In this work we propose a novel solution for 3D skeleton-based human motion prediction. The objective of task consists in forecasting future poses based on prior skeleton pose sequence. This involves solving two main challenges still present recent literature; (1) discontinuity the predicted which results unrealistic motions and (2) performance deterioration long-term horizons resulting from er...

Abstract It is evident that developing more accurate forecasting methods the pillar of building robust multi-energy systems (MES). In this context, long-term also indispensable to have a expansion planning program for modern power systems. While very short-term and are usually represented with point estimation, approach highly unreliable in medium-term due inherent uncertainty predictors like w...

We analyse the out-of-sample forecasting ability of a time-varying metric risk aversion for entire term structure US Treasury securities as reflected by three latent factors, level, slope and curvature. Daily data cover period 22nd June 1988 to 3rd September 2020 within quantiles-based framework. The results show statistically significant gains emanating from inclusion tails conditional distrib...

Long term power load has a big impact on the development of industry of power. The forecasting models of linear systems even a single forecasting model of the nonlinear systems can not forecast the long term power load greatly. In the study, the combined forecasting model of nonlinear systems including chaos and fractal was established to improve the accuracy of the forecast. First, the charact...

Abstract This paper incorporates the Baidu Index into various heterogeneous autoregressive type time series models and shows that is a superior predictor of realized volatility in SSE 50 Index. Furthermore, predictability found to rise as forecasting horizon increases. We also find continuous components enhance predictive power across all horizons, but increases are only sustained short medium ...

With an uninterrupted power supply to the consumer, it is obligatory balance electricity generated by load. The effective planning of economic dispatch, reserve requirements, and quality provision for accurate consumer information concerning load needed. burden on system engineers eased forecasting essential ensure enhanced operation reliable provision. Fickle nature, atmospheric parameters inf...

Accurate electricity price forecasting plays an important role in the profits of electricity market participants and the healthy development of electricity market. However, the electricity price time series hold the characteristics of volatility and randomness, which make it quite hard to forecast electricity price accurately. In this paper, a novel hybrid model for electricity price forecastin...

The least squares estimation method as well as other ordinary estimation method for regression models can be severely affected by a small number of outliers, thus providing poor out-ofsample forecasts. This paper suggests a robust regression approach, based on the S-estimation method, to construct forecasting models that are less sensitive to data contamination by outliers. A robust linear auto...

Short term load forecasting (STLF) plays an important role in the economic and reliable operation ofpower systems. Electric load demand has a complex profile with many multivariable and nonlineardependencies. In this study, recurrent neural network (RNN) architecture is presented for STLF. Theproposed model is capable of forecasting next 24-hour load profile. The main feature in this networkis ...