mobility data
Recently Published Documents

The study of human mobility is crucial due to its impact on several aspects of our society, such as disease spreading, urban planning, well-being, pollution, and more. The proliferation of digital mobility data, such as phone records, GPS traces, and social media posts, combined with the predictive power of artificial intelligence, triggered the application of deep learning to human mobility. Existing surveys focus on single tasks, data sources, mechanistic or traditional machine learning approaches, while a comprehensive description of deep learning solutions is missing. This survey provides a taxonomy of mobility tasks, a discussion on the challenges related to each task and how deep learning may overcome the limitations of traditional models, a description of the most relevant solutions to the mobility tasks described above, and the relevant challenges for the future. Our survey is a guide to the leading deep learning solutions to next-location prediction, crowd flow prediction, trajectory generation, and flow generation. At the same time, it helps deep learning scientists and practitioners understand the fundamental concepts and the open challenges of the study of human mobility.

The pervasiveness of smartphones has shaped our lives, social norms, and the structure that dictates human behavior. They now directly influence how individuals demand resources or interact with network services. From this scenario, identifying key locations in cities is fundamental for the investigation of human mobility and also for the understanding of social problems. In this context, we propose the first graph-based methodology in the literature to quantify the power of Point-of-Interests (POIs) over its vicinity by means of user mobility trajectories. Different from literature, we consider the flow of people in our analysis, instead of the number of neighbor POIs or their structural locations in the city. Thus, we modeled POI’s visits using the multiflow graph model where each POI is a node and the transitions of users among POIs are a weighted direct edge. Using this multiflow graph model, we compute the attract, support, and independence powers . The attract power and support power measure how many visits a POI gathers from and disseminate over its neighborhood, respectively. Moreover, the independence power captures the capacity of a POI to receive visitors independently from other POIs. We tested our methodology on well-known university campus mobility datasets and validated on Location-Based Social Networks (LBSNs) datasets from various cities around the world. Our findings show that in university campus: (i) buildings have low support power and attract power ; (ii) people tend to move over a few buildings and spend most of their time in the same building; and (iii) there is a slight dependence among buildings, even those with high independence power receive user visits from other buildings on campus. Globally, we reveal that (i) our metrics capture places that impact the number of visits in their neighborhood; (ii) cities in the same continent have similar independence patterns; and (iii) places with a high number of visitation and city central areas are the regions with the highest degree of independence.

This paper discusses the comparative results of surface and satellite measurements made during the Phase1 (25 March to 14 April), Phase2 (15 April to 3 May) and Phase3 (3 May to 17May) of Covid-19 imposed lockdown periods of 2020 and those of the same locations and periods during 2019 over India. These comparative analyses are performed for Indian states and Tier 1 megacities where economic activities have been severely affected with the nationwide lockdown. The focus is on changes in the surface concentration of sulfur dioxide (SO2), carbon monoxide (CO), PM2.5 and PM10, Ozone (O3), Nitrogen dioxide (NO2)  and retrieved columnar NO2 from TROPOMI and Aerosol Optical Depth (AOD) from MODIS satellite. Surface concentrations of PM2.5 were reduced by 30.59%, 31.64%  and 37.06%, PM10 by 40.64%, 44.95% and 46.58%, SO2 by 16.73%, 12.13% and 6.71%, columnar NO2 by 46.34%, 45.82% and 39.58% and CO by 45.08%, 41.51% and 60.45% during lockdown periods of Phase1, Phase2 and Phase3 respectively as compared to those of 2019 periods over India. During 1st phase of lockdown, model simulated PM2.5 shows overestimations to those of observed PM2.5 mass concentrations. The model underestimates the PM2.5 to those of without reduction before lockdown and 1st phase of lockdown periods. The reduction in emissions of PM2.5, PM10, CO and columnar NO2 are discussed with the surface transportation mobility maps during the study periods. Reduction in the emissions based on the observed reduction in the surface mobility data, the model showed excellent skills in capturing the observed PM2.5 concentrations. Nevertheless, during the 1st & 3rd phases of lockdown periods AOD reduced by 5 to 40%. Surface O3 was increased by 1.52% and 5.91% during 1st and 3rd Phases of lockdown periods respectively, while decreased by -8.29% during 2nd Phase of lockdown period.

IntroductionTo combat and mitigate the transmission of the SARS-CoV-2 virus, reducing the number of social contacts within a population is highly effective. Non-pharmaceutical policy interventions, e.g. stay-at-home orders, closing schools, universities, and (non-essential) businesses, are expected to decrease pedestrian flows in public areas, leading to reduced social contacts. The extent to which such interventions show the targeted effect is often measured retrospectively by surveying behavioural changes. Approaches that use data generated through mobile phones are hindered by data confidentiality and privacy regulations and complicated by selection effects. Furthermore, access to such sensitive data is limited. However, a complex pandemic situation requires a fast evaluation of the effectiveness of the introduced interventions aiming to reduce social contacts. Location-based sensor systems installed in cities, providing objective measurements of spatial mobility in the form of pedestrian flows, are suited for such a purpose. These devices record changes in a population’s behaviour in real-time, do not have privacy problems as they do not identify persons, and have no selection problems due to ownership of a device. ObjectiveThis work aimed to analyse location-based sensor measurements of pedestrian flows in 49 metropolitan areas at 100 locations in Germany to study whether such technology is suitable for the real-time assessment of behavioural changes during a phase of several different pandemic-related policy interventions. MethodsSpatial mobility data of pedestrian flows was linked with policy interventions using the date as a unique linkage key. Data was visualised to observe potential changes in pedestrian flows before or after interventions. Furthermore, differences in time series of pedestrian counts between the pandemic and the pre-pandemic year were analysed. ResultsThe sensors detected changes in mobility patterns even before policy interventions were enacted. Compared to the pre-pandemic year, pedestrian counts were 85% lower. ConclusionsThe study illustrated the practical value of sensor-based real-time measurements when linked with non-pharmaceutical policy intervention data. This study’s core contribution is that the sensors detected behavioural changes before enacting or loosening non-pharmaceutical policy interventions. Therefore, such technologies should be considered in the future by policymakers for crisis management and policy evaluation.

Since the outbreak of the corona virus in the end of 2019, many worldwide attempts have been made to monitor and control the COVID-19 pandemic. A wealth of empirical data has been collected and used by national health authorities to understand and mitigate the spread and impacts of the corona virus. In various countries this serious health concern has led to the development of corona dashboards monitoring the COVID-19 evolution. The present study aims to design and test an extended corona dashboard, in which—beside up-to-date daily core data on infections, hospital and intensive care admissions, and numbers of deceased people—also the evolution of vaccinations in a country is mapped out. This dashboard system is next extended with time-dependent contextual information on lockdown and policy stringency measures, while disaggregate information on the geographic spread of the COVID-19 disease is provided by means of big data on contact intensity and mobility motives based on detailed Google Mobility data. Finally, this context-specific corona dashboard, named ‘Dutchboard’, is further extended towards the regional and local level so as to allow also for space-specific ‘health checks’ and assessments.

Background: During the first year of the COVID-19 pandemic, the most effective way to reduce transmission and to protect oneself was to reduce contact with others. However, it is unclear how behavior changed, despite numerous surveys about peoples' attitudes and actions during the pandemic and public health efforts to influence behavior. Methods: We used two sources of data to quantify changes in behavior at the county level during the first year of the pandemic in the United States: aggregated mobile device (smartphone) location data to approximate the fraction of people staying at home each day and digital invitation data to capture the number and size of social gatherings. Results: Between mid-March to early April 2020, the number of events fell and the fraction of devices staying at home peaked, independently of when states issued emergency orders or stay-at-home recommendations. Activity began to recover in May or June, with later rebounds in counties that suffered an early spring wave of reported COVID-19 cases. Counties with high incidence in the summer had more events, higher mobility, and less stringent state-level COVID-related restrictions the month before than counties with low incidence. Counties with high incidence in early fall stayed at home less and had less stringent state-level COVID-related restrictions in October, when cases began to rise in some parts of the US. During the early months of the pandemic, the number of events was inversely correlated with the fraction of devices staying at home, but after the fall of 2020 mobility appeared to stay constant as the number of events fell. Greater changes in behavior were observed in counties where a larger fraction voted for Biden in the 2020 US Presidential election. The number of people invited per event dropped gradually throughout the first year of the pandemic. Conclusions: The mobility and events datasets uncovered different kinds of behavioral responses to the pandemic. Our results indicate that people did in fact change their behavior in ways that likely reduced COVID exposure and transmission, though the degree of change appeared to be affected by political views. Though the mobility data captured the initial massive behavior changes in the first months of the pandemic, the digital invitation data, presented here for the first time, continued to show large changes in behavior later in the first year of the pandemic.

IntroductionConcerns have been raised about the potential for risk compensation in the context of mask mandates for mitigating the spread of COVID-19. However, the debate about the presence or absence of risk compensation for universal mandatory mask-wearing rules—especially in the context of COVID-19—is not settled yet.MethodsMobility is used as a proxy for risky behaviour before and after the mask mandates. Two sets of regressions are estimated to decipher (any) risk-compensating effect of mask mandate in Bangladesh. These include: (1) intervention regression analysis of daily activities at six types of locations, using pre-mask-mandate and post-mandate data; and (2) multiple regression analysis of daily new COVID-19 cases on daily mobility (lagged) to establish mobility as a valid proxy.Results(1) Statistically, mobility increased at all five non-residential locations, while home stays decreased after the mask mandate was issued; (2) daily mobility had a statistically significant association on daily new cases (with around 10 days of lag). Both significances were calculated at 95% confidence level.ConclusionCommunity mobility had increased (and stay at home decreased) after the mandatory mask-wearing rule, and given mobility is associated with increases in new COVID-19 cases, there is evidence of risk compensation effect of the mask mandate—at least partially—in Bangladesh.

<p><em>In this study, researchers examined the role of the Village Care for Migrant Workers (Desbumi) program in mentoring female migrant workers in Darek Village, Praya Barat Daya District, Central Lombok Regency. This research is field research with data collection steps, namely interviews, documentation and observation. Therefore, this research aims o find out female migrant worker assistance patterns through the Desbumi program in Darek Village, Praya Barat Daya District, Central Lombok Regency. The results and discussion in this study are that the Desbumi program has three roles. First. Information center provides information to migrant workers about safe and legal migration (safety migrations). Second is the mobility data center, which assists prospective migrant workers in arranging migration filings at the village office. Third, the center for case advocacy, namely the role in providing protection and assistance to migrant workers who experience problems abroad.</em> <em>Meanwhile, the pattern of assisting female migrant workers in the Desbumi program approach is namely. First, pre-work mentoring, namely conducting socialization to the community by bringing migration flyers that have been given by Migrant Care and from the BNP2TKI office in Central Lombok Regency. It then provides an opportunity for people to ask questions about safe migration. Second, after work assistance, the Desbumi program can carry out consolidation and integration with Migrant Care, PPK and BNP2TKI if they encounter problems with migrant workers abroad. Furthermore, they confirm through social media with the Desbumi program in Darek Village, Praya Barat Daya District, Central Lombok Regency. Third, post-work mentoring, where former migrant workers are empowered in the village with various empowerment approaches. These approaches included making crackers, chips, sewing training and soft skills activities supported by the village government, Migrant Care, the Mataram City Panca Karsa Association (PPK), and BNP2TKI Central Lombok Regency </em></p><p> </p><p>Dalam penelitian ini, peneliti mengkaji peran dari program Desa Peduli Buruh Migran (Desbumi) dalam pendampingan buruh migrant perempuan di Desa Darek Kecamatan Praya Barat Daya Kabupaten Lombok Tengah. Penelitian ini merupakan penelitian lapangan dengan langkah pengumpulan data yakni wawancara, dokumentasi dan observasi. Oleh karenaitu, tujuan dalam penelitian ini yakni untuk mengetahui bagaimana pola pendampingan buruh migrant perempuan melalui program Desbumi di Desa Darek Kecamatan Praya Barat Daya Kabupaten Lombok Tengah. Hasil dan pembahasan dalam penelitian ini yakni, bahwasannya program Desbumi memiliki tiga peran seperti. Pertama. Pusat Informasi yakni untuk memberikan informasi pada buruh migrant tentang bermigrasi yang aman yang legal. Kedua, pusat data mobilitas yakni untuk membantu calon buruh migrant mengurus pemberkasan migrasi di kantor desa. Ketiga, pusat advokasi kasus yakni peran dalam memberikan perlindungan dan pendampingan pada buruh migran yang mengalami permasalahan di luar negeri. Sedangkan pola pendampingan buruh migrant perempuan dalam pendekatan program Desbumi yakni. Pertama, pendampingan sebelum bekerja yakni melakukan sosialisasi ke masyarakat dengan membawa pamphlet migrasi yang sudah diberikan oleh pihak Migrant Care serta dari kantor BNP2TKI Kabupaten Lombok Tengah. Kemudian memberikan kesempatan bagi masyarakat untuk bertanya tentang migrasi yang aman. Kedua, pendampingan setelah bekerja yakni program Desbumi dapat melakukan dengan konsolidasi dan integrasi dengan Migran Care, PPK dan BNP2TKI jika menerima problematika buruh migran di luar negeri, dan melakukan konfirmasi melalui media social dengan adanya program Desbumi di Desa Darek Kecamatan Praya Barat Daya Kabupaten Lombok Tengah. Ketiga, pendampingan purna bekerja yakni mantan buruh migrant diperdayakan di desa dengan berbagai pendekatan pemberdayaan yakni pembuatan kerupuk, keripik, pelatihan menjahit dan kegiatan soft skill yang di dukung oleh pemerintah desa, pihak Migran Care, pihak Perkumpulan Panca Karsa (PPK) Kota Mataram, dan BNP2TKI Kabupaten Lombok Tengah. Dalam penelitian ini, peneliti mengkaji peran dari program Desa Peduli Buruh Migran (Desbumi) dalam pendampingan buruh migrant perempuan di Desa Darek Kecamatan Praya Barat Daya Kabupaten Lombok Tengah. Penelitian ini merupakan penelitian lapangan dengan langkah pengumpulan data yakni wawancara, dokumentasi dan observasi. Oleh karenaitu, tujuan dalam penelitian ini yakni untuk mengetahui bagaimana pola pendampingan buruh migrant perempuan melalui program Desbumi di Desa Darek Kecamatan Praya Barat Daya Kabupaten Lombok Tengah. Hasil dan pembahasan dalam penelitian ini yakni, bahwasannya program Desbumi memiliki tiga peran seperti. Pertama. Pusat Informasi yakni untuk memberikan informasi pada buruh migrant tentang bermigrasi yang aman yang legal. Kedua, pusat data mobilitas yakni untuk membantu calon buruh migrant mengurus pemberkasan migrasi di kantor desa. Ketiga, pusat advokasi kasus yakni peran dalam memberikan perlindungan dan pendampingan pada buruh migran yang mengalami permasalahan di luar negeri. Sedangkan pola pendampingan buruh migrant perempuan dalam pendekatan program Desbumi yakni. Pertama, pendampingan sebelum bekerja yakni melakukan sosialisasi ke masyarakat dengan membawa pamphlet migrasi yang sudah diberikan oleh pihak Migrant Care serta dari kantor BNP2TKI Kabupaten Lombok Tengah. Kemudian memberikan kesempatan bagi masyarakat untuk bertanya tentang migrasi yang aman. Kedua, pendampingan setelah bekerja yakni program Desbumi dapat melakukan dengan konsolidasi dan integrasi dengan Migran Care, PPK dan BNP2TKI jika menerima problematika buruh migran di luar negeri, dan melakukan konfirmasi melalui media social dengan adanya program Desbumi di Desa Darek Kecamatan Praya Barat Daya Kabupaten Lombok Tengah. Ketiga, pendampingan purna bekerja yakni mantan buruh migrant diperdayakan di desa dengan berbagai pendekatan pemberdayaan yakni pembuatan kerupuk, keripik, pelatihan menjahit dan kegiatan soft skill yang di dukung oleh pemerintah desa, pihak Migran Care, pihak Perkumpulan Panca Karsa (PPK) Kota Mataram, dan BNP2TKI Kabupaten Lombok Tengah. </p>

Large-scale microsimulations are increasingly resourceful tools for analysing in detail citywide effects and alternative scenarios of our policy decisions, approximating the ideal of ‘urban digital twins’. Yet, these models are costly and impractical, and there are surprisingly few published examples robustly validated with empirical data. This paper, therefore, presents a new large-scale agent-based traffic microsimulation for the Barcelona urban area using SUMO to show the possibilities and challenges of building these scenarios based on novel fine-grained empirical big data. It combines novel mobility data from real cell phone records with conventional surveys to calibrate the model comparing two different dynamic assignment methods for getting an operationally realistic and efficient simulation. Including through traffic and the use of a stochastic adaptive routing approach results in a larger 24-hour model closer to reality. Based on an extensive multi-scalar evaluation including traffic counts, hourly distribution of trips, and macroscopic metrics, this model expands and outperforms previous large-scale scenarios, which provides new operational opportunities in city co-creation and policy. The novelty of this work relies on the effective modelling approach using newly available data and the realistic robust evaluation. This allows the identification of the fundamental challenges of simulation to accurately capture real-world dynamical systems and to their predictive power at a large scale, even when fed by big data, as envisioned by the digital twin concept applied to smart cities.

Learning human mobility behaviors from location-sensing data are crucial to mobility data mining because of its potential to address a range of analytical purposes in mobile context reasoning, including exploration, inference, and prediction. However, existing approaches suffer from two practical problems: temporal and spatial sparsity. To address these shortcomings, we present two unsupervised learning methods to model the mobility behaviors of multiple users (i.e., a population), considering efficiency and accuracy. These methods intelligently overcome the sparsity in individual data by seeking temporal commonality among users’ heterogeneous location behaviors. The advantages of our models are highlighted through experiments on several real-world mobility data sets, which also show how our methods can realize the three analytical purposes in a unified manner.