Search

In this paper we propose a machine learning-based approach to predict a multitude of insurance claim categories related to canine diseases. We introduce several machine learning approaches that are evaluated on a pet insurance dataset consisting of 785,565 dogs from the US and Canada whose insurance claims have been recorded over 17 years. 270,203 dogs with a long insurance tenure were used to train a model while the inference is applicable to all dogs in the dataset. Through this analysis we demonstrate that with this richness of data, supported by the right feature engineering, and machine learning approaches, 45 disease categories can be predicted with high accuracy. [ABSTRACT FROM AUTHOR]

The complexity of industrial processes imposes a lot of challenges in building accurate and representative causal models for abnormal events diagnosis, control and maintenance of equipment and process units. This paper presents an innovative data-driven causality modeling approach using interpretable machine learning and process mining techniques, in addition to human expertise, to efficiently and automatically capture the complex dynamics of industrial systems. The approach tackles a significant challenge in the causality analysis community, which is the discovery of high-level causal models from low-level continuous observations. It is based on the exploitation of event data logs by analyzing the dependency relationships between events to generate accurate multi-level models that can take the form of various state-event diagrams. Highly accurate and trustworthy patterns are extracted from the original data using interpretable machine learning integrated with a model enhancement technique to construct event data logs. Afterward, the causal model is generated from the event log using the inductive miner technique, which is one of the most powerful process mining techniques. The causal model generated is a Petri net model, which is used to infer causality between important events as well as a visualization tool for real-time tracking of the system's dynamics. The proposed causality modeling approach has been successfully tested based on a real industrial dataset acquired from complex equipment in a Kraft pulp mill located in eastern Canada. The generated causality model was validated by ensuring high model fitness scores, in addition to the process expert's validation of the results. [ABSTRACT FROM AUTHOR]

In response to calls for greater interdisciplinary involvement from the social sciences and humanities in the development, governance, and study of artificial intelligence systems, this paper presents one sociologist's view on the problem of algorithmic bias and the reproduction of societal bias. Discussions of bias in AI cover much of the same conceptual terrain that sociologists studying inequality have long understood using more specific terms and theories. Concerns over reproducing societal bias should be informed by an understanding of the ways that inequality is continually reproduced in society—processes that AI systems are either complicit in, or can be designed to disrupt and counter. The contrast presented here is between conservative and radical approaches to AI, with conservatism referring to dominant tendencies that reproduce and strengthen the status quo, while radical approaches work to disrupt systemic forms of inequality. The limitations of a conservative approach to racial bias are discussed through the specific example of biased criminal risk assessments and Indigenous overrepresentation in Canada's criminal justice system. This illustrates the dangers of treating racial bias as a generalizable problem and equality as a generalizable solution, emphasizing the importance of considering inequality in context. Societal issues can no longer be out of scope for AI and machine learning, given the impact of these systems on human lives. This requires engagement with a growing body of critical AI scholarship that goes beyond biased data to analyze structured ways of perpetuating inequality, opening up the possibility for interdisciplinary engagement and radical alternatives. [ABSTRACT FROM AUTHOR]

Offsite construction shifts construction work to the factory environment, enabling automation of traditionally manual operations. While this approach has proven to be advantageous for the construction industry in Canada, changes in the process of manufacturing panelized walls have brought new challenges and opportunities. With the aim of providing alternatives to current manual quality control activities, an automated vision-based online inspection system for screw-fastening operations in light-gauge steel frame manufacturing is proposed in this paper. Targeting two common defects in the framing process, squareness and the quality of the screw-fastening operation itself, real-time quality assessment of the frame is achieved. The proposed system uses novel machine vision algorithms to generate the inspection data: a squareness estimation algorithm is developed, based on edge detection and the Hough transform, that can determine the squareness of a steel connection with a margin of error less than two degrees, whereas a R-CNN is designed based on a pre-trained ResNet-50 for detection and classification of screw-fastening operations, achieving an overall accuracy of 91.67%. All the inspection results are made accessible through a Python-based interface in order to direct operators towards either identifying potential quality issues or confirming the quality of the product leaving the station. The inspection system is validated over a real frame in a semi-automated machine environment. In future work, the inspection system will be deployed in continuous production setups in order to further test its accuracy and applicability. [ABSTRACT FROM AUTHOR]

The current prostate cancer (PCa) screen test, prostate-specific antigen (PSA), has a high sensitivity for PCa but low specificity for high-risk, clinically significant PCa (csPCa), resulting in overdiagnosis and overtreatment of non-csPCa. Early identification of csPCa while avoiding unnecessary biopsies in men with non-csPCa is challenging. We built an optimized machine learning platform (ClarityDX) and showed its utility in generating models predicting csPCa. Integrating the ClarityDX platform with blood-based biomarkers for clinically significant PCa and clinical biomarker data from a 3448-patient cohort, we developed a test to stratify patients' risk of csPCa; called ClarityDX Prostate. When predicting high risk cancer in the validation cohort, ClarityDX Prostate showed 95% sensitivity, 35% specificity, 54% positive predictive value, and 91% negative predictive value, at a ≥ 25% threshold. Using ClarityDX Prostate at this threshold could avoid up to 35% of unnecessary prostate biopsies. ClarityDX Prostate showed higher accuracy for predicting the risk of csPCa than PSA alone and the tested model-based risk calculators. Using this test as a reflex test in men with elevated PSA levels may help patients and their healthcare providers decide if a prostate biopsy is necessary. [ABSTRACT FROM AUTHOR]

Many impact studies require climate change information at a finer resolution than that provided by global climate models (GCMs). This paper investigates the performances of existing state-of-the-art rule induction and tree algorithms, namely single conjunctive rule learner, decision table, M5 model tree, and REPTree, and explores the impact of climate change on maximum and minimum temperatures (i.e., predictands) of 14 meteorological stations in the Upper Thames River Basin, Ontario, Canada. The data used for evaluation were large-scale predictor variables, extracted from National Centers for Environmental Prediction/National Center for Atmospheric Research reanalysis dataset and the simulations from third generation Canadian coupled global climate model. Data for four grid points covering the study region were used for developing the downscaling model. M5 model tree algorithm was found to yield better performance among all other learning techniques explored in the present study. Hence, this technique was applied to project predictands generated from GCM using three scenarios (A1B, A2, and B1) for the periods (2046-2065 and 2081-2100). A simple multiplicative shift was used for correcting predictand values. The potential of the downscaling models in simulating predictands was evaluated, and downscaling results reveal that the proposed downscaling model can reproduce local daily predictands from large-scale weather variables. Trend of projected maximum and minimum temperatures was studied for historical as well as downscaled values using GCM and scenario uncertainty. There is likely an increasing trend for T and T for A1B, A2, and B1 scenarios while decreasing trend has been observed for B1 scenarios during 2081-2100. [ABSTRACT FROM AUTHOR]

Drug shortages are a global and complex issue having negative impacts on patients, pharmacists, and the broader health care system. Using sales data from 22 Canadian pharmacies and historical drug shortage data, we built machine learning models predicting shortages for the majority of the drugs in the most-dispensed interchangeable groups in Canada. When breaking drug shortages into four classes (none, low, medium, high), we were able to correctly predict the shortage class with 69% accuracy and a kappa value of 0.44, one month in advance, without access to any inventory data from drug manufacturers and suppliers. We also predicted 59% of the shortages deemed to be most impactful (given the demand for the drugs and the potential lack of interchangeable options). The models consider many variables, including the average days of a drug supply per patient, the total days of a drug supply, previous shortages, and the hierarchy of drugs within different drug groups and therapeutic classes. Once in production, the models will allow pharmacists to optimize their orders and inventories, and ultimately reduce the impact of drug shortages on their patients and operations. [ABSTRACT FROM AUTHOR]

Lake water quality plays a vital role in the lake ecosystem, including biotic (for living creatures, such as plants, animals, and micro-organisms) and abiotic interactions. In this research, various types of machine learning (ML) methodologies, such as classification and regression tree (CART), chi-squared automatic interaction detector (CHAID), C5 tree, quick, unbiased, and efficient statistical tree (QUEST), along with multilayer perceptron (MLP) neural network, and radial basis function (RBF) neural network, are employed to predict the concentration of water quality parameters (P, EC, TDS, pH, DO, NH3, SO4, and θ). Lake Erie is situated at the international border of the USA and Canada. The C5 tree and QUEST tree are used to classify data and predict the number of groups, while the other methods are used to predict the concentration of water quality parameters in the form of a 3-year moving average. The greater matching between the observed and predicted data of dissolved oxygen (NSE = 0.978, bias = 0.126) shows that the CART decision tree has higher accuracy in correctly detecting the concentration of this parameter. The C5 tree could identify 33 groups correctly out of 36 total groups, which shows better accuracy for the C5 tree in classifying the data for this parameter. [ABSTRACT FROM AUTHOR]

Accurate forecasting of runoff as an important hydrological variable is a key task for water resources planning and management. Given the importance of this variable, in the current study, a multivariate linear stochastic model (MLSM) is combined with a multilayer nonlinear machine learning model (MNMLM) to generate a hybrid model for the spatial and temporal simulation of runoff in the Quebec basin, Canada. Monthly hydrological data from 2001 to 2013, including precipitation and runoff data from nine stations and Normalized Difference Vegetation Index (NDVI) extraction of MODIS data, are applied as input to the proposed hybrid model. At the first step of the hybrid modeling, data normality and stationary were examined by performing various tests. In the second step, MLSM was developed by defining four different scenarios and as a result 15 sub-scenarios. The first and second scenarios were developed based on one exogenous variable (precipitation or NDVI). In contrast, the second and third scenarios were developed based on two additional variables. In the first and third scenarios, the data are modeled without preprocessing. In the second and fourth scenarios, a preprocessing step is performed on the data. Then, in the third step, various combinations based on different time delays from runoff data were applied for developing nonlinear model. The comparisons are made between observed and simulated time series at various stations and based on the root mean squared error (RMSE), mean absolute error (MAE), correlation coefficient (R) and Akaike information criterion (AIC). The efficiency of the proposed hybrid model is compared with a novel machine learning model that was introduced in 2021 by Sultani et al., and it was also compared with the results obtained from the linear and nonlinear models. In most stations, delays (t-1) and (t-24) are identified as the most effective delays in hybrid and nonlinear modeling of runoff. Also, in most stations, the use of climatic parameters and physiographic factors as exogenous variables along with runoff data improves the results compared to the use of one variable. Results showed that at all stations, proposed hybrid model generally leads to more accurate estimates of runoff compared with various linear and nonlinear models. More accurate estimates of peak runoff values at all stations were another excellence of proposed hybrid model than other models. [ABSTRACT FROM AUTHOR]

The volcanic-hosted massive sulfide (VHMS) deposits of the Bathurst Mining Camp have been significant contributors to Canada's historic Zn, Pb, Cu, and Ag production. Most of these deposits are hosted by the Tetagouche Group, many of which occur at the top of the Nepisiguit Falls Formation (footwall) along the contact with the conformably overlying Flat Landing Brook Formation (hanging wall), i.e., the Brunswick belt. Exploration along this prolific belt can benefit greatly from predictive modeling of prospectivity for VHMS deposits using machine learning (ML)-based mineral prospectivity mapping (MPM), which is the chief objective of this study. However, ML-aided MPM of this belt is faced with three challenges: (i) weak geochemical and geophysical signatures of VHMS deposits (i.e., poor predictor variables) owing to the complex tectono-stratigraphy of the host sequence and extensive glacial cover, (ii) over-fitting stemming from its limited number of VHMS deposits, and (iii) stochastic uncertainties of predictive models linked to the diversity in local geological settings of various VHMS deposits. This study adopted an ensemble regularized regression methodology combining ensemble modeling with LASSO, Ridge, and Elastic Net regularized regression techniques for addressing the above challenges. Herein, we demonstrate that the adopted framework can reduce the severity of over-fitting, handle poor predictor variables, and mitigate the effects of stochastic uncertainties in ML-based MPM. These results are followed by discussions of the pros and cons of the framework adopted in this study. [ABSTRACT FROM AUTHOR]

New 'big data' streams such as street-level imagery are offering unprecedented possibilities for developing health-relevant data on the urban environment. Urban environmental features derived from street-level imagery have been used to assess pedestrian-friendly neighbourhood design and to predict active commuting, but few such studies have been conducted in Canada. Using 1.15 million Google Street View (GSV) images in seven Canadian cities, we applied image segmentation and object detection computer vision methods to extract data on persons, bicycles, buildings, sidewalks, open sky (without trees or buildings), and vegetation at postal codes. The associations between urban features and walk-to-work rates obtained from the Canadian Census were assessed. We also assessed how GSV-derived urban features perform in predicting walk-to-work rates relative to more widely used walkability measures. Results showed that features derived from street-level images are better able to predict the percent of people walking to work as their primary mode of transportation compared to data derived from traditional walkability metrics. Given the increasing coverage of street-level imagery around the world, there is considerable potential for machine learning and computer vision to help researchers study patterns of active transportation and other health-related behaviours and exposures. [ABSTRACT FROM AUTHOR]

Seven artificial neural network (ANN) models were developed to predict daytime actual evapotranspiration (ET) for Nissouri Creek in Oxford County, Canada, from April to July 2018, using the Bowen ratio energy balance method as target output for the first time. In total, 12 variations of each model were deployed using different combinations of model parameters, including the sigmoid and rectified linear unit (ReLU) activation functions, stochastic gradient descent (SGD), and root-mean-square-propagation (RMSprop) learning algorithms, three different network architectures, and 100 and 500 training epochs. This is the first time that ReLU has been used in ANNs that predict ET and it outperformed sigmoid in six of the seven models. This is particularly significant because until now the sigmoid activation function (or variations therein) had been exclusively employed in the ET literature. RMSprop was also used for the first time and typically demonstrated equivalent performance to that of SGD. The optimal model employs the ReLU activation function, consists of a 4-4-1 network architecture, includes the input parameters of net radiation, air temperature, soil heat flux, and wind speed, and is trained by the SGD learning algorithm for 500 training epochs. This model boasts a coefficient of determination (R2) of 0.997, root-mean-square error (RMSE) of 0.39 mm/day, and mean absolute error (MAE) of 0.18 mm/day. Furthermore, all seven models developed adequately model the ET process, with R2 ranging from 0.988 to 0.997, RMSE from 0.39 to 0.78 mm/day, and MAE from 0.18 to 0.58 mm/day. [ABSTRACT FROM AUTHOR]