Using a heuristic approach to derive a grey-box model through an artificial neural network knowledge extraction technique

Abstract

Artificial neural networks (ANNs) are primarily used in academia for their ability to model complex nonlinear systems. Though ANNs have been used to solve practical problems in industry, they are not typically used in nonacademic environments because they are not very well understood, complicated to implement, or have the reputation of being a ''black-box'' model. Few mathematical models exist that outperform ANNs. If a highly accurate model can be constructed, the knowledge should be used to understand and explain relationships in a system. Output surfaces can be analyzed in order to gain additional knowledge about a system being modeled. This paper presents a systematic approach to derive a ''grey-box'' model from the knowledge obtained from the ANN. A database for an automobile's gas mileage performance is used as a case study for the proposed methodology. The results show a greater ability to generalize system behavior than other benchmarked methods.

Applying electromagnetism-like mechanism for feature selection

“…BPNN and LVQ belong to artificial neural networks that are black-box models [58]. The parameters in BPNN and LVQ have to be established through trial and error to minimize RMSE and this requires more operational time [26].…”

Modeling microalgal abundance with artificial neural networks: Demonstration of a heuristic ‘Grey-Box’ to deconvolve and quantify environmental influences

“…The chlorophyll (CHL) a concentration of a water column is a universally accepted measurement of planktonic algal abundance and used to quantify community dynamics and/or growth in changing environments (Millie et al, 2010). Here, we present a network-based approach e hereafter, referred to as a 'Grey-Box' (Young and Weckman, 2009; see Oussar and Dreyfus, 2001;Johannet et al, 2007), originating the iterative selection, depiction, and quantitation of environmental variable relationships in modeling water-column CHL a concentrations within a coastal environment. The Grey-Box formulation: 1) was based upon knowledge extracted from a trained and validated ANN; 2) provided interpretable, multi-dimensional response surfaces depicting modeled environmental-CHL a relationships; and 3) Fig.…”