Publications in Journals / Series (Conference paper / Meeting)

Multi-objective Learning of Neural Network Time Series Prediction Intervals

  • Lecture Notes in Computer Science, 10423 (EPIA 2017), 561-572, 2017

Publisher: Springer Verlag

Abstract

In this paper, we address multi-step ahead time series Prediction Intervals (PI). We extend two Neural Network (NN) methods, Lower Upper Bound Estimation (LUBE) and Multi-objective Evolutionary Algorithm (MOEA) LUBE (MLUBE), for multi-step PI. Furthermore, we propose two new MOEA methods based on a 2-phase gradient and MOEA based learning: M2LUBET1 and M2LUBET2. Also, we present a robust evaluation procedure to compare PI methods. Using four distinct seasonal time series, we compared all four PI methods. Overall, competitive results were achieved by the 2-phase learning methods, in terms of bo ...

CEB Authors

Groups

Citations

ISI Web of Science® Citations: 0

0

Share Content