Statistical model applied to NetFlow for network intrusion detection

The computers and network services became presence guaranteed in several places. These characteristics resulted in the growth of illicit events and therefore the computers and networks security has become an essential point in any computing environment. Many methodologies were created to identify these events; however, with increasing of users and services on the Internet, many difficulties are found in trying to monitor a large network environment. This paper proposes a methodology for events detection in large-scale networks. The proposal approaches the anomaly detection using the NetFlow protocol, statistical methods and monitoring the environment in a best time for the application. © 2010 Springer-Verlag Berlin Heidelberg.

Anfis applied to the prediction of surface roughness in grinding of advanced ceramics

This paper introduces a methodology for predicting the surface roughness of advanced ceramics using Adaptive Neuro-Fuzzy Inference System (ANFIS). To this end, a grinding machine was used, equipped with an acoustic emission sensor and a power transducer connected to the electric motor rotating the diamond grinding wheel. The alumina workpieces used in this work were pressed and sintered into rectangular bars. Acoustic emission and cutting power signals were collected during the tests and digitally processed to calculate the mean, standard deviation, and two other statistical data. These statistics, as well the root mean square of the acoustic emission and cutting power signals were used as input data for ANFIS. The output values of surface roughness (measured during the tests) were implemented for training and validation of the model. The results indicated that an ANFIS network is an excellent tool when applied to predict the surface roughness of ceramic workpieces in the grinding process.

A model for computing vibration induced stresses of electronic components in a general flexible mounting

This paper develops a novel full analytic model for vibration analysis of solid-state electronic components. The model is just as accurate as finite element models and numerically light enough to permit for quick design trade-offs and statistical analysis. The paper shows the development of the model, comparison to finite elements and an application to a common engineering problem. A gull-wing flat pack component was selected as the benchmark test case, although the presented methodology is applicable to a wide range of component packages. Results showed very good agreement between the presented method and finite elements and demonstrated the usefulness of the method in how to use standard test data for a general application. © 2013 Elsevier Ltd.

Efeito do extrato hidroalcoólico de própolis em girinos de rã touro (Rana Catesbeiana)

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Comparação de modelos mistos, AMMI e Eberhart-Russel via simulação no estudo da interação genótipo x ambiente em cana-de-açúcar

Pós-graduação em Agronomia (Genética e Melhoramento de Plantas) - FCAV

Avaliação de níveis de proteína digestível para girinos de rã-touro

Pós-graduação em Aquicultura - FCAV

Statistical properties for a dissipative model of relativistic particles in a wave packet: A parameter space investigation

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Analise do sistema de medição em peças aeronaúticas através do estudo de R&R (repetibilidade e reprodutibilidade)

The Measurement System Analysis (MSA - Measurement System Analysis) is a statistical methodology developed to study and analyze the behavior of the measurement systems, and, therefore, allow the increased of the confidence readings performed by measuring instruments. It’s widely used in the automotive industry since the 90’s and is a mandatory requirement for the approval of the parts according to ISO Standard of the automotive sector. However, the aerospace industry doesn’t require this type of Study, once which the vast majority of aeronautics parts have characteristics (dimensions) with very tight tolerances, closed, ie, at the home of microns. This work aims to create lists of recommendations for definitions of measuring instruments in developing of control plans, which correlates tolerances fields of characteristics for different settings and acceptance of the instrument, classified as optimum, recommended and not recommended, through of the study of R&R (Repeatability and Reproducibility) in aeronautics parts. Every methodology of the experimental part was based on modern strategy of continuous improvement, the DMAIC (Define Measure Analyze Implant Control), in order to achieve better measurement method used in the control of milling aeronautics parts, identifying and reducing the variations of the measurement process. The results of the R&R Study in large part of measuring instrument manuals were considered acceptable and/or recommended, ie with values of %P/T and %RR lower than 30%, providing statistical data which have enabled the elaboration of tables of recommendations, which, from this work, have turned into very important documents and aid for Process Engineering, having in their hands a technical study able to identify which is the most appropriate instrument to get a more robust dimensional... (Complete abstract click electronic access below)

O efeito da autocorrelação no desempenho dos gráficos de X e R e dos gráficos de X e S²

Control charts are very important tools in statistical quality control of industrial processes and its use started last century. Since its development, the charts have always been attributed to independent processes, i.e. without any correlation between samples. But nowadays, with the high level of automation in the industrial environment, it is noticeable the autocorrelation factor between samples. The main Xcharts used in monitoring quality characteristics represented by continuous variables are the mean (X ), amplitude (R) and variance (S²). Therefore, this work aims to analyze the performance of X and R charts and in of X and S² charts with different sample sizes (4 and 5) for monitoring autocorrelated processes. Through computer simulations using the Fortran software and the use of mathematical expressions was possible to obtain data and performance analysis of the detection power charts for independent observations and for autocorrelated observations according to the model AR (1). The results show that the effect of autocorrelation reduces the ability of monitoring the control charts and that, the greater this effect, the slower the chart becomes in misfits signaling

The effect of power-ultrasound on the pretreatment of acidified aqueous solutions of banana flower-stalk: Structural, chemical and statistical analysis

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Joint economic design of X̄ and R control charts for processes subject to two independent assignable causes

A model for the joint economic design of X̄ and R control charts is developed. This model assumes that the process is subject to two assignable causes. One assignable cause shifts the process mean; the other shifts the process variance. The occurrence of the assignable cause of one kind does not block the occurrence of the assignable cause of another kind. Consequently, a second process parameter can go out-of-control after the first process parameter has gone out-of-control. A numerical study of the cost surface to the model considered has revealed that it is convex, at least in the interest region.