HYBRIDIZATION OF ARTIFICIAL NEURAL NETWORK USING DESIRABILITY FUNCTIONS FOR PROCESS OPTIMIZATION

Journal Title: International Journal for Quality Research - Year 2010, Vol 4, Issue 1

Abstract

As desirability functions, proposed by many authors, follow most of the properties of standard transfer functions used for ANN, the objective of hybridsation in this study is to make use the property of desirability function in the neural network architecture and evaluate their performances while training and optimizing the architecture for an inputoutput relationship including the concept of composite desirability optimization technique when multiple responses are present. Two important desirability functions, proposed by Harrington, 1965 and Gatza et al., 1972 are used in different combinations with the most useful tan-hyperbolic transfer function using real life data. Three useful hybrid combinations oftransfer/desirability functions are observed based on consistent simulation performance, number of nodes and a new measure of composite MSE is proposed here. The work on incorporating the knowledge of composite desirability into ANN architecture and exploiting the non-linearity in inputs versus outputs during normalization is also attempted.

Authors and Affiliations

Prasun Das

Keywords

Related Articles

Chlorophyll Biodegradation Products from Hamamelis Virgianana Autumnal Leaves

The biodegradation of bioorganic solid waste involves several million tons of senescent plant leaves every autumn. Chemical evidence about bioorganic matter contained in the senescent leaves remains undetermined. The bio...

VALIDATING QUALITY PROCESS MANAGEMENT INSTRUMENT FOR HIGHER EDUCATION USING STRUCTURAL EQUATION MODELLING

This study attempts to validate process management scale using rigorous validation procedures. An adapted questionnaire comprising 77 items was administered to faculty members in two public universities in Nigeria. The d...

ESTIMATION OF PROCESSES REALIZATION RISK AS A MANNER OF SAFETY MANAGEMENT IN THE INTEGRATED SYSTEMS

Realization of quality, environmental and occupational health and safety policy using the proposed model of processes’ integrated risk estimation leads to the improvement of the analyzed productive processes by the preve...

IDENTIFICATION AND TRACKING COSTS IN ORGANIZATION

Lake Skadar is located on the Yugoslav-Albanian border. The lake is the largest at the Balkan and has a surface area which fluctuates seasonally from 370 to 600 km2. Although its precise origin is unknown, the lake proba...

UTILIZATION OF QUALITY MANAGERIAL SYSTEMS IN BUSINESS ENTITIES IN THE SLOVAK REPUBLIC

Current global trends force businesses to enhance their competitiveness via quality, innovations, leaning of production processes and shortening of production cycles, development of employees and satisfying of customer’s...

Download PDF file
  • EP ID EP256742
  • DOI -
  • Views 87
  • Downloads 0

How To Cite

Prasun Das (2010). HYBRIDIZATION OF ARTIFICIAL NEURAL NETWORK USING DESIRABILITY FUNCTIONS FOR PROCESS OPTIMIZATION. International Journal for Quality Research, 4(1), 37-50. https://europub.co.uk/articles/-A-256742