Nowadays, there is a wide range of forecasting methods and forecasters encounter several challenges during selection of an optimal method for volatility forecasting. In order to make use of wide selection of forecasts, this thesis tests multiple forecast combination methods. Notwithstanding, there exists a plethora of forecast combination literature, combination of traditional methods with machine learning methods is relatively rare. We implement the following combination techniques: (1) simple mean forecast combination, (2) OLS combination, (3) ARIMA on OLS combined fit, (4) NNAR on OLS combined fit and (5) KNN regression on OLS combined fit. To our best knowledge, the latter two combination techniques are not yet researched in academic literature. Additionally, this thesis should help a forecaster with three choice complication causes: (1) choice of volatility proxy, (2) choice of forecast accuracy measure and (3) choice of training sample length. We found that squared and absolute return volatility proxies are much less efficient than Parkinson and Garman-Klass volatility proxies. Likewise, we show that forecast accuracy measure (RMSE, MAE or MAPE) influences optimal forecasts ranking. Finally, we found that though forecast quality does not depend on training sample length, we see that forecast...

Wastewater Treatment Plants (WWTPs) are sophisticated systems that have to sustain long-term qualified performance, regardless of temporally volatile volumes or compositions of the incoming wastewater. Membrane filtration in the Membrane Bioreactors (MBRs) reduces the WWTPs footprint and produces effluents of proper quality. The energy or electric power consumption of the WWTPs, mainly from aeration equipment and pumping, is directly linked to greenhouse gas emission and economic input. Biological treatment requires oxygen from aeration to perform aerobic decomposition of aquatic pollutants, while pumping consumes energy to overcome friction in the channels, piping systems, and membrane filtration. In this thesis, we researched full-scale WWTPs Influent Conditions (ICs) monitoring and forecasting models to facilitate the energy consumption budgeting and raise early alarms when facing latent abnormal events. Accurate and efficient forecasts of ICs could avoid unexpected system disruption, maintain steady product quality, support efficient downstream processes, improve reliability and save energy. We carried out a numerical study of bioreactor microbial ecology for MBRs microbial communities to identify indicator species and typical working conditions that would assist in reactor status confirmation and support energy consumption budgeting. To quantify membrane fouling and cleaning effects at various scales, we proposed quantitative methods based on Matern covariances to analyze biofouling layer thickness and roughness obtained from Optical Coherence Tomography (OCT) images taken from gravitydriven MBRs under various working conditions. Such methods would support practitioners to design suitable data-driven process operation or replacement cycles and lead to quantified WWTPs monitoring and energy saving. For future research, we would investigate data from other full-scale water or wastewater treatment process with higher sampling frequency and apply kernel machine learning techniques for process global monitoring. The forecasting models would be incorporated into optimization scenarios to support data-driven decision-making. Samples from more MBRs would be considered to gather information of microbial community structures and corresponding oxygen-energy consumption in various working conditions. We would investigate the relationship between pressure drop and spatial roughness measures. Anisotropic Matern covariance related metrics would be adopted to quantify the directional effects under various operation and cleaning working conditions.

Submitted by Ronaldo Cesar Dametto (rdametto@uol.com.br) on 2018-09-18T19:17:34Z No. of bitstreams: 1 Dissertação_Completa_Final.pdf: 2885777 bytes, checksum: 05b2d5417efbec72f927cf8a62eef3fb (MD5) / Approved for entry into archive by Lucilene Cordeiro da Silva Messias null (lubiblio@bauru.unesp.br) on 2018-09-20T12:19:07Z (GMT) No. of bitstreams: 1 dametto_rc_me_bauru.pdf: 2877027 bytes, checksum: cee33d724090a01372e1292109af2ce9 (MD5) / Made available in DSpace on 2018-09-20T12:19:07Z (GMT). No. of bitstreams: 1 dametto_rc_me_bauru.pdf: 2877027 bytes, checksum: cee33d724090a01372e1292109af2ce9 (MD5) Previous issue date: 2018-08-06 / O aprendizado de máquina vem sendo utilizado em diferentes segmentos da área financeira, como na previsão de preços de ações, mercado de câmbio, índices de mercado e composição de carteira de investimento. Este trabalho busca comparar e combinar três tipos de algoritmos de aprendizagem de máquina, mais especificamente, o método Ensemble de Redes Neurais Artificias com as redes Multilayer Perceptrons (MLP), auto-regressiva com entradas exógenas (NARX) e Long Short-Term Memory (LSTM) para predição do Índice Bovespa. A amostra da série do Ibovespa foi obtida pelo Yahoo!Finance no período de 04 de janeiro de 2010 a 28 de dezembro de 2017, de periodicidade diária. Foram utilizadas as séries temporais referentes a cotação do Dólar, além de indicadores numéricos da Análise Técnica como variáveis independentes para compor a predição. Os algoritmos foram desenvolvidos através da linguagem Python usando framework Keras. Para avaliação dos algoritmos foram utilizadas as métricas de desempenho MSE, RMSE e MAPE, além da comparação entre as previsões obtidas e os valores reais. Os resultados das métricas indicam bom desempenho de predição pelo modelo Ensemble proposto, obtendo 70% de acerto no movimento do índice, porém, não conseguiu atingir melhores resultados que as redes MLP e NARX, ambas com 80% de acerto. / Different segments of the financial area, such as the forecast of stock prices, the foreign exchange market, the market indices and the composition of investment portfolio, use machine learning. This work aims to compare and combine two types of machine learning algorithms, the Artificial Neural Network Ensemble method with Multilayer Perceptrons (MLP), auto-regressive with exogenous inputs (NARX) and Long Short-Term Memory (LSTM) for prediction of the Bovespa Index. The Bovespa time series samples were obtained daily, using Yahoo! Finance, from January 4th, 2010 to December 28th, 2017. Dollar quotation, Google trends and numerical indicators of the Technical Analysis were used as independent variables to compose the prediction. The algorithms were developed using Python and Keras framework. Finally, in order to evaluate the algorithms, the MSE, RMSE and MAPE performance metrics, as well as the comparison between the obtained predictions and the actual values, were used. The results of the metrics indicate good prediction performance by the proposed Ensemble model, obtaining a 70% accuracy in the index movement, but failed to achieve better results than the MLP and NARX networks, both with 80% accuracy.

[pt] A série temporal é a representação mais comum para a evoluçãao no tempo de uma variável qualquer. Em um problema de previsão de séries temporais, procura-se ajustar um modelo para obter valores futuros da série, supondo que as informações necessárias para tal se encontram no próprio histórico da série. Como os fenômenos representados pelas séries temporais nem sempre existem de maneira isolada, pode-se enriquecer o modelo com os valores históricos de outras séries temporais relacionadas. A estrutura formada por diversas séries de mesmo intervalo e dimensão ocorrendo paralelamente é denominada série temporal multivariada. Esta dissertação propõe uma metodologia de geração de um Sistema de Inferência Fuzzy (SIF) para previsão de séries temporais multivariadas a partir de dados históricos, com o objetivo de obter bom desempenho tanto em termos de acurácia de previsão como no quesito interpretabilidade da base de regras – com o intuito de extrair conhecimento sobre o relacionamento entre as séries. Para tal, são abordados diversos aspectos relativos ao funcionamento e à construção de um SIF, levando em conta a sua complexidade e claridade semântica. O modelo é avaliado por meio de sua aplicação em séries temporais multivariadas da base completa da competição M3, comparandose a sua acurácia com as dos métodos participantes. Além disso, através de dois estudos de caso com dados reais públicos, suas possibilidades de extração de conhecimento são exploradas por meio de dois estudos de caso construídos a partir de dados reais. Os resultados confirmam a capacidade do AutoMFIS de modelar de maneira satisfatória séries temporais multivariadas e de extrair conhecimento da base de dados. / [en] A time series is the most commonly used representation for the evolution of a given variable over time. In a time series forecasting problem, a model aims at predicting the series future values, assuming that all information needed to do so is contained in the series past behavior. Since the phenomena described by the time series does not always exist in isolation, it is possible to enhance the model with historical data from other related time series. The structure formed by several different time series occurring in parallel, each featuring the same interval and dimension, is called a multivariate time series. This dissertation proposes a methodology for the generation of a Fuzzy Inference System (FIS) for multivariate time series forecasting from historical data, aiming at good performance in both forecasting accuracy and rule base interpretability – in order to extract knowledge about the relationship between the modeled time series. Several aspects related to the operation and construction of such a FIS are investigated regarding complexity and semantic clarity. The model is evaluated by applying it to multivariate time series obtained from the complete M3 competition database and by comparing it to other methods in terms of accuracy. In addition knowledge extraction possibilities are explored through two case studies built from actual data. Results confirm that AutoMFIS is indeed capable of modeling time series behaviors in a satisfactory way and of extractig meaningful knowldege from the databases.