Evolutionary pruning of non-nested generalized exemplars

Zaharie, Daniela; Perian, Lavinia; Negru, Viorel; Zamfirache, Flavia

doi:10.1109/saci.2011.5872973

Cited by 6 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Situação esperada para o caso estudado, uma vez que há pesquisas prévias indicando a baixa correlação entre consumo de água e variáveis climáticas (Silva et al, 2008). Informações adicionais acerca do algoritmo NNGE podem ser encontradas no trabalho de Zaharie et al (2011). Para utilização do algoritmo NNGE, utilizou-se a ferramenta de mineração de dados Weka (Waikato Environment for Knowledge Analysis).…”

Section: Seunclassified

Previsão consumo diário de água: um estudo de caso de Nobres (Brasil)

2016

View full text Add to dashboard Cite

Para obter eficiência operacional em sistema de abastecimento de água (SAA) a previsão de consumo de água em curto prazo (para o próximo dia) é necessária. Esse trabalho teve o objetivo de desenvolver um modelo matemático de previsão do consumo diário de água da cidade de Nobres, Estado de Mato Grosso, no Brasil. As etapas metodológicas realizadas foram: (1) revisão de literatura; (2) coleta e análise de dados (consumo de água e clima); (3) proposição de modelo de previsão de consumo diário de água; (4) calibração e verificação do modelo; e, (5) aplicação de modelo. As técnicas de modelagem matemática empregadas foram Regressão Linear, Séries de Fourier e Sistema Especialista. Os resultados indicaram um erro médio percentual do modelo inferior a 10% indicando que apresentou bom ajuste e que pode ser utilizado para prever o consumo de água. Como principal conclusão apresenta-se que o modelo desenvolvido pode ser utilizado para o planejamento operacional do SAA estudado.Palavras chave | Demanda de água; Regressão Linear; Séries de Fourier; Sistema Especialista. ABSTRACT In order to move operational efficiency from the water system supply (Waterworks, i.e. a combined water purification plant and pumping station) forecast water consumption values 24 h ahead are required. The objective of this paper is to develop mathematical model forecast water consumption 24 h ahead for Nobres city, Mato Grosso

show abstract

Section: Seunclassified

Previsão consumo diário de água: um estudo de caso de Nobres (Brasil)

2016

View full text Add to dashboard Cite

show abstract

“…Several approaches have been proposed to secure the CPPS systems such as the behavior rule-based monitoring devices methodology [1] in the smart grid that is used to detect the insider threats, the anomaly detection techniques [2], which extract the normal behaviors from various communication protocols of Industrial Control Systems (ICSs) to create a full description of the communication pattern, The Specification-Based IDS [3] that monitors system security states and sends the alerts when the system behavior approaches an unsafe or disallowed state, the common path mining approach [4] that creates an IDS using heterogeneous data for detecting power system cyberattacks using the State Tracking and Extraction Method (STEM) algorithm [5] to preprocess data and then uses frequent item set mining to extract common paths associated with specific system behaviors, and recently a NNGE with a Hoeffding Adaptive Trees approach [5,6] that is used to create an offline and online Event Intrusion Detection Systems using STEM to process the power system security datasets. However, these approaches are still neither accurate nor scalable enough to process the high speed big data of the CPPS [5,[7][8][9].…”

Section: Introductionmentioning

confidence: 99%

“…(2) Pruning of nongeneralized exemplars using the highest ranked features of the PSO: VHDRA uses the Evolutionary Pruning Algorithms (EPA-NNGE) [19] to improve the classification accuracy of NNGE and to reduce the model size by reducing the hyperrectangles and ignoring the nonselected features among the significant ones defined by PSO. (3) A horizontal reduction for the size of the dataset while preserving original key events and patterns within the datasets using an approach called STEM, State Tracking and Extraction Method [6], which is used to quantize and reduce the heterogeneous datasets to reduce STEM tracks system states from measurements and creates a compressed sequence of states for each observed scenario.…”

Section: Introductionmentioning

confidence: 99%

“…To evaluate the accuracy of the VHDRA, we compare the detection rates of the NNGE using VHDRA against current classification approaches including the NNGE with its best feature selection approach, namely, the Correlation based Feature Selection (CFS) [6]. The comparison uses an existing intrusion detection power grid dataset [15].…”

Section: Introductionmentioning

confidence: 99%

“…The NNGE. NNGE [4,6,20] is an instance based classifier in which the algorithm creates if then else like rules represented by generalized exemplars. Generalized exemplars may be singles in which case the exemplar represents exactly one example from the training database.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

VHDRA: A Vertical and Horizontal Intelligent Dataset Reduction Approach for Cyber-Physical Power Aware Intrusion Detection Systems

Kholidy

Erradi

2019

Security and Communication Networks

View full text Add to dashboard Cite

The Cypher Physical Power Systems (CPPS) became vital targets for intruders because of the large volume of high speed heterogeneous data provided from the Wide Area Measurement Systems (WAMS). The Nonnested Generalized Exemplars (NNGE) algorithm is one of the most accurate classification techniques that can work with such data of CPPS. However, NNGE algorithm tends to produce rules that test a large number of input features. This poses some problems for the large volume data and hinders the scalability of any detection system. In this paper, we introduce VHDRA, a Vertical and Horizontal Data Reduction Approach, to improve the classification accuracy and speed of the NNGE algorithm and reduce the computational resource consumption. VHDRA provides the following functionalities: (1) it vertically reduces the dataset features by selecting the most significant features and by reducing the NNGE’s hyperrectangles. (2) It horizontally reduces the size of data while preserving original key events and patterns within the datasets using an approach called STEM, State Tracking and Extraction Method. The experiments show that the overall performance of VHDRA using both the vertical and the horizontal reduction reduces the NNGE hyperrectangles by 29.06%, 37.34%, and 26.76% and improves the accuracy of the NNGE by 8.57%, 4.19%, and 3.78% using the Multi-, Binary, and Triple class datasets, respectively.

show abstract

Campaign management design based on segmentation by rank clusters

Paetz

2015

J Market Anal

View full text Add to dashboard Cite

Evolutionary pruning of non-nested generalized exemplars

Cited by 6 publications

References 10 publications

Previsão consumo diário de água: um estudo de caso de Nobres (Brasil)

Previsão consumo diário de água: um estudo de caso de Nobres (Brasil)

VHDRA: A Vertical and Horizontal Intelligent Dataset Reduction Approach for Cyber-Physical Power Aware Intrusion Detection Systems

Campaign management design based on segmentation by rank clusters

Contact Info

Product

Resources

About