Spelling suggestions: "subject:"time series forecasting"" "subject:"lime series forecasting""
41 |
Predicting Electricity Consumption with ARIMA and Recurrent Neural NetworksEnerud, Klara January 2024 (has links)
Due to the growing share of renewable energy in countries' power systems, the need for precise forecasting of electricity consumption will increase. This paper considers two different approaches to time series forecasting, autoregressive moving average (ARMA) models and recurrent neural networks (RNNs). These are applied to Swedish electricity consumption data, with the aim of deriving simple yet efficient predictors. An additional aim is to analyse the impact of day of week and temperature on forecast accuracy. The models are evaluated on both long- and mid-term forecasting horizons, ranging from one day to one month. The results show that neural networks are superior for this task, although stochastic seasonal ARMA models also perform quite well. Including external variables only marginally improved the ARMA predictions, and had somewhat unclear effects on the RNN forecasting accuracy. Depending on the network model used, adding external variables had either a slightly positive or slightly negative impact on prediction accuracy.
|
42 |
Forecasting Volume of Sales During the Abnormal Time Period of COVID-19. An Investigation on How to Forecast, Where the Classical ARIMA Family of Models Fail / Estimering av försäljningsprognoser under den abnorma tidsperioden av coronapandeminGhawi, Christina January 2021 (has links)
During the COVID-19 pandemic, customer shopping habits have changed. Some industries experienced an abrupt shift during the pandemic outbreak while others navigate in new normal states. For some merchants, the highly-uncertain new phenomena of COVID-19 expresses as outliers in time series of volume of sales. As forecasting models tend to replicate past behavior of a series, outliers complicates the procedure of forecasting; the abnormal events tend to unreliably replicate in forecasts of the subsequent year(s). In this thesis, we investigate how to forecast volume of sales during the abnormal time period of COVID-19, where the classical ARIMA family of models produce unreliable forecasts. The research revolved around three time series exhibiting three types of outliers: a level shift, a transient change and an additive outlier. Upon detecting the time period of the abnormal behavior in each series, two experiments were carried out as attempts for increasing the predictive accuracy for the three extreme cases. The first experiment was related to imputing the abnormal data in the series and the second was related to using a combined model of a pre-pandemic and a post-abnormal forecast. The results of the experiments pointed at significant improvement of the mean absolute percentage error at significance level alpha=0.05 for the level shift when using a combined model compared to the pre-pandemic best-fit SARIMA model. Also, at significant improvement for the additive outlier when using a linear impute. For the transient change, the results pointed at no significant improvement in the predictive accuracy of the experimental models compared to the pre-pandemic best-fit SARIMA model. For the purpose of generalizing to large-scale conclusions of methods' superiority or feasibility for particular abnormal behaviors, empirical evaluations are required. The proposed experimental models were discussed in terms of reliability, validity and quality. By residual diagnostics, it was argued that the models were valid; however, that further improvements can be made. Also, it was argued that the models fulfilled desired attributes of simplicity, scaleability and flexibility. Due to the uncertain phenomena of the COVID-19 pandemic, it was suggested not to take the outputs as long-term reliable solutions. Rather, as temporary solutions requiring more frequent updating of forecasts. / Under coronapandemin har kundbeteenden och köpvanor förändrats. I vissa branscher upplevdes ett plötsligt skifte vid pandemiutbrottet och i andra navigerar handlare i nya normaltillstånd. För vissa handlare är förändringarna så pass distinkta att de yttrar sig som avvikelser i tidsserier över försäljningsvolym. Dessa avvikelser komplicerar prognosering. Då prognosmodeller tenderar att replikera tidsseriers tidigare beteenden, tenderas det avvikande beteendet att replikeras i försäljningsprognoser för nästkommande år. I detta examensarbete ämnar vi att undersöka tillvägagångssätt för att estimera försäljningsprognoser under den abnorma tidsperioden av COVID-19, då klassiska tidsseriemodeller felprognoserar. Detta arbete kretsade kring tre tidsserier som uttryckte tre avvikelsertyper: en nivåförskjutning, en övergående förändring och en additiv avvikelse. Efter att ha definierat en specifik tidsperiod relaterat till det abnorma beteendet i varje tidsserie, utfördes två experiment med syftet att öka den prediktiva noggrannheten för de tre extremfallen. Det första experimentet handlade om att ersätta den abnorma datan i varje serie och det andra experimentet handlade om att använda en kombinerad pronosmodell av två estimerade prognoser, en pre-pandemisk och en post-abnorm. Resultaten av experimenten pekade på signifikant förbättring av ett absolut procentuellt genomsnittsfel för nivåförskjutningen vid användande av den kombinerade modellen, i jämförelse med den pre-pandemiskt bäst passande SARIMA-modellen. Även, signifikant förbättring för den additiva avvikelsen vid ersättning av abnorm data till ett motsvarande linjärt polynom. För den övergående förändringen pekade resultaten inte på en signifikant förbättring vid användande av de experimentella modellerna. För att generalisera till storskaliga slutsatser giltiga för specifika avvikande beteenden krävs empirisk utvärdering. De föreslagna modellerna diskuterades utifrån tillförlitlighet, validitet och kvalitet. Modellerna uppfyllde önskvärda kvalitativa attribut såsom enkelhet, skalbarhet och flexibilitet. På grund av hög osäkerhet i den nuvarande abnorma tidsperioden av coronapandemin, föreslogs det att inte se prognoserna som långsiktigt pålitliga lösningar, utan snarare som tillfälliga tillvägagångssätt som regelbundet kräver om-prognosering.
|
43 |
TDNet : A Generative Model for Taxi Demand Prediction / TDNet : En Generativ Modell för att Prediktera TaxiefterfråganSvensk, Gustav January 2019 (has links)
Supplying the right amount of taxis in the right place at the right time is very important for taxi companies. In this paper, the machine learning model Taxi Demand Net (TDNet) is presented which predicts short-term taxi demand in different zones of a city. It is based on WaveNet which is a causal dilated convolutional neural net for time-series generation. TDNet uses historical demand from the last years and transforms features such as time of day, day of week and day of month into 26-hour taxi demand forecasts for all zones in a city. It has been applied to one city in northern Europe and one in South America. In northern europe, an error of one taxi or less per hour per zone was achieved in 64% of the cases, in South America the number was 40%. In both cities, it beat the SARIMA and stacked ensemble benchmarks. This performance has been achieved by tuning the hyperparameters with a Bayesian optimization algorithm. Additionally, weather and holiday features were added as input features in the northern European city and they did not improve the accuracy of TDNet.
|
44 |
Predição de séries temporais econômicas por meio de redes neurais artificiais e transformada Wavelet: combinando modelo técnico e fundamentalista / Technique of economic time series prediction by artificial neural network and wavelet transform: joining technical and fundamental modelSoares, Anderson da Silva 07 March 2008 (has links)
Este trabalho apresenta um método de predição não linear de séries temporais econômicas. O método baseia-se na análise técnica e fundamentalista de cotação de ações, filtragem wavelet, seleção de padrões e redes neurais artificiais. No modelo técnico emprega-se a transformada wavelet para filtrar a série temporal econômica de comportamentos aleatórios ou não econômicos. Após a filtragem dos dados o algoritmo de projeções sucessivas é utilizado para a seleção de padrões de treinamento para a rede neural artificial, com o objetivo de selecionar os padrões de comportamento mais importantes na série. No modelo fundamentalista utiliza-se variáveis econômicas que podem estar correlacionadas com a série, com o objetivo de aprimorar a predição da série na rede neural artificial. Para avaliação do método são utilizados dados de séries temporais econômicas referentes à cotação de preços de ações negociadas na bolsa de valores de São Paulo, onde os resultados da predição do comportamento futuro são comparados com modelos matemáticos clássicos e com o modelo convencional, que se baseia somente na análise técnica. Apresenta-se uma comparação dos resultados entre modelos técnicos, modelos matemáticos e o método proposto. O modelo matemático utilizado (ARIMA) apresentou seu melhor desempenho em séries com pouca variância, porém com desempenho inferior quando comparado com o modelo técnico e com o método proposto. A avaliação do erro de predição em termos de RMSEP evidenciou que o método proposto apresenta os melhores resultados em relação aos demais métodos. / This work presents a method for predicting nonlinear economic time series. The method is based on fundamental and technical analysis of script quotation, a multiscale wavelet filtering, pattern selection and artificial neural networks. In the technical model is used the wavelet transform in order to filter the economic time series from random or not economic behaviors. After the data filtering, the successive projections algorithm was used for the training pattern selection to the artificial neural network. In the fundamentalist model is used financial and macroeconomics variables that is correlated with the time serie in order to improve the network forecasting. For the evaluation of the proposed method are used temporal series data related to scrips prices quotation of São Paulo stock market. It presents a comparison of the results between technical model, mathematical model and proposed method. The mathematical model (ARIMA) presented better results in series with few variance, however have low performance when compared with the technical model and with the proposed method. The prediction error evaluation shows that the proposed method has better results than the other methods.
|
45 |
Predição de séries temporais econômicas por meio de redes neurais artificiais e transformada Wavelet: combinando modelo técnico e fundamentalista / Technique of economic time series prediction by artificial neural network and wavelet transform: joining technical and fundamental modelAnderson da Silva Soares 07 March 2008 (has links)
Este trabalho apresenta um método de predição não linear de séries temporais econômicas. O método baseia-se na análise técnica e fundamentalista de cotação de ações, filtragem wavelet, seleção de padrões e redes neurais artificiais. No modelo técnico emprega-se a transformada wavelet para filtrar a série temporal econômica de comportamentos aleatórios ou não econômicos. Após a filtragem dos dados o algoritmo de projeções sucessivas é utilizado para a seleção de padrões de treinamento para a rede neural artificial, com o objetivo de selecionar os padrões de comportamento mais importantes na série. No modelo fundamentalista utiliza-se variáveis econômicas que podem estar correlacionadas com a série, com o objetivo de aprimorar a predição da série na rede neural artificial. Para avaliação do método são utilizados dados de séries temporais econômicas referentes à cotação de preços de ações negociadas na bolsa de valores de São Paulo, onde os resultados da predição do comportamento futuro são comparados com modelos matemáticos clássicos e com o modelo convencional, que se baseia somente na análise técnica. Apresenta-se uma comparação dos resultados entre modelos técnicos, modelos matemáticos e o método proposto. O modelo matemático utilizado (ARIMA) apresentou seu melhor desempenho em séries com pouca variância, porém com desempenho inferior quando comparado com o modelo técnico e com o método proposto. A avaliação do erro de predição em termos de RMSEP evidenciou que o método proposto apresenta os melhores resultados em relação aos demais métodos. / This work presents a method for predicting nonlinear economic time series. The method is based on fundamental and technical analysis of script quotation, a multiscale wavelet filtering, pattern selection and artificial neural networks. In the technical model is used the wavelet transform in order to filter the economic time series from random or not economic behaviors. After the data filtering, the successive projections algorithm was used for the training pattern selection to the artificial neural network. In the fundamentalist model is used financial and macroeconomics variables that is correlated with the time serie in order to improve the network forecasting. For the evaluation of the proposed method are used temporal series data related to scrips prices quotation of São Paulo stock market. It presents a comparison of the results between technical model, mathematical model and proposed method. The mathematical model (ARIMA) presented better results in series with few variance, however have low performance when compared with the technical model and with the proposed method. The prediction error evaluation shows that the proposed method has better results than the other methods.
|
46 |
Novel computationally intelligent machine learning algorithms for data mining and knowledge discoveryGheyas, Iffat A. January 2009 (has links)
This thesis addresses three major issues in data mining regarding feature subset selection in large dimensionality domains, plausible reconstruction of incomplete data in cross-sectional applications, and forecasting univariate time series. For the automated selection of an optimal subset of features in real time, we present an improved hybrid algorithm: SAGA. SAGA combines the ability to avoid being trapped in local minima of Simulated Annealing with the very high convergence rate of the crossover operator of Genetic Algorithms, the strong local search ability of greedy algorithms and the high computational efficiency of generalized regression neural networks (GRNN). For imputing missing values and forecasting univariate time series, we propose a homogeneous neural network ensemble. The proposed ensemble consists of a committee of Generalized Regression Neural Networks (GRNNs) trained on different subsets of features generated by SAGA and the predictions of base classifiers are combined by a fusion rule. This approach makes it possible to discover all important interrelations between the values of the target variable and the input features. The proposed ensemble scheme has two innovative features which make it stand out amongst ensemble learning algorithms: (1) the ensemble makeup is optimized automatically by SAGA; and (2) GRNN is used for both base classifiers and the top level combiner classifier. Because of GRNN, the proposed ensemble is a dynamic weighting scheme. This is in contrast to the existing ensemble approaches which belong to the simple voting and static weighting strategy. The basic idea of the dynamic weighting procedure is to give a higher reliability weight to those scenarios that are similar to the new ones. The simulation results demonstrate the validity of the proposed ensemble model.
|
47 |
Fast Algorithms for Mining Co-evolving Time SeriesLi, Lei 01 September 2011 (has links)
Time series data arise in many applications, from motion capture, environmental monitoring, temperatures in data centers, to physiological signals in health care. In the thesis, I will focus on the theme of learning and mining large collections of co-evolving sequences, with the goal of developing fast algorithms for finding patterns, summarization, and anomalies. In particular, this thesis will answer the following recurring challenges for time series:
1. Forecasting and imputation: How to do forecasting and to recover missing values in time series data?
2. Pattern discovery and summarization: How to identify the patterns in the time sequences that would facilitate further mining tasks such as compression, segmentation and anomaly detection?
3. Similarity and feature extraction: How to extract compact and meaningful features from multiple co-evolving sequences that will enable better clustering and similarity queries of time series?
4. Scale up: How to handle large data sets on modern computing hardware?
We develop models to mine time series with missing values, to extract compact representation from time sequences, to segment the sequences, and to do forecasting. For large scale data, we propose algorithms for learning time series models, in particular, including Linear Dynamical Systems (LDS) and Hidden Markov Models (HMM). We also develop a distributed algorithm for finding patterns in large web-click streams. Our thesis will present special models and algorithms that incorporate domain knowledge. For motion capture, we will describe the natural motion stitching and occlusion filling for human motion. In particular, we provide a metric for evaluating the naturalness of motion stitching, based which we choose the best stitching. Thanks to domain knowledge (body structure and bone lengths), our algorithm is capable of recovering occlusions in mocap sequences, better in accuracy and longer in missing period. We also develop an algorithm for forecasting thermal conditions in a warehouse-sized data center. The forecast will help us control and manage the data center in a energy-efficient way, which can save a significant percentage of electric power consumption in data centers.
|
48 |
[en] PREDICTING TRENDS IN THE STOCK MARKET / [pt] PREDIZENDO TENDÊNCIAS NA BOLSA DE VALORESJOAO PAULO FORNY DE MELO 02 August 2018 (has links)
[pt] Investidores estão sempre à procura de uma vantagem. Porém, tradicionais teorias financeiras nos dizem que tentar predizer tendências na bolsa de valores é um esforço em vão, uma vez que seguem um passeio aleatório, i.e., um processo estocástico ou randômico. Além disso, afirma-se que o mercado é eficiente de maneira que sempre incorpora e reflete toda informação relevante, o que torna impossível bater o mercado. Recentemente, com o crescimento da web e aumento da disponibilidade de dados em conjunto
com a evolução dos algoritmos de Aprendizado de Máquina, diversos trabalhos tem aplicado técnicas de Processamento de Linguagem Natural em notícias financeiras e dados de redes sociais para prever variações do preço de ações. Consequentemente, estão surgindo fortes evidências que o mercado pode, em algum grau, ser previsto. Este trabalho descreve o desenvolvimento de uma aplicação baseada em Aprendizado de Máquina para realizar a predição de tendências no mercado de ações, i.e., variações negativas, positivas ou neutras de preços com granularidade de minuto. Avaliamos o sistema usando dados de cotação de ações da B3 (Brasil Bolsa Balcão), antiga BM&FBOVESPA, e um dataset de tópicos mais relevantes buscados no Google Search e seus artigos relacionados, que são disponibilizados pela
plataforma Google Trends e coletados, minuto a minuto, de 15/08/2016 até 10/07/2017. Os experimentos mostram que esses dados provêem informação relevante para a tarefa em questão, onde conseguimos uma acurácia de 69.24 porcento para a predição de tendências do ativo PETR4, criando alguma / [en] Investors are always looking for an edge. However, traditional economic theories tell us that trying to predict short-term stock price movements is wasted effort, since it approximate a random walk, i.e., a stochastic or random process. Besides, these theories state that the market is efficient enough to always incorporate and reflect all relevant information, making it impossible to beat the market. In recent years, with the growth of the web and data availability in conjunction with advances in Machine Learning, a number of works are using Natural Language Processing to predict share price variations based on financial news and social networks data. Therefore, strong evidences are surfacing that the market can, in some level, be predicted. This work describes the development of an application based on Machine Learning to predict trends in the stock market, i.e., positive, negative or neutral price variations with minute granularity. We evaluate our system using B3 (Brasil Bolsa Balcão), formerly BM&FBOVESPA, stock quotes data, and a dataset with the most relevant topics of Google Search and its related articles, provided by the Google Trends platform and collected, minute by minute, from 08/15/2016 to 07/10/2017. The
experiments show that this data provides useful information to the task at hand, in which we achieve 69.24 per cent accuracy predicting trends for the PETR4 stock, creating some leverage to make profits possible with intraday trading.
|
49 |
[en] TEMPORAL NEURAL NETWORKS FOR TREATING TIME VARIANT SERIES / [pt] REDES NEURAIS TEMPORAIS PARA O TRATAMENTO DE SISTEMAS VARIANTES NO TEMPOCLAVER PARI SOTO 07 November 2005 (has links)
[pt] As RNA Temporais, em função de sua estrutura, consideram o
tempo na sua operação, incorporando memória de curto prazo
distribuída na rede em todos os neurônios escondidos e em
alguns dos casos nos neurônios de saída. Esta classe de
redes é utilizada para representar melhor a natureza
temporal dos sistemas dinâmicos. Em contraste, a RNA
estática tem uma estrutura apropriada para tarefas de
reconhecimento de padrões, classificação e outras de
natureza estática ou estacionária tendo sido utilizada com
sucesso em diversas aplicações.
O objetivo desta tese, portanto foi estudar a teoria e
avaliar o desempenho das Redes Neurais Temporais em
comparação com as Redes Neurais Estáticas, em aplicações
de sistemas dinâmicos. O desenvolvimento desta pesquisa
envolveu 3 etapas principais: pesquisa bibliográfica das
metodologias desenvolvidas para RNA Temporais; seleção e
implementação de modelos para a avaliação destas redes; e
estudo de casos.
A pesquisa bibliográfica permitiu compila e classificar os
principais trabalhos sobre RNA Temporais. Tipicamente,
estas redes podem ser classificadas em dois grupos: Redes
com Atraso no Tempo e Redes Recorrentes.
Para a análise de desempenho, selecionou-se uma redee de
cada grupo para implementação. Do primeiro grupo foi
selecionada a Rede FIR, onde as sinapses são filtros FIR
(Finite-duration Impulse Response) que representam a
natureza temporal do problema. A rede FIR foi selecionada
por englobar praticamente, todos os outros métodos de sua
classe e apresentar um modelo matemático mais formal. Do
segundo grupo, considerou-se a rede recorrente de Elman
que apresenta realimentação global de cada um dos
neurônios escondidos para todos eles.
No estudo de casos testou-se o desempenho das redes
selecionadas em duas linhas de aplicação: previsão de
séries temporais e processamento digital de sinais. No
caso de previsão de séries temporais, foram utilizadas
séries de consumo de energia elétrica, comparando-se os
resultados com os encontrados na literatura a partir de
métodos de Holt-Winters, Box & Jenkins e RNA estáticas. No
caso da aplicação das RNA em processamento digital de
sinais, utilizou-se a filtragem de ruído em sinais de voz
onde foram feitas comparações com os resultados
apresentados pelo filtro neural convencional, que é uma
rede feed-forward multicamada com o algoritmo de
retropropagação para o aprendizado.
Este trabalho demonstrou na prática que as RNA temporais
conseguem capturar as características dos processos
temporais de forma mais eficiente que as RNA Estatísticas
e outros métodos tradicionais, podendo aprender
diretamente o comportamento não estacionário das séries
temporais. Os resultados demonstraram que a rede neural
FIR e a rede Elman aprendem melhor a complexidade dos
sinais de voz. / [en] This dissertation investigates the development of
Artificial Neural Network (ANN) in the solution of
problems where the patterns presented to the network have
a temporary relationship to each other, such as time
series forecast and voice processing.
Temporary ANN considers the time in its operation,
incorporating memory of short period distributed in the
network in all the hidden neurons and in the output
neurons in some cases. This class of network in better
used to represent the temporary nature of the dynamic
systems. In contrast, Static ANN has a structure adapted
for tasks of pattern recognition, classification and
another static or stationary problems, achieving great
success in several applications. Considered an universal
approximator, Static ANN has also been used in
applications of dynamic systems, through some artifices in
the input of the network and through statistical data pre-
processings.
The objective of this work is, therefore to study
the theory and evaluate the performance of Temporal ANN,
in comparison with Static ANN, in applications of dynamics
systems. The development of this research involved 3 main
stages: bibliographical research of the methodologies
developed for Temporal ANN; selection and implementation
of the models for the evaluation of these networks; and
case studies.
The bibliographical research allowed to compile
and to classify the main on Temporal ANN, Typically, these
network was selected, where the synapses are filters FIR
(Finite-duration Impulse Response) that represent the
temporary nature of the problem. The FIR network has been
selected since it includes practically all other methods
of its class, presenting a more formal mathematical model.
On the second group, the Elman recurrent network was
considered, that presents global feedback of each neuron
in the hidden layer to all other neurons in this layer.
In the case studies the network selected have been
tested in two application: forecast of time series and
digital signal processing. In the case of forecast, result
of electric energy consumption time series prediction were
compared with the result found in the literature such as
Holt-Winters, Box & Jenkins and Static ANN methods. In the
case of the application of processing where the
comparisons were made with the results presented by the
standard neural filter, made of a multilayer feed-forward
network with the back propagation learning algorithm.
This work showed in practice that Temporal ANN
captures the characteristics of the temporary processes in
a more efficient way that Static ANN and other methods,
being able to learn the non stationary behavior of the
temporary series directly. The results showed that the FIR
neural network and de Elman network learned better the
complexity of the voice signals.
|
50 |
Memórias associativas L-fuzzy com ênfase em memórias associativas fuzzy intervalares / L-fuzzy associative memories with an emphasis on interval-valued fuzzy associative memoriesSchuster, Tiago, 1987- 26 August 2018 (has links)
Orientador: Peter Sussner / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-26T17:27:37Z (GMT). No. of bitstreams: 1
Schuster_Tiago_M.pdf: 2910336 bytes, checksum: 1f5147831dd6410a0fdb0c0fa53d94c8 (MD5)
Previous issue date: 2015 / Resumo: As últimas décadas têm testemunhado a emergência de uma variedade de abordagens à resolução de problemas com base na computação em reticulados como, por exemplo, as redes neurais morfológicas e os modelos neurocomputação e de raciocínio fuzzy em reticulados. Usamos aqui o termo "reticulado'' no sentido dado no trabalho seminal de Birkhoff. A teoria dos reticulados nasceu da álgebra booleana e tem um grande leque de aplicações como a análise de conceitos formais, a inteligência computacional, a teoria dos conjuntos fuzzy e a morfologia matemática (MM). A MM em reticulados completos representa a base teórica para uma série de modelos de inteligência computacional conhecidos como redes neurais morfológicas (MNNs), que incluem as memórias associativas morfológicas em tons de cinza e as memórias associativas morfológicas fuzzy (FMAMs). As últimas décadas têm testemunhado a emergência de uma variedade de abordagens à resolução de problemas com base na computação em reticulados como, por exemplo, as redes neurais morfológicas e os modelos neurocomputação e de raciocínio fuzzy em reticulados. Usamos aqui o termo "reticulado'' no sentido dado no trabalho seminal de Birkhoff. A teoria dos reticulados nasceu da álgebra booleana e tem um grande leque de aplicações como a análise de conceitos formais, a inteligência computacional, a teoria dos conjuntos fuzzy e a morfologia matemática (MM). A MM em reticulados completos representa a base teórica para uma série de modelos de inteligência computacional conhecidos como redes neurais morfológicas (MNNs), que incluem as memórias associativas morfológicas em tons de cinza e as memórias associativas morfológicas fuzzy (FMAMs). O advento de sistemas fuzzy tipo-2 sugere o desenvolvimento das FMAMs tipo-2 e em particular FMAMs tipo-2 intervalar, ou FMAMs intervalar (IV-FMAMs). Observemos aqui que a classe dos conjuntos fuzzy, assim como a dos conjuntos fuzzy tipo-2, fuzzy tipo-2 intervalar e fuzzy intervalar sobre um universo arbitrário em conjunção com diferentes escolhas de ordens parciais formam classes de conjuntos L-fuzzy, em que L denota um reticulado completo. Nessa dissertação de mestrado, introduzimos as memórias associativas L-fuzzy (L-FMAMs) com base na morfologia matemática L-fuzzy (L-FMM). Nosso foco está nas FMAMs fuzzy intervalar, uma vez que sistemas fuzzy intervalar têm sido aplicados com sucesso em problemas de engenharia, computação com palavras e raciocínio aproximado. Nós aplicamos os modelos de IV-FMAMs em conjunção com a técnica de clusterização fuzzy c-means intervalar a um problema de predição de série temporal, especificamente o prognóstico da vazão mensal de uma usina hidroelétrica localizada no sudeste brasileiro. Por fim, comparamos as predições produzidas pela abordagem das IV-FMAMs com aquelas produzidas por modelos competitivos da literatura / Abstract: The last decade has witnessed the emergence of a variety of lattice computing approaches towards computational intelligence such as morphological neural networks and fuzzy lattice reasoning / neuro-computing models. Here, the technical term "lattice" refers to a lattice in the mathematical sense of Birkhoff's seminal work. Lattice theory grew out of Boolean algebra and has found a wide range of applications such as mathematical morphology, formal concept analysis, computational intelligence, and fuzzy set theory. Mathematical morphology on complete lattices represents the theoretical basis for a range of computational intelligence models known as morphological neural networks (MNNs) including gray-scale and fuzzy morphological associative memories (FMAMs). The advent of type-2 fuzzy systems suggests the development of type-2 FMAMs and in particular interval type-2 FMAMs or interval-valued FMAMs. Recall that the class of fuzzy sets as well as the classes of type-2, interval type-2, and interval-valued fuzzy sets over an arbitrary universe together with different choices of partial orderings form classes of L-fuzzy sets, where L denotes a complete lattice. In this master's thesis, we introduce L-fuzzy morphological associative memories (L-FMAMs) on the basis of L-FMM. Our focus is on interval-valued FMAMs since interval type-2 fuzzy systems, have found various applications in engineering, computing with words, and approximate reasoning. We applied the aforementioned interval-valued FMAM models in conjunction with the interval-valued fuzzy c-means clustering technique to a time-series prediction problem in industry, namely the problem of forecasting the average monthly streamflow of a hydroelectric plant located in southeastern Brazil, and compared the predictions produced by the IV-FMAM approach with the ones produced by a number of competitive models from the literature / Mestrado / Matematica Aplicada / Mestre em Matemática Aplicada
|
Page generated in 0.1019 seconds