Infrastructure Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 18
-
ItemApplication of Machine Learning to Ranking Predictors of Anti-VEGF Response(MDPI, 2022-11)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.
-
ItemEpistemic Uncertainties in the Assessment of Regional Soil Acidification(MDPI AG, 2022-08-01)The increasing acidification of soil due to pollution and agricultural management practices is a growing problem worldwide, where food production is already under threat by climate change, more frequent droughts, and soil nutrient depletion. Soil acidification is quantified by pH measurements and is a primary metric for soil health. High soil acidity is a constraint on the production of grains and other crops because it decreases the bioavailability of important plant nutrients while increasing soil toxicity arising from an imbalance of essential soil elements. Field pH can be estimated by colour test kits which are very cost-effective and particularly suitable for developing countries where laboratory services are not available or fail to provide timely results. Because the pH test kit is based on visual colour matching between a colour card scale and a soil sample in solution, there are epistemic uncertainties, such as variability in expert opinion, differences in colour vision, measurement error, instrumentation, and changes in daylight spectral content. In this study, expert human observers were compared in experiments conducted using a standard pH test kit under a range of environmental conditions. A significant difference in uncertainty in colour discrimination was evident between male and female experts, whereas changes in daylight conditions had lower impact on the variance of pH estimates. In a group of subject matter experts, the male standard error (0.35 pH) was 57% higher on average over the range of pH values (pH = 4 → 10) compared to females (0.22 pH). This error was largest (70%) in the low pH 4 to 6.5 range, which is a critical range for successful amelioration of soil acidification. The results suggest that historical database measurements may have hitherto unrecognised uncertainties that affect confidence intervals for experimental data that in turn will have an impact on predictive models and policy development.
-
ItemSegmentation of Visually Similar Textures by Convolution Filtering(Australian Computer Society, 1987-08-01)We describe an approach to texture segmentation designed for the extraction of a textured object from a textured background. The approach assumesthatno information is available on the objecttexture butthat a prior analysis ofthe background texture has been undertaken. The power ofthe approach is demonstrated on a texture composite for which object extraction and identification is almost impossible by visual inspection.
-
ItemDeep Learning Applied to Automated Segmentation of Geographic Atrophy in Fundus Autofluorescence Images.(Association for Research in Vision and Ophthalmology (ARVO), 2021-07-01)PURPOSE: This study describes the development of a deep learning algorithm based on the U-Net architecture for automated segmentation of geographic atrophy (GA) lesions in fundus autofluorescence (FAF) images. METHODS: Image preprocessing and normalization by modified adaptive histogram equalization were used for image standardization to improve effectiveness of deep learning. A U-Net-based deep learning algorithm was developed and trained and tested by fivefold cross-validation using FAF images from clinical datasets. The following metrics were used for evaluating the performance for lesion segmentation in GA: dice similarity coefficient (DSC), DSC loss, sensitivity, specificity, mean absolute error (MAE), accuracy, recall, and precision. RESULTS: In total, 702 FAF images from 51 patients were analyzed. After fivefold cross-validation for lesion segmentation, the average training and validation scores were found for the most important metric, DSC (0.9874 and 0.9779), for accuracy (0.9912 and 0.9815), for sensitivity (0.9955 and 0.9928), and for specificity (0.8686 and 0.7261). Scores for testing were all similar to the validation scores. The algorithm segmented GA lesions six times more quickly than human performance. CONCLUSIONS: The deep learning algorithm can be implemented using clinical data with a very high level of performance for lesion segmentation. Automation of diagnostics for GA assessment has the potential to provide savings with respect to patient visit duration, operational cost and measurement reliability in routine GA assessments. TRANSLATIONAL RELEVANCE: A deep learning algorithm based on the U-Net architecture and image preprocessing appears to be suitable for automated segmentation of GA lesions on clinical data, producing fast and accurate results.
-
ItemArtificial Intelligence and Telehealth may Provide Early Warning of Epidemics(FRONTIERS MEDIA SA, 2021)The COVID-19 pandemic produced a very sudden and serious impact on public health around the world, greatly adding to the burden of overloaded professionals and national medical systems. Recent medical research has demonstrated the value of using online systems to predict emerging spatial distributions of transmittable diseases. Concerned internet users often resort to online sources in an effort to explain their medical symptoms. This raises the prospect that incidence of COVID-19 may be tracked online by search queries and social media posts analyzed by advanced methods in data science, such as Artificial Intelligence. Online queries can provide early warning of an impending epidemic, which is valuable information needed to support planning timely interventions. Identification of the location of clusters geographically helps to support containment measures by providing information for decision-making and modeling.
-
ItemProgression of Geographic Atrophy: Epistemic Uncertainties Affecting Mathematical Models and Machine Learning(ASSOC RESEARCH VISION OPHTHALMOLOGY INC, 2021-11)PURPOSE: The purpose of this study was to identify a taxonomy of epistemic uncertainties that affect results for geographic atrophy (GA) assessment and progression. METHODS: An important source of variability is called "epistemic uncertainty," which is due to incomplete system knowledge (i.e. limitations in measurement devices, artifacts, and human subjective evaluation, including annotation errors). In this study, different epistemic uncertainties affecting the analysis of GA were identified and organized into a taxonomy. The uncertainties were discussed and analyzed, and an example was provided in the case of model structure uncertainty by characterizing progression of GA by mathematical modelling and machine learning. It was hypothesized that GA growth follows a logistic (sigmoidal) function. Using case studies, the GA growth data were used to test the sigmoidal hypothesis. RESULTS: Epistemic uncertainties were identified, including measurement error (imperfect outcomes from measuring tools), subjective judgment (grading affected by grader's vision and experience), model input uncertainties (data corruption or entry errors), and model structure uncertainties (elucidating the right progression pattern). Using GA growth data from case studies, it was demonstrated that GA growth can be represented by a sigmoidal function, where growth eventually approaches an upper limit. CONCLUSION: Epistemic uncertainties contribute to errors in study results and are reducible if identified and addressed. By prior identification of epistemic uncertainties, it is possible to (a) quantify uncertainty not accounted for by natural statistical variability, and (b) reduce the presence of these uncertainties in future studies. TRANSLATIONAL RELEVANCE: Lowering epistemic uncertainty will reduce experimental error, improve consistency and reproducibility, and increase confidence in diagnostics.
-
ItemImproving the information content in soil pH maps: a case study(WILEY, 2017-09)Summary Uncertainties associated with legacy data contribute to the spatial uncertainty of predictions for soil properties such as pH. Examples of potential sources of error in maps of soil pH include temporal variation and changes in land use over time. Prediction of soil pH can be improved with a linear mixed model (LMM) to analyse factors that contribute to uncertainty. Probabilities from conditional simulations in combination with agronomic critical thresholds for acid‐sensitive species can be used to identify areas that are likely, or very likely, to be below these critical thresholds for plant production. Because of rapid changes in farming systems and management practices, there is a need to be vigilant in monitoring changes in soil acidification. This is because soil acidification is an important factor in primary production and soil sustainability. In this research, legacy data from south‐western Victoria (Australia) were used with model‐based geostatistics to produce a map of soil pH that accommodates a variety of error sources, such as the time of sampling, seasonal variation, differences in analytical method, effects of changes in land use and variable soil sample depth in legacy data. Spatial covariates that are representative of soil‐forming factors were used to improve predictions. To transform spatial prediction and estimates of error in soil pH into more informative and usable maps with more information content, simulations from the conditional distribution were used to compute the probability of a soil's pH being less than critical agronomic production thresholds at each of the prediction locations. These probabilities were mapped to reveal areas of potential risk. Highlights Can maps of soil pH be improved by accounting for temporal variation and change in land use? First example of taking account of temporal variability in sampling for pH in spatial models. Key factors for uncertainty in spatial prediction include time of sampling and sample depth. Accuracy improved by accounting for additional sources of error combined with conditional simulations.
-
ItemEstimating global arthropod species richness: refining probabilistic models using probability bounds analysis(SPRINGER, 2013-02)A key challenge in the estimation of tropical arthropod species richness is the appropriate management of the large uncertainties associated with any model. Such uncertainties had largely been ignored until recently, when we attempted to account for uncertainty associated with model variables, using Monte Carlo analysis. This model is restricted by various assumptions. Here, we use a technique known as probability bounds analysis to assess the influence of assumptions about (1) distributional form and (2) dependencies between variables, and to construct probability bounds around the original model prediction distribution. The original Monte Carlo model yielded a median estimate of 6.1 million species, with a 90 % confidence interval of [3.6, 11.4]. Here we found that the probability bounds (p-bounds) surrounding this cumulative distribution were very broad, owing to uncertainties in distributional form and dependencies between variables. Replacing the implicit assumption of pure statistical independence between variables in the model with no dependency assumptions resulted in lower and upper p-bounds at 0.5 cumulative probability (i.e., at the median estimate) of 2.9-12.7 million. From here, replacing probability distributions with probability boxes, which represent classes of distributions, led to even wider bounds (2.4-20.0 million at 0.5 cumulative probability). Even the 100th percentile of the uppermost bound produced (i.e., the absolutely most conservative scenario) did not encompass the well-known hyper-estimate of 30 million species of tropical arthropods. This supports the lower estimates made by several authors over the last two decades.
-
Item
-
ItemIwao's patchiness regression through the origin: biological importance and efficiency of sampling applications(WILEY, 2014-04)Abstract Iwao's mean crowding‐mean density relation can be treated both as a linear function describing the biological characteristics of a species at a population level, or a regression model fitted to empirical data (Iwao's patchiness regression). In this latter form its parameters are commonly used to construct sampling plans for insect pests, which are characteristically patchily distributed or overdispersed. It is shown in this paper that modifying both the linear function and statistical model to force the intercept or lower functional limit through the origin results in more intuitive biological interpretation of parameters and better sampling economy. Firstly, forcing the function through the origin has the effect of ensuring that zero crowding occurs when zero individuals occupy a patch. Secondly, it ensures that negative values of the intercept, which do not yield an intuitive biological interpretation, will not arise. It is shown analytically that sequential sampling plans based on regression through the origin should be more efficient compared to plans based on conventional regression. For two overdispersed data sets, through‐origin based plans collected a significantly lower sample size during validation than plans based on conventional regression, but the improvement in sampling efficiency was not large enough to be of practical benefit. No difference in sample size was observed when through‐origin and conventional regression based plans were validated using underdispersed data. A field researcher wishing to adopt a through‐origin form of Iwao's regression for the biological reasons outlined above can therefore be confident that their sampling strategies will not be affected by doing so.