To enhance the performance of the inertial navigation system (INS)/global position system (GPS) integrated navigation system for the land vehicle during GPS outages is an extremely challenging task. ...Though existing researches have made reasonable progress in positioning accuracy, they largely ignore sophisticated vehicle stopping events, and the further improvement of positioning performance is urgently needed in complex urban environments. In this article, we propose a heterogeneous multi-task learning (MTL) structure with a shared de-noising process to conduct pseudo-GPS position prediction and zero-velocity detection. The raised model builds upon three vital parts: 1) a shared de-noising convolutional autoencoder (CAE), which can effectively filter the measurement noises in the original inputs and provide more clean data for subsequent calculations without the ground-truth sensor data; 2) a predictor that uses a deep temporal convolutional network (TCN) to predict pseudo-GPS position to bridge GPS gaps; and 3) a robust zero-velocity detector that utilizes a 1-D deep convolutional neural network to accurately detect the vehicle stationary pattern, allowing for timely correcting the velocity and heading. Our proposed MTL model is evaluated on extensive practical road data and achieves a root mean square error of 3.794 m for 120-s GPS outages under long-term vehicle stopping scenarios, which obviously outperforms the stand-alone long short-term memory, TCN, and TCN + CAE. Experimental results also demonstrate that our proposed MTL method yields a remarkable accuracy of over 99.0% for vehicle stationary detection.
•The inclusion of trip purpose significantly increases the accuracy of pre-trip destination prediction algorithms.•Trip purpose is imputed from passively collected data with machine learning ...approaches.•Destination can be predicted accurately with relatively short learning periods.•Prediction accuracy is improved the most for school, shopping, social, driving-others trips.
In everyday travel, U.S. commuters will each spend 38 h a year stuck in traffic and waste over $800 in fuel (TTI, 2015). Yet, despite this statistic, the regular commute of drivers is often predictable, leading many federal projects to aim at alleviating congestion through traveler information and intelligent transportation systems (e.g., INFLO, Queue WARN, CACC, EnableATIS, ATIS2.0). Short-term destination prediction is a developing field of research that can improve these approaches through real-traveler information, such as route, traffic incidence, and congestion levels. The short-term destination prediction problem consists of capturing vehicle Global Positioning System (GPS) traces and learning from historic locations and trajectories to predict a vehicle's destination. Drivers have predictable trip destinations that can be estimated through probabilistic modeling of past trips. To study these concepts, a database of GPS driving traces (260 participants for 70 days) was collected. To model the user's trip purpose in the prediction algorithm, a new data source was explored: point of interest (POI)/land use data. An open source land use/POI dataset is merged with the GPS dataset. The resulting database includes over 20,000 trips with travel characteristics and land use/POI data. From land use/POI data and travel patterns, trip purpose was calculated with machine learning methods. To take advantage of this data source, a new prediction model structure was developed that uses trip purpose when it is available and that falls back on traditional spatial temporal Markov models when it is not. For the first time, there is an understanding of “why” a trip is taken (not just “where” and “when”), allowing the use of “why” in the prediction model. This paper explores the baseline model followed by the inclusion of trip purpose. First, a baseline tiered time origin model was developed using the Markov Chain approach. This modelling structure allows for a short training period of current modeling techniques. The other major advantage to this structure is it allows for easy implementation of the trip purpose module. Then, a machine learning technique derived the trip purpose on 5-, 15- and 30-trip learning sets, followed by results organized by purpose, time, and origin. The machine learning technique does not require future land use data and is feasible for applicable use. This model is the first to use trip purpose to make a short-term destination prediction in pseudo real-time. Results show improved accuracy and speed over the current start-of-trip destination prediction models.
•An adaptive factor graph (AFG) is proposed by introducing the maximum correlation entropy criterion and adaptive technology to develop an information fusion model.•Extreme learning machine (ELM) is ...optimized by minimal learning parameter (MLP) to predict the observation information of the INS/GPS integrated system and tackle the performance deterioration of the system during GPS outages.•A hybrid optimization method using MLP to improve ELM aided AFG is proposed to enhance the navigation capability of INS/GPS integrated system.•Designing different test schemes to verify the validity and advantage of the proposed navigation strategy under satellite denied.
To enhance the navigation capability of the microelectromechanical system (MEMS)-based inertial navigation system (INS)/global positioning system (GPS) integrated system under satellite denied, a hybrid optimization navigation method using minimal learning parameter (MLP) to improve extreme learning machine (ELM) aided adaptive factor graph (AFG) is proposed. The proposed method mainly contains two innovative optimizations: (1) Fully considering the key parameters of each sensor in the INS/GPS integrated navigation system, the factor graph technology is introduced to develop an information fusion model for the system. Based on the maximum correlation entropy criterion and adaptive technology, the existing factor graph method for information fusion is optimized to solve the problem that the abnormal output of each sensor in the INS/GPS integrated system caused by complex environments affects the accuracy of information fusion, thus enhancing the robustness and navigation performance of the INS/GPS integrated system; (2) Moreover, ELM is optimized by MLP to predict the velocity and position observation information of the INS/GPS integrated system and tackle the performance deterioration of the system during GPS outages. The structural parameters of ELM are optimized with the MLP method, aiming to abate the computational burden of the traditional neural network (NN) to avoid “dimension explosion”, as well as enhance the generalization ability and robustness of the network to make it learn from the uncertainty of the system smoothly and quickly. Relevant ground vehicle experiments are designed to evaluate the proposed method. The experimental results demonstrate that the proposed strategy has superior performance and is more feasible for real-time implementation than other comparison approaches.
The variability of space weather can best be captured using total electron content (TEC), which corresponds to total number of electrons on a ray path. The dual‐frequency ground based GPS receivers ...provide a cost‐effective means for monitoring TEC. Computation of TEC for a single GPS station is a challenge due to various unknowns and ambiguities such as inter‐frequency receiver bias and satellite bias, choice of mapping function, and peak height of ionosphere for ionospheric piercing point. In this study, IONOLAB group introduces a robust, automatic, online computation routine near‐real time TEC, IONOLAB‐TEC, for IGS and/or EUREF stations from www.ionolab.org. The user can choose online one station or multiple stations, date or dates for the computation. The IONOLAB‐TEC values can be compared with TEC estimates from IGS analysis centers. The output can be obtained either in graphical form, or IONOLAB‐TEC estimates can be provided in an excel file. The service is easy to use with a graphical user interface. This unique and original space weather application is provided online, and IONOLAB‐TEC estimates are downloaded automatically to the user defined directories under user defined filenames.
Key PointsOnline, automatic, near real‐time GPS‐TEC is estimated as IONOLAB‐TECIONOLAB‐TEC is available from www.ionolab.org for single/multiple stations/daysIONOLAB‐TEC is available in graphics and as excel file
•A transportation resilience measure based on origin destination paces is proposed.•The method is applied to New York City using data from nearly 700,000,000 taxis.•The method indicates minor ...disruptions are observed immediately before Hurricane Sandy.•Grid-lock traffic conditions are observed following Hurricane Sandy.
This article proposes a method to quantitatively measure the resilience of transportation systems using GPS data from probe vehicles such as taxis. The granularity of the GPS data necessary for the method is relatively coarse; it only requires coordinates for the beginning and end of trips, the metered distance, and the total travel time. The method works by computing the historical distribution of pace (normalized travel times) between various regions of a city and measuring the pace deviations during an unusual event. Periods of time containing extreme deviations are identified as events. The method is applied to a dataset of nearly 700 million taxi trips in New York City, which is used to analyze the city transportation infrastructure resilience to Hurricane Sandy. The analysis indicates that Hurricane Sandy impacted traffic conditions for more than five days, and caused a peak delay of two minutes per mile. Practically, it identifies that the evacuation announcements coincided with only minor disruptions, but significant delays were encountered during the post-disaster response period. Since the implementation of this method is very efficient, it could potentially be used as an online monitoring tool, representing a first step toward quantifying city scale resilience with coarse GPS data.
Pointwise GPS measurements of tropospheric zenith total delay can be interpolated to provide high‐resolution water vapor maps which may be used for correcting synthetic aperture radar images, for ...numeral weather prediction, and for correcting Network Real‐time Kinematic GPS observations. Several previous studies have addressed the importance of the elevation dependency of water vapor, but it is often a challenge to separate elevation‐dependent tropospheric delays from turbulent components. In this paper, we present an iterative tropospheric decomposition interpolation model that decouples the elevation and turbulent tropospheric delay components. For a 150 km × 150 km California study region, we estimate real‐time mode zenith total delays at 41 GPS stations over 1 year by using the precise point positioning technique and demonstrate that the decoupled interpolation model generates improved high‐resolution tropospheric delay maps compared with previous tropospheric turbulence‐ and elevation‐dependent models. Cross validation of the GPS zenith total delays yields an RMS error of 4.6 mm with the decoupled interpolation model, compared with 8.4 mm with the previous model. On converting the GPS zenith wet delays to precipitable water vapor and interpolating to 1 km grid cells across the region, validations with the Moderate Resolution Imaging Spectroradiometer near‐IR water vapor product show 1.7 mm RMS differences by using the decoupled model, compared with 2.0 mm for the previous interpolation model. Such results are obtained without differencing the tropospheric delays or water vapor estimates in time or space, while the errors are similar over flat and mountainous terrains, as well as for both inland and coastal areas.
Key Points
An iterative tropospheric decomposition model for zero differenced ZTD interpolation
Generation of high‐resolution real‐time mode GPS‐based ZTD and PWV maps
Validation of ITD PWV maps with the MODIS near‐IR water vapor product
When the global position system (GPS) signal is unavailable, the performance of the GPS/inertial navigation system (INS) integrated navigation system degrades severely. In this article, the ...performance of the ultra-low cost inertial measurement unit (IMU) is studied and the objective is to enhance its performance during GPS outages. To be specific, a performance compensation method is proposed, which consists of two parts. First, to deal with the large noise and drift of the micro-electro-mechanical system (MEMS)-based inertial measurement unit (IMU), a wavelet regional correlation threshold denoising algorithm is proposed. Then, to improve the performance of traditional LSTM network when dealing with navigation data with strong coupling, a convolutional neural network-long short-term memory (CNN–LSTM) model is formulated. It employs CNN to quickly extract the features of the input, and utilizes LSTM network to output pseudo-GPS signals as the compensation object. Finally, simulation experiments and real road tests are implemented to evaluate the proposed method. Comparison experiment results show that the proposed method can effectively improve the performance of the integrated navigation system during GPS outages.
•The ultra-low cost IMU with relative poor performance is the object of this study.•A wavelet correlation threshold algorithm is proposed to process raw sensing data.•Practical and comparison experiments are implemented to verify the proposed method.
High‐density GPS receivers located in Southeast Asia (SEA) were utilized to study the two‐dimensional structure of ionospheric plasma irregularities in the equatorial region. The longitudinal and ...latitudinal variations of tens of kilometer‐scale irregularities associated with equatorial plasma bubbles (EPBs) were investigated using two‐dimensional maps of the rate of total electron content change index (ROTI) from 127 GPS receivers with an average spacing of about 50–100 km. The longitudinal variations of the two‐dimensional maps of GPS ROTI measurement on 5 April 2011 revealed that 16 striations of EPBs were generated continuously around the passage of the solar terminator. The separation distance between the subsequent onset locations varied from 100 to 550 km with 10 min intervals. The lifetimes of the EPBs observed by GPS ROTI measurement were between 50 min and over 7 h. The EPBs propagated 440–3000 km toward the east with velocities of 83–162 m s−1. The longitudinal variations of EPBs by GPS ROTI keogram coincided with the depletions of 630 nm emission observed using the airglow imager. Six EPBs were observed by GPS ROTI along the meridian of Equatorial Atmosphere Radar (EAR), while only three EPBs were detected by the EAR. The high‐density GPS receivers in SEA have an advantage of providing time continuous descriptions of latitudinal/longitudinal variations of EPBs with both high spatial resolution and broad geographical coverage. The spatial periodicity of the EPBs could be associated with a wavelength of the quasiperiodic structures on the bottomside of the F region which initiate the Rayleigh‐Taylor instability.
Key Points
The observation of EPB using high‐density GPS receivers in SEA
The continuous generation of 16 EPB structures during the solar terminator
The simultaneous observations of EPB with airglow imager and EAR
Human activities shape resources available to wild animals, impacting diet and probably altering their microbiota and overall health. We examined drivers shaping microbiota profiles of common cranes ...(Grus grus) in agricultural habitats by comparing gut microbiota and crane movement patterns (GPS‐tracking) over three periods of their migratory cycle, and by analysing the effect of artificially supplemented food provided as part of a crane‐agriculture management programme. We sampled faecal droppings in Russia (nonsupplemented, premigration) and in Israel in late autumn (nonsupplemented, postmigration) and winter (supplemented and nonsupplemented, wintering). As supplemented food is typically homogenous, we predicted lower microbiota diversity and different composition in birds relying on supplementary feeding. We did not observe changes in microbial diversity with food supplementation, as diversity differed only in samples from nonsupplemented wintering sites. However, both food supplementation and season affected bacterial community composition and led to increased abundance of specific genera (mostly Firmicutes). Cranes from the nonsupplemented groups spent most of their time in agricultural fields, probably feeding on residual grain when available, while food‐supplemented cranes spent most of their time at the feeding station. Thus, nonsupplemented and food‐supplemented diets probably diverge only in winter, when crop rotation and depletion of anthropogenic resources may lead to a more variable diet in nonsupplemented sites. Our results support the role of diet in structuring bacterial communities and show that they undergo both seasonal and human‐induced shifts. Movement analyses provide important clues regarding host diet and behaviour towards understanding how human‐induced changes shape the gut microbiota in wild animals.
The developments in GNSS receiver and antenna technologies, especially the increased sampling rate up to 100 sps, open up the possibility to measure high-rate earthquake ground motions with GNSS. In ...this paper we focus on the GPS errors in the frequency band above 1 Hz. The dominant error sources are mainly the carrier phase jitter caused by thermal noise and the stress error caused by the dynamics, e.g. antenna motions. To generate a large set of different motions, we used a single-axis shake table, where a GNSS antenna and a strong motion seismometer were mounted with a well-known ground truth. The generated motions were recorded with three different GNSS receivers with sampling rates up to 100 sps and different receiver baseband parameters. The baseband parameters directly dictate the carrier phase jitter and the correlations between subsequent epochs. A narrow loop filter bandwidth keeps the carrier phase jitter on a low level, but has an extreme impact on the receiver response for motions above 1 Hz. The amplitudes above 3 Hz are overestimated up to 50 % or reduced by well over half. The corresponding phase errors are between 30 and 90 degrees. Compared to the GNSS receiver response, the strong motion seismometer measurements do not show any amplitude or phase variations for the frequency range from 1 to 20 Hz. Due to the large errors for dynamic GNSS measurements, it is essential to account for the baseband parameters of the GNSS receivers if high-rate GNSS is to become a valuable tool for seismic displacement measurements above 1 Hz. Fortunately, the receiver response can be corrected by an inverse filter if the baseband parameters are known.