GPS-enabled Smartphones Research Articles

Remote exercise testing in pulmonary hypertension (PHRET).

Remote exercise tests for patients with pulmonary hypertension (PH) would improve the telemedicine strategies in this disease. The PHRET study assessed the validity and feasibility of four remote exercise tests performed by PH patients at home. Participants undergoing diagnostic assessment for PH were included. At baseline, patients completed a 6MWT followed by a range of study tests including a Timed Up and Go (TUG) test, a Sit-to-Stand (STS), a Step Test (ST), and a tele-6MWT (T6MWT) performed outside using a GPS-enabled smartphone. Patients performed these tests at home following discharge and at first follow-up. Analysis focused on comparing the results of study tests to the standard 6MWT. The discontinuation rate was 15%. Ninety-seven percentof patients were able to complete a TUG, 92% a STS, 73% a ST, and 49% a T6MWT. At baseline, correlation between the standard 6MWT and study tests, respectively, wasT6MWT 0.93, ST 0.78, STS 0.71, and TUG -0.76 (p < 0.001). Direction of change in the study test agreed with the standard 6MWT in 68% of the follow-up ST, 68% of the STS, 71% of the TUG, and 79% of the T6MWT. Patients were able to complete the tests at home, there were no adverse incidents and ≥92% of patients were happy to continue performing home tests. Remote exercise testing is feasible. The T6MWT was a valid remote measure of exercise capacity, but could only be performed by a limited number of patients. The high discontinuation rate may impact the utility of remote tests.

Estimating fundamental diagram for multi-modal signalized urban links with limited probe data

Being one of the most classic concepts in the traffic flow theory, the fundamental diagram (FD) describes the relationship between average flow and average density of link-level traffic flow dynamics. Inductive loop detectors or closed-circuit television are commonly used for FD estimations and they are known to have cost-effective and accuracy issues. Thanks to the GPS-enabled smartphones and GPS-equipped probe vehicles, high temporal and spatial resolution traffic data are available which enable traffic condition inference over time and space continuously. Several existing studies have explored FD estimation algorithms on freeways where flow is generally uninterrupted and uni-modal, based on GPS trajectory data. These developments motivate this study, where the objective is to extend the application to multi-modal and interrupted environment, i.e., urban signalized areas. In this paper, an estimation method is developed to capture the FD of multi-modal traffic streams on signalized urban links. The proposed algorithm is empirically tested using real-world GPS datasets collected on a signalized arterial road in Shenzhen City. Promising results show that the proposed algorithm is capable to estimate the FD under such condition. Furthermore, impacts of multi-modal traffic and signal operations on the FD estimation are analyzed and discussed.

Becoming-Data, Becoming-Mountain

This article explores our ecological relation to both information and information technologies as we "mediate mountains." Starting with a Gibsonian approach to affordances, and considering how an agent-specific account of action limits human access to "the digital," I suggest that the interface between human and device marks a double-coupling of two agents—one digital the other embodied—each of which draws out the other to alter potential action. The essay explores the affordances of agents and the environments in which they act, and how action seemingly occurs across the boundaries marked by the human-device interface. Drawing on actor network theory, assemblage theory, and Don Ihde's "inter-relational ontology," I examine how, within an ecology of humans and mobile devices, "agency" and "action" operate within a Deleuzean transversal, cutting across body-machine boundaries. As an application of this analysis, I examine the relationship between embodied and digital agents "in the wild" of the mountains, through AR and GPS-enabled smartphone apps, and how each agent, acting upon its own environment, gives rise to transversal events that alter the affordances offered to agents across a seemingly uncrossable divide.

Examining the Effect of Spatial Proximity of Geo-located Dumpsites on Groundwater Quality in Samaru-Nigeria

The effect of improper waste disposal on man’s health and environment due to the closeness of solid waste dumpsites to underground water sources in some parts of the world has raised issues of serious concern. This study thus sought to examine groundwater quality dependence on the spatial proximity of dumpsites in Samaru, Kaduna state-Nigeria. The coordinates of 10 solid waste dumpsites in proximity to groundwater sources (boreholes) in the study area were acquired for spatial analyses with a GPS-enabled smartphone. Ten groundwater samples from boreholes in relation to dumpsites were collected for testing and analyses of 11 physical and chemical parameters of water quality based on the Canadian Council of Ministers of the Environment (CCME) and World Health Organisation (WHO) standard limits. Thereafter, the water quality index (WQI) for all the locations was calculated. The results of the spatial proximity analyses carried out revealed that the requirement for locating dumpsites was not met as specified by the Environmental Protection Agency (EPA) regarding the minimum safe distance from groundwater sources as a majority (about 80%) of the dumpsites were located too close to the boreholes. The results of the study, however, revealed that the majority (about 80%) of the groundwater samples met the conditions for good drinking water (suitable for drinking water) even with their closeness to the dumpsites based on the computed WQI values and ratings. Meanwhile, only Calcium, Dissolved Oxygen, and Biochemical Oxygen Demand concentrations were significantly affected (p &amp;lt; 0.05 at the 95% significance level) by the closeness of the solid waste dumpsites to the boreholes with very strong (R2 = 86%) and strong (R2 = 79%) relationships, respectively. Suggestions were nonetheless made for the monitoring of land use activities in the areas surrounding groundwater sources to prevent groundwater contamination.

Youth tobacco and cannabis use and co-use: Associations with daily exposure to tobacco marketing within activity spaces and by travel patterns

BackgroundWe investigated youth daily activity spaces, travel patterns, exposure to tobacco retail marketing, and tobacco and cannabis use and co-use. Methods: Data included 1,060 daily assessments from 100 participants (16–20 years old) in 8 California cities. Using GPS-enabled smartphones with a survey application, youth completed brief daily surveys, and location coordinates were obtained at one-minute intervals. Tobacco outlets in study cities were visited by observers to record outlet GPS point locations and data concerning tobacco marketing. Tobacco outlet addresses and GPS location coordinates were geocoded. Activity spaces were constructed by joining sequential location points. Measures included the number of outlets with outdoor tobacco marketing within 50 m of activity space polylines and the amount of time participants were within 50 m of these outlets each day. Participants also reported tobacco and cannabis use and whether they saw tobacco ads by their neighborhood, school, workplace, and anywhere else each day. Additionally each day they reported how much time they traveled by different modes of transportation, with parents/guardians, and with friends. Results: In mixed effects multinomial regression models, perceived exposure to tobacco marketing was associated with co-use of tobacco and cannabis on a given day (RRR = 1.66, p < 0.05). Although perceived exposure to tobacco marketing was not associated with tobacco use only, moderation analysis indicated that the likelihood of tobacco use was greater among youth who walked/biked/skated more (RRR = 5.22, p < 0.05). Conclusion: Perceived exposure to tobacco marketing contributes to youth tobacco and cannabis use or co-use, especially for those who travel by walking/biking/skating.

Assessing internet and web services based webdom and virtual web-data-centric geographical study.

At present, the traditional geographical study is somewhat shifted to virtual web-datacentric geographical study and it was started almost around last decade of the twentieth century concerning remotely sensed earth surface, digitisation, virtual data storing and their artificial intelligence based machine learning for spatio-temporal analysis, prediction and thematic mapping. Now in the age of webdom—a global digital kingdom of internet and web services, when internet services flooded everything relating to continuous up-gradation of computer-related science and technologies along with increasing number of internet users and GPS enabled smart phones, geographical data are generated by exaflood leading to bigdata. Many online data are now easily available to everyone from anywhere at any time. The objective is to assess the webdom and to understand the scope of contemporary virtual web-data-centric geographical study involving geographical bigdata, machine learning and WebGIS, when virtual world abundantly expands gradually during this period of webdom. Each data in bigdata contains geospatial attributes. Worldwide under the exponential growth and advancement of data science like other scientific disciplines geography is also predicting different phenomenon based on artificial intelligence and machine learning. The three main facets of virtual web-data-centric geographical study are geographical bigdata, geographical machine learning, and WebGIS. It is centrally concerned with digital data and web services. Here data are analysed through machine learning methods. Sometimes reliability of web-data is in question without field verification which is considered as the primary requisition of traditional geography.

Baseline malaria prevalence at the targeted pre-elimination districts in Ethiopia

BackgroundEncouraged by the previous success in malaria control and prevention strategies, the Ethiopian ministry of health launched malaria elimination with a stepwise approach by primarily targeting the low-transmission Districts and their adjacent areas/zones in order to shrink the country’s malaria map progressively. Hence, this community survey was conducted to establish baseline malaria information at the preliminary phase of elimination at targeted settings.MethodsA community-based cross-sectional survey was conducted at 20 malaria-elimination targeted Districts selected from five Regional states and one city administration in Ethiopia. The GPS-enabled smartphones programmed with Open Data Kit were used to enumerate 9326 study households and collect data from 29,993 residents. CareStart™ Malaria PAN (pLDH) Rapid Diagnostic Tests (RDTs) were used for blood testing at the field level. Armpit digital thermometers were used to measure axillary temperature.ResultOverall malaria prevalence by RDTs was 1.17% (339/28973). The prevalence at District levels ranged from 0.0 to 4.7%. The proportion of symptomatic cases (axillary temperature > 37.5oc) in the survey was 9.2% (2760/29993). Among the 2510 symptomatic individuals tested with RDTs, only 3.35% (84/2510) were malaria positive. The 75.2% (255/339) of all malaria positives were asymptomatic. Of the total asymptomatic malaria cases, 10.2% (26/255) were under-five children and 89.8% (229/255) were above 5 years of age.ConclusionThe study shows a decrease in malaria prevalence compared to the reports of previous malaria indicator surveys in the country. The finding can be used as a baseline for measuring the achievement of ongoing malaria elimination efforts. Particularly, the high prevalence of asymptomatic individuals (0.88%) in these transmission settings indicates there may be sustaining hidden transmission. Therefore, active case detection with more sensitive diagnostic techniques is suggested to know more real magnitude of residual malaria in the elimination-targeted areas.

Cognitive bias modification for threat interpretations: using passive Mobile Sensing to detect intervention effects in daily life

ABSTRACT Background Social anxiety disorder is associated with distinct mobility patterns (e.g., increased time spent at home compared to non-anxious individuals), but we know little about if these patterns change following interventions. The ubiquity of GPS-enabled smartphones offers new opportunities to assess the benefits of mental health interventions beyond self-reported data. Objectives This pre-registered study (https://osf.io/em4vn/?view_only=b97da9ef22df41189f1302870fdc9dfe) assesses the impact of a brief, online cognitive training intervention for threat interpretations using passively-collected mobile sensing data. Design Ninety-eight participants scoring high on a measure of trait social anxiety completed five weeks of mobile phone monitoring, with 49 participants randomly assigned to receive the intervention halfway through the monitoring period. Results The brief intervention was not reliably associated with changes to participant mobility patterns. Conclusions Despite the lack of significant findings, this paper offers a framework within which to test future intervention effects using GPS data. We present a template for combining clinical theory and empirical GPS findings to derive testable hypotheses, outline data processing steps, and provide human-readable data processing scripts to guide future research. This manuscript illustrates how data processing steps common in engineering can be harnessed to extend our understanding of the impact of mental health interventions in daily life.

An IoT-Based Participatory Antitheft System for Public Safety Enhancement in Smart Cities

The risk of theft of goods is certainly an important source of negative influence in human psychology. This article focuses on the development of a scheme that, despite its low cost, acts as a smart antitheft system that achieves small property detection. Specifically, an Internet of Things (IoT)-based participatory platform was developed in order to allow asset-tracking tasks to be crowd-sourced to a community. Stolen objects are traced by using a prototype Bluetooth Low Energy (BLE)-based system, which sends signals, thus becoming a beacon. Once such an item (e.g., a bicycle) is stolen, the owner informs the authorities, which, in turn, broadcast an alert signal to activate the BLE sensor. To trace the asset with the antitheft tag, participants use their GPS-enabled smart phones to scan BLE tags through a specific smartphone client application and report the location of the asset to an operation center so that owners can locate their assets. A stolen item tracking simulator was created to support and optimize the aforementioned tracking process and to produce the best possible outcome, evaluating the impact of different parameters and strategies regarding the selection of how many and which users to activate when searching for a stolen item within a given area.

Efficient Processing of All Nearest Neighbor Queries in Dynamic Road Networks

The increasing trend of GPS-enabled smartphones has led to the tremendous usage of Location-Based Service applications. In the past few years, a significant amount of studies have been conducted to process All nearest neighbor (ANN) queries. An ANN query on a road network extracts and returns all the closest data objects for all query objects. Most of the existing studies on ANN queries are performed either in Euclidean space or static road networks. Moreover, combining the nearest neighbor query and join operation is an expensive procedure because it requires computing the distance between each pair of query objects and data objects. This study considers the problem of processing the ANN queries on a dynamic road network where the weight, i.e., the traveling distance and time varies due to various traffic conditions. To address this problem, a shared execution-based approach called standard clustered loop (SCL) is proposed that allows efficient processing of ANN queries on a dynamic road network. The key concept behind the shared execution technique is to exploit the coherence property of road networks by clustering objects that share common paths and processing the cluster as a single path. In an empirical study, the SCL method achieves significantly better performance than competitive methods and efficiently reduces the computational cost to process ANN queries in various problem settings.

The spatiotemporal movement of patients in and out of a psychiatric hospital: an observational GPS study

BackgroundMovement is a basic component of health. Little is known about the spatiotemporal movement of patients with mental disorders. The aim of this study was to determine how spatiotemporal movement of patients related to their symptoms and wellbeing.MethodA total of 106 patients (inpatients (n = 69) and outpatients (n = 37)) treated for a wide range of mental disorders (transdiagnostic sample) carried a GPS-enabled smartphone for one week at the beginning of treatment. Algorithms were applied to establish spatiotemporal clusters and subsequently related to known characteristics of these groups (i.e., at the hospital, at home). Symptomatology, Wellbeing, and Psychological flexibility were also assessed.ResultsSpatiotemporal patterns of inpatients and outpatients showed differences consistent with predictions (e.g., outpatients showed higher active areas). These patterns were largely unassociated with symptoms (except for agoraphobic symptoms). Greater movement and variety of movement were more predictive of wellbeing, however, in both inpatients and outpatients.ConclusionMeasuring spatiotemporal patterns is feasible, predictive of wellbeing, and may be a marker of patient functioning. Ethical issues of collecting GPS data are discussed.

Efficient Similarity-Aware Influence Maximization in Geo-Social Network

With the explosion of GPS-enabled smartphones and social media platforms, geo-social networks are increasing as tools for businesses to promote their products or services. Influence maximization, which aims to maximize the expected spread of influence in the networks, has drawn increasing attention. However, most recent work tries to study influence maximization by only considering geographic distance, while ignoring the influence of users’ spatio-temporal behavior on information propagation or location promotion, which can often lead to poor results. To relieve this problem, we propose a Similarity-aware Influence Maximization (SIM) model to efficiently maximize the influence spread by taking the effect of users’ spatio-temporal behavior into account, which is more reasonable to describe the real information propagation. We first calculate the similarity between users according to their historical check-ins, and then we propose a Propagation to Consumption (PTC) model to capture both online and offline behaviors of users. Finally, we propose two greedy algorithms to efficiently maximize the influence spread. The extensive experiments over real datasets demonstrate the efficiency and effectiveness of the proposed algorithms.

Classifying Transport Mode from Global Positioning Systems and Accelerometer Data: A Machine Learning Approach

Smartphones and wearable devices are driving a boom in mobility data. We use data-driven tools for classifying movement data into five different travel modes (bicycle, walk, bus, motor vehicle and SkyTrain) in Vancouver and St. John’s, Canada. Using data from a GPS-enabled smartphone app (Itinerum) combined with a wrist-worn accelerometer (GENEActiv) collected over a period of 67 days, we classified modes using Support Vector Machines from 4071 trips. Pre-labelled data were used to classify modes with 90.9% accuracy when data from both devices were combined in comparison to a single data source with accuracy ranging between 55.5% and 79.4%.

Navigating the Aegean Sea: smartphones, transnational activism and viapolitical in(ter)ventions in contested maritime borderzones

ABSTRACT Scholars concerned with the use of ICTs at the EU’s external borders have mainly focused on practices of control that draw on sophisticated surveillance technologies. In this paper I address migrants’ use of ICT itself, arguing that it has fundamentally transformed how undocumented border crossings are actually accomplished. In late 2015, when every day thousands of migrants crossed the Aegean Sea from Turkey to Greece, GPS-enabled smartphones played a pivotal role during their journeys, allowing migrants to navigate the sea and to get in touch with transnational support networks. Based on my own work for one of these networks, the WatchTheMed Alarm Phone, I demonstrate how migrants made emergency calls or alerted supporters via WhatsApp, who in turn mapped and tracked their positions and movements at sea and intervened in situations of distress in real-time. The paper contributes to debates on ‘data politics’ (Bigo, Isin, and Ruppert [2019]. Data Politics. Worlds, Subjects, Rights. London: Routledge) by drawing on the concepts of viapolitics and tempo-politics. While the former captures how journeys, vehicles and routes of migration become means and sites of contestation, the latter addresses situations in which the time-spaces of migration become matters of concern in border struggles.

Crowdsourced data for bicycling research and practice

ABSTRACT Cities are promoting bicycling for transportation as an antidote to increased traffic congestion, obesity and related health issues, and air pollution. However, both research and practice have been stalled by lack of data on bicycling volumes, safety, infrastructure, and public attitudes. New technologies such as GPS-enabled smartphones, crowdsourcing tools, and social media are changing the potential sources for bicycling data. However, many of the developments are coming from data science and it can be difficult evaluate the strengths and limitations of crowdsourced data. In this narrative review we provide an overview and critique of crowdsourced data that are being used to fill gaps and advance bicycling behaviour and safety knowledge. We assess crowdsourced data used to map ridership (fitness, bike share, and GPS/accelerometer data), assess safety (web-map tools), map infrastructure (OpenStreetMap), and track attitudes (social media). For each category of data, we discuss the challenges and opportunities they offer for researchers and practitioners. Fitness app data can be used to model spatial variation in bicycling ridership volumes, and GPS/accelerometer data offer new potential to characterise route choice and origin-destination of bicycling trips; however, working with these data requires a high level of training in data science. New sources of safety and near miss data can be used to address underreporting and increase predictive capacity but require grassroots promotion and are often best used when combined with official reports. Crowdsourced bicycling infrastructure data can be timely and facilitate comparisons across multiple cities; however, such data must be assessed for consistency in route type labels. Using social media, it is possible to track reactions to bicycle policy and infrastructure changes, yet linking attitudes expressed on social media platforms with broader populations is a challenge. New data present opportunities for improving our understanding of bicycling and supporting decision making towards transportation options that are healthy and safe for all. However, there are challenges, such as who has data access and how data crowdsourced tools are funded, protection of individual privacy, representativeness of data and impact of biased data on equity in decision making, and stakeholder capacity to use data given the requirement for advanced data science skills. If cities are to benefit from these new data, methodological developments and tools and training for end-users will need to track with the momentum of crowdsourced data.

Validating a GPS-based approach to detect health facility visits against maternal response to prompted recall survey.

IntroductionCommon approaches to measure health behaviors rely on participant responses and are subject to bias. Technology-based alternatives, particularly using GPS, address these biases while opening new channels for research. This study describes the development and implementation of a GPS-based approach to detect health facility visits in rural Pune district, India.MethodsParticipants were mothers of under-five year old children within the Vadu Demographic Surveillance area. Participants received GPS-enabled smartphones pre-installed with a location-aware application to continuously record and transmit participant location data to a central server. Data were analyzed to identify health facility visits according to a parameter-based approach, optimal thresholds of which were calibrated through a simulation exercise. Lists of GPS-detected health facility visits were generated at each of six follow-up home visits and reviewed with participants through prompted recall survey, confirming visits which were correctly identified. Detected visits were analyzed using logistic regression to explore factors associated with the identification of false positive GPS-detected visits.ResultsWe enrolled 200 participants and completed 1098 follow-up visits over the six-month study period. Prompted recall surveys were completed for 694 follow-up visits with one or more GPS-detected health facility visits. While the approach performed well during calibration (positive predictive value (PPV) 78%), performance was poor when applied to participant data. Only 440 of 22 251 detected visits were confirmed (PPV 2%). False positives increased as participants spent more time in areas of high health facility density (odds ratio (OR) = 2.29, 95% confidence interval (CI) = 1.62-3.25). Visits detected at facilities other than hospitals and clinics were also more likely to be false positives (OR = 2.78, 95% CI = 1.65-4.67) as were visits detected to facilities nearby participant homes, with the likelihood decreasing as distance increased (OR = 0.89, 95% CI = 0.82-0.97). Visit duration was not associated with confirmation status.ConclusionsThe optimal parameter combination for health facility visits simulated by field workers substantially overestimated health visits from participant GPS data. This study provides useful insights into the challenges in detecting health facility visits where providers are numerous, highly clustered within urban centers and located near residential areas of the population which they serve.

GEOLOCATION: LOCATING TRUST IN DIGITAL PLATFORMS AND ECONOMIES

Digital location—or geolocation—is a fixture of digital platforms and economies, figuring as an organizational logic for content and user experience (e.g., map-based interfaces), native technical affordance (e.g., locational functionalities of GPS-enabled smartphones), and core enabling agent behind the rise of ‘disruptive’ platform enterprises (e.g., Uber, Deliveroo, and Waze all rely on geolocation for service delivery). Despite its inextricability from contemporary media, data productions, and digital practices, geolocation’s role in fostering mis/trust in digital systems has to date been unaddressed. The papers in this panel identify and theorize the ways in which geolocation functions as simultaneously a key ‘technology of trust’ (sociotechnical agent through which mis/trust is bred and/or secured in digital ecosystems), and a social relation of trustworthiness in digital platforms and economies, exploring the role geolocation plays form the perspectives of both securing trust and breeding mistrust in digital systems.

Crime concentration in Perth CBD: a comparison of officer predicted hot spots, data derived hot spots and officer GPS patrol data

ABSTRACTIn an applied criminology context, recent meta-analyses and randomized control trials have demonstrated the benefits of targeting police patrols at hot spots or concentrations of street level crime and disorder. This study asked a group of 79 police officers from Perth to make a prediction, based on their experience, of where hot spots of crime would occur in the near future. Officer-defined hot spots were then compared with hot spots derived from police crime data over the preceding 24 month period. Finally, officer patrol time was tracked using a GPS-enabled smart phone and overlayed against both types of hot spot. This analysis indicates that police officers should be supported with hot spot mapping tools which identify data derived micro-places with persistent issues. Analysis also reveals officers patrol both their own and data-derived hot spots regularly; however, they only stay for a matter of a few minutes. These short stays are contrary to best evidence, which dictates officer patrols in hot spots should last for approximately 15 minutes in order to create both initial and residual deterrence.

Are People from Households with Children More Likely to Travel by Car? An Empirical Investigation of Individual Travel Mode Choices in Shanghai, China

China is expected to have more children now that its family planning policy has been relaxed, and the influence of children on transportation and sustainability should not be neglected. This study uses econometric methods to explore the impact that the presence of children has on household car ownership, car-travel behavior of family members, and variability in their car-use frequency across weekdays and weekends. Models are estimated using multi-day travel patterns imputed from GPS-enabled smartphone data collected in Shanghai, China. Results indicate that: (1) households with children have more private cars than those without children, and the presence of preschoolers and pupils both increase families’ demand for car ownership; (2) travel behavior of people from households with children is influenced subtly by the children’s presence, which leads them to prefer to travel by car, although the presence of retired or unemployed household members can weaken that influence; and (3) car-travel frequency of individuals is significantly different between weekdays and weekends, with the presence of pupils in the household diminishing that variability and the presence of preschoolers enlarging it. Policymakers and transportation planners should be concerned about these issues and take appropriate measures.

Concordance between GPS-based smartphone app for continuous location tracking and mother’s recall of care-seeking for child illness in India

BackgroundTraditionally, health care-seeking behaviour for child illness is assessed through population-based national demographic and health surveys. GPS-based technologies are increasingly used in human behavioural research including tracking human mobility and spatial behaviour. This paper assesses how well a care-seeking event to a health care facility for child illness, as recalled by the mother in a survey setting using questions sourced from Demographic and Health Surveys, concurs with one that is identified by TrackCare, a GPS-based location-aware smartphone application.MethodsMothers residing in the Vadu HDSS area in Pune district, India having at least one young child were randomly assigned to receive a GPS-enabled smartphone with a pre-installed TrackCare app configured to record the device location data at one-minute intervals over a 6-month period. Spatio-temporal parameters were derived from the location data and used to detect a care-seeking event to any of the health care facilities in the area. Mothers were asked to recall a child illness and if, where and when care was sought, using a questionnaire during monthly visits over a 6-month period. Concordance between the mother’s recall and the TrackCare app to identify a care-seeking event was estimated according to percent positive agreement.ResultsMean concordance for a care-seeking event between the two methods (mother’s recall and TrackCare location data) ranged up to 45%, was significantly higher (P-value <0.001) for care-seeking at a hospital as compared to a clinic and for a health care facility in the private sector compared to that in the public sector. Overall, the proportion of disagreement for a care-seeking event not detected by TrackCare but reported by mother ranged up to 77% and was significantly higher (P-value <0.001) compared to those not reported by mother but detected by TrackCare.ConclusionsGiven the uncertainty and limitations in use of continuous location tracking data in a field setting and the complexity of classifying human activity patterns, additional research is needed before continuous location tracking can serve as a gold standard substitute for other methods to determine health care-seeking behaviour. Future performance may be improved by incorporating other smartphone-based sensors, such as Wi-Fi and Bluetooth, to obtain more precise location estimates in areas where GPS signal is weakest.