extraction efficiency and optimize the operation parameters, a setup to load radioactivity to LS and a laboratory scale setup to measure radioactivity which use Bi^{212}-Po^{212}-Pb^{208} cascade decay are developed. Experiences from laboratory study will be useful to large scale water extraction plants design and the optimization of working in future.

physics.ins-det↗

arXiv2014

Quantifying long-term evolution of intra-urban spatial interactions

Understanding the long-term impact that changes in a city's transportation infrastructure have on its spatial interactions remains a challenge. The difficulty arises from the fact that the real impact may not be revealed in static or aggregated mobility measures, as these are remarkably robust to perturbations. More generally, the lack of longitudinal, cross-sectional data demonstrating the evolution of spatial interactions at a meaningful urban scale also hinders us from evaluating the sensitivity of movement indicators, limiting our capacity to understand the evolution of urban mobility in depth. Using very large mobility records distributed over three years we quantify the impact of the completion of a metro line extension: the circle line (CCL) in Singapore. We find that the commonly used movement indicators are almost identical before and after the project was completed. However, in comparing the temporal community structure across years, we do observe significant differences in the spatial reorganization of the affected geographical areas. The completion of CCL enables travelers to re-identify their desired destinations collectively with lower transport cost, making the community structure more consistent. These changes in locality are dynamic, and characterized over short time-scales, offering us a different approach to identify and analyze the long-term impact of new infrastructures on cities and their evolution dynamics.

physics.soc-ph↗

arXiv2014

Efficient detection of contagious outbreaks in massive metropolitan encounter networks

Physical contact remains difficult to trace in large metropolitan networks, though it is a key vehicle for the transmission of contagious outbreaks. Co-presence encounters during daily transit use provide us with a city-scale time-resolved physical contact network, consisting of 1 billion contacts among 3 million transit users. Here, we study the advantage that knowledge of such co-presence structures may provide for early detection of contagious outbreaks. We first examine the "friend sensor" scheme --- a simple, but universal strategy requiring only local information --- and demonstrate that it provides significant early detection of simulated outbreaks. Taking advantage of the full network structure, we then identify advanced "global sensor sets", obtaining substantial early warning times savings over the friends sensor scheme. Individuals with highest number of encounters are the most efficient sensors, with performance comparable to individuals with the highest travel frequency, exploratory behavior and structural centrality. An efficiency balance emerges when testing the dependency on sensor size and evaluating sensor reliability; we find that substantial and reliable lead-time could be attained by monitoring only 0.01% of the population with the highest degree.

physics.soc-ph↗

arXiv2013

Understanding metropolitan patterns of daily encounters

Understanding of the mechanisms driving our daily face-to-face encounters is still limited; the field lacks large-scale datasets describing both individual behaviors and their collective interactions. However, here, with the help of travel smart card data, we uncover such encounter mechanisms and structures by constructing a time-resolved in-vehicle social encounter network on public buses in a city (about 5 million residents). This is the first time that such a large network of encounters has been identified and analyzed. Using a population scale dataset, we find physical encounters display reproducible temporal patterns, indicating that repeated encounters are regular and identical. On an individual scale, we find that collective regularities dominate distinct encounters' bounded nature. An individual's encounter capability is rooted in his/her daily behavioral regularity, explaining the emergence of "familiar strangers" in daily life. Strikingly, we find individuals with repeated encounters are not grouped into small communities, but become strongly connected over time, resulting in a large, but imperceptible, small-world contact network or "structure of co-presence" across the whole metropolitan area. Revealing the encounter pattern and identifying this large-scale contact network are crucial to understanding the dynamics in patterns of social acquaintances, collective human behaviors, and -- particularly -- disclosing the impact of human behavior on various diffusion/spreading processes.

physics.soc-ph↗