Folded normal distribution

Some Useful Concepts of Univariate and Multivariate Statistics

Published in Ashis Kumar Chakraborty, Moutushi Chatterjee, Handbook of Multivariate Process Capability Indices, 2021

Ashis Kumar Chakraborty, Moutushi Chatterjee

Another very useful statistical distribution is folded normal distribution. It originates when, for example, the actual algebraic signs of the observations, coming from a normal distribution, are ignored or irretrievably lost. Leone [32] has enlisted the following examples of folded normal distribution: When an object is placed convex side up and while measuring its flatness, a feeler gauge is used to find the difference between the surface plate and the object. The flatness, thus measured, follows folded normal distribution.Measurement of straightness of miniature radio tube leads.Distance between two objects.In all the above cases, the algebraic signs of the measurement become redundant. If the original measurement values follow normal distribution, then these absolute values will follow folded normal distribution;

A multi-objective reinforcement learning approach for resequencing scheduling problems in automotive manufacturing systems

View Article

Journal Information

Published in International Journal of Production Research, 2023

Jinling Leng, Xingyuan Wang, Shiping Wu, Chun Jin, Meng Tang, Rui Liu, Alexander Vogl, Huiyu Liu

Second, MRSP is described as a Multi-objective Markov Decision Process (MOMDP) and a MORL-based MODQN algorithm is proposed to obtain the Pareto frontier set from a multi-policy network. A MODQN agent implements a shaped reward and preference generation approach that obeys a two-dimensional folded normal distribution (2dFND) to minimize the CC and ST of the MRSP.

Folded normal distribution

Explore chapters and articles related to this topic

Some Useful Concepts of Univariate and Multivariate Statistics

A multi-objective reinforcement learning approach for resequencing scheduling problems in automotive manufacturing systems