Behrang Assemi

The widespread and increased use of smartphones, equipped with the global positioning system (GPS), has facilitated the automation of travel data collection. Most studies on travel mode detection that used GPS data have employed hand‐crafted features that may not have the capabilities to detect all complex travel behaviours since their performance is highly dependent on the skills of domain experts and may limit the performance of classifiers. In this study, a genetic programming (GP) approach is proposed to select and construct features for GPS trajectories. GP increased the macro‐average of the F1‐score from 77.3 to 80.0 in feature construction when applied to the GeoLife dataset. It could transform the decision tree into a competitive classifier with support vector machines (SVMs) and neural networks that are both able to extract high‐level features. Simplicity, interpretability, and a relatively lower risk of overfitting allow the proposed model to be readily used for passive travel data collection even on smartphones with limited computational capacities. The model is validated by a second dataset from Australia and New Zealand, which indicated that a decision tree with the GP constructed features as its input has a considerably higher transferability than SVMs and neural networks.

A record of spatial and temporal parking occupancy is critical to optimize on-street parking resources and to develop effective parking policies. Such data are often obtained through advanced and costly occupancy monitoring technologies. Moreover, it is usually challenging to integrate bay-level occupancies and parking data from other systems. Accurate occupancy–payment data are required for a wide range of analytical and practical purposes, including but not limited to investigating payment behavior, estimating and forecasting occupancy, and evaluating the efficiency and effectiveness of enforcement policies. This study proposes a metaheuristic optimization algorithm to integrate snapshots of bay-level parking occupancy, captured using simple cameras, with transactions from a conventional parking payment management system. The resulting integrated data were used to develop, calibrate and validate a parking occupancy estimation method utilizing parking payment data only. Details of the design, implementation, and validation of the proposed algorithm and modelling technique are provided. Logistic regression analysis was used to tune parameters of the data integration algorithm. Deep learning, gradient boosting and random forests were used to develop a model of parking occupancy. Evaluation of the algorithm indicated an accuracy of 76% of correct data integration; that is, individual bay occupancies integrated with the correct corresponding payment transactions. The best occupancy estimation model also showed a very high accuracy, with an R ² above 94% and a root mean square error (RMSE) of 1.2 (occupied bays), when tested with a random sample from the integrated data.

Heavy vehicle crashes incur significant economic and social costs. Although most crashes are considered to be related to driver error, the effects of vehicle defects are major in many crashes. Therefore, various vehicle inspections including Queensland’s Certificate of Inspection (COI) scheme have been implemented to improve the safety of heavy vehicles. This study analyzes the trends of heavy vehicle crashes and their relationships with COI results. Longitudinal data provided by Queensland’s Department of Transport and Main Roads for the period of June 2009 through December 2013 were used to perform the analyses. The data include 474,640 programmed inspections and 2,274 crashes in which heavy vehicles were involved. The results show significant relationships between the monthly average inspection failure rate as well as the monthly average failure severity level, and the total number of heavy vehicle crashes. The results also reveal significant relationships between the monthly average inspection failure rate, average vehicle age, as well as monthly average mean maximum temperature, and the number of defect-related crashes. The implications of these results are discussed with respect to heavy vehicle safety policies.

This study proposes an algorithm to integrate bay-based parking occupancy, captured using an image processing system, with information from a common conventional parking payment management system. The algorithm enables the use of simple and inexpensive cameras to collect parking utilization to complement conventional payment transaction data. Details about the design, implementation, testing, and validation of the algorithm are provided. Validation was performed using data collected through an accurate observational survey, including plate numbers of all vehicles parked in the areas of analysis. Results from a case study using the proposed algorithm provided an accuracy of 76% in terms of correct data integration. Logistic regression analysis was used to improve parameters used by the proposed algorithm. To illustrate the value of the algorithm, the integrated data were used to evaluate parking payment behavior. Various performance measures can be proposed and estimated using the integrated data. The integrated data can be used to address questions of high importance for more efficient and effective management of parking facilities.

Background: The existing smartphones’ technology allows for the objective measurement of a person’s movements at a fine-grained level of geographic and temporal detail, and in doing so, it mitigates the issues associated with self-report biases and lack of spatial details. This study proposes and evaluates the advantages of using a smartphone app for collecting accurate, fine-grained, and objective data on people’s transport-related walking. Methods: A sample of 142 participants (mostly young adults) was recruited in a large Australian university, for whom the app recorded all their travel activities over two weekdays during August–September 2014. We identified eight main activity nodes which operate as transport-related walking generators. We explored the participants’ transport-related walking patterns around and between these activity nodes through the use of di-graphs to better understand patterns of incidental physical activity and opportunities for intervention to increase incidental walking. Results: We found that the educational node — in other samples may be represented by the workplace — is as important as the residential node for generating walking trips. We also found that the likelihood of transport-related walking trips is larger during the daytime, whereas at night time walking trips tend to be longer. We also showed that patterns of transport-related walking relate to the presence of ‘chaining’ trips in the afternoon period. Conclusions: The findings of this study show how the proposed data collection and analytic approach can inform urban design to enhance walkability at locations that are likely to generate walking trips. This study’s insights can help to shape public education and awareness campaigns that aim to encourage walking trips throughout the day by suggesting locations and times of the day when engaging in these forms of exercise is easiest and least intrusive.

Estimating longitudinal vehicle speed is required in a wide range of applications from road safety to vehicular emissions modelling. Each vehicle speed estimation method has specific challenges including the high cost of measurement equipment, the small range of vehicle models accessible for performing tests and the low resolution of data in time and space. Thus, the goals of this study are (a) to investigate the use of smartphones’ integrated sensors as a convenient, reliable and powerful means of vehicle speed data collection which would mitigate the issues observed in previous methods, and (b) to propose a post‐processing pipeline for generating vehicles’ speed profiles based on the raw data captured by the proposed data collection method. Accordingly, a smartphone application is developed to facilitate the collection of vehicles’ movement data, particularly inside tunnels and high‐density urban areas, where state‐of‐the‐art global positioning system (GPS) applications fail to record the desired data. Moreover, a post‐processing pipeline is proposed for calculating vehicles’ speed profiles and emissions from the raw smartphone acceleration data, and the full system is evaluated through a series of controlled experiments as well as simulations.