Hybridizing mixtures of experts with support vector machines: Investigation into nonlinear dynamic systems identification

Lima, Clodoaldo A. M.; Coelho, André L. V.; Zuben, Fernando J. Von

doi:10.1016/j.ins.2007.01.009

Cited by 58 publications

(23 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…That is, we obtained 138 fingerprints with 14 measurements for each fingerprint. In the case of the camera based system, we International Journal of Distributed Sensor Networks 9 [33] obtained 20 images per floor that correspond to the names of the rooms that are placed in the walls, close to the door of the room.…”

Section: Results and Conclusionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Organizing Architecture for Information Fusion in Distributed Sensor Networks

Bajo

Paz

Villarrubia

et al. 2015

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

The management of heterogeneous distributed sensor networks requires new solutions that can address the problem of automatically fusing the information coming from different sources in an efficient and effective manner. In the literature it is possible to find different types of data fusion and information fusion techniques in use today, but it is still a challenge to obtain systems that allow the automation or semiautomation of information processing and fusion. In this paper, we present a multiagent system that based on the organizational theory proposes a new model to automatically process and fuse information in heterogeneous distributed sensor networks. The proposed architecture is applied to a case study for indoor location where information is taken from different heterogeneous sensors.

show abstract

Section: Results and Conclusionmentioning

confidence: 99%

“…These are supervised methods that require a previous training and it is necessary to have available a dataset for training the system. As an alternative to the supervised methods, we also incorporate a linear programming method to the fusion organization, based on the simplex algorithm [33].…”

Section: Fusion Organizationmentioning

confidence: 99%

Self-Organizing Architecture for Information Fusion in Distributed Sensor Networks

Bajo

Paz

Villarrubia

et al. 2015

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…Following this, Yip [60] compared the predictive performance of CBR with that of MDA, finding CBR clearly outperformed MDA. Support vector machine (SVM) has been gaining popularity recently because of its high generalization performance and global optimal solution [3,7,15,16,22,27,31,54,61]. Studies of SVM-based BFP [4,9,12,14,35,36,45,58] indicate that SVM outperforms BPNN, MDA, and Logit.…”

Section: The Problem Addressed In This Researchmentioning

confidence: 99%

Gaussian case-based reasoning for business failure prediction with empirical data in China

Sun

2009

Information Sciences

View full text Add to dashboard Cite

“…Finally, it is pertinent mentioning that in a previous work [26] we have already investigated the idea of combining SVM and ME models. However, our focus there was specifically on regression (not classification) problems, and the resulting formulation was based on standard (not least-squares) SVMs.…”

Section: Comparison With Related Workmentioning

confidence: 99%

Pattern classification with mixtures of weighted least-squares support vector machine experts

Lima

Coelho

Zuben

2008

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Support Vector Machine (SVM) classifiers are high-performance classification models devised to comply with the structural risk minimization principle and to properly exploit the kernel artifice of nonlinearly mapping input data into high-dimensional feature spaces toward the automatic construction of better discriminating linear decision boundaries. Among several SVM variants, LeastSquares SVMs (LS-SVMs) have gained increased attention recently due mainly to their computationally attractive properties coming as the direct result of applying a modified formulation that makes use of a sum-squared-error cost function jointly with equality, instead of inequality, constraints. In this work, we present a flexible hybrid approach aimed at augmenting the proficiency of LS-SVM classifiers with regard to accuracy/generalization as well as to hyperparameter calibration issues. Such approach, named as Mixtures of Weighted Least-Squares Support Vector Machine Experts, centers around the fusion of the weighted variant of LS-SVMs with Mixtures of Experts models. After the formal characterization of the novel learning framework, simulation results obtained with respect to both binary and multiclass pattern classification problems are reported, ratifying the suitability of the novel hybrid approach in improving the performance issues considered.

show abstract

Hybridizing mixtures of experts with support vector machines: Investigation into nonlinear dynamic systems identification

Cited by 58 publications

References 23 publications

Self-Organizing Architecture for Information Fusion in Distributed Sensor Networks

Self-Organizing Architecture for Information Fusion in Distributed Sensor Networks

Gaussian case-based reasoning for business failure prediction with empirical data in China

Pattern classification with mixtures of weighted least-squares support vector machine experts

Contact Info

Product

Resources

About