Infrastructure Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 1242
-
ItemNo Preview AvailableExploring the role and decision-making behavior of irrigation water supply authorities in Australia(ROUTLEDGE JOURNALS, TAYLOR & FRANCIS LTD, 2021-11-07)
-
ItemPrivacy- and context-aware release of trajectory data(ACM, 2020-03)The availability of large-scale spatio-temporal datasets along with the advancements in analytical models and tools have created a unique opportunity to create valuable insights into managing key areas of society from transportation and urban planning to epidemiology and natural disasters management. This has encouraged the practice of releasing/publishing trajectory datasets among data owners. However, an ill-informed publication of such rich datasets may have serious privacy implications for individuals. Balancing privacy and utility, as a major goal in the data exchange process, is challenging due to the richness of spatio-temporal datasets. In this article, we focus on an individual's stops as the most sensitive part of the trajectory and aim to preserve them through spatio-temporal perturbation. We model a trajectory as a sequence of stops and moves and propose an efficient algorithm that either substitutes sensitive stop points of a trajectory with moves from the same trajectory or introduces a minimal detour if no safe Point of Interest (POI) can be found on the same route. This hinders the amount of unnecessary distortion, since the footprint of the original trajectory is preserved as much as possible. Our experiments shows that our method balances user privacy and data utility: It protects privacy through preventing an adversary from making inferences about sensitive stops while maintaining a high level of similarity to the original dataset.
-
ItemDetecting and explaining long-term changes in river water quality in south-eastern Australia(WILEY, 2022-11-01)Abstract Understanding the temporal changes in river water quality is important for catchment water quality management. This study aims to detect and attribute long‐term trends and abrupt changes in river water quality. We used 26 years of water quality data (1994–2020) collected from 102 river monitoring sites across Victoria, south‐eastern Australia. We analysed six water quality constituents that are of key concerns for Australian catchment management, namely: electrical conductivity (EC), total suspended solids, nitrate‐nitrite, total Kjeldahl nitrogen, total phosphorous and filtered reactive phosphorus. To detect trends and abrupt changes in water quality at each site, a Bayesian ensemble modelling approach was applied, namely, the Bayesian estimator of abrupt change, seasonal change, and trend (BEAST). To explain water quality trends, we then built multivariate regressions to link water quality with streamflow and seasonality, and then compared alternative model structures with and without a change in the regression relationships informed by the changes detected by BEAST. Among the six constituents studied, EC shows the most distinct systematic trends, with 21 sites having a significant increase followed by a non‐significant trend; within the 21 sites, 14 had a significant change point in EC around Year 2010. The regression analyses between water quality and streamflow suggested that the observed systematic change in EC could be largely related to reduced streamflow during the Millennium drought, which greatly impacted the climate and hydrology of south‐eastern Australia over the first decade of 2000. The results of this study can help inform the design of effective mitigation strategies and avoid further degradation of water quality across Victoria. Besides, our trend analysis and attribution approaches are applicable to water quality time series in other regions for robust trend analysis and change point detection.
-
ItemThe carbon footprint of treating patients with septic shock in the intensive care unit(College of Intensive Care Medicine of Australia and New Zealand, 2018-12-01)OBJECTIVE: To use life cycle assessment to determine the environmental footprint of the care of patients with septic shock in the intensive care unit (ICU). DESIGN, SETTING AND PARTICIPANTS: Prospective, observational life cycle assessment examining the use of energy for heating, ventilation and air conditioning; lighting; machines; and all consumables and waste associated with treating ten patients with septic shock in the ICU at BarnesJewish Hospital, St. Louis, MO, United States (US-ICU) and ten patients at Footscray Hospital, Melbourne, Vic, Australia (Aus-ICU). MAIN OUTCOME MEASURES: Environmental footprint, particularly greenhouse gas emissions. RESULTS: Energy use per patient averaged 272 kWh/day for the US-ICU and 143 kWh/day for the Aus-ICU. The average daily amount of single-use materials per patient was 3.4 kg (range, 1.0-6.3 kg) for the US-ICU and 3.4 kg (range, 1.2-8.7 kg) for the Aus-ICU. The average daily particularly greenhouse gas emissions arising from treating patients in the US-ICU was 178 kg carbon dioxide equivalent (CO2-e) emissions (range, 165-228 kg CO2-e), while for the Aus-ICU the carbon footprint was 88 kg CO2-e (range, 77-107 kg CO2-e). Energy accounted for 155 kg CO2-e in the US-ICU (87%) and 67 kg CO2-e in the Aus-ICU (76%). The daily treatment of one patient with septic shock in the US-ICU was equivalent to the total daily carbon footprint of 3.5 Americans' CO2-e emissions, and for the Aus-ICU, it was equivalent to the emissions of 1.5 Australians. CONCLUSION: The carbon footprints of the ICUs were dominated by the energy use for heating, ventilation and air conditioning; consumables were relatively less important, with limited effect of intensity of patient care. There is large opportunity for reducing the ICUs' carbon footprint by improving the energy efficiency of buildings and increasing the use of renewable energy sources.
-
ItemPrediction of the post-failure behavior of rocks: Combining artificial intelligence and acoustic emission sensing(WILEY, 2022-07)Abstract Acoustic emission (AE) reading is among the most common methods for monitoring the behavior of brittle materials such as rock and concrete. This study uses discrete element method (DEM) simulations to explore the correlations between the pre‐failure AE readings with the post‐failure behavior and residual strength of rock masses. The deep learning (DL) method based on long short‐term memory (LSTM) algorithms has been applied to generate predictive models based on the data from DEM simulations of biaxial compression. The dataset has been populated by varying interparticle friction while keeping bond cohesion constant. Various configurations of the LSTM algorithm were evaluated considering different scenarios for input features (strain, stress, and AE energy records) and a range of values for the key hyperparameters. The prime AI models show promising accuracy in predicting residual strength decay with strain based on pre‐failure patterns in AE readings. The results indicate that the pre‐failure AE indeed encapsulates information about the developing failure mechanisms and the post‐failure response in rocks, which can be captured through artificial intelligence.
-
ItemQuantitative contribution of the Grain for Green Program to vegetation greening and its spatiotemporal variation across the Chinese Loess Plateau(WILEY, 2022-07-15)Abstract A distinct greening trend is evident in Asia, especially on the Loess Plateau (LP) of China, which is driven by climate change and large‐scale land‐use‐related ecological projects, especially the 'Grain for Green Program' (GFGP). However, the specific contributions of the GFGP to vegetation greening and the variation of this greening on a large spatiotemporal scale are not yet clear. We used long‐time‐series normalized difference vegetation index datasets and climate datasets based on the double mass curve method to quantify the contributions of ecological projects and climate change to the greening trend on the LP. We found that the interannual fluctuation of vegetation change was likely related to the interannual fluctuation of climate, especially precipitation. The increasing trend of vegetation change after 2005 indicated that the GFGP, as a type of external disturbance, began to improve vegetation growth. The GFGP failed initially to make a positive contribution in the first few years because of the drought conditions in 1999 and 2005. The increased precipitation played a critical role in enhancing the output of the GFGP on the LP after 2005. Then, the contribution of the GFGP increased quickly until 2013, after which it remained stable and reached average values of 58.8% ± 19.34% and 31.7% ± 24.3% in the representative areas that conducted the GFGP and in other regions with a lower implementation intensity of the GFGP, respectively. Our results highlight the contribution the GFGP has made to spatiotemporal variation due to the spatial heterogeneity of the projects, their intensity and the effect of forest stand age.
-
ItemModeling consolidation of soft clay by developing a fractional differential constitutive model in conjunction with an intelligent displacement inversion method(PUBLIC LIBRARY SCIENCE, 2022-09-30)Studying the constitutive relation of soft clays is of critical importance for fundamentally understanding their complex consolidation behavior. This study proposes a fractional differential constitutive model in conjunction with an intelligent displacement inversion method based on the classic particle swarm optimization for modeling the deformation behavior of soft clay. The model considered the rheological properties of soft clay at different consolidation stages. In addition, statistical adaptive dynamic particle swarm optimization-least squares support vector machines were implemented to identify the model parameters efficiently. The accuracy and effectiveness of the model were validated using available experimental results. Finally, the application results showed that the proposed model could efficiently simulate coupling properties of soft clay's primary and secondary consolidations.
-
ItemModelling attenuation of irregular wave fields by artificial ice floes in the laboratory(ROYAL SOC, 2022-10-31)A summary is given on the utility of laboratory experiments for gaining understanding of wave attenuation in the marginal ice zone, as a complement to field observations, theory and numerical models. It is noted that most results to date are for regular incident waves, which, combined with the highly nonlinear wave-floe interaction phenomena observed and measured during experimental tests, implies that the attenuation of regular waves cannot necessarily be used to infer the attenuation of irregular waves. Two experiments are revisited in which irregular wave tests were conducted but not previously reported, one involving a single floe and the other a large number of floes, and the transmission coefficients for the irregular and regular wave tests are compared. The transmission spectra derived from the irregular wave tests agree with the regular wave data but are overpredicted by linear models due to nonlinear dissipative processes, regardless of floe configuration. This article is part of the theme issue 'Theory, modelling and observations of marginal ice zone dynamics: multidisciplinary perspectives and outlooks'.
-
ItemPedestrian Origin-Destination Estimation Based on Multi-Camera Person Re-Identification(MDPI, 2022-10)Pedestrian origin-destination (O-D) estimates that record traffic flows between origins and destinations, are essential for the management of pedestrian facilities including pedestrian flow simulation in the planning phase and crowd control in the operation phase. However, current O-D data collection techniques such as surveys, mobile sensing using GPS, Wi-Fi, and Bluetooth, and smart card data have the disadvantage that they are either time consuming and costly, or cannot provide complete O-D information for pedestrian facilities without entrances and exits or pedestrian flow inside the facilities. Due to the full coverage of CCTV cameras and the huge potential of image processing techniques, we address the challenges of pedestrian O-D estimation and propose an image-based O-D estimation framework. By identifying the same person in disjoint camera views, the O-D trajectory of each identity can be accurately generated. Then, state-of-the-art deep neural networks (DNNs) for person re-ID at different congestion levels were compared and improved. Finally, an O-D matrix based on trajectories was generated and the resident time was calculated, which provides recommendations for pedestrian facility improvement. The factors that affect the accuracy of the framework are discussed in this paper, which we believe could provide new insights and stimulate further research into the application of the Internet of cameras to intelligent transport infrastructure management.
-
ItemApplication of Machine Learning to Ranking Predictors of Anti-VEGF Response.(MDPI AG, 2022-11-18)Age-related macular degeneration (AMD) is a heterogeneous disease affecting the macula of individuals and is a cause of irreversible vision loss. Patients with neovascular AMD (nAMD) are candidates for the anti-vascular endothelial growth factor (anti-VEGF) treatment, designed to regress the growth of abnormal blood vessels in the eye. Some patients fail to maintain vision despite treatment. This study aimed to develop a prediction model based on features weighted in order of importance with respect to their impact on visual acuity (VA). Evaluations included an assessment of clinical, lifestyle, and demographic factors from patients that were treated over a period of two years. The methods included mixed-effects and relative importance modelling, and models were tested against model selection criteria, diagnostic and assumption checks, and forecasting errors. The most important predictors of an anti-VEGF response were the baseline VA of the treated eye, the time (in weeks), treatment quantity, and the treated eye. The model also ranked the impact of other variables, such as intra-retinal fluid, haemorrhage, pigment epithelium detachment, treatment drug, baseline VA of the untreated eye, and various lifestyle and demographic factors. The results identified variables that could be targeted for further investigation in support of personalised treatments based on patient data.