No abstract

The current paper presents a novel method for reducing a multiclass confusion matrix into a 2×2 version enabling the exploitation of the relevant performance metrics and methods such as the receiver operating characteristic and area under the curve for the assessment of different classification algorithms. The reduction method is based on class grouping and leads to a special type of matrix called the reduced confusion matrix. The developed method is then exploited for the assessment of state of the art machine learning algorithms applied on the net promoter score classification problem in the field of customer experience analytics indicating the value of the proposed method in real world classification problems.

No abstract

Accurate prediction of the seawater intrusion extent is necessary for many applications, such as groundwater management or protection of coastal aquifers from water quality deterioration. However, most applications require a large number of simulations usually at the expense of prediction accuracy. In this study, the Gaussian process regression method is investigated as a potential surrogate model for the computationally expensive variable density model. Gaussian process regression is a nonparametric kernel-based probabilistic model able to handle complex relations between input and output. In this study, the extent of seawater intrusion is represented by the location of the 0.5 kg/m3 iso-chlore at the bottom of the aquifer (seawater intrusion toe). The initial position of the toe, expressed as the distance of the specific line from a number of observation points across the coastline, along with the pumping rates are the surrogate model inputs, whereas the final position of the toe constitutes the output variable set. The training sample of the surrogate model consists of 4000 variable density simulations, which differ not only in the pumping rate pattern but also in the initial concentration distribution. The Latin hypercube sampling method is used to obtain the pumping rate patterns. For comparison purposes, a number of widely used regression methods are employed, specifically regression trees and Support Vector Machine regression (linear and nonlinear). A Bayesian optimization method is applied to all the regressors, to maximize their efficiency in the prediction of seawater intrusion. The final results indicate that the Gaussian process regression method, albeit more time consuming, proved to be more efficient in terms of the mean absolute error (MAE), the root mean square error (RMSE), and the coefficient of determination (R2).

Dam break studies consist of two submodels: a) the dam breach submodel which derives the flood hydrograph and b) the hydrodynamic submodel which, using the flood hydrograph, derives the flood peaks and maximum water depths in the downstream reaches of the river. In this paper, a thorough investigation of the uncertainty observed in the output of the hydrodynamic model, due to the seven dam breach parameters, is performed in a real-world case study (Papadiana Dam, located at Tavronitis River in Crete, Greece). Three levels of uncertainty are examined (flow peak of the flood hydrograph at the dam location, flow peaks and maximum water depths downstream along the river) with two methods: a) a Morris-based sensitivity analysis for investigating the influence of each parameter on the final results; b) a Monte Carlo-based forward uncertainty analysis for defining the distribution of uncertainty band and its statistical characteristics. Among others, it is found that uncertainty of the flow peaks is greater than the uncertainty of the maximum water depths, whereas there is a decreasing trend of uncertainty as we move downstream along the river.