Brain Emotional Learning Based Fuzzy Inference System (BELFIS) for Solar Activity Forecasting

2014 10th International Conference on Natural Computation (ICNC)

Svensson

2014

Abstract-This study presents comparative results obtained from employing four different neuro-fuzzy models to predict geomagnetic storms. Two of thes neuro-fuzzy models can be classified as Brain Emotional Learning Inspired Models (BELIMs) These two models are BELFIS (Brain Emotional Learning Based Fuzzy Inference System) and BELRFS (Brain Emotional Learning Recurrent Fuzzy System). The two other models are Adaptive Neuro-Fuzzy Inference System (ANFIS) and Locally Linear Model Tree (LoLiMoT) learning algorithm, two powerful neuro-fuzzy models to accurately predict a nonlinear system. These models are compared for their ability to predict geomagnetic storms using the AE index. , a real-time learning model was proposed to model the AE index and predict geomagnetic sub storms. A neuro-fuzzy method using a locally linear neuro-fuzzy model tree algorithm has been used to predict the AE index in [7]. Keywords-AdaptiveAn emotion-based machine-learning approach called BEL was utilized to predict the AE index in [9]. The above mentioned algorithms aimsat providing accurate results when predicting geomagnetic storms, using the AE index. This paper compares the performance of four neuro-fuzzy models to predict AE time series. The goal is to find a powerful neuro-fuzzy model in order to develop an alert system of geomagnetic sub storms.The rest of the paper is organized as follows: Section II describes the general structure of BELFIS and BELRFS. Section III redefines the algorithms of two well-known neuro-fuzzy models: ANFIS and LoLiMoT. In Section IV, the results of different methods to model AE time series are compared. Finally, conclusions about this research work are presented and the future work of this study is discussed in Section V. Neuro-fuzzy Models for Geomagnetic Storms PredictionUsing the Auroral Electrojet Index

Section: Brain Emotional Learning Inspired Modelsmentioning

confidence: 99%

Neuro-fuzzy models for geomagnetic storms prediction: Using the auroral electrojet index

Parsapoor

2014 10th International Conference on Natural Computation (ICNC)

Svensson

2014

“…The amygdala-orbitofrontal subsystem (see Fig. 3 ) that is the basis of many computational models has a simple structure [1], [9]. The amygdala-orbitofrontal subsystem consists of four parts which interact with each other to form the association between the conditioned and the unconditioned stimuli [1], [9], [11], [12].…”

Section: B Inspired Algorithms By Emotionsmentioning

confidence: 99%

“…Various architectures have been presented to provide computational models of emotional learning [1]- [7]. These models have been applied in numerous applications such as control applications and prediction applications [1]- [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Brain emotional learning based fuzzy inference system (Modified using radial basis function)

Pasrapoor

Eighth International Conference on Digital Information Management (ICDIM 2013)

2013

“…Thus, the suggested algorithm can be used for other combinatorial optimization problems e.g., rate, bandwidth allocation, , traffic scheduling, and multi-channel MAC scheme [18]- [19]. In addition, the obtained results can be compared with a new inspired optimization algorithm that will be suggested based on our pervious work related to brain emotional learning [20]- [22]. suggested algorithm can be part of a joint clustering and channel assignment algorithm in ad hoc networks.…”

Section: Introductionmentioning

confidence: 98%

An Imperialist Competitive Algorithm for Interference-Aware Cluster-Heads Selection in Ad Hoc Networks

Parsapoor

2014 IEEE 28th International Conference on Advanced Information Networking and Applications

2014

This paper presents the results of applying a new clustering algorithm in ad hoc networks. This algorithm is a centralized method and it is designed on the basis of an imperialist competitive algorithm (ICA). This algorithm aims to find a minimum number of cluster-heads while satisfying two constraints, connectivity and interference. This work is a part of an ongoing research to develop a distributed interference aware cluster-based channel allocation method. The results of the centralized method are required to provide an ideal case when investigating the performance of the distributed version. The suggested method is evaluated for several scenarios and compares the obtained results with the reported results of ant colony optimization-based methods.