Efficient Data Projection for Visual Analysis of Large Data Sets Using Neural Networks

Medvedev, Viktor; Dzemyda, Gintautas; Kurasova, Olga; Marcinkevičius, Virginijus

doi:10.15388/informatica.2011.339

Cited by 17 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence methods are under wide development in various directions. These developments cover artificial neural networks (Haykin, 2009;Schmidhuber, 2011;Dzemyda et al, 2007Dzemyda et al, , 2013Medvedev et al, 2011;Ivanikovas et al, 2011), evolutionary computation (Simon, 2013;Eiben and Smith, 2003;Filatovas et al, 2015;Kurasova, 2013, 2014), fuzzy set theory (Ross, 2010), artificial immune systems (Al-Enezi et al, 2010), etc. Some taxonomy of nature inspired artificial intelligence is given in Goel et al (2012).…”

Section: Swarm Intelligencementioning

confidence: 99%

Swarm Intelligence for Frequency Management in Smart Grids

Evora¹,

Hernández²,

Hernández³

et al. 2015

Informatica

Self Cite

View full text Add to dashboard Cite

A secure and high-quality operation of power grids requires frequency to be managed to keep it stable around a reference value. The deviation of the frequency from this reference value is caused by the imbalance between the active power produced and consumed. In the Smart Grid paradigm, the balance can be achieved by adjusting the demand to the production constraints, instead of the other way round. In this paper, an swarm intelligence-based approach for frequency management is proposed. It is grounded on the idea that a swarm is composed of decentralised individual agents (particles) and that each of them interacts with other ones via a shared environment. Three swarm intelligence-based policies ensure a decentralised frequency management in the smart power grid, where agents of swarm are making decisions and acting on the demand side. Policies differ in behaviour function of agents. Finally, these policies are evaluated and compared using indicators that point out their advantages.

show abstract

Section: Swarm Intelligencementioning

confidence: 99%

Swarm Intelligence for Frequency Management in Smart Grids

Evora¹,

Hernández²,

Hernández³

et al. 2015

Informatica

Self Cite

View full text Add to dashboard Cite

show abstract

“…The option to analyze the correlation matrix of human emotions with features characterizing the built environment is Multidimensional Scaling (MDS). This method is the most popular method for a visual representation of multidimensional data in a low-dimensional manner [56][57][58]. It has a number of realizations using artificial neural networks and in combinations with neural networks, too.…”

Section: Multidimensional Scaling For Visual Analysis Of Correlationsmentioning

confidence: 99%

“…, Y m ) is a set of points of lower dimensionality, and (d<n); d (Yi, Yj) is the Euclidean distance between the points, Y i , Y j , in our case. More stress functions are available in Medvedev et al [57]. The optimization problem is quite complicated because of the number of variables, which is equal to d×n, in the general case.…”

Section: Multidimensional Scaling For Visual Analysis Of Correlationsmentioning

confidence: 99%

Customized ViNeRS Method for Video Neuro-Advertising of Green Housing

Kaklauskas

Zavadskas

Schuller

et al. 2020

IJERPH

Self Cite

View full text Add to dashboard Cite

The implementation of advertising for green housing usually involves consideration of individual differences among potential buyers, their desires for residential unit features as well as location impacts on a selected property. Much more rarely, there is consideration of the arousal and valence, affective behavior, emotional, and physiological states of possible buyers of green housing (AVABEPS) while they review the advertising. Yet, no integrated consideration of all these factors has been undertaken to date. The objective of this study was to consider, in an integrated manner, the AVABEPS, individual differences, and location impacts on property and desired residential unit features. During this research, the applications for the above data involved neuromarketing and multicriteria examination of video advertisements for diverse client segments by applying neuro decision tables. All of this can be performed by employing the method for planning and analyzing and by multiple criteria and customized video neuro-advertising green-housing variants (hereafter abbreviated as the ViNeRS Method), which the authors of this article have developed and present herein. The developed ViNeRS Method permits a compilation of as many as millions of alternative advertising variants. During the time of the ViNeRS project, we accumulated more than 350 million depersonalized AVABEPS data. The strong and average correlations determined in this research (over 35,000) and data examination by IBM SPSS tool support demonstrate the need to use AVABEPS in neuromarketing and neuro decision tables. The obtained dependencies constituted the basis for calculating and graphically submitting the ViNeRS circumplex model of affect, which the authors of this article developed. This model is similar to Russell’s well-known earlier circumplex model of affect. Real case studies with their related contextual conditions presented in this manuscript show a practical application of the ViNeRS Method.

show abstract

“…Each data instance (point) is characterized by some features. Feature reduction is a fundamental step before applying data analysis methods [12,13,14]. High dimensionality data can be efficiently reduced to a much smaller number of variables (features) without a significant loss of information.…”

Section: Introductionmentioning

confidence: 99%

Projection error evaluation for large multidimensional data sets

Paulauskienė

Kurasova

2016

NAMC

Self Cite

View full text Add to dashboard Cite

This research deals with projection error evaluation for large data sets using only a personal computer without any particular technologies for high performance computing. A shortcoming of basic projection error calculation ways is such that they require a large amount of computer memory or computation time is not acceptable when large data sets are analyzed. This paper proposes two ways for projection error evaluation: the first one is based on calculating the projection error for not full data set, but only for representative data sample, the second one obtains the projection error by dividing a data set into the smaller data sets. The experiments have been carried out with twelve real and artificial data sets. The computational efficiency of the projection error evaluation ways is confirmed by a comprehensive set of comparisons. We demonstrate that dividing data set into the smaller data sets allows us to calculate the projection error for large data sets.

show abstract

Efficient Data Projection for Visual Analysis of Large Data Sets Using Neural Networks

Cited by 17 publications

References 18 publications

Swarm Intelligence for Frequency Management in Smart Grids

Swarm Intelligence for Frequency Management in Smart Grids

Customized ViNeRS Method for Video Neuro-Advertising of Green Housing

Projection error evaluation for large multidimensional data sets

Contact Info

Product

Resources

About