Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

Understanding the determinants on household electricity consumption in Korea: OLS regression and quantile regression

The paper aims to investigate the determinants of household electricity consumption in Korea by using both the OLS regression and quantile regression. The results show that the effects of socio-demographic, dwelling, and electricity consumption characteristics on household electricity consumption may differ between two regressions and may differ across quantiles. We found that age group of household head, number of household, housing area, the number of household appliances, and refrigerator usage time were significant in all quantiles.     

Modeling Regression Quantile Process Using Monotone B-Splines

Quantile regression as an alternative to conditional mean regression (i.e., least-square regression) is widely used in many areas. It can be used to study the covariate effects on the entire response distribution by fitting quantile regression models at multiple different quantiles or even fitting the entire regression quantile process. However, estimating the regression quantile process is inherently difficult because the induced conditional quantile function needs to be monotone at all covariate values. In this article, we proposed a regression quantile process estimation method based on monotone B-splines. The proposed method can easily ensure the validity of the regression quantile process and offers a concise framework for variable selection and adaptive complexity control. We thoroughly investigated the properties of the proposed procedure, both theoretically and numerically. We also used a case study on wind power generation to demonstrate its use and effectiveness in real problems. Supplementary materials for this article are available online.     

Forecasting financial time series volatility using Particle Swarm Optimization trained Quantile Regression Neural Network

Accurate forecasting of volatility from financial time series is paramount in financial decision making. This paper presents a novel, Particle Swarm Optimization (PSO)-trained Quantile Regression Neural Network namely PSOQRNN, to forecast volatility from financial time series. We compared the effectiveness of PSOQRNN with that of the traditional volatility forecasting models, i.e., Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and three Artificial Neural Networks (ANNs) including Multi-Layer Perceptron (MLP), General Regression Neural Network (GRNN), Group Method of Data Handling (GMDH), Random Forest (RF) and two Quantile Regression (QR)-based hybrids including Quantile Regression Neural Network (QRNN) and Quantile Regression Random Forest (QRRF). The results indicate that the proposed PSOQRNN outperformed these models in terms of Mean Squared Error (MSE), on a majority of the eight financial time series including exchange rates of USD versus JPY, GBP, EUR and INR, Gold Price, Crude Oil Price, Standard and Poor 500 (S&P 500) Stock Index and NSE India Stock Index considered here. It was corroborated by the Diebold–Mariano test of statistical significance. It also performed well in terms of other important measures such as Directional Change Statistic (Dstat) and Theil's Inequality Coefficient. The superior performance of PSOQRNN can be attributed to the role played by PSO in obtaining the better solutions. Therefore, we conclude that the proposed PSOQRNN can be used as a viable alternative in forecasting volatility.     

Use of a quantile regression based echo state network ensemble for construction of prediction Intervals of gas flow in a blast furnace

The usual huge fluctuations in the blast furnace gas (BFG) generation make the scheduling of the gas system become a difficult problem. Considering that there are high level noises and outliers mixed in original industrial data, a quantile regression-based echo state network ensemble (QR-ESNE) is modeled to construct the prediction intervals (PIs) of the BFG generation. In the process of network training, a linear regression model of the output matrix is reported by the proposed quantile regression to improve the generalization ability. Then, in view of the practical demands on reliability and further improving the prediction accuracy, a bootstrap strategy based on QR-ESN is designed to construct the confidence intervals and the prediction ones via combining with the regression models of various quantiles. To verify the performance of the proposed method, the practical data coming from a steel plant are employed, and the results indicate that the proposed method exhibits high accuracy and reliability for the industrial data. Furthermore, an application software system based on the proposed method is developed and applied to the practice of this plant.     

Estimating probabilistic fatigue of Nitinol with scarce samples

Current work estimates probabilistic fatigue life efficiently with scarce samples. The underlying idea of the estimation is to approximate the cumulative distribution function of the fatigue life in a transformed space using a third order polynomial subject to monotonicity constraint. The variations associated with the estimated quantiles are quantified using bootstrap. The proposed approach is validated on a data obtained from literature. It is observed that the life quantiles with reasonable accuracy can be estimated even with 10 samples. Finally, the probabilistic fatigue of Nitinol in austenitic condition is obtained with limited experiments.     

Quantile autoregression neural network model with applications to evaluating value at risk

We develop a new quantile autoregression neural network (QARNN) model based on an artificial neural network architecture. The proposed QARNN model is flexible and can be used to explore potential nonlinear relationships among quantiles in time series data. By optimizing an approximate error function and standard gradient based optimization algorithms, QARNN outputs conditional quantile functions recursively. The utility of our new model is illustrated by Monte Carlo simulation studies and empirical analyses of three real stock indices from the Hong Kong Hang Seng Index (HSI), the US S&P500 Index (S&P500) and the Financial Times Stock Exchange 100 Index (FTSE100).     

Identifying crash-prone locations with quantile regression

Identifying locations that exhibit the greatest potential for safety improvements is becoming more and more important because of competing needs and a tightening safety improvement budget. Current crash modeling practices mainly target changes at the mean level. However, crash data often have skewed distributions and exhibit substantial heterogeneity. Changes at mean level do not adequately represent patterns present in the data. This study employs a regression technique known as the quantile regression. Quantile regression offers the flexibility of estimating trends at different quantiles. It is particularly useful for summarizing data with heterogeneity. Here, we consider its application for identifying intersections with severe safety issues. Several classic approaches for determining risk-prone intersections are also compared. Our findings suggest that relative to other methods, quantile regression yields a sensible and much more refined subset of risk-prone locations.     

Asymmetric inter-linkages between green technology innovation and consumption-based carbon emissions in BRICS countries using quantile-on-quantile framework

The role of reliable Carbon emission measures and relevant climate policy is imperative in realizing Sustainable Development Goals. A large extent of the literature concludes the emissions-mitigating effect of green innovations in a linear framework and ignored structural changes, technological revolutions, and socio-economic reforms that create non-linearity. Apart from that, there is a murky relationship between emissions and green innovation, where two-way links exist between both variables. Therefore, this study draws the inter-linkages between green technology innovation (GI) and carbon emissions (consumption-based and terrestrial emissions) in BRICS countries using monthly data from 1990 to 2017. Our preliminary findings strictly reject the preposition of data normality and highlight that the observed relationship is quantile-dependent. Therefore, a complete set of non-linear modeling is employed that included; Quantile unit root, Quantile cointegration, Quantile causality, and Quantile on Quantile regression to unveil hidden unit root, cointegration, causality, and association between variables. The results exhibit that the emissions-mitigating effect of GI is only pronounced at higher emissions quantiles in Brazil, China, India, and Russia, whereas at lower emissions quantile, GI is weekly or positively linked with carbon emissions. On the flipside, higher carbon emissions instigate GI across medium to higher emissions quantiles in Brazil, China, and India. Unlike them, Russia produces different outcomes, where higher emissions are associated with lower GI across all quantiles. The overall results suggest that GI (carbon emissions) mitigate (instigate) carbon emissions (GI) when a country is embodied with higher level of emissions.