Infrastructure Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 18
-
ItemLightweight traffic anomaly detection: A case study with SCATS volume data of Melbourne(Australasian Transport Research Forum, 2023)In this paper, we evaluate performance of an anomaly detection framework with real traffic count data collected by SCATS (Sydney Coordinated Adaptive Traffic System) loop detectors in Melbourne. The goal is to detect anomalous daily volume profiles within temporally large historical traffic data utilizing a lightweight and parameter-free approach and use it for live applications. To achieve this, daily volume profiles are first compressed into two dimensions benefiting from the Principal Component analysis (PCA). Then, a parameter-free version of DBSCAN is applied to the data with unique days of the week. Results from more than 20 different locations in Melbourne are fully visualized and the advantages and disadvantages of the method are discussed. We found that, with this approach, anomalous volume profiles can be accurately detected in a wide range of spatiotemporal data without any pre-training, parameter setting, or using complex learning methods.
-
ItemTesting request prioritization strategies to improve the quality of a shared autonomous vehicles service: A Melbourne case study(Australasian Transport Research Forum, 2023)Shared autonomous vehicles (SAVs) have the potential to revolutionize urban transport by offering a mobility service that combines the benefits of autonomous vehicles and ride-hailing systems. However, one of the main limitations of these services is the handling of all request types in a singular way, which can increase biases towards a fixed type of passengers who have different properties and accessibility-based constraints. This study proposes a prioritization approach based on different request properties and the urgency of the request. The study uses the MATSim simulator to evaluate the prioritization schemes and implements five different scenarios to assess the collective and individual effects of the schemes. The case study focuses on Melbourne Metropolitan Area, and the prioritization is done based on the existing public transport (PT) service and pre-calculated SAV demand of the network. The study considers different performance measures, such as service efficiency, externalities, and provision equity, to estimate the benefits of the prioritization. The results indicate that prioritization can improve overall equity by spreading wait times evenly across the network. The prioritization approach improves the service with more riders finding the service attractive, resulting in more served rides with lower average vehicle kilometers traveled per ride. In addition, the study shows that the PT mode share is increased in multiple scenarios, demonstrating the positive effect of considering accessibility when prioritizing requests.
-
ItemWhat influences passenger’s arrival rate at stops in Melbourne: WASEA-LSTM: a novel deep learning model leveraging multi-source data fusion(ATRF, 2023)Public transportation demand plays a crucial role in service planning and operation. Accurate prediction of passenger arrival rates at transit stops allows transportation planners and operators to optimize resources and improve service efficiency. Current methodologies primarily focus on weather's impact in the aviation industry, supply dynamics, and arrival time prediction, while overlooking its influence on public transport demand variation. This study addresses these gaps by designing a deep neural network model that can predict public transit demand, using large-scale datasets from multiple sources in Melbourne, Australia. We propose a novel deep learning architecture called Wasea-Lstm (Weather-Aware Smart Exponential Activation LSTM) that captures spatial, temporal, and external correlations for passenger arrival rate prediction at tram stops. The model is trained and tested on integrated datasets from automatic fare collection (AFC), automatic passenger count (APC), and weather data over a period of three months. Results show that the Wasea-Lstm model significantly outperforms benchmark models, including gradient boosting machine (GBMR) and multi-layer perceptron (MLP) regression by 15% and 6% in R2 metric, respectively. The feature importance ranking reveals that stop location, time of the day, temperature, and humidity are the key influencers of passenger arrival behaviour in Melbourne. Overall, this study contributes to the development of a model that accounts for multi-dimensional, high-resolution determinants of passenger demand using large-scale datasets from real world. The proposed Wasea-Lstm architecture shows exceptional performance in precisely forecasting stop-level demand for one of Melbourne's largest tram routes. Moreover, its applicability extends seamlessly to all routes within the network.
-
ItemNo Preview AvailableTraffic Anomaly Detection: Exploiting Temporal Positioning of Flow-Density Samples(Institute of Electrical and Electronics Engineers (IEEE), 2023)It is of paramount importance to detect traffic data anomalies in a real-time manner as it helps efficient traffic control and management. Several unsupervised anomaly detection algorithms are proposed previously in the literature; however, lack of proper ground truth labels for traffic data has been always a substantial barrier to deploy and evaluate them. In this paper, we introduce a concept named Temporal Positioning of Flow-Density Samples (TP-FDS) that can be used by domain experts for fast and reliable traffic data labeling. We mathematically show that deviations in two-dimensional TP-FDS completely reflect point and subsequence anomalies previously defined in the literature of time series data. Furthermore, benefiting from this concept, we propose a novel anomaly detection framework with the help of Fast Angle Based Outlier Detection (Fast-ABOD) to be used for traffic data. Extensive data labeling experiments are conducted with the opinions of 20 different experts. Implementation of several machine learning algorithms, like KNN, OC-SVM, iForest, and LOF, is also adapted with two different setups of hyper-parameters to be used in the proposed framework. Results indicate that our framework integrated with Fast-ABOD is able to detect anomalies in traffic data better than other machine learning and state-of-the-art deep learning algorithms with more than 72% and 96% of F1 score and AUC.
-
ItemCrowdshipping for sustainable urban logistics: A systematic review of the literature(Elsevier BV, 2023-10)Crowd-Shipping (CS) solutions have been gaining popularity in industry and academia. Despite numerous CS platforms having been introduced in the real world, only a limited number of them have managed to remain viable. Academics have explored many challenges facing CS platforms and recommended appropriate solution measures. While the growing literature sporadically indicates “economic”, “environmental” or even “societal” benefits of CS initiatives, there is a lack of systematic and conclusive understanding of CS initiatives from these essential “sustainability perspectives”. Considering that sustainability and societal impacts of such new and emerging initiatives are key factors in gaining public policy support and potential government investments and involvements, as critical success factors for the uptake, growth and continuity of these initiatives, this paper aims to present a review of this topic in light of sustainability considerations. A content-based framework grounded on the Triple Bottom Line (TBL) approach is adopted in this review and papers are reviewed, classified, synthesised, and analysed to reveal dominant research trends, challenges, potential and gaps. Furthermore, our analysis of the economic and behavioural considerations of CS actors reveals important insights into how various pricing strategies can be adopted to regulate supply and demand for operational continuity. Finally, using an intersectional sustainability approach, future research directions are also recommended to fill the gaps and improve the practical relevance of CS.
-
ItemTransferable supervised learning model for public transport service load estimation(Springer Science and Business Media LLC, 2023-07-28)Detailed knowledge of service utilisation and passenger load profiles is the basis for the design, operation, and adjustment of a public transport service. The advancement in sensing technologies enable transit operators to monitor the variabilities in passenger flows continuously and consistently. There is a growing body of literature on using supervised learning models with direct passenger counts from historical observations. However, the incomplete, inaccurate, and biased data from automatic sensors pose challenges in this process. This paper proposes novel supervised learning models to estimate the onboard load profile of public transport services based on two main data sources: (1) limited data collected on a subset of service vehicles by automatic passenger counting (APC) systems, and (2) fare data collected by automatic fare collection (AFC) systems. The specific consideration is given to the fact that the developed models can be transferred across different routes. This is motivated by the commonly “limited coverage” of automated passenger counter devices on service vehicles. We introduce an array of new models, including a superior segment-based model, which demonstrates remarkable improvement in model transferability and accuracy. The proposed methodology utilises separate methods in different segments of a transit line. The proposed models were applied to three tram lines in Melbourne, Australia, where various types of shortcomings exist in the automated data. The test results demonstrate that the proposed models can be transferred and applied to other transit route without relying on historical observations. This would enable transit operators to reduce the number of required devices and monitor service utilisation in a more cost-efficiently manner, particularly in public transport networks where AFC coverage is usually incomplete and negatively skewed. The information on service utilisation will not only help operators to accommodate the variability in passenger demand but also assist passengers in journey planning to avoid overcrowding on services.
-
ItemTemporal pattern mining of urban traffic volume data: a pairwise hybrid clustering method(Taylor and Francis Group, 2023)Multiple pattern analyses of traffic data have been conducted previously; however, it has yet to be explored with an awareness of temporal factors in big real-world traffic data. In this paper, we introduce a hybrid method to measure the intensity of differences among various temporal factors’ data. The proposed method can efficiently process the historical data given temporal factors and provide insightful information about the intensity of variations. After data denoising with basis splines, we reshape the time series into a 2-D latent space using Principal Component Analysis (PCA) according to the type of analysis. Pairwise K-means clustering is then applied after anomaly elimination with DBSCAN to derive Adjusted Rand Index (ARI) matrices. Finally, these matrices are then systematically used to find similar patterns of different temporal perspectives. Multiple analyses are carried out with real data from Melbourne, Australia. Dissimilarities with intensities of up to 80% are detected that are not detectable with general clustering approaches.
-
ItemNo Preview AvailableIntelligent vehicle pedestrian light (IVPL): A deep reinforcement learning approach for traffic signal control(PERGAMON-ELSEVIER SCIENCE LTD, 2023-04)Deep reinforcement learning (RL) has been widely studied in traffic signal control. Despite the promising results that indicate the superiority of deep RL in terms of the quality of solution and optimality over fixed time signal control, the real-world multi-modal traffic flows, especially pedestrians, are not properly considered nor sufficiently investigated. This study presents a novel deep RL-based adaptive traffic signal model to control the vehicles and pedestrian flows by allocating an equitable green time to each, aiming at minimizing “total user delays” as opposed to “total vehicle delays” dominantly being used in the literature. Our proposed intelligent vehicle pedestrian light (IVPL) method can perform in the absence or presence of pedestrians, especially when there is jaywalking at the intersection, interrupting vehicle flows. To this end, an extended reward function is designed to capture delays due to vehicle-to-vehicle, vehicle-to-pedestrian, and pedestrian-to-pedestrian interactions, as well as red-light delays for vehicles and pedestrians. To evaluate the performance of IVPL, a microsimulation model of an intersection in city of Melbourne is used as a case-study. The real traffic signal parameters of an existing operation system (SCATS) are employed, and the simulation is calibrated using video-based camera data and loop detectors data collected at intersection. The experimental results demonstrate the superiority of the proposed model over fully actuated traffic signal, not only in terms of the quality of optimal solution, but also considering the fact that the proposed model can minimize the “total user delays”.
-
ItemNo Preview AvailableValue of Intersection Cross Box Data in Traffic Signal Control(ITS World Congress, 2022)
-
ItemNo Preview AvailableA Graph and Attentive Multi-Path Convolutional Network for Traffic Prediction(Institute of Electrical and Electronics Engineers, 2022-06-02)Traffic prediction is an important and yet highly challenging problem due to the complexity and constantly changing nature of traffic systems. To address the challenges, we propose a graph and attentive multi-path convolutional network (GAMCN) model to predict traffic conditions such as traffic speed across a given road network into the future. Our model focuses on the spatial and temporal factors that impact traffic conditions. To model the spatial factors, we propose a variant of the graph convolutional network (GCN) named LPGCN to embed road network graph vertices into a latent space, where vertices with correlated traffic conditions are close to each other. To model the temporal factors, we use a multi-path convolutional neural network (CNN) to learn the joint impact of different combinations of past traffic conditions on the future traffic conditions. Such a joint impact is further modulated by an attention generated from an embedding of the prediction time, which encodes the periodic patterns of traffic conditions. We evaluate our model on real-world road networks and traffic data. The experimental results show that our model outperforms state-of-art traffic prediction models by up to 18.9% in terms of prediction errors and 23.4% in terms of prediction efficiency.