Non Linear Process Identification Using a Neural Network Based Multiple Models Generator

Madani, Kurosh; Rybnik, Mariusz; Chebira, Abdennasser

doi:10.1007/3-540-44869-1_82

Cited by 8 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first one, described in [9] and [10], takes advantage from a weighted contribution of several local models. Figure 1 gives the general bloc diagram of this kind of modular connectionist systems.…”

Section: Fig 1 -General Bloc Diagram Of Weighted Contribution Based Modular Connectionist Systemmentioning

confidence: 99%

“…In fact, in this approach, the number of local models (modules), the "contribution rate" (called also "activation degree", setting the contribution degree of each local model in whole modular system's output), local models' natures and other parameters are adjusted in order to minimize either the whole modular system's output error (global learning criterion) or the local models' output errors (local learning criterion). Different tuning mechanisms, based essentially on feature space partitioning (splitting) techniques, have been described and implemented in [10]. Two of the most promising of them are "output error based decision tree" and "output error based Fuzzy partitioning" mechanisms (described and implemented in [10]).…”

Section: Fig 1 -General Bloc Diagram Of Weighted Contribution Based Modular Connectionist Systemmentioning

confidence: 99%

“…These major points could be defeated by adding selforganizing skill to a multi-model (or to a modular architecture) leading to powerful structure, especially if local models (or local modules) are ANN based units. A number of such self-organizing multiple ANN structures have been proposed and described in [9], [10], [12] and [13]. These works could be divided into two main directions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Modular and Self-Organizing Connectionist Systems: Toward Higher Level Intelligent Functions

Madani¹

2014

IJC

Self Cite

View full text Add to dashboard Cite

Recent advances in “neurobiology” allowed highlighting some of key mechanisms of animal intelligence. Among them one can emphasizes brain’s “modular” structure and its “self-organizing” capabilities. The main goal of this paper is to show how these primary supplies could be exploited and combined in the frame of “soft-computing” issued techniques in order to design intelligent artificial systems emerging higher level intelligent behavior than conventional Artificial Neural Networks (ANN) based structures.

show abstract

Section: Fig 1 -General Bloc Diagram Of Weighted Contribution Based Modular Connectionist Systemmentioning

confidence: 99%

Section: Fig 1 -General Bloc Diagram Of Weighted Contribution Based Modular Connectionist Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modular and Self-Organizing Connectionist Systems: Toward Higher Level Intelligent Functions

Madani¹

2014

IJC

Self Cite

View full text Add to dashboard Cite

show abstract

“…Usually, a model consists in a set of functional relationships between the elements of a set of variables. One way to overcome the complexity related to nonlinearity is to adopt multi-model approaches [2][3][4][5].…”

Section: Nonlinear Systems and Multi-model Approachesmentioning

confidence: 99%

E2GKpro: An evidential evolving multi-modeling approach for system behavior prediction with applications

Serir

Ramasso²,

Nectoux³

et al. 2013

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Nonlinear dynamical systems identification and behavior prediction are difficult problems encountered in many areas of industrial applications such as fault diagnosis and prognosis. In practice, the analytical description of a nonlinear system directly from observed data is a very challenging task because of the the too large number of the related parameters to be estimated. As a solution, multi-modeling approaches have lately been applied and consist in dividing the operating range of the system under study into different operating regions easier to describe by simpler functions to be combined. In order to take into consideration the uncertainty related to the available data as well as the uncertainty resulting from the nonlinearity of the system, evidence theory is of particular interest, because it permits the explicit modeling of doubt and ignorance. In the context of multi-modeling, information of doubt may be exploited to properly segment the data and take into account the uncertainty in the transitions between the operating regions. Recently, the Evidential Evolving Gustafson-Kessel algorithm (E2GK) has been proposed to ensure an online partitioning of the data into clusters that correspond to operating regions. Based on E2GK, a multi-modeling approach called E2GKpro is introduced in this paper, which dynamically performs the estimation of the local models by upgrading and modifying their parameters while data arrive. The proposed algorithm is tested on several datasets and compared to existing approaches. The results show that the use of virtual centroids in E2GKpro account for its robustness to noise and generating less operating regions while ensuring precise predictions.

show abstract

“…Recently, a number of works propose multimodel based approaches to avoid difficulties (modelling complexity) related to non-linearity ( [7], [8] [9] and [12]). In a general way, in such approaches, a set of models, corresponding to a set of operating ranges contributes to identify the whole system.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study Between a Multi-Models Based Approach and an Artificial Neural Network Based Technique for Nonlinear Systems Identification

Thiaw¹,

Rybnik²,

Malti³

et al. 2014

IJC

Self Cite

View full text Add to dashboard Cite

Recently, a number of works propose multi-model based approaches to model non-linear systems. Such approach could also been seen as some “specific” approach, inspired from ANN operation mode, where each neurone, represented by one of the local models, realizes some higher level transfer function. In this paper we present two different neural based approaches to such multiple models concept: one issued from conventional structure and the other based on self-organizing dynamic architecture. A comparative study between a multi-model based architecture and an ANN based one, in the frame of nonlinear system identification is reported.

show abstract

Non Linear Process Identification Using a Neural Network Based Multiple Models Generator

Cited by 8 publications

References 5 publications

Modular and Self-Organizing Connectionist Systems: Toward Higher Level Intelligent Functions

Modular and Self-Organizing Connectionist Systems: Toward Higher Level Intelligent Functions

E2GKpro: An evidential evolving multi-modeling approach for system behavior prediction with applications

A Comparative Study Between a Multi-Models Based Approach and an Artificial Neural Network Based Technique for Nonlinear Systems Identification

Contact Info

Product

Resources

About