ORCID Profile
0000-0002-5832-4134
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Elsevier BV
Date: 10-2016
Publisher: SAGE Publications
Date: 10-07-2019
Abstract: Transportation mode distribution has a large implication on the resilience, economic output, social cost of cities and the health of urban residents. Recent advances in artificial intelligence and the availability of remote sensing data have opened up opportunities for bottom-up modeling techniques that allow understanding of how subtle differences in the urban fabric can impact transportation mode share distribution. This project presents a novel neural network-based modeling technique capable of predicting transportation mode distribution. Trained with millions of images labeled with information from a georeferenced transportation survey, the resulting model is able to infer transportation mode share with high accuracy ( R 2 = 0.58) from satellite images alone. Additionally, this method can disaggregate data in areas where only aggregated information is available and infer transportation mode share in areas without underlying information. This work demonstrates a new and objective method to evaluate the impact of the urban fabric on transportation mode share. The methodology is robust and can be adapted for cases around the world as well as deployed to evaluate the impact of new developments on the transportation mode choice.
Publisher: Elsevier BV
Date: 09-2019
Publisher: Wiley
Date: 19-10-2020
DOI: 10.1111/MICE.12623
Publisher: Elsevier BV
Date: 08-2017
Publisher: Elsevier BV
Date: 06-2022
Publisher: Informa UK Limited
Date: 18-03-2020
Publisher: Springer Singapore
Date: 2019
Publisher: Informa UK Limited
Date: 23-12-2019
DOI: 10.1080/17457300.2019.1704790
Abstract: Over the past four decades considerable efforts have been taken to mitigate the growing burden of road injury. With increasing urbanisation along with global mobility that demands not only safe but equitable, efficient and clean (reduced carbon footprint) transport, the responses to dealing with the burgeoning road traffic injury in low- and middle-income countries has become increasingly complex. In this paper, we apply unique methods to identify important strategies that could be implemented to reduce road traffic injury in the Asia-Pacific region a region comprising large middle-income countries (China and India) that are currently in the throes of rapid motorisation. Using a convolutional neural network approach, we clustered countries containing a total of 1632 cities from around the world into groups based on urban characteristics related to road and public transport infrastructure. We then analysed 20 countries (containing 689 cities) from the Asia-Pacific region and assessed the global burden of disease attributed to road traffic injury and these various urban characteristics. This study demonstrates the utility of employing image recognition methods to discover new insights that afford urban and transport planning opportunities to mitigate road traffic injury at a regional and global scale.
Publisher: Copernicus GmbH
Date: 02-05-2023
DOI: 10.5194/AMT-2023-80
Abstract: Abstract. The mixing layer height (MLH) indicates the change between vertical mixing of air near the surface and less turbulent air above. MLH is important for the dispersion of air pollutants and greenhouse gases, and for assessing the performance of numerical weather prediction systems. Existing lidar-based MLH detection algorithms typically do not use the full resolution of the ceilometer, require manual feature engineering, and often do not enforce temporal consistency of the MLH. To address these limitations, a novel MLH detection approach has been developed based on deep learning techniques for image segmentation. The concept of our Deep-Pathfinder algorithm is to represent the 24-hour MLH profile as a mask and directly predict it from an image with lidar observations. Therefore, range-corrected signal data was obtained from Lufft CHM 15k ceilometers at five locations in the Netherlands that were part of the operational ceilometer network. Input s les of 224 × 224 pixels were extracted, each covering a 45-minute observation period. A customised U-Net architecture was developed with a nighttime indicator and MobileNetV2 encoder for fast inference times. The model was pre-trained on 19.4 million s les of unlabelled data and fine-tuned using 50 days of high-resolution annotations. Qualitative and quantitative results showed competitive performance compared to two benchmark models: the Lufft and STRATfinder algorithms. Existing path optimisation algorithms have good temporal consistency, but can only be evaluated after a full day of ceilometer data has been recorded. Deep-Pathfinder retains the advantages of temporal consistency but can also provide real-time estimates. This makes our approach valuable for operational settings, as real-time MLH detection better meets the requirements of users such as in aviation, weather forecasting and air quality monitoring.
Publisher: Elsevier BV
Date: 02-2018
Publisher: Elsevier BV
Date: 08-2020
Publisher: Elsevier BV
Date: 10-2018
DOI: 10.1016/J.AAP.2018.06.014
Abstract: Recent studies have demonstrated that financial incentives can improve driving behaviour but high-value incentives are unlikely to be cost-effective and attempts to lify the impact of low-value incentives have so far proven disappointing. The present study provides experimental evidence to inform the design of 'smart' and potentially more cost-effective incentives for safe driving in novice drivers. Study participants (n = 78) were randomised to one of four financial incentives: high-value penalty low-value penalty high-value reward low-value reward allowing us to compare high-value versus low-value incentives, penalties versus rewards, and to test specific hypotheses regarding motivational crowding out and gain/loss asymmetry. Results suggest that (i) penalties may be more effective than rewards of equal value, (ii) even low-value incentives can deliver net reductions in risky driving behaviours and, (iii) increasing the dollar-value of incentives may not increase their effectiveness. These design principles are currently being used to optimise the design of financial incentives embedded within PAYD insurance, with their impact on the driving behaviour of novice drivers to be evaluated in on-road trials.
Publisher: Portico
Date: 29-01-2015
Abstract: The Australian Bureau of Meteorology (Bureau) issues operational tropical cyclone (TC) seasonal forecasts for the Australian region (AR) and the South Pacific Ocean (SPO) and subregions therein. The forecasts are issued in October, ahead of the Southern Hemisphere TC season (November to April). Improvement of operational TC seasonal forecasts can lead to more accurate warnings for coastal communities to prepare for TC hazards. This study investigates the use of support vector regression (SVR) models, exploring new explanatory variables and non-linear relationships between them, the use of model averaging, and lastly the integration of forecast intervals based on a bias-corrected and accelerated non-parametric bootstrap. Hindcasting analyses show that the SVR model outperforms several benchmark methods. Analysis of the generated models shows that the Dipole Mode Index, 5VAR index and the Southern Oscillation Index are the most frequently selected as explanatory variables for TC seasonal forecasting in all regions. The usage of ENSOrelated covariates implies that definitions of regions and subregions may have to be updated to achieve optimal forecasting performance. Overall, the new SVR methodology is an improvement over the current linear discriminant analysis models and has the potential to increase accuracy of TC seasonal forecasts in the AR and SPO.
Publisher: Hindawi Limited
Date: 2014
DOI: 10.1155/2014/838746
Abstract: Tropical cyclones (TCs) can have a major impact on the coastal communities of Australia and Pacific Island countries. Preparedness is one of the key factors to limit TC impacts and the Australian Bureau of Meteorology issues an outlook of TC seasonal activity ahead of TC season for the Australian Region (AR 5°S to 40°S, 90°E to 160°E) and the South Pacific Ocean (SPO 5°S to 40°S, 142.5°E to 120°W). This paper investigates the use of support vector regression models and new explanatory variables to improve the accuracy of seasonal TC predictions. Correlation analysis and subsequent cross-validation of the generated models showed that the Dipole Mode Index (DMI) performs well as an explanatory variable for TC prediction in both AR and SPO, Niño4 SST anomalies—in AR and Niño1+2 SST anomalies—in SPO. For both AR and SPO, the developed model which utilised the combination of Niño1+2 SST anomalies, Niño4 SST anomalies, and DMI had the best forecasting performance. The support vector regression models outperform the current models based on linear discriminant analysis approach for both regions, improving the standard deviation of errors in cross-validation from 2.87 to 2.27 for AR and from 4.91 to 3.92 for SPO.
Publisher: Elsevier BV
Date: 2020
Publisher: Wiley
Date: 11-07-2020
DOI: 10.1111/MICE.12594
Publisher: Springer Science and Business Media LLC
Date: 13-10-2020
DOI: 10.1007/S00521-019-04506-0
Abstract: Driver drowsiness increases crash risk, leading to substantial road trauma each year. Drowsiness detection methods have received considerable attention, but few studies have investigated the implementation of a detection approach on a mobile phone. Phone applications reduce the need for specialised hardware and hence, enable a cost-effective roll-out of the technology across the driving population. While it has been shown that three-dimensional (3D) operations are more suitable for spatiotemporal feature learning, current methods for drowsiness detection commonly use frame-based, multi-step approaches. However, computationally expensive techniques that achieve superior results on action recognition benchmarks (e.g. 3D convolutions, optical flow extraction) create bottlenecks for real-time, safety-critical applications on mobile devices. Here, we show how depthwise separable 3D convolutions, combined with an early fusion of spatial and temporal information, can achieve a balance between high prediction accuracy and real-time inference requirements. In particular, increased accuracy is achieved when assessment requires motion information, for ex le, when sunglasses conceal the eyes. Further, a custom TensorFlow-based smartphone application shows the true impact of various approaches on inference times and demonstrates the effectiveness of real-time monitoring based on out-of-s le data to alert a drowsy driver. Our model is pre-trained on ImageNet and Kinetics and fine-tuned on a publicly available Driver Drowsiness Detection dataset. Fine-tuning on large naturalistic driving datasets could further improve accuracy to obtain robust in-vehicle performance. Overall, our research is a step towards practical deep learning applications, potentially preventing micro-sleeps and reducing road trauma.
Publisher: BMJ
Date: 10-01-2018
DOI: 10.1136/INJURYPREV-2016-042280
Abstract: Road injury is the leading cause of death for young people, with human error a contributing factor in many crash events. This research is the first experimental study to examine the extent to which direct feedback and incentive-based insurance modifies a driver's behaviour. The study applies in-vehicle telematics and will link the information obtained from the technology directly to personalised safety messaging and personal injury and property damage insurance premiums. The study has two stages. The first stage involves laboratory experiments using a state-of-the-art driving simulator. These experiments will test the effects of various monetary incentives on unsafe driving behaviours. The second stage builds on these experiments and involves a randomised control trial to test the effects of both direct feedback (safety messaging) and monetary incentives on driving behaviour. Assuming a positive finding associated with the monetary incentive-based approach, the study will dramatically influence the personal injury and property damage insurance industry. In addition, the findings will also illustrate the role that in-vehicle telematics can play in providing direct feedback to young/novice drivers in relation to their driving behaviours which has the potential to transform road safety.
Publisher: Informa UK Limited
Date: 06-05-2020
Publisher: MDPI AG
Date: 27-05-2020
Abstract: Urban typologies allow areas to be categorised according to form and the social, demographic, and political uses of the areas. The use of these typologies and finding similarities and dissimilarities between cities enables better targeted interventions for improved health, transport, and environmental outcomes in urban areas. A better understanding of local contexts can also assist in applying lessons learned from other cities. Constructing urban typologies at a global scale through traditional methods, such as functional or network analysis, requires the collection of data across multiple political districts, which can be inconsistent and then require a level of subjective classification. To overcome these limitations, we use neural networks to analyse millions of images of urban form (consisting of street view, satellite imagery, and street maps) to find shared characteristics between the largest 1692 cities in the world. The comparison city of Paris is used as an exemplar and we perform a case study using two Australian cities, Melbourne and Sydney, to determine if a “Paris-end” of town exists or can be found in these cities using these three big data imagery sets. The results show specific advantages and disadvantages of each type of imagery in constructing urban typologies. Neural networks trained with map imagery will be highly influenced by the structural mix of roads, public transport, and green and blue space. Satellite imagery captures a combination of both urban form and decorative and natural details. The use of street view imagery emphasises the features of a human-scaled visual geography of streetscapes. However, for both satellite and street view imagery to be highly effective, a reduction in scale and more aggressive pre-processing might be required in order to reduce detail and create greater abstraction in the imagery.
Publisher: MDPI AG
Date: 28-11-2019
DOI: 10.3390/SU11236755
Abstract: Although a lot of work has been conducted on car-following modeling, model calibration and validation are still a great challenge, especially in the era of autonomous driving. Most challengingly, besides the immediate benefit incurred with a car-following action, a smart vehicle needs to learn to evaluate the long-term benefits and become foresighted in conducting car-following behaviors. Driving memory, which plays a significant role in car-following, has seldom been considered in current models. This paper focuses on the impact of driving memory on car-following behavior, particularly, historical driving memory represents certain types of driving regimes and drivers’ maneuver in coordination with the variety of driving regimes. An autoencoder was used to extract the main features underlying the time-series data in historical driving memory. Long short-term memory (LSTM) neural network model has been employed to investigate the relationship between driving memory and car-following behavior. The results show that velocity, relative velocity, instant perception time (IPT), and time gap are the most relevant parameters, while distance gap is insignificant. Furthermore, we compared the accuracy and robustness of three patterns including various driving memory information and span levels. This study contributes to bridging the gap between historical driving memory and car-following behavior modeling. The developed LSTM methodology has the potential to provide personalized warnings of dangerous car-following distance over the next second.
Publisher: Copernicus GmbH
Date: 15-05-2023
DOI: 10.5194/EGUSPHERE-EGU23-135
Abstract: The mixing layer height (MLH) indicates the change between vertical mixing of air near the surface and less turbulent air above. MLH is important for the dispersion of air pollutants and greenhouse gases, and assessing the performance of numerical weather prediction systems. Existing lidar-based MLH detection algorithms typically do not use the full resolution of the ceilometer, require manual feature engineering, and often do not enforce temporal consistency of the MLH profile. Given the large-scale availability of lidar remote sensing data and the high temporal and spatial resolution at which it is recorded, this domain is very suitable for machine learning approaches such as deep learning. This presentation introduces a completely new approach to estimate MLH: the Deep-Pathfinder algorithm, based on deep learning techniques for image segmentation.The concept of Deep-Pathfinder is to represent the 24-hour MLH profile as a mask (i.e., black indicating the mixing layer, white indicating the non-turbulent atmosphere above) and directly predict the mask from an image with lidar observations. Range-corrected signal (RCS) data at 12-second temporal and 10-meter vertical resolution was obtained from Lufft CHM 15k ceilometers at five locations in the Netherlands (2020& #8211 ). High-resolution annotations were created for 50 days, informed by a visual inspection of the RCS image, the manufacturer's layer detection algorithm, gradient fields, thermodynamic MLH estimates, and humidity profiles of the 213-meter mast at Cabauw.Our model is based on a customised U-Net architecture with MobileNetV2 encoder to ensure fast inference times. A nighttime variable indicated whether the s le occurred between sunset and sunrise and hence, whether an estimate of the stable or convective boundary layer was required. Model calibration was performed on the Dutch National Supercomputer Snellius. First, input s les were randomly cropped to 224x224 pixels, covering a 45-minute period and maximum altitude of 2240 meters. Then, the model was pre-trained on 19.4 million s les of unlabelled data. Finally, the labelled data was used to fine-tune the model for the task of mask prediction. Performance on a test set was compared to MLH estimates from ceilometer manufacturer Lufft and the STRATfinder algorithm.Results showed that days with a clear convective boundary layer were captured well by all three methods, with minimal differences between them. The Lufft wavelet covariance transform algorithm contained a slight temporal shift in MLH estimates. Further, it had more missing data in complex atmospheric conditions. STRATfinder estimates for the nocturnal boundary layer were consistently low due to guiding restrictions in the algorithm. In contrast, Deep-Pathfinder followed short-term fluctuations in MLH more closely due to the use of high-resolution input data. Path optimisation algorithms like STRATfinder have good temporal consistency but can only be evaluated after a full day of ceilometer data has been recorded. Deep-Pathfinder retains the advantages of temporal consistency by assessing MLH evolution in 45-minute s les, however, it can also provide real-time estimates. This makes a deep learning approach as presented here valuable for operational use, as real-time MLH detection better meets the requirements of users in aviation, weather forecasting and air quality monitoring.
Publisher: BMJ
Date: 12-10-2019
DOI: 10.1136/INJURYPREV-2018-042763
Abstract: The safety in numbers (SiN) effect for cyclists is widely observed but remains poorly understood. Although most studies investigating the SiN phenomenon have focused on behavioural adaptation to ‘numbers’ of cyclists in the road network, previous work in simulated environments has suggested SiN may instead be driven by increases in local cyclist spatial density, which prevents drivers from attempting to move through groups of oncoming cyclists. This study therefore set out to validate the results of prior simulation studies in a real-world environment. Time-gap analysis of cyclists passing through an intersection was conducted using 5 hours of video observation of a single intersection in the city of Melbourne, Australia, where motorists were required to ‘yield’ to oncoming cyclists. Results demonstrated that potential collisions between motor vehicles and cyclists reduced with increasing cyclists per minute passing through the intersection. These results successfully validate those observed under simulated conditions, supporting evidence of a proposed causal mechanism related to safety in density rather than SiN, per se. Implications of these results for transportation planners, cyclists and transportation safety researchers are discussed, suggesting that increased cyclist safety could be achieved through directing cyclists towards focused, strategic corridors rather than dispersed across a network.
Publisher: Elsevier BV
Date: 06-2022
DOI: 10.1016/J.AAP.2022.106661
Abstract: Reliable knowledge of driving states is of great importance to ensure road safety. Anomaly detection in driving behavior means recognizing anomalous driving states as a direct result of either environmental or psychological factors. This paper provides an efficient anomaly recognition approach to identify anomalous lane-changing events in a personalized manner. The proposed framework includes three unsupervised algorithms. First, a Recurrent-Convolutional Autoencoder extracts the spatio-temporal characteristics from a high-dimensional naturalistic driving dataset. Second, in order to recognize anomalous lane-changing events of in idual drivers, the extracted latent feature space is analyzed using Pauta criterion-based reconstruction loss analysis, as well as one-class Support Vector Machine. Last, t-Distributed Stochastic Neighbor Embedding is employed to visualize the latent space for better understanding and interpretability. Temporal anomalies of lane-changing events were analyzed by a personalized grey relational coefficient analysis, to represent robust similarities for in idual drivers. Validation and calibration were performed with a natural driving study dataset collected from 50 drivers with 59,372 lane change events. The results showed heterogeneity in the pattern of abnormal lane changing behavior across the s le. At the same time, each driver exhibited heterogeneous anomalous behaviors in both temporal and spatial sequences. Without prior labels, the proposed model effectively captures personalized driving patterns and abnormal lane-changing events from high-dimensional time-series data. This unsupervised hybrid approach is a novel attempt to complete personalized anomalous lane-changing behaviors identification based on naturalistic driving data involving various traffic environments. Our approach enables the extraction of natural in idual lane-changing behavior patterns and provides insights for the improvement of personalized driving behavior monitoring systems.
Publisher: Elsevier BV
Date: 08-2021
Publisher: American Meteorological Society
Date: 07-11-2016
Abstract: Variable selection for short-term forecasting (up to 72 h) of tropical cyclone (TC) genesis has been investigated. IBTrACS data (1979–2014) are used to identify the genesis time and position of over 2500 TCs between 30°N and 30°S. Tracks are extended using a tropical cloud cluster (TCC) dataset, which is also used to identify over 28 000 nondeveloping TCCs. Subsequently, corresponding local environment states at various atmospheric pressure levels are retrieved from ERA-Interim data. An initial selection of potentially favorable variables for TC genesis is made based on mutual information, which forms the set of nodes for graphical model structure learning using the Peter–Clark (PC) algorithm. Structure learning identifies the variables with the strongest influence on TC genesis, while taking into account the interrelationship with other variables. Variables are ranked based on the maximum observed p value in all (conditional) independence tests of the variable with the TC genesis node. The results indicate that potential vorticity (600 hPa), relative vorticity (925 hPa), and (vector) vertical wind shear (200–700 hPa) are the highest ranked variables for forecasting up to 72 h. These are followed by the basin and zonal wind speed (200 hPa), and for very short lead-time ergence (925 hPa), air temperature (300 hPa), and average vertical velocity. Predictive modeling with logistic regression confirms the superior performance of the top-ranked variables. The presented variable ranking (methodology) can be used as a building block for the creation of genesis indices or predictive models in the future.
Publisher: Elsevier BV
Date: 03-2019
Publisher: Elsevier BV
Date: 09-2019
No related grants have been discovered for Jasper Wijnands.