Mobile Location Data Research Articles

Mapping Human Activity Volumes Through Remote Sensing Imagery

The spatial concentration of the human activity is a crucial indication of socioeconomic vitality. Accurately mapping activity volumes is fundamental to support the regional sustainable development. Current approaches rely on mobile positioning data, which record information about human daily activity but are inaccessible in most cities due to privacy and data sharing concerns. Alternative methods are needed to provide more generalized predictions on extensive areas while maintaining low cost. This study demonstrates how remote sensing imagery can be used through an end-to-end deep learning framework for reliable estimates of human activity volumes. The neighbor effect, representing the inherent nature of spatial autocorrelation in the volumes, is incorporated to improve the network. The proposed model exhibits strong predictive power and demonstrates great explainability of physical environment on variations of activity volumes. Landscape interpretations based on hierarchical features provide both object-based and region-based insights into the coevolvement of landscape and human activity. Our findings indicate the possibility of extensively predicting activity volumes, especially in areas with limited access to mobile data, and provide support for the promising framework to better comprehend broad aspects of the human society from observable physical environments.

Towards big data as official statistics: Case study of the use of mobile positioning data to delineate metropolitan areas in Indonesia

Nowadays, the use of so-called big data as a new data source to complement official statistics has become an opportunity for organizations focusing on statistics. The use of big data can lead to a more efficient data collection. However, currently, there has not been any standard business process for big data collection and processing in BPS-Statistics Indonesia. Meanwhile, the adoption of technologies alone cannot determine the success of big data use. It is widely known that big data use can be challenging, since there are issues regarding data access, quality, and methodology, as well as the development of required skillsets. This paper proposes a framework for a business process that is specifically designed to support the use of big data for official statistics at BPS-Statistics Indonesia along with how existing technology will support it. The development of this framework is based on the wider Statistical Business Process Framework and Architecture (SBFA) developed by BPS-Statistics Indonesia to describe and manage its overall statistical business processes. The paper uses the example of the use of Mobile Positioning Data (MPD) as a big data source to delineate Metropolitan Areas in Indonesia as a way to explain the implementation of the framework.

The Behavior of Using Simcard in Indonesia Border Area

Digital life exists in the border area. The cellphone is a part of daily life. Signals from many telecommunication service providers, both Indonesia and foreign, are captured. The problem is when foreign signals captured, then the roaming rate charged. Some people avoid it by switching their simcard to a local simcard. Some people in border area using local simcard (from Indonesian service providers) some use foreign simcard, and other use mixed of them (local and foreign). Knowing about border crosser behavior in using simcard is important not only for the telecommunication service provider but also for the government. The study aims to estimate the number of border crosser based on their behavior in using simcards when entering Indonesia. This study uses data from Survey of Foreign Tourist Based on Mobile Positioning Data conducted by Statistics Indonesia in 2017. Based on that survey, there were 28.305 of border crosser having cellphones. The method of analysis is multinomial logistic regression. The responsese variable is the behavior of using simcard with 3 categories; foreign, local, and mixed. The model fit the data well. The result show that 53,8 percent of border crosser are foreigners most of them entering Indonesia through Kalimantan. The use of simcard in the boundaries area is significantly influenced by sex, age, purpose to visit Indonesia, and region. There are 7,3 percent of foreigner use mixed cards and only 1,4 percent use local cards. For border crossers from Indonesia, there is 99,7 percent use local cards while the other 0,3 percent use mixed cards and no one uses foreign cards.

A Bayesian Nonparametric Mixture Measurement Error Model With Application to Spatial Density Estimation Using Mobile Positioning Data With Multi-Accuracy and Multi-Coverage

The development of mobile network technologies has made it possible to collect location data of mobile devices through various positioning technologies. The location data can be used to estimate the spatial density of mobile devices, which in turn can be used by mobile service providers to plan for network capacity improvements. The two most prevalent positioning technologies are the assisted global positioning system (AGPS) and cell tower triangulation (CTT) methods. AGPS data provide more accurate location information than CTT data but can cover only a fraction of mobile devices, while CTT data can cover all mobile devices. Motivated by this problem, we propose a Bayesian nonparametric mixture measurement error model to estimate the spatial density function by integrating both noise-free data (i.e., AGPS data) and data contaminated with measurement errors (i.e., CTT data). The proposed model estimates the true latent locations from contaminated data, and the estimated latent locations, combined with noise-free data, are used to infer the model parameters. We model the true density function using a Dirichlet process (DP) mixture model with a bivariate beta distribution for the mixture kernel and a DP prior for the mixing distribution. The use of bivariate beta distributions for the mixture kernel allows the density function to have various shapes with a bounded support. Moreover, the use of a DP prior for the mixing distribution allows the number of mixture components to be determined automatically without being specified in advance. Therefore, the proposed model is very flexible. We demonstrate the effective performance of the proposed model via simulated and real-data examples.

Spatial heterogeneity in spatial interaction of human movements—Insights from large-scale mobile positioning data

Distance decay is a primary characteristic of spatial interaction in human movements, and it has been incorporated into many spatial interaction models. Existing approaches mainly rely on travel survey datasets to fit the frictional coefficient of distance decay. However, limited sample size and spatiotemporal resolution make the determination of the spatial interaction characteristic from a comprehensive view difficult. Recently, this situation has been reversed due to emerging large human trajectory datasets, which have stimulated a body of literatures to re-examine the traditional issue of distance decay. However, these studies only focused on distance decay from a global perspective and neglected the spatial non-stationarity of spatial interaction. This study aims to reveal the spatial heterogeneity of distance decay of human movements extracted from massive mobile phone location data from Shenzhen, China. The power law function is utilized to fit the distance decay coefficients for inflow and outflow of each spatial analysis unit. Then, geographically weighted regression is employed to quantify the relationship between distance decay coefficients and land use distribution and between distance decay coefficients and traffic facilities. Results show that considerable spatial non-stationarity appears in the distance decay of spatial interaction, and the regression coefficients indicate the spatial variations of the influence of land use and traffic facilities on distance decay across urban space. These findings provide an in-depth insight into the distance decay characteristics of human movements in a more microcosmic space.

Efficient Parcel Delivery by Predicting Customers’ Locations*

ABSTRACTAn important aspect of the growing e‐commerce sector involves the delivery of tangible goods to the end customer, the so‐called last mile. This final stage of the logistics chain remains highly inefficient due to the problem of failed deliveries. To address this problem, delivery service providers can apply data science to determine the optimal, customer‐centered location and time window for handover. In this article, we present a three‐step approach for location prediction, based on mobile location data, in order to support delivery planning. The first step is identifying a user's locations of interest through density‐based clustering. Next, the semantics (home or work) of the user's locations of interest are discovered, based on temporal assumptions. Finally, we predict future locations with a decision tree model that is trained on each user's historical location data. Though the problem of location prediction is not new, this work is the first to apply it to the field of parcel delivery with its corresponding implications. Moreover, we provide a novel and detailed evaluation on real‐world data from a parcel delivery service. The promising results indicate that our approach has the potential to help delivery service providers to gain insights into their customers’ optimal delivery time and location in order to support delivery planning. Eventually this will decrease last‐mile delivery costs and boost customer satisfaction.

Migration patterns in China extracted from mobile positioning data

Nationwide migrations have drawn much attention from both geographical and social sciences. Compared to census-data-based studies, data collected from broadly used location-awareness devices enable us to describe migrant patterns with timely and fine spatial resolutions. Using a mobile positioning dataset, this paper first analyzes the spatial patterns of mobile-data-based active population estimation (MAPE) and aims to uncover the socioeconomic factors associated with migrant patterns based on the MAPE change around the Chinese Spring Festival of 2016. Time series analysis presents obvious regular patterns and characteristics of MAPE before and during the holiday. Results from a geographically weighted regression (GWR) model show that MAPE differences are significantly associated with the development of secondary and tertiary industries, wage levels and foreign investments. Spatial disparities of the GWR model coefficients reveal that areas in China have different degrees of association with the explanatory variables. Explanations of this spatial nonstationary phenomenon are further detailed with the perspective of a geographical background. Finally, associated social and economic development strategies among cities in China are analyzed, and policy implications regarding the newly emerged data and their insightful findings are discussed.

Measuring mobility, disease connectivity and individual risk: a review of using mobile phone data and mHealth for travel medicine.

The increasing mobility of populations allows pathogens to move rapidly and far, making endemic or epidemic regions more connected to the rest of the world than at any time in history. However, the ability to measure and monitor human mobility, health risk and their changing patterns across spatial and temporal scales using traditional data sources has been limited. To facilitate a better understanding of the use of emerging mobile phone technology and data in travel medicine, we reviewed relevant work aiming at measuring human mobility, disease connectivity and health risk in travellers using mobile geopositioning data. Despite some inherent biases of mobile phone data, analysing anonymized positions from mobile users could precisely quantify the dynamical processes associated with contemporary human movements and connectivity of infectious diseases at multiple temporal and spatial scales. Moreover, recent progress in mobile health (mHealth) technology and applications, integrating with mobile positioning data, shows great potential for innovation in travel medicine to monitor and assess real-time health risk for individuals during travel. Mobile phones and mHealth have become a novel and tremendously powerful source of information on measuring human movements and origin-destination-specific risks of infectious and non-infectious health issues. The high penetration rate of mobile phones across the globe provides an unprecedented opportunity to quantify human mobility and accurately estimate the health risks in travellers. Continued efforts are needed to establish the most promising uses of these data and technologies for travel health.

Daily commuting in the Bratislava metropolitan area: case study with mobile positioning data

Suburban development in the metropolitan area of Bratislava (Slovakia) led to an unprecedented redistribution of population. As the majority of suburbanized families are car-dependent, the influx of new residents is a major source of growing traffic problems. However, due to the unwillingness of suburban in-migrants to change their registration (approximately 100,000 unregistered residents), the commuting based on the census data is insufficient to capture the real pattern of daily mobility in the hinterland of Bratislava. Yet, mobile positioning data represent a powerful source of information with high spatial accuracy and endless options for use. The objective of this study is to analyze mobility patterns of commuting in the Bratislava metropolitan area using mobile positioning data. The experiment was carried out in September 2017 over a fourteen-day period with a sample of 191,404 mobile phone users. The key task was to find a suitable methodological approach to extract useful information of human mobility patterns. We used the concept of anchor points, which represent main nodes of human activity and space–time trajectories. Extracting the localization of “work” and “sleep” we modeled the origin-destination matrix of daily commuting with a spatial accuracy not available until now.

Extracting typical occupancy data of different buildings from mobile positioning data

Occupancy is one of the main factors affecting building energy consumption. The occupancy data, which refer to the occupancy number in this paper, has been widely used in the building simulation field. However, due to the stochastic nature of occupant behavior, it is hard to predict and measure how many people stay in a given building. The rapid development of mobile Internet technology provides an efficient and convenient option for occupancy detection. This paper proposes a concept of typical occupancy data (TOD), which are extracted from real-time occupancy data collected by mobile devices. K-means algorithm is employed to generate the TOD data through cluster analysis. An energy performance model of an office building is used as a case study to demonstrate the effectiveness of the TOD data.

Using mobile location data in biomedical research while preserving privacy.

Location data are becoming easier to obtain and are now bundled with other metadata in a variety of biomedical research applications. At the same time, the level of sophistication required to protect patient privacy is also increasing. In this article, we provide guidance for institutional review boards (IRBs) to make informed decisions about privacy protections in protocols involving location data. We provide an overview of some of the major categories of technical algorithms and medical-legal tools at the disposal of investigators, as well as the shortcomings of each. Although there is no "one size fits all" approach to privacy protection, this article attempts to describe a set of practical considerations that can be used by investigators, journal editors, and IRBs.

Important Location Identification and Personal Location Inference Based on Mobile Subscriber Location Data Preparation of Camera-Ready Contributions to SCITEPRESS Proceedings

As an emerging spatial trajectory data, mobile terminal location data can be widely used to analyze the behavior characteristics and interests of individuals or groups in smart cities, transportation planning and other civil fields. It can also be used to track suspects in anti-terrorism security and public opinion management. Aiming at the problem that it is difficult to determine suitable input parameters of clustering caused by different subscriber location data size and distribution difference, an improved density peak clustering algorithm is proposed and the performance of the improved algorithm is verified on the UCI data set. Firstly the important location is identified by the proposed algorithm, and the personal location is further inferred by the algorithm based on the subscriber's schedule and maximum cluster. Then, the algorithm adopts Google's inverse geocoding technology to obtain the semantic names corresponding to the coordinate points, and introduces the natural language processing technology to achieve word frequency statistics and keyword extraction. The simulation results based on the Geolife data set show that the algorithm is feasible for identifying important locations and inferring personal locations.

Are younger age groups less segregated? Measuring ethnic segregation in activity spaces using mobile phone data

ABSTRACTBoth assimilation theory and common sense suggest that the longer the immigrants reside in a host society, the more they become integrated. However, studies conducted in many countries show the opposite: younger generations of immigrants are more segregated than their parents. The aim of this study is to examine differences in ethnic segregation between age groups of the Estonian majority and Russian-speaking minority in Estonia. We use census data and passive mobile positioning data (CDR) to measure levels of segregation at the individual level for important activity locations and for the whole activity space. Results indicate that segregation in both places of residence and out-of-home non-employment activity districts is higher in younger than in older age groups. Measures of activity space show that the activity spaces of Russian-speakers of all age groups are smaller and less diverse than those of Estonians, and are mainly bound to the places of residence of Russian-speakers. The differences between the activity space measures for Estonians and Russian-speakers generally reduce with age, which suggests higher ethnic segregation in younger age groups. The results thus show that, contrary to assimilation theory, the spatial behaviour of Russian-speakers has not become similar to that of Estonians over generations.

HIGHWAYS DISTURBANCE DETECTION WITH THE USE OF OPEN SOURCE CODE GEOGRAPHIC INFORMATION SYSTEMS, MOBILE AND WEB APPLICATIONS

Abstract. Road disturbances are occurring in our country due to the highway-weighted transportation. These disturbances are caused by human and natural causes. Disturbances in the roads have a negative effect on human life as well as damage to the vehicles. Regardless of how it occurs, it is important to quickly detect and eliminate roadside disturbances. The use of mobile devices has become widespread with developing technologies. Today, many sensors such as GPS and accelerometer are used to detect road disturbances on mobile devices. In this context, it is important to use mobile applications for fast and in-situ detection. In this study, it is investigated the use of mobile devices' location data received from GPS sensors with special mobile interfaces in gathering road data for road disturbances.

Mapping changes of residence with passive mobile positioning data: the case of Estonia

ABSTRACTSimilar to every process involving quantitative research, the study of migration heavily depends on the data available for analysis. The available movement data limit the type of questions that can be asked, and as a result, certain aspects of human spatial mobility have yet to be examined. The development of information and communication technologies and their widespread adoption offers new datasets, methods and interpretations that make it possible to study social processes at a new level. For example, mobile positioning data can aid in overcoming certain constraints embedded in traditional data sources (such as censuses or questionnaires) for study of the connections between daily mobility and change of residence. This study presents a framework for mapping changes of residence using data from passive mobile positioning and an anchor point model to better understand the limits of these methods and their contribution to understanding long-term mobility. The study concludes that the most important considerations in monitoring change of residence using passive mobile position data include the continuity of the time-series data, the varying structure of the mobile tower network and the diversified nature of human mobility. The fine spatial and temporal granularities of passive mobile positioning data allow us to study human movement at a detailed scale.

Mobile Sensing for Data-Driven Mobility Modeling

The use of mobile sensed location data for realistic human track generation is privacy sensitive. People are unlikely to share their private mobile phone data if their tracks were to be simulated. However, the ability to realistically generate human mobility in computer simulations is critical for advances in many domains, including urban planning, emergency handling, and epidemiology studies. In this paper, we present a data-driven mobility model to generate human spatial and temporal movement patterns on a real map applied to an agent based setting. We address the privacy aspect by considering collective participant transitions between semantic locations, defined in a privacy preserving way. Our modeling approach considers three cases which decreasingly use real data to assess the value in generating realistic mobility, considering data of 89 participants over 6079 days. First, we consider a dynamic case which uses data on a half-hourly basis. Second, we consider a data-driven case without time of day dynamics. Finally, we consider a homogeneous case where the transitions between locations are uniform, random, and not data-driven. Overall, we find the dynamic data-driven case best generates the semantic transitions of previously unseen participant data.

Measuring tourism destinations using mobile tracking data

We develop a methodology for measuring visitor flows to destinations using space-time tracking data. Based on a review of the literature on this topic we propose that a tourism destination has five dimensions – spatial, temporal, compositional, social and dynamic – that can be measured using space-time tracking data. We analyse three of these dimensions, namely the spatial, temporal and compositional, using the mobile positioning data of foreign visitors in Estonia from 2011 to 2013. Results show that smaller destination areas can be differentiated inside the whole country by the geographical, temporal and compositional parameters of the visits. These findings demonstrate applications of “BIG” data in destination management. A monitoring tool based on this methodology and data is currently being used by the Estonian Tourist Board.

MobHet: Predicting human mobility using heterogeneous data sources

The literature is rich in mobility models that aim at predicting human mobility. Yet, these models typically consider only a single kind of data source, such as data from mobile calls or location data obtained from GPS and web applications. Thus, the robustness and effectiveness of such data-driven models from the literature remain unknown when using heterogeneous types of data. In contrast, this paper proposes a novel family of data-driven models, called MobHet, to predict human mobility using heterogeneous data sources. Our proposal is designed to use a combination of features capturing the popularity of a region, the frequency of transitions between regions, and the contacts of a user, which can be extracted from data obtained from various sources, both separately and conjointly. We evaluate the MobHet models, comparing them among themselves and with two single-source data-driven models, namely SMOOTH and Leap Graph, while considering different scenarios with single as well as multiple data sources. Our experimental results show that our best MobHet model produces results that are better than or at least comparable to the best baseline in all considered scenarios, unlike the previous models whose performance is very dependent on the particular type of data used. Our results thus attest the robustness of our proposed solution to the use of heterogeneous data sources in predicting human mobility.

Research on Monitoring Crowd Density Method Based on GIS and Mobile Location Data

To effectively control and reduce the occurrence of accidents in public places, where crowds are easily gathered, is the problem of urban management. The paper proposes a method of monitoring population density which based on the combination of GIS and mobile location data. With the secondary-development which based on component GIS, this method can position the mobile location data in order to map the graph model and monitor the area, counting the number, area and crowddensity of monitoring area. We design and implement some system functions such as display warning messages and cartographic visualization to provide decision support for urban population management and control.

Finding Similar Mobile Consumers with a Privacy-Friendly Geosocial Design

This paper focuses on finding the same and similar users based on location-visitation data in a mobile environment. We propose a new design that uses consumer-location data from mobile devices (smartphones, smart pads, laptops, etc.) to build a “geosimilarity network” among users. The geosimilarity network (GSN) could be used for a variety of analytics-driven applications, such as targeting advertisements to the same user on different devices or to users with similar tastes, and to improve online interactions by selecting users with similar tastes. The basic idea is that two devices are similar, and thereby connected in the GSN, when they share at least one visited location. They are more similar as they visit more shared locations and as the locations they share are visited by fewer people. This paper first introduces the main ideas and ties them to theory and related work. It next introduces a specific design for selecting entities with similar location distributions, the results of which are shown using real mobile location data across seven ad exchanges. We focus on two high-level questions: (1) Does geosimilarity allow us to find different entities corresponding to the same individual, for example, as seen through different bidding systems? And (2) do entities linked by similarities in local mobile behavior show similar interests, as measured by visits to particular publishers? The results show positive results for both. Specifically, for (1), even with the data sample’s limited observability, 70%–80% of the time the same individual is connected to herself in the GSN. For (2), the GSN neighbors of visitors to a wide variety of publishers are substantially more likely also to visit those same publishers. Highly similar GSN neighbors show very substantial lift.