Predicting Human Mobility via Long Short-Term Patterns

Predicting human mobility has great significance in Location based Social Network applications,while it is challenging due to the impact of historical mobility patterns and current trajectories.Among these challenges,historical patterns tend to be crucial in the prediction task.However,it is difficult to capture complex patterns from long historical trajectories.Motivated by recent success of Convolutional Neural Network(CNN)-based methods,we propose a Union ConvGRU(UCG)Net,which can capture long short-term patterns of historical trajectories and sequential impact of current trajectories.Specifically,we first incorporate historical trajectories into hidden states by a shared-weight layer,and then utilize a 1D CNN to capture short-term pattern of hidden states.Next,an average pooling method is involved to generate separated hidden states of historical trajectories,on which we use a Fully Connected(FC)layer to capture longterm pattern subsequently.Finally,we use a Recurrent Neural Net-work(RNN)to predict future trajectories by integrating current trajectories and long short-term patterns.Experiments demonstrate that UCG Net performs best in comparison with neural network-based methods.

Clustering Indoor Location Data for Social Distancing and Human Mobility to Combat COVID-19

The world is experiencing the unprecedented time of a pandemic caused by the coronavirus disease(i.e.,COVID-19).As a countermeasure,contact tracing and social distancing are essential to prevent the transmission of the virus,which can be achieved using indoor location analytics.Based on the indoor location analytics,the human mobility on a site can be monitored and planned to minimize human’s contact and enforce social distancing to contain the transmission of COVID-19.Given the indoor location data,the clustering can be applied to cluster spatial data,spatio-temporal data and movement behavior features for proximity detection or contact tracing applications.More specifically,we propose the Coherent Moving Cluster(CMC)algorithm for contact tracing,the density-based clustering(DBScan)algorithm for identification of hotspots and the trajectory clustering(TRACLUS)algorithm for clustering indoor trajectories.The feature extraction mechanism is then developed to extract useful and valuable features that can assist the proposed system to construct the network of users based on the similarity of the movement behaviors of the users.The network of users is used to model an optimization problem to manage the human mobility on a site.The objective function is formulated to minimize the probability of contact between the users and the optimization problem is solved using the proposed effective scheduling solution based on OR-Tools.The simulation results show that the proposed indoor location analytics system outperforms the existing clustering methods by about 30%in terms of accuracy of clustering trajectories.By adopting this system for human mobility management,the count of close contacts among the users within a confined area can be reduced by 80%in the scenario where all users are allowed to access the site.

Parking Availability Prediction with Coarse-Grained Human Mobility Data

Nowadays,the anticipation of parking-space demand is an instrumental service in order to reduce traffic congestion levels in urban spaces.The purpose of our work is to study,design and develop a parking-availability predictor that extracts the knowledge from human mobility data,based on the anonymized human displacements of an urban area,and also from weather conditions.Most of the existing solutions for this prediction take as contextual data the current road-traffic state defined at very high temporal or spatial resolution.However,access to this type of fine-grained location data is usually quite limited due to several economic or privacy-related restrictions.To overcome this limitation,our proposal uses urban areas that are defined at very low spatial and temporal resolution.We conducted several experiments using three Artificial Neural Networks:Multilayer Perceptron,Gated Recurrent Units and bidirectional Long Short Term Memory networks and we tested their suitability using different combinations of inputs.Several metrics are provided for the sake of comparison within our study and between other studies.The solution has been evaluated in a real-world testbed in the city of Murcia(Spain)integrating an open human-mobility dataset showing high accuracy.A MAPE between 4%and 10%was reported in horizons of 1 to 3 h.

Modeling urban scale human mobility through big data analysis and machinelearning

In the United States,the buildings sector consumes about 76%of electricity use and 40% of all primary energy use and associated greenhouse gas emissions.Occupant behavior has drawn increasing research interests due to its impacts on the building energy consumption.However,occupant behavior study at urban scale remains a challenge,and very limited studies have been conducted.As an effort to couple big data analysis with human mobility modeling,this study has explored urban scale human mobility utilizing three months Global Positioning System(GPS)data of 93,o00 users at Phoenix Metropolitan Area.This research extracted stay points from raw data,and identified users'home,work,and other locations by Density-Based Spatial Clustering algorithm.Then,daily mobility patterns were constructed using different types of locations.We propose a novel approach to predict urban scale daily human mobility patterns with 12-hour prediction horizon,using Long Short-Term Memory(LSTM)neural network model.Results shows the developed models achieved around 85%average accuracy and about 86%mean precision.The developed models can be further applied to analyze urban scale occupant behavior,building energy demand and flexibility,and contributed to urban planning.

Impact of human mobility on the epidemic spread during holidays

COVID-19 has posed formidable challenges as a significant global health crisis.Its complexity stems from factors like viral contagiousness,population density,social behaviors,governmental regulations,and environmental conditions,with interpersonal interactions and large-scale activities being particularly pivotal.To unravel these complexities,we used a modified SEIR epidemiological model to simulate various outbreak scenarios during the holiday season,incorporating both inter-regional and intra-regional human mobility effects into the parameterization scheme.In addition,evaluation metrics were used to evaluate the accuracy of the model simulation by comparing the congruence between simulated results and recorded confirmed cases.The findings suggested that intra-city mobility led to an average surge of 57.35%in confirmed cases of China,while inter-city mobility contributed to an average increase of 15.18%.In the simulation for Tianjin,China,a one-week delay in human mobility attenuated the peak number of cases by 34.47%and postponed the peak time by 6 days.The simulation for the United States revealed that human mobility played a more pronounced part in the outbreak,with a notable disparity in peak cases when mobility was considered.This study highlights that while inter-regional mobility acted as a trigger for the epidemic spread,the diffusion effect of intra-regional mobility was primarily responsible for the outbreak.We have a better understanding on how human mobility and infectious disease epidemics interact,and provide empirical evidence that could contribute to disease prevention and control measures.

Social media and mobility landscape:Uncovering spatial patterns of urban human mobility with multi source data

In this paper,we present a three-step methodological framework,including location identification,bias modification,and out-of-sample validation,so as to promote human mobility analysis with social media data.More specifically,we propose ways of identifying personal activity-specific places and commuting patterns in Beijing,China,based on Weibo(China’s Twitter)check-in records,as well as modifying sample bias of check-in data with population synthesis technique.An independent citywide travel logistic survey is used as the benchmark for validating the results.Obvious differences are discerned from Weibo users’and survey respondents’activity-mobility patterns,while there is a large variation of population representativeness between data from the two sources.After bias modification,the similarity coefficient between commuting distance distributions of Weibo data and survey observations increases substantially from 23% to 63%.Synthetic data proves to be a satisfactory costeffective alternative source of mobility information.The proposed framework can inform many applications related to human mobility,ranging from transportation,through urban planning to transport emission modeling.

Human mobility data in the COVID-19 pandemic:characteristics,applications,and challenges

The COVID-19 pandemic poses unprecedented challenges around the world.Many studies have applied mobility data to explore spatiotemporal trends over time,investigate associations with other variables,and predict or simulate the spread of COVID-19.Our objective was to provide a comprehensive overview of human mobility open data to guide researchers and policymakers in conducting data-driven evaluations and decision-making for the COVID-19 pandemic and other infectious disease outbreaks.We summarized the mobility data usage in COVID-19 studies by reviewing recent publications on COVID-19 and human mobility from a data-oriented perspective.We identified three major sources of mobility data:public transit systems,mobile operators,and mobile phone applications.Four approaches have been commonly used to estimate human mobility:public transit-based flow,social activity patterns,index-based mobility data,and social media-derived mobility data.We compared mobility datasets’characteristics by assessing data privacy,quality,space–time coverage,high-performance data storage and processing,and accessibility.We also present challenges and future directions of using mobility data.This review makes a pivotal contribution to understanding the use of and access to human mobility data in the COVID-19 pandemic and future disease outbreaks.

COVID-19 Pandemic with Human Mobility Across Countries

This study develops a holistic view of the novel coronavirus(COVID-19)spread worldwide through a spatial–temporal model with network dynamics.By using a unique human mobility dataset containing 547166 flights with a total capacity of 101455913 passengers from January 22 to April 24,2020,we analyze the epidemic correlations across 22 countries in six continents and particularly the changes in such correlations before and after implementing the international travel restriction policies targeting different countries.Results show that policymakers should move away from the previous practices that focus only on restricting hotspot areas with high infection rates.Instead,they should develop a new holistic view of global human mobility to impose the international movement restriction.The study further highlights potential correlations between international human mobility and focal countries’epidemic situations in the global network of COVID-19 pandemic.

Incorporation of intra-city human mobility into urban growth simulation:A case study in Beijing

The effective modeling of urban growth is crucial for urban planning and analyzing the causes of land-use dynamics.As urbanization has slowed down in most megacities,improved urban growth modeling with minor changes has become a crucial open issue for these cities.Most existing models are based on stationary factors and spatial proximity,which are unlikely to depict spatial connectivity between regions.This research attempts to leverage the power of real-world human mobility and consider intra-city spatial interaction as an imperative driver in the context of urban growth simulation.Specifically,the gravity model,which considers both the scale and distance effects of geographical locations within cities,is employed to characterize the connection between land areas using individual trajectory data from a macro perspective.It then becomes possible to integrate human mobility factors into a neural-network-based cellular automata(ANN-CA)for urban growth modeling in Beijing from 2013 to 2016.The results indicate that the proposed model outperforms traditional models in terms of the overall accuracy with a 0.60%improvement in Cohen’s Kappa coefficient and a 0.41%improvement in the figure of merit.In addition,the improvements are even more significant in districts with strong relationships with the central area of Beijing.For example,we find that the Kappa coefficients in three districts(Chaoyang,Daxing,and Shunyi)are considerably higher by more than 2.00%,suggesting the possible existence of a positive link between intense human interaction and urban growth.This paper provides valuable insights into how fine-grained human mobility data can be integrated into urban growth simulation,helping us to better understand the human-land relationship.

Measuring spatio-temporal autocorrelation in time series data of collective human mobility

Massive spatio-temporal big data about human mobility have become increasingly available.Revealing underlying dynamic patterns from these data is essential for understanding people’s behavior and urban deployment.Spatio-temporal autocorrelation analysis is an exploratory approach to recognizing data distribution in space and time.The most widely used spatial autocorrelation measurements,such as Moran’s I and local indicators of spatial association(LISA),only apply to static data,so are powerless to spatio-temporal big data about human mobility.Thus,we proposed a new method by extending Moran’s I to measure the spatial autocorrelation of time series data.Then the method was applied to taxi ride data in Beijing,China to reveal the spatial pattern of collective human mobility.The result shows that there is strong positive spatio-temporal autocorrelation within the 5th Ring Road,weak negative spatio-temporal autocorrelation nearby the Sixth Ring Road,and almost no spatiotemporal autocorrelation between the roads.Local spatial patterns of taxi travel were also recognized.This method is useful for discovering underlying patterns from spatio-temporal big data to understand human mobility.

Participants Recruitment for Coverage Maximization by Mobility Predicting in Mobile Crowd Sensing

Mobile Crowd Sensing(MCS)is an emerging paradigm that leverages sensor-equipped smart devices to collect data.The introduction of MCS also poses some challenges such as providing highquality data for upper layer MCS applications,which requires adequate participants.However,recruiting enough participants to provide the sensing data for free is hard for the MCS platform under a limited budget,which may lead to a low coverage ratio of sensing area.This paper proposes a novel method to choose participants uniformly distributed in a specific sensing area based on the mobility patterns of mobile users.The method consists of two steps:(1)A second-order Markov chain is used to predict the next positions of users,and select users whose next places are in the target sensing area to form a candidate pool.(2)The Average Entropy(DAE)is proposed to measure the distribution of participants.The participant maximizing the DAE value of a specific sensing area with different granular sub-areas is chosen to maximize the coverage ratio of the sensing area.Experimental results show that the proposed method can maximize the coverage ratio of a sensing area under different partition granularities.

Affinity-based human mobility pattern for improved region function discovering

The process of urbanization is formed by regular movements of human beings. It yields different functional zones in a city, such as residential zone and commercial zone. Consequently, there exists a close connection between the human mobility pattern and the city＇s zones. However, it is not easy to collect large-scale society-wide data that can precisely capture the underlying relations between the individual＇s movement and the regional functions. Hence, our knowledge for understanding the basic patterns of human mobility is still limited. In order to discover the functions of different regions in a city, we propose an affinity based method in this paper. The affinity is a recently introduced metric for measuring the correlation of two connecting node in a complex network. The proposed model groups different functional zones by measuring user＇s arrival/departure distribution via relative entropy. In addition to this, we also identify the intensity of each functional zone by taking kernel density estimation （KDE） method. In the end, some experiments are conducted to evaluate our method with a large-scale real-life dataset, which consists of 3 million cellphone users＇ records from a period of one month. Our findings on the interaction between the mobility pattern and the regional functions can capture the city dynamics efficiently and provide a valuable reference for urban planners.

Exploring Temporal Activity Patterns of Urban Areas Using Aggregated Network-driven Mobile Phone Data:A Case Study of Wuhu,China

The increasing availability of data in the urban context(e.g.,mobile phone,smart card and social media data)allows us to study urban dynamics at much finer temporal resolutions(e.g.,diurnal urban dynamics).Mobile phone data,for instance,are found to be a useful data source for extracting diurnal human mobility patterns and for understanding urban dynamics.While previous studies often use call detail record(CDR)data,this study deploys aggregated network-driven mobile phone data that may reveal human mobility patterns more comprehensively and can mitigate some of the privacy concerns raised by mobile phone data usage.We first propose an analytical framework for characterizing and classifying urban areas based on their temporal activity patterns extracted from mobile phone data.Specifically,urban areas’diurnal spatiotemporal signatures of human mobility patterns are obtained through longitudinal mobile phone data.Urban areas are then classified based on the obtained signatures.The classification provides insights into city planning and development.Using the proposed framework,a case study was implemented in the city of Wuhu,China to understand its urban dynamics.The empirical study suggests that human activities in the city of Wuhu are highly concentrated at the Traffic Analysis Zone(TAZ)level.This large portion of local activities suggests that development and planning strategies that are different from those used by metropolitan Chinese cities should be applied in the city of Wuhu.This article concludes with discussions on several common challenges associated with using network-driven mobile phone data,which should be addressed in future studies.

Clustering the Stations of Bicycle Sharing System

Bicycle sharing system has emerged as a new mode of transportation in many big cities over the past decade.Since the large number of bicycle stations distribute widely in the city,it is difficult to identify their unique attributes and characteristics directly.Oriented to the real bicycle hire dataset in Hangzhou,China,the clustering analysis for the bicycle stations based on the temporal flow data was carried out firstly.Then,based on the spatial distribution and temporal attributes of calculated clusters,visual diagram and map were used to vividly analyze the bicycle hire behavior related to station category and study the travel rules of citizens.The experimental results demonstrate the relation between human mobility,the time of day,day of week and the station location.

On the potential of iPhone significant location data to characterize individual mobility for air pollution health studies

In many air pollution health studies,the time-activity pattern of individuals is often ignored largely due to lack of data.However,a better understanding of this location-based information is expected to decrease uncertainties in exposure estimation.Here,we showcase the potential of iPhone’s Significant Location(iSL)data in capturing the user’s historical time-activity patterns in order to estimate exposure to ambient air pollutants.In this study,one subject carried an iPhone in tandem with a reference GPS tracking device for one month.The GPS device recorded locations in 10 second intervals while the iSL recorded the time spent in locations the subject visited frequently.Using GPS data as a reference,we then evaluated the accuracy of iSL data in capturing the subject’s time-activity patterns and time-weighted air pollution concentration within the study time period.We found the iSL data accurately captured the time the subject spent in 16 microenvironments(i.e.locations the subject visited more than once),which was 93%of the time during the study period.The average error of time-weighted aerosol optical depth value,a surrogate of particle pollution,is only 0.012%.To explore the availability of iSL data among iPhone users,an online survey was conducted.Among the 349 surveyed participants,72%of them have iSL data available.Considering the popularity of iPhones,iSL data may be available for a significant portion of the general population.Our results suggest iSL data have great potential for characterizing historical time-activity patterns to improve air pollution exposure estimation.

The allometric propagation of COVID-19 is explained by human travel

We analyzed the number of cumulative positive cases of COVID-19 as a function of time in countries around the World.We tracked the increase in cases from the onset of the pandemic in each region for up to 150 days.We found that in 81 out of 146 regions the trajectory was described with a power-law function for up to 30 days.We also detected scale-free properties in the majority of sub-regions in Australia,Canada,China,and the United States(US).We developed an allometric model that was capable of fitting the initial phase of the pandemic and was the best predictor for the propagation of the illness for up to 100 days.We then determined that the power-law COVID-19 exponent correlated with measurements of human mobility.The COVID-19 exponent correlated with the magnitude of air passengers per country.This correlation persisted when we analyzed the number of air passengers per US states,and even per US metropolitan areas.Furthermore,the COVID19 exponent correlated with the number of vehicle miles traveled in the US.Together,air and vehicular travel explained 70%of the variability of the COVID-19 exponent.Taken together,our results suggest that the scale-free propagation of the virus is present at multiple geographical scales and is correlated with human mobility.We conclude that models of disease transmission should integrate scale-free dynamics as part of the modeling strategy and not only as an emergent phenomenological property.

Mobility Pattern of Taxi Passengers at Intra-Urban Scale:Empirical Study of Three Cities

The study of human mobility patterns is of both theoretical and practical values in many aspects. For long-distance travel, a few research endeavors have shown that the displacements of human travels follow a power-law distribution. However, controversies remain regarding the issue of the scaling laws of human mobility in intra-urban areas. In this work, we focus on the mobility pattern of taxi passengers by examining five datasets of three metropolitans. Through statistical analysis, we find that the lognormal distribution with a power-law tail can best approximate both the displacement and the duration time of taxi trips in all the examined cities. The universality of the scaling laws of human mobility is subsequently discussed, in view of the analysis of the data. The consistency of the statistical properties of the selected datasets that cover different cities and study periods suggests that, the identified pattern of taxi-based intra-urban travels seems to be ubiquitous over cities and time periods.

BGMM： A Body Gauss-Markov Based Mobility Model for Body Area Networks

Existing mobility models have limitations in their ability to simulate the movement of Wireless Body Area Network（WBAN） since body nodes do not exactly follow either classic mobility models or human contact distributions. In this paper, we propose a new mobility model called Body Gauss–Markov Mobility（BGMM） model,which is oriented specially to WBAN. First, we present the random Gauss-Markov mobility model as the most suitable theoretical basis for developing our new model, as its movement pattern can reveal real human body movements. Next, we examine the transfer of human movement states and derive a simplified mathematical Human Mobility Model（HMM）. We then construct the BGMM model by combining the RGMM and HMM models. Finally,we simulate the traces of the new mobility model. We use four direct metrics in our proposed mobility model to evaluate its performance. The simulation results show that the proposed BGMM model performs with respect to the direct mobility metrics and can effectively represent a general WBAN-nodes movement pattern.

A GIS-based analytical framework for evaluating the effect of COVID-19 on the restaurant industry with big data

COVID-19 cripples the restaurant industry as a crucial socioeconomic sector that contributes immensely to the global economy.However,what the current literature less explored is to quantify the effect of COVID-19 on restaurant visitation and revenue at different spatial scales,as well as its relationship with the neighborhood character-istics of customers’origins.Based on the Point of Interest(POI)measures derived from SafeGraph data providing mobility records of 45 million cell phone users in the US,our study takes Lower Manhattan,New York City,as the pilot study,and aims to examine 1)the change of restaurant visitations and revenue in the period prior to and after the COVID-19 outbreak,2)the areas where restaurant customers live,and 3)the association between the neighborhood characteristics of these areas and lost customers.By doing so,we provide a geographic information system-based analytical frame-work integrating the big data mining,web crawling techniques,and spatial-economic modelling.Our analytical framework can be implemented to estimate the broader effect of COVID-19 on other industries and can be augmented in a financially monitoring manner in response to future pandemics or public emergencies.

Assessing the spread risk of COVID-19 associated with multi-mode transportation networks in China

The spatial spread of COVID-19 during early 2020 in China was primarily driven by outbound travelers leaving the epicenter,Wuhan,Hubei province.Existing studies focus on the influence of aggregated out-bound population flows originating from Wuhan;however,the impacts of different modes of transportation and the network structure of transportation systems on the early spread of COVID-19 in China are not well understood.Here,we assess the roles of the road,railway,and air transportation networks in driving the spatial spread of COVID-19 in China.We find that the short-range spread within Hubei province was dominated by ground traffic,notably,the railway transportation.In contrast,long-range spread to cities in other provinces was mediated by multiple factors,including a higher risk of case importation associated with air transportation and a larger outbreak size in hub cities located at the center of transportation networks.We further show that,although the dissemination of SARS-CoV-2 across countries and continents is determined by the worldwide air transportation network,the early geographic dispersal of COVID-19 within China is better predicted by the railway traffic.Given the recent emergence of multiple more transmissible variants of SARS-CoV-2,our findings can support a better assessment of the spread risk of those variants and improve future pandemic preparedness and responses.