Spelling suggestions: "subject:"degression tre"" "subject:"aregression tre""
31 |
L'évaluation du risque de récidive chez les agresseurs sexuels adultesParent, Geneviève January 2008 (has links)
Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal
|
32 |
Credit Scoring Methods And Accuracy RatioIscanoglu, Aysegul 01 August 2005 (has links) (PDF)
The credit scoring with the help of classification techniques provides to take easy and quick decisions in lending. However, no definite consensus has been reached with regard to the best method for credit scoring and in what conditions the methods performs best. Although a huge range of classification techniques has been used in this area, the logistic regression has been seen an important tool and used
very widely in studies. This study aims to examine accuracy and bias properties in parameter estimation of the logistic regression by using Monte Carlo simulations in four aspect which are dimension of the sets, length, the included percentage defaults in data and effect of variables on estimation. Moreover, application of some important statistical and non-statistical methods on Turkish credit default
data is provided and the method accuracies are compared for Turkish market. Finally, ratings on the results of best method is done by using receiver operating characteristic curve.
|
33 |
Desempenho de redes neurais artificiais e árvores de regressão na modelagem do processo chuva-vazão da bacia do Alto Canoas / Performance of artificial neural networks and regression trees in the rainfall-runoff modeling in the basin Alto Canoas processDebastiani, Aline Bernarda 15 February 2016 (has links)
Submitted by Claudia Rocha (claudia.rocha@udesc.br) on 2017-12-07T12:49:04Z
No. of bitstreams: 1
PGEF16MA053.pdf: 1576798 bytes, checksum: 649706432937dc5a8116984a2bb20aa7 (MD5) / Made available in DSpace on 2017-12-07T12:49:04Z (GMT). No. of bitstreams: 1
PGEF16MA053.pdf: 1576798 bytes, checksum: 649706432937dc5a8116984a2bb20aa7 (MD5)
Previous issue date: 2016-02-15 / FAPESC / The future behavior estimate of minimum, medium and maximum
discharges of a watershed is essential to elaborate themanagement plan
of its water resources.There are two modelling approaches to generate
predictions series: models that consider the physical processes occurring
in the basin and data-oriented models.This work aims to evaluate dataoriented
models, among which the most popular are the Artificial Neural
Networks (ANN). The Regression Trees (RT) also have great potential
for this kind of application, but they are not so widespread in
Hydrology, which is why they were included in this work. These models
were evaluated in the Upper Canoas basin, whose outlet coincides with
Rio Bonito Station. In the first chapter, the objective was to evaluate the
performance of an ANN method called Multi Layer Perceptron (MLP)
in closed-loop mode to estimate daily discharge, considering different
input vectors in order to assess the most appropriate combinations. The
input vectors data series were composed of observed precipitation,
evapotranspiration and discharge of the previous day. The training was
held in open-loop mode, where all model input treatments were
constituted of observed flow rate of the previous day (t-1) among other
variables. To simulate the flow in the test period was the MLP used for
open-loop and closed-loop mode, the latter being composed of a
simulated flow of entries in t-1. The combination of input vectors with
the best performance constituted of daily rainfall of the four rainfall
stations, rainfall with t-2 days delay of the same four stations and
discharge with t-1 day delay. The second chapter presents an evaluation
of modeling performance in the monthly scale comparing some RTs
(M5P, REP Tree and Decision Stump) and the MLP ANN. The
experiment was set up with one period for training and two periods for
testing. Among the RTs, the M5P produced the best results. In one of
the test periods, M5P presented similar performance to the MLP, being
considered an interesting alternative to using ANNs / A estimativa do comportamento futuro das vazões mínimas, médias e
máximas de uma bacia hidrográfica é fundamental para a elaboração do
plano de gerenciamento dos seus recursos hídricos. Existem duas
abordagens de modelos que possibilitam gerar séries de previsões: a
abordagem dos modelos baseados nos processos físicos que ocorrem na
bacia e a abordagem dos modelos orientados a dados. Esta dissertação
se propõe a avaliar modelos orientados a dados, dentre os quais, os mais
populares são as Redes Neurais Artificiais (RNAs). As Árvores de
Regressão (RT) também apresentam grande potencial de aplicação,
embora pouco difundidas na Hidrologia, motivo pelo qual estão
incluídas neste trabalho. Estes modelos foram avaliados na bacia
hidrográfica do Alto Canoas, cujo exutório coincide com a Estação Rio
Bonito. No capitulo 1, o objetivo foi avaliar o desempenho de uma RNA
do tipo Multi Layer Perceptron (MLP), em modo closed-loop, tratandose
diferentes combinações de vetores de entrada, visando determinar o
mais adequado para estimar as vazões diárias. Os vetores de entrada
foram constituídos de séries observadas de precipitação,
evapotranspiração e da vazão do dia anterior. O treinamento foi
realizado em modo open-loop, em que todos os tratamentos de entrada
do modelo foram constituídos pela vazão observada do dia anterior (t-1)
entre outras. Para a simulação da vazão no período de teste foi utilizada
a MLP em modo open-loop e closed-loop, sendo a última composta por
uma das entradas a vazão simulada em t-1. A combinação de vetores de
entrada que apresentou melhor desempenho foi constituído pelo registro
da precipitação diária nas quatro estações pluviométricas, precipitação
com atraso de t-2 dias para as mesmas quatro estações e vazão em t-1. O
capitulo 2 apresenta a avaliação do desempenho, na escala mensal, de
algumas RTs (M5P, REP Tree e Decision Stump) frente ao desempenho
de uma RNA do tipo MLP. O experimento foi configurado com um
período para treinamento e dois períodos para teste. Entre as RTs, a
M5P produziu os melhores resultados. Em um dos períodos de teste, a
M5P apresentou desempenho semelhante ao da MLP, sendo considerada
uma alternativa interessante ao uso de RNAs
|
34 |
Dinâmica temporal e influência de variáveis ambientais no recrutamento de peixes recifais do Banco dos Abrolho, BA, Brasil. / Temporal dynamics and influence of environmental variables in the recruitment of reef fish of the Abrolhos Bank, BrazilDaniel Sartor 25 June 2015 (has links)
O recrutamento é extremamente importante no ambiente recifal, sendo o principal responsável pelo reabastecimento de populações adultas de peixes. Esse fenômeno é altamente complexo, não sendo claro se é influenciado apenas por processos estocásticos ou também por processos determinísticos. No presente estudo avaliamos a dinâmica temporal do recrutamento de diversas espécies de peixes recifais, identificando sítios de berçário (i.e. recrutamento estável e alto) e a influência de variáveis ambientais. Para tal, utilizamos dados de um monitoramento de médio prazo (i.e. 2001 a 2014) realizado no Banco dos Abrolhos (BA-Brasil). Foram amostrados mais de 45 sítios, sendo levantados dados sobre a comunidade de peixes, comunidade bentônica e outras variáveis ambientais. A partir desses dados, avaliamos a variação do recrutamento por sítio em dois períodos distintos (i.e. 2001-2008/2006-2014) e a influência de variáveis ambientais no recrutamento, através da técnica Boosted Regression Trees. Constatamos que diversas espécies de peixe apresentam-se com recrutamento estável em distintos sítios de amostragem. Também observamos um efeito positivo da densidade de peixes recifais coespecíficos adultos e da cobertura relativa de algas frondosas no recrutamento de diversas espécies analisadas. No geral, observamos que há certa espécie especificidade no processo de recrutamento, porém, em escalas espaciais maiores, os padrões podem estar ligados a características mais gerais, relacionadas a um grupo taxonômico mais elevado. Em relação aos sítios de berçário, um se destacou, sendo berçário de 5 diferentes espécies, incluindo Scarus trispinosus, uma das espécies prioritárias para conservação na região de Abrolhos. Assim, recomendamos a criação de uma área marinha de proteção integral que englobe o sítio em questão. Além disso, as descobertas deste trabalho nos permitem reforçar a teoria de que o recrutamento de peixes recifais pode ser influenciado por fenômenos determinísticos e não varia simplesmente de maneira estocástica. / Recruitment is extremely important in the reef environment, because it is the main source of population replenishment. Reef fish recruitment is a highly complex process and it is not clear whether it is influenced only by stochastic processes or also by deterministic processes. Herein, we aimed to investigate temporal dynamics of reef fish recruitment, identify nursery sites (i.e. predictably high recruitment sites) and evaluate the influence of environmental variables on recruitment. We used data from a medium-term time series (i.e. 2001-2014) of scientific surveys in Abrolhos Bank (BA-Brazil). We sampled more than 45 sites, for several consecutive years and recorded data about fish community, benthic community and other environmental variables. We assessed the variation of recruitment on each site, during two distinct periods (i.e. 2001-2008 / 2006-2014), and used the Boosted Regression Trees technique to evaluate the influence of environmental variables in recruitment. We found that several reef fish species present a low variable recruitment at different sampling sites. BRT showed a positive effect of the coverage of flesh algae and abundance of conspecific in the abundance of recruits (i.e. young-of-year) of many species. Overall, we notice that the recruitment traits seems to be species specific, but we also found indications that in larger spatial scales, recruitment spatial and temporal patterns may be related to general characteristics among species of the higher taxa. Nursery sites varied among species and one site was a nursery to 5 different reef fish species, including Scarus trispinosus, a species that require priority conservation in the Abrolhos Bank. Therefore, we recommend the creation of a new no-take marine protected area that encompasses this site. Our results also indicated that reef fish recruitment may be influenced by deterministic processes and do not vary only stochastically.
|
35 |
EducaÃÃo ambiental e sua relaÃÃo com as atitudes, valores e comportamentos dos indivÃduos de uma instituiÃÃo pÃblica federal de ensino / Environmental Education and its Relation with Attitudes , Values and Behaviors Environmentally Responsible Individuals of a Public Institution Federal TeachingAdriano Monteiro da Silva 31 March 2014 (has links)
nÃo hà / Entende-se a EducaÃÃo Ambiental como os processos por meio dos quais os homens e a sociedade edificam valores sociais, conhecimentos, habilidades, atitudes e competÃncias voltadas para a conservaÃÃo do meio ambiente. à a partir da inserÃÃo da EducaÃÃo Ambiental no processo educativo que a construÃÃo de valores, atitudes, habilidades e competÃncias sÃo construÃdas para que o indivÃduo possa atuar de forma proativa na proteÃÃo do meio ambiente. Valores e atitudes, nesse sentido, sÃo os construtos psicolÃgicos apontados pela literatura como preditores de comportamentos. Baseado nisto, esta pesquisa visa responder ao seguinte problema de pesquisa: qual a relaÃÃo existente entre a percepÃÃo da EducaÃÃo Ambiental e os valores, as atitudes e os comportamentos ambientalmente responsÃveis dos indivÃduos de uma InstituiÃÃo PÃblica Federal de Ensino (IPFE)? Nesse sentido, este trabalho consiste em examinar as relaÃÃes existentes entre aqueles construtos psicolÃgicos e a EducaÃÃo Ambiental de alunos e servidores de uma IPFE, por meio de um questionÃrio eletrÃnico aplicado aos alunos e servidores da InstituiÃÃo. A anÃlise dos dados foi realizada atravÃs de estatÃstica descritiva, anÃlise fatorial exploratÃria e confirmatÃria, da tÃcnica de modelagem de equaÃÃes estruturais, testes t para amostras independentes, anÃlises de variÃncia e Ãrvores de regressÃo. Os resultados da pesquisa apontam para uma correlaÃÃo significativa entre a percepÃÃo da EducaÃÃo Ambiental e a maioria das dimensÃes dos construtos dos valores, atitudes e comportamentos ambientalmente responsÃveis. Os mesmos resultados ainda mostram coerÃncia entre as anÃlises fatoriais, apresentando encaixe entre a literatura e o que se pretende discutir. Esses resultados contribuem para entender o comportamento dito como ambientalmente responsÃvel dos indivÃduos de uma InstituiÃÃo PÃblica Federal de Ensino, frente à percepÃÃo que tÃm da EducaÃÃo Ambiental. Nesta pesquisa, foram encontradas, ainda, relaÃÃes significativas entre os valores, atitudes e comportamentos. A partir dos resultados apresentados nesta pesquisa, pode-se traÃar estratÃgias para o ensino, pesquisa, extensÃo, capacitaÃÃo e conscientizaÃÃo dos futuros tÃcnicos, bacharÃis e tecnÃlogos e demais envolvidos acerca da problemÃtica ambiental. Assim, este estudo contribui com a instituiÃÃo pesquisada no sentido de que, a partir dele, podem ser traÃadas metas e estratÃgias para a capacitaÃÃo em educaÃÃo e gestÃo ambiental, valorizando temas que abordem a gestÃo de resÃduos, licitaÃÃes sustentÃveis, qualidade de vida no trabalho, sensibilizaÃÃo dos alunos, capacitaÃÃo dos servidores e uso racional dos recursos. O estudo contribui para identificar quais sÃo os valores, as atitudes e os comportamentos ambientalmente responsÃveis em um ambiente organizacional de ensino, servindo como ponto de partida para elaboraÃÃo de instrumentos que permitam a compreensÃo desses construtos no Ãmbito de outras instituiÃÃes. Dentre os fatores que influenciam o comportamento ecolÃgico dos indivÃduos, a variÃvel mais importante como preditora de um comportamento ecolÃgico geral à o gÃnero
|
36 |
[pt] MODELO STAR-TREE DE TRANSIÇÃO SUAVE ESTRUTURADO EM ÁRVORE PARA PREVISÃO DE ENERGIA EÓLICA / [en] TREE STRUCTURED SMOOTH TRANSITION MODEL STAR-TREE FOR WIND POWER FORECASTING05 November 2021 (has links)
[pt] O principal objetivo desta dissertação é estudar modelos de previsão da geração eólica utilizando os dados de cinco parques eólicos, mais precisamente comparar o desempenho dos modelos lineares e não lineares. Utilizando a metodologia do modelo não-linear STAR-TREE (Smooth Transition AutoRegression Tree) e comparando com o modelo linear Box e Jenkins através de medidas estatísticas. Basicamente, o modelo STAR-TREE é uma combinação dos modelos STAR (Smooth Transition AutoRegression) e CART (Classification
and Regression Tree), realizando assim uma modelagem em árvore onde a transição entre os regimes é feita de forma suave através da função logística e nos nós terminais são ajustados modelos preditivos. Neste estudo será ajustado nos nós terminais um modelo simples constante e também modelos autorregressivos. / [en] The main objective of this dissertation is to study wind generation forecasting models using data from five wind farms, more accurately compare the performance of linear and nonlinear models. Using the methodology of the nonlinear model STAR-TREE (Smooth Transition Autoregression Tree) and compare with the linear model BoxandJenkins through statistical measures. Basically the model STAR-TREE is a combination of models STAR (Smooth Transition Autoregression) and CART (Classification and Regression Tree), thus creating a modeling tree where the transition between regimes is done smoothly through the logistics function and in the terminal nodes are adjusted predictive models. In this study will fit in the terminal nodes, a simple model of constant and a autoregressive models.
|
37 |
Adding value to upground drinking water reservoirs: what makes a good yellow perch (Perca flavescens) fishery?Crouch, Ryan T. 01 March 2011 (has links)
No description available.
|
38 |
SPECIES DISTRIBUTION MODELING OF AMERICAN BEECH (FAGUS GRANDIFOLIA EHRH.) DISTRIBUTION IN SOUTHWESTERN OHIOFlessner, Brandon P. 05 May 2014 (has links)
No description available.
|
39 |
Identification of Factors Affecting Contaminant Levels and Determination of Infiltration of Ambient Contaminants in Public Transport Buses Operating on Biodiesel and ULSD FuelsKadiyala, Akhil 30 September 2008 (has links)
No description available.
|
40 |
Development of a Surface Roughness Prediction & Optimization Framework for CNC TurningBennett, Kristin S. January 2024 (has links)
Computer numerical control (CNC) machining is an integral element to the
manufacturing industry for production of components with requirements to meet several
outcome conditions. The surface roughness (Ra) of a workpiece is one of the most
important outcomes in finish machining processes due to it’s direct impact on the
functionality and lifespan of components in their intended applications. Several factors
contribute to the creation of Ra in machining including, but not limited to, the machining
parameters, properties of the workpiece, tool geometry and wear. Alternative to traditional
selection of machining parameters using existing standards and/or expert knowledge,
current studies in literature have examined methods to consider these factors for prediction
and optimization of machining parameters to minimize Ra. These methods span many
approaches including theoretical modelling and simulation, design of experiments,
statistical and machine learning methods. Despite the abundance of research in this area,
challenges remain regarding the generalizability of models for multiple machining
conditions, and lengthy training requirements of methods based solely on machine learning
methods. Furthermore, many machine learning methods focus on static cutting parameters
rather than consideration of properties of the tool and workpiece, and dynamic factors such
as tool wear.
The main contribution of this research was to develop a prediction and optimization
model framework to minimize Ra for finish turning that combines theoretical and machine
learning methods, and can be practically utilized by CNC machine operators for parameter
v
decision making. The presented research work was divided into four distinct objectives.
The first objective of this research focused on analyzing the relationship between the
machining parameters and Ra for three different materials with varying properties (AISI
4340, AISI 316, and CGI 450). This was followed by the second objective that targeted the
development of an Ra prediction framework that utilized a kinematics-based prediction
model with an ensemble gradient boosted regression tree (GBRT) to create a multi-material
model with justified results, while strengthening accuracy with the machine learning
component. The results demonstrated the multi-material model was able to provide
predictions with a root-mean-square error (RMSE) of 0.166 μm and attained 70% of testing
predictions to fall within limits set by the ASME B46.1-2019 standard. This standard was
utilized as an efficient evaluation tool for determining if the prediction accuracy was within
an acceptable range.
The remaining objectives of this research focused on investigating the relationship
between tool wear and Ra through a focused study on AISI 316, followed by application
of the prediction model framework as the fitness function for testing of three different
metaheuristic optimization algorithms to minimize Ra. The results revealed a significant
relationship between tool wear and Ra, which enabled improvement in the prediction
framework through the use of the tool’s total cutting distance for an indicator of tool wear
as an input into the prediction model. Significant prediction improvement was achieved,
demonstrated by metrics including RMSE of 0.108 μm and 87% of predictions were within
the ASME B46.1-2019 limits. The improved prediction model was used as the fitness
function for comparison performance of genetic algorithm (GA), particle swarm
vi
optimization (PSO), and simulated annealing (SA), under constrained and unconstrained
conditions. SA demonstrated superior performance with less than 5% error between the
optimal and experimental Ra when constrained to the experimental data set during
validation testing. The overall results of this research establish the feasibility of a
framework that could be applied in an industrial setting for both prediction of Ra for
multiple materials, and supports the determination of parameters for minimizing Ra
considering the dynamic nature of tool wear. / Thesis / Master of Applied Science (MASc) / The surface quality produced on a workpiece via computer numerical control
(CNC) machining is influenced by many factors, including the machining parameters,
characteristics of the workpiece, and the cutting tool’s geometry and wear. When the
optimal machining parameters are not used, manufacturing companies may incur
unexpected costs associated with scrapped components, as well as time and materials
required for re-machining the component. This research focuses on developing a model to
indirectly predict surface roughness (Ra) in CNC turning, and to provide operators
guidance regarding the optimal machining parameters to ensure the machined surface is
within specifications. A multi-material Ra prediction model was produced to allow for use
under multiple machining conditions. This was enhanced by comparing three different
optimization algorithms to evaluate their suitability with the prediction framework for
providing recommendation on the optimal machining parameters, considering an indicator
for tool wear as an input factor.
|
Page generated in 0.0895 seconds