Mobile Data Analysis Research Articles

Mobile Eye-Tracking Data Analysis Using Object Detection via YOLO v4.

Remote eye tracking has become an important tool for the online analysis of learning processes. Mobile eye trackers can even extend the range of opportunities (in comparison to stationary eye trackers) to real settings, such as classrooms or experimental lab courses. However, the complex and sometimes manual analysis of mobile eye-tracking data often hinders the realization of extensive studies, as this is a very time-consuming process and usually not feasible for real-world situations in which participants move or manipulate objects. In this work, we explore the opportunities to use object recognition models to assign mobile eye-tracking data for real objects during an authentic students’ lab course. In a comparison of three different Convolutional Neural Networks (CNN), a Faster Region-Based-CNN, you only look once (YOLO) v3, and YOLO v4, we found that YOLO v4, together with an optical flow estimation, provides the fastest results with the highest accuracy for object detection in this setting. The automatic assignment of the gaze data to real objects simplifies the time-consuming analysis of mobile eye-tracking data and offers an opportunity for real-time system responses to the user’s gaze. Additionally, we identify and discuss several problems in using object detection for mobile eye-tracking data that need to be considered.

Mobility functional areas and COVID-19 spread

This work introduces a new concept of functional areas called Mobility Functional Areas (MFAs), i.e., the geographic zones highly interconnected according to the analysis of mobile positioning data. The MFAs do not coincide necessarily with administrative borders as they are built observing natural human mobility and, therefore, they can be used to inform, in a bottom-up approach, local transportation, spatial planning, health and economic policies. After presenting the methodology behind the MFAs, this study focuses on the link between the COVID-19 pandemic and the MFAs in Austria. It emerges that the MFAs registered an average number of infections statistically larger than the areas in the rest of the country, suggesting the usefulness of the MFAs in the context of targeted re-escalation policy responses to this health crisis. The MFAs dataset is openly available to other scholars for further analyses.

Health care visits during the COVID-19 pandemic: A spatial and temporal analysis of mobile device data.

Transportation disruptions caused by COVID-19 have exacerbated difficulties in health care delivery and access, which may lead to changes in health care use. This study uses mobile device data from SafeGraph to explore the temporal patterns of visits to health care points of interest (POIs) during 2020 and examines how these patterns are associated with socio-demographic and spatial characteristics at the Census Block Group level in North Carolina. Specifically, using the K-medoid time-series clustering method, we identify three distinct types of temporal patterns of visits to health care facilities. Furthermore, by estimating multinomial logit models, we find that Census Block Groups with higher percentages of elderly persons, minorities, low-income individuals, and people without vehicle access are areas most at-risk for decreased health care access during the pandemic and exhibit lower health care access prior to the pandemic. The results suggest that the ability to conduct in-person medical visits during the pandemic has been unequally distributed, which highlights the importance of tailoring policy strategies for specific socio-demographic groups to ensure equitable health care access and delivery.

A Survey on Big Data Processing Frameworks for Mobility Analytics

In the current era of big spatial data, the vast amount of produced mobility data (by sensors, GPS-equipped devices, surveillance networks, radars, etc.) poses new challenges related to mobility analytics. A cornerstone facilitator for performing mobility analytics at scale is the availability of big data processing frameworks and techniques tailored for spatial and spatio-temporal data. Motivated by this pressing need, in this paper, we provide a survey of big data processing frameworks for mobility analytics. Particular focus is put on the underlying techniques; indexing, partitioning, query processing are essential for enabling efficient and scalable data management. In this way, this report serves as a useful guide of state-of-the-art methods and modern techniques for scalable mobility data management and analytics.

RETRACTED ARTICLE: Personalized service recommendation for mobile voice communication users based on improved k-means algorithm

At present, the clustering analysis ability of personalized service recommendation method for mobile voice communication users is low, which leads to low accuracy of service recommendation. Therefore, a personalized service recommendation method for mobile communication users based on improved k-means algorithm is designed. The improved k-means algorithm is used to complete the clustering analysis of mobile voice communication subscriber data. The architecture of personalized recommendation service is set to Hadoop, which realizes personalized recommendation for mobile users. Simulation results show that this method is superior to the existing methods. In the future research, this method can be used to complete personalized service recommendation for mobile communication users.

Analysis of mobile monitoring data from the microAeth® MA200 for measuring changes in black carbon on the roadside in Augsburg

Abstract. The portable microAeth® MA200 (MA200) is widely applied for measuring black carbon in human exposure profiling and mobile air quality monitoring. Due to it being relatively new on the market, the field lacks a refined assessment of the instrument's performance under various settings and data post-processing approaches. This study assessed the mobile real-time performance of the MA200 to determine a suitable noise reduction algorithm in an urban area, Augsburg, Germany. Noise reduction and negative value mitigation were explored via different data post-processing methods (i.e., local polynomial regression (LPR), optimized noise reduction averaging (ONA), and centred moving average (CMA)) under common sampling interval times (i.e., 5, 10, and 30 s). After noise reduction, the treated data were evaluated and compared by (1) the amount of useful information attributed to retention of microenvironmental characteristics, (2) the relative number of negative values remaining, (3) the reduction and retention of peak samples, and (4) the amount of useful signal retained after correction for local background conditions. Our results identify CMA as a useful tool for isolating the central trends of raw black carbon concentration data in real time while reducing nonsensical negative values and the occurrence and magnitudes of peak samples that affect visual assessment of the data without substantially affecting bias. Correction for local background concentrations improved the CMA treatment by bringing nuanced microenvironmental changes into view. This analysis employs a number of different post-processing methods for black carbon data, providing comparative insights for researchers looking for black carbon data smoothing approaches, specifically in a mobile monitoring framework and data collected using the microAeth® series of Aethalometer.

Mobility Change and COVID-19 in Japan: Mobile Data Analysis of Locations of Infection.

BackgroundAs the COVID-19 pandemic spread, the Japanese government declared a state of emergency on April 7, 2020 for seven prefectures, and on April 16, 2020 for all prefectures. The Japanese Prime Minister and governors requested people to adopt self-restraint behaviors, including working from home and refraining from visiting nightlife spots. However, the effectiveness of the mobility change due to such requests in reducing the spread of COVID-19 has been little investigated. The present study examined the association of the mobility change in working, nightlife, and residential places and the COVID-19 outbreaks in Tokyo, Osaka, and Nagoya metropolitan areas in Japan.MethodsFirst, we calculated the daily mobility change in working, nightlife, and residential places compared to the mobility before the outbreak using mobile device data. Second, we estimated the sensitivity of mobility changes to the reproduction number by generalized least squares.ResultsMobility change had already started in March, 2020. However, mobility reduction in nightlife places was particularly significant due to the state of emergency declaration. Although the mobility in each place type was associated with the COVID-19 outbreak, the mobility changes in nightlife places were more significantly associated with the outbreak than those in the other place types. There were regional differences in intensity of sensitivity among each metropolitan area.ConclusionsOur findings indicated the effectiveness of the mobility changes, particularly in nightlife places, in reducing the outbreak of COVID-19.

Uncovering generative mechanisms of information use for project monitoring in humanitarian health management information systems

AbstractHumanitarian medical organizations rely on information on and from the ground to evaluate their effectiveness and accountability. Related digitalization efforts within health information systems assume an instrumental rationality in the use of data. However, previous research identified a multitude of factors influencing actual information use for evidence‐based decision‐making for healthcare delivery. This case study, anchored by critical realism philosophy, unpacks these nuances against the backdrop of a globally operating organization (Médecins Sans Frontières). It aims to highlight the contextual conditions and structures that enact the contingent mechanisms at work in project monitoring within humanitarian health management information systems. By applying an affordance‐based causal analysis, three mechanisms are identified: first, an analytics service provides templated analysis modalities resulting in user–producer–provider relationships; second, the rationalization and synchronization of content and software artifacts gives rise to the standardization strategy of flexible generification; third, the study uncovers the potential for increased internal social discourse and advocacy through collaborative and mobile data analysis. This paper proposes that mechanism‐based explanations can be useful for theory‐building in information systems research as well as for providing insights to practitioners in the humanitarian health sector.

Implementation of Mobile Phone Data Collection in the Conduct EPI Comprehensive Review in East and Southern African Countries.

Mobile phone data collection tools are increasingly becoming very usable collecting, collating and analysing data in the health sector. In this paper, we documented the experiences with mobile phone data collection, collation and analysis in 5 countries of the East and Southern African, using Open Data Kit (ODK), where questionnaires were designed and coded on an XML form, uploaded and data collected using Android-Based mobile phones, with a web-based system to monitor data in real-time during EPI comprehensive review. The ODK interface supports in real-time monitoring of the flow of data, detection of missing or incomplete data, coordinate location of all locations visited, embedded charts for basic analysis. It also minimized data quality errors at entry level with the use of validation codes and constraint developed into the checklist. These benefits, combined with the improvement that mobile phones offer over paper-based in terms of timeliness, data loss, collation, and real-time data collection, analysis and uploading difficulties, make mobile phone data collection a feasible method of data collection that needs to be further explored in the conduct of all surveys in the organization.

Evaluation of Mood Check-in Feature for Participation in Meditation Mobile App Users: Retrospective Longitudinal Analysis.

BackgroundMindfulness meditation smartphone apps may improve mental health but lack evidence-based behavioral strategies to encourage their regular use for attaining mental health benefits. In October 2019, the Calm mindfulness meditation app introduced a mood check-in feature, but its effects on participation in meditation have yet to be tested.ObjectiveThe objective of this study was to investigate how a mood check-in feature impacts meditation behavior in Calm app subscribers.MethodsThis was a retrospective longitudinal analysis of mobile app usage data from a random sample of first-time subscribers to the Calm app (n=2600) who joined in summer 2018 or summer 2019. The mood check-in feature allows users to rate their mood using an emoji after completing a meditation session and displays a monthly calendar of their past mood check-ins. Regression analyses were used to compare the rate of change in meditation behavior before and after the introduction of mood check-ins and to estimate how usage of mood check-ins was associated with individuals’ future meditation behavior (ie, intent-to-treat effects). Additional regression models examined the heterogenous effect of mood check-ins between subscribers who were active or inactive users prior to the introduction to mood check-ins (ie, above or below the median number of weeks with any meditation within their cohort). In order to confirm the specific associations between mood check-ins and meditation engagement, we modeled the direct relationship between the use of mood check-ins in previous weeks and subsequent meditation behavior (ie, treatment on the treated effects).ResultsDuring the first 9 months of their subscription, the 2019 cohort completed an average of 0.482 more sessions per week (95% CI 0.309 to 0.655) than the 2018 cohort; however, across both cohorts, average weekly meditation declined (–0.033 sessions per week, 95% CI –0.035 to –0.031). Controlled for trends in meditation before mood check-ins and aggregate differences between the 2018 and 2019 samples, the time trend in the number of weekly meditation sessions increased by 0.045 sessions among the 2019 cohort after the introduction of mood check-ins (95% CI 0.039 to 0.052). This increase in meditation was most pronounced among the inactive subscribers (0.063 sessions, 95% CI 0.052 to 0.074). When controlled for past-week meditation, use of mood check-ins during the previous week was positively associated with the likelihood of meditating the following week (odds ratio 1.132, 95% CI 1.059 to 1.211); however, these associations were not sustained beyond 1 week.ConclusionsUsing mood check-ins increases meditation participation in Calm app subscribers and may be especially beneficial for inactive subscribers. Mobile apps should consider incorporating mood check-ins to help better engage a wider range of users in app-based meditation, but more research is warranted.

Passive Mobile Data for Studying Seasonal Tourism Mobilities: An Application in a Mediterranean Coastal Destination

The article uses passive mobile data to analyse the complex mobilities that occur in a coastal region characterised by seasonal patterns of tourism activity. A large volume of data generated by mobile phone users has been selected and processed to subsequently display the information in the form of visualisations that are useful for transport and tourism research, policy, and practice. More specifically, the analysis consisted of four steps: (1) a dataset containing records for four days—two on summer days and two in winter—was selected, (2) these were aggregated spatially, temporally, and differentiating trips by local residents, national tourists, and international tourists, (3) origin-destination matrices were built, and (4) graph-based visualisations were created to provide evidence on the nature of the mobilities affecting the study area. The results of our work provide new evidence of how the analysis of passive mobile data can be useful to study the effects of tourism seasonality in local mobility patterns.

Health care visits during the COVID-19 pandemic: A spatial and temporal analysis of mobile device data

Health care visits during the COVID-19 pandemic: A spatial and temporal analysis of mobile device data

BIG MOBILITY DATA ANALYTICS FOR TRAFFIC MONITORING AND CONTROL

With the overpopulation of large cities, the problems with citizens’ mobility, transport inefficiency, traffic congestions and environmental pollution caused by the heavy traffic require advanced ITS solutions to be overcome. Recent advances and wide proliferation of mobile and Internet of Things (IoT) devices, carried by people, built in vehicles and integrated in a road infrastructure, enable collection of large scale data related to mobility and traffic in smart cities, still with a limited use in real world applications. In this paper, we propose the traffic monitoring, control and adaptation platform, named TrafficSense, based on Big Mobility Data processing and analytics. It provides a continuous monitoring of a traffic situation and detection of important traffic parameters, conditions and events, such as travel times along the street segments and traffic congestions in real time. Upon detecting a traffic congestion on an intersection, the TrafficSense application leverages the feedback control loop mechanism to provide a traffic adaptation based on the dynamic configuration of traffic lights duration in order to increase the traffic flows in critical directions at the intersections. We tested and evaluated the developed application on the distributed cloud computing infrastructure. By varying the streaming workload and the cluster parameters we show the feasibility and applicability of our approach and the platform.

The Reach, Use, and Impact of a Free mHealth Mindfulness App in the General Population: Mobile Data Analysis.

BackgroundAs smartphones are now used by most Americans, it is increasingly possible for mental health mobile apps to be disseminated to the general public. However, little is known about how mobile mental health apps are used by the general population outside of a controlled research design.ObjectiveOur objective is to describe how the general population engages with Mindfulness Coach, an iOS- and Android-based app designed to deliver a mindfulness training course.MethodsUsing anonymous download and analytics data, we characterized the reach, usage, retention, and impact of Mindfulness Coach. We included mobile analytics data from all unique downloads of Mindfulness Coach between August 1, 2018, and April 8, 2019 (N=104,067) as well as starred reviews from all Mindfulness Coach users who provided reviews of the app as of March 1, 2020. Mindfulness characteristics were measured by an in-app assessment using the Five-Facet Mindfulness Questionnaire–Short Form (FFMQ-SF).ResultsUsers engaged, on average, in 4.3 visits to the app (SD 8.8; median 2; 90th percentile 8) and associated with an average total of 49.2 interactions with the app (ie, clicks within the app) (SD 113.8; median 19; 90th percentile 105). Users spent an average of 16.2 minutes (SD 63.1) engaged with the app over the full study time period. There were strong linear effects of app engagement on total FFMQ-SF scores. For example, FFMQ-SF scores were associated with more time spent engaged with the app (R2=.23; P<.001). Mindfulness Coach has been reviewed in the Google Play Store 3415 times, with an average rating of 4.7 out of 5 stars, and over 2000 times in the Apple App Store, with an average rating of 4.8 out of 5 stars.ConclusionsThese findings suggest that Mindfulness Coach has achieved substantial and sustained reach in the general population; however, it was used less frequently by many downloaders than researchers and designers intended. There was a subpopulation of users who engaged in the app regularly over an extended period of time, and there was a clear relationship between app use and improvements in mindfulness. To strengthen Mindfulness Coach’s public health impact, more research is needed to understand who is using the app and how, and to design strategies to increase user engagement in order for users to receive a larger dose of mindfulness treatment.

Monitoring travel patterns in German city regions with the help of mobile phone network data

ABSTRACT This paper discusses the possibility to use mobile phone network data to monitor spatial policies in land use and transport planning. Monitoring requires robust time series and reproducible concepts linking spatial policies to monitoring outcomes, a requirement differing from current literature where mobile phone data analysis is exemplified in selected areas with privileged data access. Concepts need to serve the evaluation of policy objectives, for example in regional or local area plans. In this study, we, therefore, extend the application of mobile phone network data to monitoring applications comparing urban settlement types and their characteristic mobility patterns. To accomplish this, we link mobile phone records with urban classifications and transport network data, using both visual and computational approaches to mine the data. The article presents comparisons of travel patterns for selected monocentric and polycentric city regions in Germany, testing hypotheses of transit-oriented regional development, as well as testing for congestion risks in the transport network. The results help us to gain a more detailed understanding of spatial and temporal patterns in mobility for different urban types and assess future potentials for monitoring spatial policies with mobile phone network data.

Collaboration of Network Operators and Cloud Providers in Software-Controlled Networks

The next generation of networks will need to support massive requests for services that have very stringent performance requirements, and their delivery involves significant computing and storage resources. Prominent examples are the mobile augmented and virtual reality services, processing of large-scale IoT data, and mobile data analytics. In order to address these arising challenges, mobile network operators need innovative solutions, and one such is the close collaboration with the cloud service providers. In this article, we propose a novel system architecture that integrates the infrastructure of Mobile Network Operator (MNO) and Cloud Service Provider (CSP), leveraging recent developments in network softwarization that allows the unified control of the network, computing, and storage resources. We envision a multi-tier architecture where the CSP and MNO exchange real-time information about their resource availability and the users' needs, and jointly devise the servicing policy. We present a blueprint of the architecture, several application examples, and a numerical case study that focuses on distributed computing.

Blurring the Lines between Physical and Digital Spaces: Business Model Innovation in Retailing

Traditional retail practices are under stress as retailers ponder various ways of setting up a sustainable omnichannel business model. A significant challenge in their endeavor relates to the blurring lines between physical and digital worlds. This article analyzes three retailers’ exploratory efforts of alternative physical retail spaces. There are five key innovation areas to revamp for such a retail store: in-store technology, the role of sales associates, leveraging a mobile channel, data analytics, and collaborations. Moreover, physical retail space can serve as an aggregation hub that connects various retailer-customer interaction points across physical and digital spaces.

Mobile-based and open-source infectious disease surveillance and outbreak management in Tanzania

Abstract Introduction The PANDORA-ID-NET consortium aims to build capacity for effective outbreak response in sub-Saharan Africa. Part of this mission is to develop a real-time data sharing platform for disease outbreaks that leverages centralised data management and uses mobile technologies for data gathering and feedback. We have committed to using open-source technologies, so that the platform can be deployed on regional IT infrastructure and further developed by local staff, and collected data can be stored and processed in the region of origin. This abstract aims to describe how we identified a state of the art open-source system that fulfils these criteria, and the process of how we are extending it to function within the current infectious disease control framework in Tanzania, under our partnership with the Ifakara Health Institute (IHI). Methods To find state of the art open-source systems matching our criteria, we performed a rapid review of the literature. We screened 1022 articles and found 15 candidate systems, out of which only SORMAS satisfied the criteria. SORMAS was developed jointly by the Helmholtz Centre for Infection Research (HZI) and the Nigeria CDC, and was modeled on Nigeria's successful response to the Ebola outbreak. The system can be used for case management, contact tracing, surveillance, and laboratory sample management. Data is collected and synchronised using Android mobile devices (both online and offline) and data aggregation and analysis are performed in real-time via a web application Results Having chosen SORMAS, we established a collaboration between the SORMAS developer team and the PANDORA team. IHI are guiding ongoing work on adapting SORMAS to the Tanzanian health facility geography and the country's case definition guidelines for notifiable diseases. Conclusions Once adapted for Tanzania, SORMAS will fill an unoccupied niche in infectious disease control, improving the quality of collected case data and enabling better outbreak response Key messages A state of the art, mobile-based, open-source outbreak management and infectious disease surveillance system (SORMAS) is being deployed in Tanzania. We outline our experience with piloting SORMAS in Tanzania, building on the experience of our Nigerian and German partners, who rolled out this system nationally in Nigeria and other African countries.

Impacts of COVID-19 on the Transportation Sector: A Report on China

The COVID-19 pandemic that began in the last quarter of 2019 seriously impacted the transportation industry. Countries around the world adopted various restrictions and policies to prevent the spread of the pandemic, which resulted in a sharp drop in the demand for transportation of goods. In order to analyze the impact of the pandemic on China’s current transportation sector and envision measures that may be taken while recovering from the impact of COVID-19, the current impacts and policy measures were analyzed. This research utilizes data derived from passenger counts, analysis of mobile phone data, discusses what long-term effects may alter future transportation behavior, and how transportation operators should respond to this problem. The government preparedness, recovery measures during/after pandemic, and their effects are analyzed. Results suggested that information transparency, traceability of infection source and hierarchical prevention system is essential for epidemic prevention and control. Moreover, changes in lifestyles and business operation styles due to the pandemic are also outlined and discussed. Finally, this article summarized the influence of COVID-19 to transportation system as well as the lifestyles and the whole society in the long-term, and stated that future research could delve more deeply into this area. The research findings provided solid policy implications and experiences for constructing sustainable transportation system and improve flexibility, reliability, and resilience of traffic governance in post-pandemic era.

Mobile Network Traffic Prediction Based on Seasonal Adjacent Windows Sampling and Conditional Probability Estimation

Mobile operators collect and store the network generatedtraffic data for analysis. Time Series Prediction (TSP) has been used in mobile network traffic data analysis to produce predictive results for network planning and resource allocation. We propose a novel method of predicting mobile network traffic using neural networks based on conditional probability modeling between adjacent data windows. First, we develop a pre-processing method to aggregate the raw traffic log data and sample the aggregated time series to adjacent data windows, as training samples. Second, we use neural networks to parameterize the conditional probability between adjacent data windows and estimate the probability by training the neural networks with sampled data. The estimated conditional probability is then used to ensemble the prediction. Third, we show theoretically that the prediction based on all historical data is equivalent to the prediction based on just previous data window, given the estimation of conditional probability between adjacent data windows. We also analyze computation complexity and show that seasonality will reduce the computational complexity. In the experiment, we compare the prediction performance among the models with different seasonality, sample size and number of hidden layers, and show that the proposed schemes achieve better prediction accuracy than state-of-the-art.