Smartphone GPS Research Articles

Why do bicyclists take detours? A multilevel regression model using smartphone GPS data

Bicyclists often deviate from the shortest possible routes and take detours in search of more pleasant riding conditions. The extent of detours and the factors affecting bicyclists to ride excess distances have not yet been fully explored. This study aims to measure and analyze the detour extent of utilitarian bicycle trips and their relationships with the route-level environmental components using data collected from individual bicyclists' smartphone GPS in Columbus, Ohio. Comparing the chosen routes with their shortest counterparts, we calculate two detour indices (a distanced-based index and an area-based index) and provide a comparative analysis of built environment attributes for low, moderate, and high levels of detours. We then estimate multilevel mixed-effect generalized linear regression models to identify the contribution of built-environment characteristics to such detours while accounting for individual heterogeneity. We find that most bicycle trips (91.1%) include a detour and are 13.5% longer on average than their shortest alternatives with large variations. Detour degrees are higher for long-distance trips and for peak-period trips. We find that bicyclists choose routes with smaller shares of commercial and single-family land-uses and low levels of land-use diversity. Longer detours are positively associated with street greenery. We find that sparse bicycle facilities and high-speed limits are strong contributors to bicyclists' detour decisions, while multilevel mixed-effect linear regression models further present significant heterogeneity in bicyclists' responses to some environmental attributes. The area-based detour index performs better in explaining the relationships between land-use features and detour degrees.

Instantaneous vehicle fuel consumption estimation using smartphones and recurrent neural networks

The high level of air pollution in urban areas, caused in no small extent by road transport, requires the implementation of continuous and accurate monitoring techniques if emissions are to be minimized. The primary motivation for this paper is to enable fine spatiotemporal monitoring based on crowd sensing, whereby the instantaneous fuel consumption of a vehicle is estimated using smartphone measurements. To this end, a surrogate method based on indirect monitoring using Recurrent Neural Networks (RNNs) that process a smartphone's GPS position, speed, altitude, acceleration and number of visible satellites is proposed. Extensive field trials were conducted to gather smartphone and fuel consumption data at a wide range of driving conditions. Two different RNN types were explored, and a parametric analysis was performed to define a suitable architecture. Various training methods for tuning the RNN were evaluated based on performance and computational burden. The resulting estimator was compared with others found in the literature, and the results confirm its superior performance. The potential impact of the proposed method is noteworthy as it can facilitate accurate monitoring of in-use vehicle fuel consumption and emissions at large scales by exploiting available smartphone measurements.

Estimating a Toronto pedestrian route choice model using smartphone GPS data

This study examines the feasibility of using revealed preference GPS data collected through a smartphone-based travel survey and discrete choice modeling techniques to determine pedestrians’ preferences towards street infrastructure, built environment, and land use. Smartphone GPS points were collected after 50 m of travel and had a horizontal spatial accuracy of 30 m or less. A path size logit model with stochastic route choice generation choice set was used for this model. The results of the model showed that distance, the number of turns, the number of signalized intersections, and distance along links with sidewalks on both sides of the street were significant variables in the route choice model. Turns are found to be equivalent to an additional 32 m, signalized intersections are equivalent to a reduction of 34 m, and travel along streets with sidewalks on both sides of the road is evaluated as 33% shorter than streets with other sidewalk conditions. While the dataset used for this study was relatively small (776 trip observations), these results are consistent with other pedestrian route choice studies which support the viability of using smartphone GPS data for future pedestrian route choice studies.

Behavioral responses to pre-planned road capacity reduction based on smartphone GPS trajectory data: A functional data analysis approach

Pre-planned events such as constructions or special events lead to road capacity reductions and create bottlenecks in the traffic network. The traffic impact of such events goes beyond local areas, as informed drivers may detour to alternative corridors and consequently the traffic congestion may divert or propagate to other corridors. Due to the lack of real observation data, traditional traffic impact analyses are typically based on simulation models, fixed-location sensor data or survey questionnaires. In this research, we use high-resolution vehicle trajectory data collected via a smartphone app, which is capable of keeping track of individual driver’s behavior before and after road capacity reduction, to investigate travelers’ behavioral responses to pre-planned events and the contribution factors. For this purpose, a functional data analysis (FDA) approach-based clustering method is firstly proposed to cluster trajectory data and identify detour patterns, and two logistic and a least absolute shrinkage and selection operator (LASSO) regression models are used to explain drivers’ detour behavior choice for each pattern with spatial and temporal features of interest. A case study based on a lane closure event on MoPac expressway in Austin, TX is used as an example in this research. The case study demonstrates that: (1) the freeway capacity reduction triggered heterologous behavior responses, (2) driver detour behavior exhibits three major patterns and (3) each detour pattern highly depends on spatial features such as trip length, distance to freeway entrance and distance to other alternative freeways, in addition to the temporal features when the trip happens.

Users' location analysis based on Chinese mobile social media

SummaryAfter the rapid development for more than 20 years, Internet has gradually become the main carrier of people's information and behaviors in people's daily life. In addition, the innovation and popularization of smartphone GPS makes user location information much more available and accurate, helping it to create remarkable values by which people are attracted to focus on social media–related data mining and applications. However, because of the sparsity of social media geographical information, direct inferences of locations have plenty of difficulties. Under the background of big data, this research has revised the UGC‐LI model in the preprocess of texts and the creation of the local dictionaries in which we take existed local dictionaries from the Internet into consideration, with the purpose of the inferences for users' and texts' locations. At the time of writing, through the crawler, we acquire users' personal information, the blog content, and customer relationships' (follows, fans) information more than 410 331 pieces from Sina Weibo. The experimental results show that the recall rate of the user location inference is 86.0%, whereas the precise rate is 77.4%, and the accuracy of text posted location inference is 66.8%. Compared with some other related algorithms, this revised model has comparatively better results in location inference for users and text publication.

Measuring the use of green space with urban resource selection functions: An application using smartphone GPS locations

Data describing how individuals use their urban environment is a valuable source of information in urban planning. In many cases, data used for these purposes have low spatial and temporal resolution, or sample size. Equally, comprehensive analytical approaches suitable for these data may be lacking. We present a statistical method borrowed from wildlife ecology and management called a resource selection function (RSF). We apply it to answer questions relating to the selection of urban green space by university students, using a dataset consisting of smartphone GPS location data volunteered by participants. We ask questions relating to urban greenspace selection by comparing used locations to a set of random locations at multiple spatial extents. We found that participants altered their selection of areas according to the surrounding recreational trail density and whether those areas were classified as green space. These relationships were also influenced by season. Our study also demonstrates how the design of an urban RSF can offer different insights by varying the extent of the domain: (1) to an individual’s core area; or (2) by excluding from the domain areas that are physically unavailable. We emphasize the importance of matching availability to the research question and conclude by reviewing the opportunities presented by using RSFs combined with GPS location data in an urban context. We argue that RSFs have utility beyond wildlife ecology and management, and, given the increasing availability of smartphone GPS data, can successfully be applied to determine the use and selection of spaces by urban residents.

AN IOT BASED APPROACH TO VEHICLE ACCIDENT DETECTION, REPORTING AND NAVIGATION

Every day around the world, a large percentage of people die from traffic accident injuries. An effective approach for reducing traffic fatalities is: first building automatic traffic accident detection system, second, reducing the time between when an accident occurs and when first emergency responders are dispatched to the scene of the accident. Recent approaches are using built-in vehicle automatic accident detection and notification system. While these approaches work fine, they are expensive, maintenance complex task, and are not available in all cars. On the other hand, the ability to detect traffic accidents using smartphones has only recently become possible because of the advances in the processing power and sensors deployed on smartphones. Most of the smartphone based accident detection systems rely on the high speed of the vehicle (extracted from the smartphone GPS receiver) and the G-Force value (extracted from smartphone accelerometer sensor) to detect an accident. As many references assure that 90% of road-traffic accidents occur at low speed of the vehicle. Hence, in addition to the high speed accident detection, this paper concentrated on low speed car accident detection. The main obstacle that encounters the low speed accident is how to differentiate whether the user is inside the vehicle or outside the vehicle, walking or slowly running. The effect of this obstacle is minimized, in this work, by a proposed mechanism that distinguishes between the speed variation of low speed vehicle and walking or slowly running person. The proposed system consists of two phases; the detection phase which is used to detect car accident in low and high speeds. The notification phase, and immediately after an accident is indicated, is used to send detailed information such as images, video, accident location, etc. to the emergency responder for fast recovery. The system was practically tested in real simulated environment and achieved quite very good performance results.

S121. Measures of Behavior and Life Dynamics From Smartphone GPS Data

S121. Measures of Behavior and Life Dynamics From Smartphone GPS Data

A geographically explicit ecological momentary assessment (GEMA) mixed method for understanding substance use

Tobacco use is increasingly concentrated within marginalized groups, including LGBTQ+ young adults. Developing tailored interventions to reduce tobacco-related health disparities requires understanding the mechanisms linking individual and contextual factors associated with tobacco use to behavior. This paper presents an in-depth exploration of three cases from a novel mixed method study designed to identify the situational factors and place-based practices of substance use among high-risk individuals. We combined geographically explicit ecological momentary assessment (GEMA) with an adapted travel diary-interview method. Participants (young adult bisexual smokers, ages 18–26) reported on non-smoking and smoking situations for 30 days with a smartphone app. GEMA surveys captured internal and external situational factors (e.g., craving intensity, location type, seeing others smoking). Continuous locational data was collected via smartphone GPS. Subsequently, participants completed in-depth interviews reviewing maps of their own GEMA data. GEMA data and transcripts were analyzed separately and integrated at the case level in a matrix. Using GEMA maps to guide the interview grounded discussion in participants' everyday smoking situations and routines. Interviews clarified participant interpretation of GEMA measures and revealed experiences and meanings of smoking locations and practices. The GEMA method identified the most frequent smoking locations/times for each participant (e.g., afternoons at university). Interviews provided description of associated situational factors and perceptions of smoking contexts (e.g., peer rejection of bisexual identity) and the roles of smoking therein (e.g., physically escape uncomfortable environments). In conclusion, this mixed method contributes to advancing qualitative GIS and other hypothesis-generating approaches working to reveal the richness of individuals’ experiences of the everyday contexts of health behavior, while also providing reliable measures of situational predictors of behaviors of interest, such as substance use. Limitations of and future directions for the method are discussed.

Smartphone app versus GPS Logger: A comparative study

Abstract This paper describes a study in which a smartphone app and dedicated wearable GPS devices were used in the same study, with processing done with the same software, providing an opportunity to determine the strengths and weaknesses of each. The study found that respondents were more willing to accept the dedicated GPS device, were more likely to comply with the requested task, and provided an overall higher response rate with the GPS logger than with the smartphone app. After processing the data and matching the GPS data to the diary data, both technologies produced similar results in terms of proportion of trips that show a good match to diary data.

Investigations on Driver Unique Identification from Smartphone’s GPS Data Alone

Driver identification is an emerging area of interest in vehicle telematics, automobile control, and insurance. Recent body of works indicates that it may be possible to uniquely identify a driver using multiple dedicated sensors. In this paper, we present an approach for driver identification using smartphone GPS data alone. For our experiments, we collected data from 38 drivers for two months. We quantified the driver’s natural style by extracting a set of 137 statistical features from data generated for each completed trip. The analysis shows that, for the “driver identification” problem, an average accuracy of 82.3% is achieved for driver groups of 4-5 drivers. This is comparable to the state of the arts where mostly a multisensor approach has been taken. Further, it is shown that certain behavioral attributes like high driving skill impact identification accuracy. We observe that Random Forest classifier offers the best results. These results have great implications for various stakeholders since the proposed method can identify a driver based on his/her naturalistic driving style which is quantified in terms of statistical parameters extracted from only GPS data.

Implementing a Smartphone Application for Assessing the Raveling Performance of Asphalt Pavements

It is essential to evaluate the performance of pavements during their service life. Raveling is one of the important pavement performance defects, especially for Open Graded Friction Course mixes. The FC-5 is a type of friction course that has been used commonly in southern Florida. Florid Department of Transportation (FDOT) uses conventional qualitative visual inspection to assess pavement raveling performance. This study developed a data collection tool that uses a smartphone application and introduced a software to measure the raveling area and determine raveling location in video images, by implementing the smartphone GPS capability. This data collection tool enables users to identify the location and extension of raveling that can link the placement data with raveling performance. A project was surveyed to conduct a statistical analysis to investigate the effects of mix design, construction, and environmental factors on raveling at the lot level. Data analysis results show that raveling may affected by several parameters including ambient temperature, mix temperature, asphalt cement content and mix gradation. In light of this study, recommendations were made to enhance the longevity of the FC-5 mixtures.

Investigation of pavement raveling performance using smartphone

Raveling is one of the critical modes of failure in open graded asphalt mixtures. The Florida Department of Transportation (FDOT) Districts 4 and 6, located in southeastern Florida, have experienced a large amount of premature raveling with Open Graded Friction Course mixes (OGFC) compared to the other districts in Florida. To investigate the reason of raveling occurrence, the research team devised a data collection tool for smartphones and developed software to measure the raveling area and its location and severity in video images using smartphone GPS capability. The data used in this study were extracted from different FDOT database systems, such as the Laboratory Information Management System (LIMS) and the Electronic Data Management System (EDMS), as well as from the National Oceanic and Atmospheric Administration (NOAA).Ten projects were surveyed by the research team, and numerical raveling statistics were developed and compared with qualitative raveling ratings provided by FDOT. Good correlation was found between the two methods. The comparison was used to establish thresholds of good performance. Such thresholds can be used to develop performance specifications or warranty benchmarks.The relative effects of mix design, construction, and environmental factors were also studied. A project level of analysis was conducted. Several hypotheses were evaluated to determine the cause of premature raveling. Data analysis results indicate significant correlations between raveling and ambient temperature, mix temperature, mix spread rate, and gradation. In light of this study, recommendations were made to enhance the longevity of the OGFC mixtures.

Experiences with Citizen-Sourced VGI in Challenging Circumstances

The article explores the process of Volunteered Geographic Information (VGI) collection by assessing the relative usability and accuracy of a range of different methods (smartphone GPS, tablet, and analogue maps) for data collection among different demographic and educational groups, and in different geographical contexts within a study area. Assessments are made of positional accuracy, completeness, and the experiences of citizen data collectors with reference to the official cadastral data and the land administration system. Ownership data were validated by crowd agreement. The outcomes of this research show the varying effects of volunteers, data collection method, geographical area, and application field, on geospatial data handling in the VGI arena. An overview of the many issues affecting the development and implementation of VGI projects is included. These are focused on the specific example of VGI data handling presented here: a case study area where instability and lack of resources are found alongside strong communities and a pressing need for more robust and effective official structures. The chosen example relates to the administration of land in an area of Iraq.

More than A to B: Understanding and managing visitor spatial behaviour in urban forests using public participation GIS

Planning and management needs up-to-date, easily-obtainable and accurate information on the spatial and social aspects of visitor behaviour in order to balance human use and impacts, and protection of natural resources in public parks. We used a web-based public participation GIS (PPGIS) approach to gather citizen data on visitor behaviour in Helsinki's Central Park in order to aid collaborative spatial decision-making. The study combined smartphone GPS tracking, route drawing and a questionnaire to examine differences between user groups in their use of formal trails, off-trail behaviour and the motivations that affect it. In our sample (n = 233), different activity types were associated with distinctive spatial patterns and potential extent of impacts. The density mapping and statistical analyses indicated three types of behaviour: predominantly on or close to formal trails (runners and cyclists), spatially concentrated off-trail behaviour confined to a few informal paths (mountain bikers), and dispersed off-trail use pattern (walkers and dog walkers). Across all user groups, off-trail behaviour was mainly motivated by positive attraction towards the environment such as scenic view, exploration, and viewing flora and fauna. Study findings lead to several management recommendations that were presented to city officials. These include reducing dispersion and the spatial extent of trampling impacts by encouraging use of a limited number of well-established informal paths away from sensitive vegetation and protected habitats.

Exploring Landscape Engagement through a Participatory Touch Table Approach

Governments and national bodies are increasingly concerned with promoting outdoor activity as a means to benefit general health and wellbeing. Techniques to encourage and popularize engagement with the outdoor environment should therefore be welcome. This paper explores the use of a touch table as a method to facilitate discussions about people’s engagement with rural and urban landscapes through recreational walking. We describe a study in north-east Scotland involving 22 participants who undertook walks of their choice using GPS smartphone applications to track their routes. Tracked routes were uploaded to a touch table and small group sessions explored spatial behavior in, and perceptions and knowledge of, local landscapes. Individual interviews 4–6 weeks later elicited reflections on the touch table session and personal engagement with the landscape. Two types of findings are reported: (i) observations and recommendations relating to the use of a touch table in combination with GPS applications; and (ii) knowledge exchange and insights afforded by group discussion and individual reflection. We conclude that our approach is a promising participatory method through which to investigate spatial behavior and promote recreational opportunities in the landscape.

Smartphone‐based crowdsourcing for position estimation of public transport vehicles

In this research, a real-time positioning method, which utilises crowdsourced positioning data obtained from smartphone GPS is developed. Such vehicle location information obtained from crowdsourcing and smartphones in public transport could replace traditional automatic vehicle location systems. However, the location information from smartphone GPS is more erroneous. The proposed methodology serves as an alternative to existing positioning methods to improve the vehicle positioning accuracy. The developed enhanced particle filter algorithm takes smartphone GPS positioning data [from multiple passengers in a single transit vehicle (e.g. bus)] as input data. This `crowdsourced' data can then be utilised to calculate the vehicles' positioning information with better accuracy using the developed enhanced particle filter algorithm. The developed algorithm was tested using data collected on 14 different bus routes in urban and suburban areas of Mumbai, India, and it was identified that the algorithm is effective in reducing the average error up to 21.3% from a regular smartphone GPS and 10% from extended Kalman filter algorithm and was able to curtail positioning error within 8.672 m (average over 14 routes).

Speed, travel time and delay for intersections and road segments in the Montreal network using cyclist Smartphone GPS data

Very little is known about cyclist speeds and delays at the disaggregate level of each road segment and intersection in an entire city network. Speeds and delays serve as vital information for planning, navigation and routing purposes including how they differ for different times of the day and across road and bicycle facility types, after controlling for other factors. In this work, we explore the use of recent GPS cyclist trip data, from the Mon RésoVélo Smartphone application, to identify different performance measures such as travel time, speed and delay at the level of the entire network of roads and intersections on the island of Montreal. Also, a linear regression model is formulated to identify the geometric design and built environment characteristics affecting cyclist speeds on road segments. Among other results, on average, segment speeds are greater along arterials than on local streets and greater along segments with bicycle infrastructure than those without. Incorporating different measures of cyclist personality in the models revealed that the following characteristics all affect cyclist speeds along segments, each cyclist’s average speed on uphill, downhill and level segments as well as geometric design and built environment characteristics. The model results also identify that the factors that increase cyclist speeds along segments include, segments which have cyclists biking for work or school related purposes, segments used during morning peak and segments which do not have signalized intersections at either end.

Measuring and visualizing space–time congestion patterns in an urban road network using large-scale smartphone-collected GPS data

Congestion is a dynamic phenomenon with elements of space and time, making it a promising application of probe vehicles. The purpose of this paper is to measure and visualize the magnitude and variability of congestion on the network scale using smartphone GPS travel data. The sample of data collected in Quebec City contained over 4000 drivers and 21,000 trips. The congestion index (CI) was calculated at the link level for each hour of the peak period and congestion was visualized at aggregate and disaggregate levels. Results showed that each peak period can be viewed as having an onset period and dissipation period lasting one hour. Congestion in the evening is greater and more dispersed than in the morning. Motorways, arterials, and collectors contribute most to peak period congestion, while residential links contribute little. Further analysis of the CI data is required for practical implementation in network planning or congestion remediation.

Methods for Real-Time Prediction of the Mode of Travel Using Smartphone-Based GPS and Accelerometer Data.

We propose and compare combinations of several methods for classifying transportation activity data from smartphone GPS and accelerometer sensors. We have two main objectives. First, we aim to classify our data as accurately as possible. Second, we aim to reduce the dimensionality of the data as much as possible in order to reduce the computational burden of the classification. We combine dimension reduction and classification algorithms and compare them with a metric that balances accuracy and dimensionality. In doing so, we develop a classification algorithm that accurately classifies five different modes of transportation (i.e., walking, biking, car, bus and rail) while being computationally simple enough to run on a typical smartphone. Further, we use data that required no behavioral changes from the smartphone users to collect. Our best classification model uses the random forest algorithm to achieve 96.8% accuracy.