Raw Global Positioning System Research Articles

Biosensor-Driven IoT Wearables for Accurate Body Motion Tracking and Localization.

The domain of human locomotion identification through smartphone sensors is witnessing rapid expansion within the realm of research. This domain boasts significant potential across various sectors, including healthcare, sports, security systems, home automation, and real-time location tracking. Despite the considerable volume of existing research, the greater portion of it has primarily concentrated on locomotion activities. Comparatively less emphasis has been placed on the recognition of human localization patterns. In the current study, we introduce a system by facilitating the recognition of both human physical and location-based patterns. This system utilizes the capabilities of smartphone sensors to achieve its objectives. Our goal is to develop a system that can accurately identify different human physical and localization activities, such as walking, running, jumping, indoor, and outdoor activities. To achieve this, we perform preprocessing on the raw sensor data using a Butterworth filter for inertial sensors and a Median Filter for Global Positioning System (GPS) and then applying Hamming windowing techniques to segment the filtered data. We then extract features from the raw inertial and GPS sensors and select relevant features using the variance threshold feature selection method. The extrasensory dataset exhibits an imbalanced number of samples for certain activities. To address this issue, the permutation-based data augmentation technique is employed. The augmented features are optimized using the Yeo-Johnson power transformation algorithm before being sent to a multi-layer perceptron for classification. We evaluate our system using the K-fold cross-validation technique. The datasets used in this study are the Extrasensory and Sussex Huawei Locomotion (SHL), which contain both physical and localization activities. Our experiments demonstrate that our system achieves high accuracy with 96% and 94% over Extrasensory and SHL in physical activities and 94% and 91% over Extrasensory and SHL in the location-based activities, outperforming previous state-of-the-art methods in recognizing both types of activities.

Real-Time Monitoring of Grazing Cattle Using LORA-WAN Sensors to Improve Precision in Detecting Animal Welfare Implications via Daily Distance Walked Metrics.

Animal welfare monitoring relies on sensor accuracy for detecting changes in animal well-being. We compared the distance calculations based on global positioning system (GPS) data alone or combined with motion data from triaxial accelerometers. The assessment involved static trackers placed outdoors or indoors vs. trackers mounted on cows grazing on pasture. Trackers communicated motion data at 1 min intervals and GPS positions at 15 min intervals for seven days. Daily distance walked was determined using the following: (1) raw GPS data (RawDist), (2) data with erroneous GPS locations removed (CorrectedDist), or (3) data with erroneous GPS locations removed, combined with the exclusion of GPS data associated with no motion reading (CorrectedDist_Act). Distances were analyzed via one-way ANOVA to compare the effects of tracker placement (Indoor, Outdoor, or Animal). No difference was detected between the tracker placement for RawDist. The computation of CorrectedDist differed between the tracker placements. However, due to the random error of GPS measurements, CorrectedDist for Indoor static trackers differed from zero. The walking distance calculated by CorrectedDist_Act differed between the tracker placements, with distances for static trackers not differing from zero. The fusion of GPS and accelerometer data better detected animal welfare implications related to immobility in grazing cattle.

MULTI-BRANCH DEEP LEARNING BASED TRANSPORT MODE DETECTION USING WEAKLY SUPERVISED LABELS

Abstract. Mobility data, based on global positioning system (GPS) tracking, have been widely used in many areas. These include, but not limited to: user direction guidance, analyzing travel patterns, and evaluating travel impacts. Transport Mode Detection (TMD) is an essential factor in understanding mobility within the transport system. A TMD model assigns a GPS point or a GPS trajectory to a particular transport mode based on the user’s current activity. However, the complexity of the prediction procedure increases with the number of modes that need to be predicted given the increasing overlaps in feature values between multiple transportation modes. Hence, this study proposes a two-branch deep learning-based TMD model that predicts multi-class transport modes to improve prediction accuracy. In addition, it proposed a weakly supervised labelling model using snorkel to improve the volume of labelled data and resulting TMD model prediction accuracy. We considered publicly available road networks, railway networks, bus routes, etc., for creating road, bus, train labels by overlaying GPS points on these transportation networks. We introduced a boolean (true/false) based soft-labelling function, where the same GPS point overlaid on road or railway network. The raw GPS data were used to generate point-level features such as speed, speed difference, acceleration, acceleration difference, initial bearing and bearing difference, all used as derived features for the TMD model. To construct the model we opted to use two branches where raw GPS latitude and longitude values were used in one and the derived mobility features are used in the other.

Identifying Origin-Destination Trips from GPS Data – Application in Travel Time Reliability of Dedicated Trucks

The advancement of data collection technologies has brought an upsurge in GPS applications. For example, travel behaviour research has benefited from the integration of multiple sources of Global Positioning System (GPS) data. However, the effective use of such data is still impeded by the challenge in data processing. For instance, GPS data, despite providing detailed spatial movement information, do not label the starting and finishing points of a trip, especially for commercial trucks. Hence, there is a critical need to develop a trip identification method to effectively use the trajectory data provided by GPS without additional information. This paper focused on identifying trips from the raw GPS data. Specifically, a systematic method is proposed to extract trips on the basis of origin-destination (OD) pairs by using a 5-step procedure. An application was provided on estimating the performance of travel time reliability using three metrics based on the OD trips for each dedicated truck. The application showed that, in general, trucks on long-distance routes have less reliable travel times compared to trucks on short-distance routes. This paper provides an example of using GPS data, without further information, to study travel time for freight performance and similar needs of punctuality in logistics.

Effect of Erroneous Observations in GPS-based LEO Satellite Orbit Determination

Performance of an EKF-based Orbit Determination (OD) algorithm using Global Positioning System (GPS) measurements is examined under erroneous observation conditions. A generalized formulation of a dynamic orbit model is designed to predict the satellite states in an Earth-Centered Earth-Fixed (ECEF) frame. A suitable orbit interpolation method is then chosen for interpolating the GPS satellite position at the measurement time tag before finding the geometric range between the GPS and the LEO satellites. Thereafter, the commonly used Extended Kalman Filter (EKF) algorithm is implemented for the nonlinear OD problem. The proposed algorithm is tested for the precision in OD of two LEO satellites, namely GRACE and Megha-Tropiques based on the available raw GPS measurements in the Receiver Independent Exchange (RINEX) observation files. For the GRACE satellite, the efficacy of the present OD algorithm is validated by comparing the estimated and publicly available precise orbit information. The Megha-Tropiques satellite, however, does not have precise orbit information. Furthermore, it is observed that the RINEX file has several erroneous observations as detected by the Fault Detection and Exclusion (FDE) algorithm in-built in the OD algorithm. A comparison of the estimated satellite position with that obtained from the standard software GNSS-Lab Tool (gLAB) shows that the accuracy of the position estimates varies proportionally with the number of erroneous observations of the Megha-Tropiques satellite.

GPS2space: An Open-source Python Library for Spatial Measure Extraction from GPS Data.

Global Positioning System (GPS) data have become one of the routine data streams collected by wearable devices, cell phones, and social media platforms in this digital age. Such data provide research opportunities in that they may provide contextual information to elucidate where, when, and why individuals engage in and sustain particular behavioral patterns. However, raw GPS data consisting of densely sampled time series of latitude and longitude coordinate pairs do not readily convey meaningful information concerning intra-individual dynamics and inter-individual differences; substantial data processing is required. Raw GPS data need to be integrated into a Geographic Information System (GIS) and analyzed, from which the mobility and activity patterns of individuals can be derived, a process that is unfamiliar to many behavioral scientists. In this tutorial article, we introduced GPS2space, a free and open-source Python library that we developed to facilitate the processing of GPS data, integration with GIS to derive distances from landmarks of interest, as well as extraction of two spatial features: activity space of individuals and shared space between individuals, such as members of the same family. We demonstrated functions available in the library using data from the Colorado Online Twin Study to explore seasonal and age-related changes in individuals' activity space and twin siblings' shared space, as well as gender, zygosity and baseline age-related differences in their initial levels and/or changes over time. We concluded with discussions of other potential usages, caveats, and future developments of GPS2space.

Review and evaluation of methods in transport mode detection based on GPS tracking data

Mobility data, based on global positioning system (GPS) tracking, have been widely used in many areas, such as analyzing travel patterns, investigating transport safety and efficiency, and evaluating travel impacts. Transport modes are essential factors in understanding mobility within the transport system. Therefore, in this study, a significant number of algorithms were tested for transport mode detection. However, no conclusive recommendations can be drawn regarding which method should be used. The evaluation of the performance of the algorithms was not discussed systematically either in current literature. This paper aims to provide an in-depth review of the methods applied in transport mode detection based on GPS tracking data. The performances of the reviewed methods are then compared and evaluated to provide guidance in choosing algorithms for transport mode detection based on GPS tracking data. The results indicate that the majority of current studies are based on a supervised learning method for transport mode detection. Many of the reviewed methods first require manual dataset labeling, which can produce major drawbacks, such as inefficiency and human errors. It was also found that deep learning approaches have the potential to deal with large amounts of unlabeled raw GPS datasets and increase the accuracy and efficiency of transport mode detection. • A systematic review of methods used to detect transport mode in GPS tracking data. • Compare and evaluate the performance of the reviewed methods. • Enhance knowledge for choosing algorithms to detect transport mode. • Investigate the usefulness of additional GIS information to detect transport mode. • Provide guidance for future research to develop transport mode detection.

TEC derived from local GPS network in Pakistan and comparison with IRI-2016 and IRI-PLAS 2017

The existing global network of continuously operating stand-alone GNSS reference stations provides an opportunity to estimate total electron content (TEC) from raw Global Positioning System (GPS) measurements. The TEC driven from a local GPS network in Pakistan was compared to two international models: IRI-2016 and IRI-PLAS 2017. The performance was analyzed statistically based on residual analysis, RMSE and correlation. It is observed that the TEC estimated by all three methods follows the same diurnal trend where it maximizes around noon ( $$12:00 {-} 14:00 LT$$ ) and reduces in the afternoon ( $$15:00 {-} 17:00 LT$$ ). Both empirical models provide a better estimation of nighttime TEC as compared to daytime TEC and exhibit maximum deviation in the month of April with the lowest deviation in December. The IRI-2016 underestimates TEC by $$5 - 10 TECU,$$ whereas the IRI-PLAS 2017 overestimates TEC by $$10 - 22 TECU$$ . However, the IRI-2016 conforms better to GPS-TEC ( $$\overline{\gamma } = 0.9710$$ ) as compared to IRI-PLAS 2017 ( $$\overline{\gamma } = 0.8337$$ ). The study shows that local GNSS stations in collaboration with TEC estimated from global models may be used in development of an efficient local TEC model over Pakistan which will not only assist in local ionosphere studies but also aid in improving the positioning accuracy.

Improving GPS Code Phase Positioning Accuracy in Urban Environments Using Machine Learning

The accuracy of location information, mainly provided by the global positioning system (GPS) sensor, is critical for Internet-of-Things applications in smart cities. However, built environments attenuate GPS signals by reflecting or blocking them resulting in some cases multipath and non-line-of-sight (NLOS) reception. These effects cause range errors that degrade GPS positioning accuracy. Enhancements in the design of antennae and receivers deliver a level of reduction of multipath. However, NLOS signal reception and residual effects of multipath are still to be mitigated sufficiently for improvements in range errors and positioning accuracy. Recent machine learning-based methods have shown promise in improving pseudorange-based position solutions by considering multiple variables from raw GPS measurements. However, positioning accuracy is limited by low accuracy signal reception classification. Unlike the existing methods, which use machine learning to directly predict the signal reception classification, we use a gradient boosting decision tree (GBDT)-based method to predict the pseudorange errors by considering the signal strength, satellite elevation angle and pseudorange residuals. With the predicted pseudorange errors, two variations of the algorithm are proposed to improve positioning accuracy. The first corrects pseudorange errors and the other either corrects or excludes the signals determined to contain the effects of multipath and NLOS signals. The results for a challenging urban environment characterized by high-rise buildings on one side, show that the 3-D positioning accuracy of the pseudorange error correction-based positioning measured in terms of the root mean square error is 23.3 m, an improvement of more than 70% over the conventional methods.

Augmented extended Kalman filter with cooperative Bayesian filtering and multi‐models fusion for precise vehicle localisations

Self-localisation is vital for autonomous vehicles. In this study, the authors present an augmented extended Kalman filter (AEKF) framework for intelligent vehicle localisation applications. Compared to the previous approach, the proposed AEKF is enhanced through a model fusion, which incorporates a constant velocity model, constant acceleration model, constant turn rate and velocity, and constant turn rate and acceleration model by using the Takagi–Sugeno fuzzy inference technique, where the typical prediction procedure in the extended Kalman filter is modified by a fusion of those various motion models for the state estimation. Furthermore, they proposed a flexible cooperative Bayesian filter to incorporate the data from nearby-vehicles’ position and lateral distance from the host vehicle to the lane lines, to improve the raw global positioning system (GPS) performance under multi-sensor observation environments. They conduct simulation experiments under vividly, near-realistic scenarios with random traffic-flows to show the superiorities of the proposed framework when compared with the consumer-grade GPS implementation. The results show that the obtained positioning enhancement can significantly reduce the positioning error from the original larger than 5 m to the sub-meter level under various scenarios.

Convolutional LSTM based transportation mode learning from raw GPS trajectories

With the advancement of location acquisition technologies, a large amount of raw global positioning system (GPS) trajectory data is produced by many moving devices. Learning transportation modes from the GPS trajectory data is an important problem in the domain of trajectory data mining. Traditional supervised learning-based approaches rely heavily on data preprocessing and feature engineering, which require domain expertise and are time consuming. The authors propose a deep learning-based convolutional long short term memory (LSTM) model for transportation mode learning, in which the convolution neural network is first used to extract deep high-level features and then LSTM is used to learn the sequential patterns in the data that uses both GPS and weather features, thus making the full use of spatiotemporal operations. The authors have also analysed the impact of the geospatial region on human mobility. Experiments conducted on the Microsoft Geolife data set fused with the weather data set show that their model achieves the state-of-the-art results. The authors compare the performance of their model with the benchmark models, which shows the superiority of their model having 3% improvement in accuracy using only GPS features, and the accuracy is further improved by 4 and 7% on including the impact of geospatial region and weather attributes, respectively.

Mechanistic Identification of Freight Activity Stops from Global Positioning System Data

The identification of freight pick-ups and deliveries, referred to as “freight activity” in this paper, is crucial to characterizing freight operations and assessing the performance of freight transportation systems. However, identifying freight activity stops from global positioning system (GPS) data is challenging, particularly in urban freight where congested traffic is common. This paper presents a mechanistic—because it is based on the physics of driving patterns—procedure to identify freight activity stops from raw GPS data. The procedure was implemented to identify stops in three distinct case studies that present a wide range of traffic conditions: Barranquilla, Colombia; Dhaka, Bangladesh; and New York City, United States. The results show that the procedure achieves an average accuracy of above 98.6% when identifying freight activity stops. The results of the proposed procedure were compared with results from support vector machines, random forest, and k nearest neighbors. The mechanistic procedure outperformed these methods in correctly classifying freight activity using second-by-second GPS data.

Using GPS tracking data to validate route choice in OD trips within dense urban networks

There are presently several companies that provide processed or raw global positioning system (GPS) measurements generated by fleets of commercial vehicles, internet applications or automobile companies. The aim of this paper is to deepen our understanding of GPS data applicability in transportation modelling by providing systematic and quantified insights into the representativeness of collected data in describing individual’ route choices. Unfortunately, real data often contain noise, uncertainty, errors, redundancies or even irrelevant information. Useless models will be obtained when built over incorrect or incomplete data. This is why pre-processing is one of the most critical steps in data analysis. Yet, pre-processing has not been properly systematized, which is why this paper focuses on the necessary steps for pre-processing GPS tracking data together and puts forth a proposal for systematizing it. Furthermore, the aggregation level is at waypoint location for low latency GPS positions along the trip trajectory. Travel time reliability on OD paths is addressed, along with other OD path characteristics. Dense urban networks pose multiple possibilities for route choice, and data from new technologies offers an opportunity to understand route choice behaviour.

Metabolic power in hurling with respect to position and halves of match-play

The current investigation compared the metabolic power and energetic characteristics in team sports with respect to positional lines and halves of match-play. Global positioning system (GPS) technology data were collected from 22 elite competitive hurling matches over a 3-season period. A total of 250 complete match-files were recorded with players split into positional groups of full-back; half-back; midfield; half-forward; full-forward. Raw GPS data were exported into a customized spreadsheet that provided estimations of metabolic power and speed variables across match-play events (average metabolic power [Pmet], high metabolic load distance [HMLD], total distance, relative distance, high-speed distance, maximal speed, accelerations, and deceleration). Pmet, HMLD, total, relative and high-speed distance were 8.9 ± 1.6 W·kg-1, 1457 ± 349 m, 7506 ± 1364 m, 107 ± 20 m·min-1 and 1169 ± 260 m respectively. Half-backs, midfielders and half-forwards outperformed full-backs (Effect Size [ES] = 1.03, 1.22 and 2.07 respectively), and full-forwards in Pmet (Effect Size [ES] = 1.70, 2.07 and 1.28 respectively), and HMLD (full-backs: ES = -1.23, -1.37 and -0.84 respectively, and full-forwards: ES = -1.77, -2.00 and -1.38 respectively). Half-backs (ES = -0.60), midfielders (ES = -0.81), and half-forwards (ES = -0.74) experienced a second-half temporal decrement in HMLD. The current investigation demonstrates that metabolic power may increase our understanding of the match-play demands placed on elite hurling players. Coaches may utilize these findings to construct training drills that replicate match-play demands.

Intelligent GPS L1 LOS/Multipath/NLOS Classifiers Based on Correlator-, RINEX- and NMEA-Level Measurements

This paper proposes to use a correlator-level global positioning system (GPS) line-of-sight/multipath/non-line-of-sight (LOS/MP/NLOS) signal reception classifier to improve positioning performance in an urban environment. Conventional LOS/MP/NLOS classifiers, referred to as national marine electronics association (NMEA)-level and receiver independent exchange format (RINEX)-level classifiers, are usually performed using attributes extracted from basic observables or measurements such as received signal strength, satellite elevation angle, code pseudorange, etc. The NMEA/RINEX-level classification rate is limited because the complex signal propagation in urban environment is not fully manifested in these end attributes. In this paper, LOS/MP/NLOS features were extracted at the baseband signal processing stage. Multicorrelator is implemented in a GPS software-defined receiver (SDR) and exploited to generate features from the autocorrelation function (ACF). A robust LOS/MP/NLOS classifier using a supervised machine learning algorithm, support vector machine (SVM), is then trained. It is also proposed that the Skymask and code pseudorange double difference observable are used to label the real signal type. Raw GPS intermediate frequency data were collected in urban areas in Hong Kong and were postprocessed using a self-developed SDR, which can easily output correlator-level LOS/MP/NLOS features. The SDR measurements were saved in the file with the format of NMEA and RINEX. A fair comparison among NMEA-, RINEX-, and correlator-level classifiers was then carried out on a common ground. Results show that the correlator-level classifier improves the metric of F1 score by about 25% over the conventional NMEA- and RINEX-level classifiers for testing data collected at different places to that of training data. In addition to this finding, correlator-level classifier is found to be more feasible in practical applications due to its less dependency on surrounding scenarios compared with the NMEA/RINEX-level classifiers.

Development of a Sensor-Based Behavioral Monitoring Solution to Support Dementia Care.

BackgroundMobile and wearable technology presents exciting opportunities for monitoring behavior using widely available sensor data. This could support clinical research and practice aimed at improving quality of life among the growing number of people with dementia. However, it requires suitable tools for measuring behavior in a natural real-life setting that can be easily implemented by others.ObjectiveThe objectives of this study were to develop and test a set of algorithms for measuring mobility and activity and to describe a technical setup for collecting the sensor data that these algorithms require using off-the-shelf devices.MethodsA mobility measurement module was developed to extract travel trajectories and home location from raw GPS (global positioning system) data and to use this information to calculate a set of spatial, temporal, and count-based mobility metrics. Activity measurement comprises activity bout extraction from recognized activity data and daily step counts. Location, activity, and step count data were collected using smartwatches and mobile phones, relying on open-source resources as far as possible for accessing data from device sensors. The behavioral monitoring solution was evaluated among 5 healthy subjects who simultaneously logged their movements for 1 week.ResultsThe evaluation showed that the behavioral monitoring solution successfully measures travel trajectories and mobility metrics from location data and extracts multimodal activity bouts during travel between locations. While step count could be used to indicate overall daily activity level, a concern was raised regarding device validity for step count measurement, which was substantially higher from the smartwatches than the mobile phones.ConclusionsThis study contributes to clinical research and practice by providing a comprehensive behavioral monitoring solution for use in a real-life setting that can be replicated for a range of applications where knowledge about individual mobility and activity is relevant.

GPS Signal Reception Classification Using Adaptive Neuro-Fuzzy Inference System

The multipath effect and Non-Line-Of-Sight (NLOS) reception of Global Positioning System (GPS) signals both serve to degrade performance, particularly in urban areas. Although receiver design continues to evolve, residual multipath errors and NLOS signals remain a challenge in built-up areas. It is therefore desirable to identify direct, multipath-affected and NLOS GPS measurements in order improve ranging-based position solutions. The traditional signal strength-based methods to achieve this, however, use a single variable (for example, Signal to Noise Ratio (C/N0)) as the classifier. As this single variable does not completely represent the multipath and NLOS characteristics of the signals, the traditional methods are not robust in the classification of signals received. This paper uses a set of variables derived from the raw GPS measurements together with an algorithm based on an Adaptive Neuro Fuzzy Inference System (ANFIS) to classify direct, multipath-affected and NLOS measurements from GPS. Results from real data show that the proposed method could achieve rates of correct classification of 100%, 91% and 84%, respectively, for LOS, Multipath and NLOS based on a static test with special conditions. These results are superior to the other three state-of-the-art signal reception classification methods.

A driving cycle detection approach using map service API

Following advancements in smartphone and portable global positioning system (GPS) data collection, wearable GPS data have realized extensive use in transportation surveys and studies. The task of detecting driving cycles (driving or car-mode trajectory segments) from wearable GPS data has been the subject of much research. Specifically, distinguishing driving cycles from other motorized trips (such as taking a bus) is the main research problem in this paper. Many mode detection methods only focus on raw GPS speed data while some studies apply additional information, such as geographic information system (GIS) data, to obtain better detection performance. Procuring and maintaining dedicated road GIS data are costly and not trivial, whereas the technical maturity and broad use of map service application program interface (API) queries offers opportunities for mode detection tasks. The proposed driving cycle detection method takes advantage of map service APIs to obtain high-quality car-mode API route information and uses a trajectory segmentation algorithm to find the best-matched API route. The car-mode API route data combined with the actual route information, including the actual mode information, are used to train a logistic regression machine learning model, which estimates car modes and non-car modes with probability rates. The experimental results show promise for the proposed method’s ability to detect vehicle mode accurately.

A Method for Extracting Road Boundary Information from Crowdsourcing Vehicle GPS Trajectories.

Crowdsourcing trajectory data is an important approach for accessing and updating road information. In this paper, we present a novel approach for extracting road boundary information from crowdsourcing vehicle traces based on Delaunay triangulation (DT). First, an optimization and interpolation method is proposed to filter abnormal trace segments from raw global positioning system (GPS) traces and interpolate the optimization segments adaptively to ensure there are enough tracking points. Second, constructing the DT and the Voronoi diagram within interpolated tracking lines to calculate road boundary descriptors using the area of Voronoi cell and the length of triangle edge. Then, the road boundary detection model is established integrating the boundary descriptors and trajectory movement features (e.g., direction) by DT. Third, using the boundary detection model to detect road boundary from the DT constructed by trajectory lines, and a regional growing method based on seed polygons is proposed to extract the road boundary. Experiments were conducted using the GPS traces of taxis in Beijing, China, and the results show that the proposed method is suitable for extracting the road boundary from low-frequency GPS traces, multi-type road structures, and different time intervals. Compared with two existing methods, the automatically extracted boundary information was proved to be of higher quality.

Spatio-temporal analysis of trajectories for safer construction sites

PurposeThe purpose of this paper is to improve the safety of construction workers by understanding their behaviors on construction sites using spatio-temporal (ST) trajectories.Design/methodology/approachA review of construction safety management literature and international occupational health and safety statistics shows that the major reasons for fatalities on construction sites are mobility-related issues, such as unsafe human behaviors, difficult site conditions, and workers falling from heights and striking against or being struck by moving objects. Consequently, literature has been reviewed to find possible technological solutions to track the mobility of construction workers to reduce fatalities. This examination has suggested that location acquisition systems, such as Global Positioning System (GPS), have been widely used for real-time monitoring and tracking of workers on construction sites for hazard prevention. However, the raw data captured from GPS devices are generally available as discrete points and do not hold enough information to understand the workers’ mobility. As a solution, an application to transform raw GPS data into ST trajectories using different preprocessing algorithms is proposed for enhancing worker safety on construction sites.FindingsThe proposed system preprocesses raw GPS data for stay point detection, trajectory segmentation and intersection of multiple trajectories to find significant places and movements of workers on a construction site to enhance the information available to H&S managers for decision-making processes. In addition, it reduces the size of trajectory data for future analyses.Originality/valueApplication of location acquisition systems for construction safety management is very well addressed in the existing literature. However, a significant gap has been found: the usage of preprocessed ST trajectories is still missing in workers’ safety monitoring scenarios in the area of construction management. To address this research gap, the proposed system uses preprocessed ST trajectories to monitor workers’ movements on a construction site to identify potentially unsafe behaviors.