Passive Health Monitoring Using Large Scale Mobility Data

2021 ◽  
Vol 5 (1) ◽  
pp. 1-23
Author(s):  
Yunke Zhang ◽  
Fengli Xu ◽  
Tong Li ◽  
Vassilis Kostakos ◽  
Pan Hui ◽  
...  
Keyword(s):  
Health Monitoring ◽  
Fast Food ◽  
Large Scale ◽  
Demographic Data ◽  
High Mobility ◽  
Neighborhood Environment ◽  
Mobility Patterns ◽  
Mobility Data ◽  
Health Related ◽  
Hospital Visits

In this paper, we investigate the feasibility of using mobility patterns and demographic data to predict hospital visits. We collect mobility traces from two thousand users for around two months. We extract 16 mobility features from these passively collected mobility traces and train an XGBoost model to predict users' hospital visits. We demonstrate that the designed mobility features can significantly improve prediction accuracy (p < 0.01, AUC = 0.79). We further analyze how these mobility features affect the prediction results and measure their importance by using Shapley additive explanation values. We discover that users with less mobility activity, less visit diversity, and few sports facilities, bountiful entertainment around their visited locations are more likely to visit hospitals. Moreover, we conduct predictions on the populations with different demographic features, which achieves meaningful and insightful results, i.e. maintaining a high mobility activity is crucial for older people's health, while fast food store more substantially affects younger people's health; visit patterns can indicate females' health, while the neighborhood environment is more indicative of males, etc. These results shed light on how to use and understand large scale mobility data in health monitoring and other health-related applications in practice.

scholarly journals Mobility patterns are associated with experienced income segregation in large US cities

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Esteban Moro ◽  
Dan Calacci ◽  
Xiaowen Dong ◽  
Alex Pentland
Keyword(s):  
Large Scale ◽  
Mobility Model ◽  
Coarse Grained ◽  
Spatial Proximity ◽  
Mobility Patterns ◽  
Data Set ◽  
Residential Patterns ◽  
Income Segregation ◽  
Mobility Data ◽  
Mobility Behavior

AbstractTraditional understanding of urban income segregation is largely based on static coarse-grained residential patterns. However, these do not capture the income segregation experience implied by the rich social interactions that happen in places that may relate to individual choices, opportunities, and mobility behavior. Using a large-scale high-resolution mobility data set of 4.5 million mobile phone users and 1.1 million places in 11 large American cities, we show that income segregation experienced in places and by individuals can differ greatly even within close spatial proximity. To further understand these fine-grained income segregation patterns, we introduce a Schelling extension of a well-known mobility model, and show that experienced income segregation is associated with an individual’s tendency to explore new places (place exploration) as well as places with visitors from different income groups (social exploration). Interestingly, while the latter is more strongly associated with demographic characteristics, the former is more strongly associated with mobility behavioral variables. Our results suggest that mobility behavior plays an important role in experienced income segregation of individuals. To measure this form of income segregation, urban researchers should take into account mobility behavior and not only residential patterns.

scholarly journals Non-compulsory measures sufficiently reduced human mobility in Tokyo during the COVID-19 epidemic

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Takahiro Yabe ◽  
Kota Tsubouchi ◽  
Naoya Fujiwara ◽  
Takayuki Wada ◽  
Yoshihide Sekimoto ◽  
...  
Keyword(s):  
Large Scale ◽  
Human Mobility ◽  
Social Contact ◽  
Mobility Patterns ◽  
State Of Emergency ◽  
Social Contacts ◽  
Policy Makers ◽  
Mobility Data ◽  
Contact Rates ◽  
Mobility Behavior

Abstract While large scale mobility data has become a popular tool to monitor the mobility patterns during the COVID-19 pandemic, the impacts of non-compulsory measures in Tokyo, Japan on human mobility patterns has been under-studied. Here, we analyze the temporal changes in human mobility behavior, social contact rates, and their correlations with the transmissibility of COVID-19, using mobility data collected from more than 200K anonymized mobile phone users in Tokyo. The analysis concludes that by April 15th (1 week into state of emergency), human mobility behavior decreased by around 50%, resulting in a 70% reduction of social contacts in Tokyo, showing the strong relationships with non-compulsory measures. Furthermore, the reduction in data-driven human mobility metrics showed correlation with the decrease in estimated effective reproduction number of COVID-19 in Tokyo. Such empirical insights could inform policy makers on deciding sufficient levels of mobility reduction to contain the disease.

scholarly journals Assessing the use of mobile phone data to describe recurrent mobility patterns in spatial epidemic models

2017 ◽  
Vol 4 (5) ◽  
pp. 160950 ◽  
Author(s):  
Cecilia Panigutti ◽  
Michele Tizzoni ◽  
Paolo Bajardi ◽  
Zbigniew Smoreda ◽  
Vittoria Colizza
Keyword(s):  
Infectious Disease ◽  
Mobile Phone ◽  
Urban Areas ◽  
Large Scale ◽  
Human Mobility ◽  
Mobile Phone Data ◽  
Disease Models ◽  
Mobility Patterns ◽  
Mobility Data ◽  
Infectious Disease Models

The recent availability of large-scale call detail record data has substantially improved our ability of quantifying human travel patterns with broad applications in epidemiology. Notwithstanding a number of successful case studies, previous works have shown that using different mobility data sources, such as mobile phone data or census surveys, to parametrize infectious disease models can generate divergent outcomes. Thus, it remains unclear to what extent epidemic modelling results may vary when using different proxies for human movements. Here, we systematically compare 658 000 simulated outbreaks generated with a spatially structured epidemic model based on two different human mobility networks: a commuting network of France extracted from mobile phone data and another extracted from a census survey. We compare epidemic patterns originating from all the 329 possible outbreak seed locations and identify the structural network properties of the seeding nodes that best predict spatial and temporal epidemic patterns to be alike. We find that similarity of simulated epidemics is significantly correlated to connectivity, traffic and population size of the seeding nodes, suggesting that the adequacy of mobile phone data for infectious disease models becomes higher when epidemics spread between highly connected and heavily populated locations, such as large urban areas.

scholarly journals Including household effects in Big Data research: the experience of building a longitudinal residence algorithm using linked administrative data in Wales

2018 ◽  
Vol 3 (1) ◽  
Author(s):  
Karen Susan Tingay ◽  
Matthew Roberts ◽  
Charles B.A. Musselwhite
Keyword(s):  
Large Scale ◽  
Emotional Health ◽  
Demographic Data ◽  
Population Level ◽  
Chronically Ill ◽  
Household Composition ◽  
Health Related Research ◽  
Health Related ◽  
The Uk ◽  
The Impact

The effect of the wider social-environment on physical and emotional health has long been an area of study. Extrapolating the impact of the individual's immediate environment, such as living with a smoker or caring for a chronically-ill child, would potentially reduce confounding effects in health-related research. Surveys, including the UK Census, are beginning to collect data on household composition. However, these surveys are expensive, time consuming, and, as such, are only completed by a subsection of the population. Large-scale, linked databanks, such as the SAIL Databank at Swansea University, which hold routinely collected secondary use clinical and administrative datasets, are broader in scope, both in terms of the nature of the data held, and the population. The SAIL databank includes demographic data and a geographic indicator that makes it possible to identify groups of people that share accommodation, and in some cases the familial relationships among them. This paper describes a method for creating households, including considerations for how that information can be securely shared for research purposes. This approach has broad implications in Wales and beyond, opening up possibilities for more detailed population-level research that includes consideration of residential social interactions.

scholarly journals Mobile phone data reveals the importance of pre-disaster inter-city social ties for recovery after Hurricane Maria

2019 ◽  
Vol 4 (1) ◽  
Author(s):  
Takahiro Yabe ◽  
Satish V. Ukkusuri ◽  
P. Suresh C. Rao
Keyword(s):  
Mobile Phone ◽  
Large Scale ◽  
Human Mobility ◽  
Recovery Process ◽  
Mobile Phone Data ◽  
Mobility Patterns ◽  
Social Forms ◽  
Recovery Processes ◽  
Mobility Data ◽  
New Perspective

Abstract Recent disasters have shown the existence of large variance in recovery trajectories across cities that have experienced similar damage levels. Case studies of such events reveal the high complexity of the recovery process of cities, where inter-city dependencies and intra-city coupling of social and physical systems may affect the outcomes in unforeseen ways. Despite the large implications of understanding the recovery processes of cities after disasters for many domains including critical services, disaster management, and public health, little work have been performed to unravel this complexity. Rather, works are limited to analyzing and modeling cities as independent entities, and have largely neglected the effect that inter-city connectivity may have on the recovery of each city. Large scale mobility data (e.g. mobile phone data, social media data) have enabled us to observe human mobility patterns within and across cities with high spatial and temporal granularity. In this paper, we investigate how inter-city dependencies in both physical as well as social forms contribute to the recovery performances of cities after disasters, through a case study of the population recovery patterns of 78 Puerto Rican counties after Hurricane Maria using mobile phone location data. Various network metrics are used to quantify the types of inter-city dependencies that play an important role for effective post-disaster recovery. We find that inter-city social connectivity, which is measured by pre-disaster mobility patterns, is crucial for quicker recovery after Hurricane Maria. More specifically, counties that had more influx and outflux of people prior to the hurricane, were able to recover faster. Our findings highlight the importance of fostering the social connectivity between cities to prepare effectively for future disasters. This paper introduces a new perspective in the community resilience literature, where we take into account the inter-city dependencies in the recovery process rather than analyzing each community as independent entities.

scholarly journals Predicting the Spatio-Temporal Evolution of Chronic Diseases in Population with Human Mobility Data

2018 ◽  
Author(s):  
Yingzi Wang ◽  
Xiao Zhou ◽  
Anastasios Noulas ◽  
Cecilia Mascolo ◽  
Xing Xie ◽  
...  
Keyword(s):  
Chronic Diseases ◽  
Population Health ◽  
Large Scale ◽  
Human Life ◽  
Human Mobility ◽  
Gaussian Mixture ◽  
Disease Rate ◽  
Mobility Patterns ◽  
Mobility Data ◽  
Spatio Temporal

Chronic diseases like cancer and diabetes are major threats to human life. Understanding the distribution and progression of chronic diseases of a population is important in assisting the allocation of medical resources as well as the design of policies in preemptive healthcare. Traditional methods to obtain large scale indicators on population health, e.g., surveys and statistical analysis, can be costly and time-consuming and often lead to a coarse spatio-temporal picture. In this paper, we leverage a dataset describing the human mobility patterns of citizens in a large metropolitan area. By viewing local human lifestyles we predict the evolution rate of several chronic diseases at the level of a city neighborhood. We apply the combination of a collaborative topic modeling (CTM) and a Gaussian mixture method (GMM) to tackle the data sparsity challenge and achieve robust predictions on health conditions simultaneously. Our method enables the analysis and prediction of disease rate evolution at fine spatio-temporal scales and demonstrates the potential of incorporating datasets from mobile web sources to improve population health monitoring. Evaluations using real-world check-in and chronic disease morbidity datasets in the city of London show that the proposed CTM+GMM model outperforms various baseline methods.

scholarly journals Exploitation of Aggregate Mobility Sensing Data for the Synthesis of Disaggregate Multimodal Tours in Megacities

2021 ◽  
Vol 2 ◽  
Author(s):  
Haris Ballis ◽  
Loukas Dimitriou
Keyword(s):  
Private Information ◽  
Large Scale ◽  
Service Providers ◽  
Telecommunication Service ◽  
Mobility Patterns ◽  
Transport Mode ◽  
Sensing Data ◽  
Trip Purpose ◽  
Mobility Data ◽  
Time Period

The unprecedented volume of urban sensing data has allowed the tracking of individuals at remarkably high resolution. As an example, Telecommunication Service Providers (TSPs) cannot provide their service unless they continuously collect information regarding the location of their customers. In conjunction with appropriate post-processing methodologies, these traces can be augmented with additional dimensions such as the activity of the user or the transport mode used for the completion of journeys. However, justified privacy concerns have led to the enforcement of legal regulations aiming to hinder, if not entirely forbid, the use of such private information even for purely scientific purposes. One of the most widely applied methods for the communication of mobility information without raising anonymity concerns is the aggregation of trips in origin–destination (OD) matrices. Previous work has showcased the possibility to exploit multi-period and purpose-segmented ODs for the synthesis of realistic disaggregate tours. The current study extends this framework by incorporating the multimodality dimension into the framework. In particular, the study evaluates the potential of synthesizing multimodal, diurnal tours for the case where the available ODs are also segmented by the transport mode. In addition, the study proves the scalability of the method by evaluating its performance on a set of time period-, trip purpose-, and transport mode-segmented, large-scale ODs describing the mobility patterns for millions of citizens of the megacity of Tokyo, Japan. The resulting modeled tours utilized over 96% of the inputted trips and recreated the observed mobility traces with an accuracy exceeding 80%. The high accuracy of the framework establishes the potential to utilize privacy-safe, aggregate urban mobility data for the synthesis of highly informative and contextual disaggregate mobility information. Implications are significant since the creation of such granular mobility information from widely available data sources like aggregate ODs can prove particularly useful for deep explanatory analysis or for advanced transport modeling purposes (e.g., agent-based, microsimulation modeling).

scholarly journals Quantifying the economic impact of disasters on businesses using human mobility data: a Bayesian causal inference approach

2020 ◽  
Vol 9 (1) ◽  
Author(s):  
Takahiro Yabe ◽  
Yunchang Zhang ◽  
Satish V. Ukkusuri
Keyword(s):  
Business Performance ◽  
Large Scale ◽  
Human Mobility ◽  
Primary Source ◽  
Economic Cost ◽  
Economic Loss ◽  
Mobility Patterns ◽  
Mobility Data ◽  
Causal Impact ◽  
Spatio Temporal

AbstractIn recent years, extreme shocks, such as natural disasters, are increasing in both frequency and intensity, causing significant economic loss to many cities around the world. Quantifying the economic cost of local businesses after extreme shocks is important for post-disaster assessment and pre-disaster planning. Conventionally, surveys have been the primary source of data used to quantify damages inflicted on businesses by disasters. However, surveys often suffer from high cost and long time for implementation, spatio-temporal sparsity in observations, and limitations in scalability. Recently, large scale human mobility data (e.g. mobile phone GPS) have been used to observe and analyze human mobility patterns in an unprecedented spatio-temporal granularity and scale. In this work, we use location data collected from mobile phones to estimate and analyze the causal impact of hurricanes on business performance. To quantify the causal impact of the disaster, we use a Bayesian structural time series model to predict the counterfactual performances of affected businesses (what if the disaster did not occur?), which may use performances of other businesses outside the disaster areas as covariates. The method is tested to quantify the resilience of 635 businesses across 9 categories in Puerto Rico after Hurricane Maria. Furthermore, hierarchical Bayesian models are used to reveal the effect of business characteristics such as location and category on the long-term resilience of businesses. The study presents a novel and more efficient method to quantify business resilience, which could assist policy makers in disaster preparation and relief processes.

scholarly journals Estimation of Human Mobility Patterns for Forecasting the Early Spread of Disease

Healthcare ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 1224
Author(s):  
Zhengyan Li ◽  
Huichun Li ◽  
Xue Zhang ◽  
Chengli Zhao
Keyword(s):  
Large Scale ◽  
Human Mobility ◽  
Mainland China ◽  
Flow Data ◽  
Mobility Patterns ◽  
Spatial Spread ◽  
Structure Information ◽  
Mobility Data ◽  
Spread Model ◽  
Scale Population

Human mobility data are indispensable in modeling large-scale epidemics, especially in predicting the spatial spread of diseases and in evaluating spatial heterogeneity intervention strategies. However, statistical data that can accurately describe large-scale population migration are often difficult to obtain. We propose an algorithm model based on the network science approach, which estimates the travel flow data in mainland China by transforming location big data and airline operation data into network structure information. In addition, we established a simplified deterministic SEIR (Susceptible-Exposed-Infectious-Recovered)-metapopulation model to verify the effectiveness of the estimated travel flow data in the study of predicting epidemic spread. The results show that individual travel distance in mainland China is mainly within 100 km. There is far more travel between prefectures within the same province than across provinces. The epidemic spatial spread model incorporating estimated travel data accurately predicts the spread of COVID-19 in mainland China. The results suggest that there are far more travelers than usual during the Spring Festival in mainland China, and the number of travelers from Wuhan mainly determines the number of confirmed cases of COVID-19 in each prefecture.

scholarly journals Representing Urban Functions through Zone Embedding with Human Mobility Patterns

2018 ◽  
Author(s):  
Zijun Yao ◽  
Yanjie Fu ◽  
Bin Liu ◽  
Wangsu Hu ◽  
Hui Xiong
Keyword(s):  
New York ◽  
Large Scale ◽  
Arrival Time ◽  
Human Mobility ◽  
Location Based Service ◽  
Mobility Patterns ◽  
Mobility Data ◽  
Traffic Capacity ◽  
Spatio Temporal ◽  
Urban Functions

Urban functions refer to the purposes of land use in cities where each zone plays a distinct role and cooperates with each other to serve people’s various life needs. Understanding zone functions helps to solve a variety of urban related problems, such as increasing traffic capacity and enhancing location-based service. Therefore, it is beneficial to investigate how to learn the representations of city zones in terms of urban functions, for better supporting urban analytic applications. To this end, in this paper, we propose a framework to learn the vector representation (embedding) of city zones by exploiting large-scale taxi trajectories. Specifically, we extract human mobility patterns from taxi trajectories, and use the co-occurrence of origin-destination zones to learn zone embeddings. To utilize the spatio-temporal characteristics of human mobility patterns, we incorporate mobility direction, departure/arrival time, destination attraction, and travel distance into the modeling of zone embeddings. We conduct extensive experiments with real-world urban datasets of New York City. Experimental results demonstrate the effectiveness of the proposed embedding model to represent urban functions of zones with human mobility data.

Sign in / Sign up

Export Citation Format

Share Document