Uppsatsen ämnar att försöka förklara hur olika variabler angående matchbilden i en fotbollsmatch påverkar slutresultatet. Dessa variabler är uppdelade i prestationsvariabler och kvalitétsvariabler. Prestationsvariablerna är baserade på prestationsindikatorer inspirerat av Hughes och Bartlett (2002). Kvalitétsvariablerna förklarar hur bra de olika lagen är. Som verktyg för att uppnå syftet används olika klassificeringsmodeller utifrån både prestationsvariablerna och kvalitétsvariablerna. Först undersöktes vilka prestationsindikatorer som var viktigast. Den bästa modellen klassificerade cirka 60 % rätt och rensningar och skott på mål var de viktigaste prestationsvariablerna. Sedan undersöktes vilka prediktionsvariabler som var bäst. Den bästa modellen klassificerade rätt slutresultat cirka 88 % av matcherna. Utifrån vad författarna ansågs vara de viktigaste prediktionsvariablerna skapades en prediktionsmodell med färre variabler. Denna lyckades klassificera rätt cirka 86 % av matcherna. Prediktionsmodellen var konstruerad med spelarbetyg, odds på oavgjort och domare.

The present research aims to develop a novel technique for creation of composite riot helmet shells with reinforcing fibre continuity for better protection against low velocity impacts. In this research an innovative, simple and effective method of making a single-piece continuously textile reinforced helmet shell by vacuum bagging has been established and discussed. This technique also includes the development of solid collapsible moulding apparatus from non-woven fibres. Angle-interlock fabric due to its good mouldability, low shear rigidity and ease of production is used in this research. Several wrinkle-free single- piece composite helmet shells have been manufactured. Low-velocity impact test on the continuously reinforced helmet shells has been carried out. For this purpose an in-house helmet shell testing facility has been developed. Test rig has been designed in such a way that the impact test can be carried out at different locations at the riot helmet shell. Low-velocity impact test has been successfully conducted on the developed test rig. The practical experimentation and analysis revealed that the helmet shell performance against impact is dependent on the impact location. The helmet shell top surface has better impact protection as compared to helmet shell side and back location. Moreover, the helmet shell side is the most at risk location for the wearer. Finite Element models were created and simulated in Abaqus software to investigate the impact performance of single-piece helmet shells at different impact locations. Models parts have been designed in Rhinoceros software. Simulated results are validated by the experimental result which shows that the helmet top position is the safest position against an impact when it is compared to helmet back and helmet side positions.

The number of statistical and mathematical credit risk models that financial institutions use and manage due to international and domestic regulatory pressures in recent years has steadily increased. This thesis examines the evolution of model risk management and provides some guidance on how to effectively build and manage different bagging and boosting machine learning techniques for estimating expected credit losses. It examines the pros and cons of these machine learning models and benchmarks them against more conventional models used in practice. It also examines methods for improving their interpretability in order to gain comfort and acceptance from auditors and regulators. To the best of this author’s knowledge, there are no academic publications which review, compare, and provide effective model risk management guidance on these machine learning techniques with the purpose of estimating expected credit losses. This thesis is intended for academics, practitioners, auditors, and regulators working in the model risk management and expected credit loss forecasting space. / Dissertation / Doctor of Philosophy (PhD)

The aim of this paper is first of all to determine whether deep learning methods can recover trading strategies based on historical price and volume data, with scarcity of real data in mind. The second aim is to evaluate the methods to generate a deep learning blueprint for strategy extraction. Trading strategies can be built on many different types of data, often combined from different areas. In this paper, we focus on trading strategies based solely on historical price and volume data to limit the scope of the problem. Combinations of different deep learning architectures and methods such as transfer- and ensemble methods were evaluated. The results clearly show that deep learning models can recover relatively complex trading strategies to some extent. Models leveraging transfer learning outperform other models when data is scarce and ensemble methods elevate performance in certain regards. / Målet med denna rapport är i första hand att ta reda på om djupinlärningsmetoder kan återskapa handlingsstragetier baserat på historiska priser och volymdata, med vetskapen att datan är begränsad. Det andra målet är att utvärdera metoder för att skapa en djupinlärningsmall för att utvinna handelsstrategier. Handelsstrategier kan vara byggda på många olika datatyper, ofta i kombination från olika områden. I denna rapport fokuserar vi på strategier som enbart är baserade på historiska priser och volymdata för att begränsa problemet. Kombinationer av olika djupinlärningsarkitekturer tillsammans med metoder som till exempel överföringsinlärning och ensembleinlärning utvärderades. Resultaten visar tydligt att djupinlärningsmodeller kan återskapa relativt komplexa handlingsstrategier. Modeller som utnyttjade överföringsinlärning presterade bättre än andra modeller när datan var begränsad och ensembleinlärning ökade prestandan ytterligare i vissa sammanhang. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

[pt] O objetivo deste estudo foi explorar o problema de churn em seguros de vida, no sentido de prever se o cliente irá cancelar o produto nos próximos 6 meses. Atualmente, métodos de machine learning vêm se popularizando para este tipo de análise, tornando-se uma alternativa ao tradicional método de modelagem da probabilidade de cancelamento através da regressão logística. Em geral, um dos desafios encontrados neste tipo de modelagem é que a proporção de clientes que cancelam o serviço é relativamente pequena. Para isso, este estudo recorreu a técnicas de balanceamento para tratar a base naturalmente desbalanceada – técnicas de undersampling, oversampling e diferentes combinações destas duas foram utilizadas e comparadas entre si. As bases foram utilizadas para treinar modelos de Bagging, Random Forest e Boosting, e seus resultados foram comparados entre si e também aos resultados obtidos através do modelo de Regressão Logística. Observamos que a técnica SMOTE-modificado para balanceamento da base, aplicada ao modelo de Bagging, foi a combinação que apresentou melhores resultados dentre as combinações exploradas. / [en] The purpose of this study is to explore the churn problem in life insurance, in the sense of predicting if the client will cancel the product in the next 6 months. Currently, machine learning methods are becoming popular in this type of analysis, turning it into an alternative to the traditional method of modeling the probability of cancellation through logistics regression. In general, one of the challenges found in this type of modelling is that the proportion of clients who cancelled the service is relatively small. For this, the study resorted to balancing techniques to treat the naturally unbalanced base – under-sampling and over-sampling techniques and different combinations of these two were used and compared among each other. The bases were used to train models of Bagging, Random Forest and Boosting, and its results were compared among each other and to the results obtained through the Logistics Regression model. We observed that the modified SMOTE technique to balance the base, applied to the Bagging model, was the combination that presented the best results among the explored combinations.

[pt] O presente trabalho traz 6 diferentes técnicas de previsão para a variação mensal do Índice da Produção Industrial americana em 3 ambientes diferentes totalizando 18 modelos. No primeiro ambiente foram usados como variáveis explicativas a própria defasagem da variação mensal do Índice da produção industrial e outras 55 variáveis de mercado e de expectativa tais quais retornos setoriais, prêmio de risco de mercado, volatilidade implícita, prêmio de taxa de juros (corporate e longo prazo), sentimento do consumidor e índice de incerteza. No segundo ambiente foi usado à data base do FRED com 130 variáveis econômicas como variáveis explicativas. No terceiro ambiente foram usadas as variáveis mais relevantes do ambiente 1 e do ambiente 2. Observa-se no trabalho uma melhora em prever o IP contra um modelo AR e algumas interpretações a respeito do comportamento da economia americana nos últimos 45 anos (importância de setores econômicos, períodos de incerteza, mudanças na resposta a prêmio de risco, volatilidade e taxa de juros). / [en] This thesis presents 6 different forecasting techniques for the monthly variation of the American Industrial Production Index in 3 different environments, totaling 18 models. In the first environment, the lags of the monthly variation of the industrial production index and other 55 market and expectation variables such as sector returns, market risk premium, implied volatility, and interest rate risk premiums (corporate premium and long term premium), consumer sentiment and uncertainty index. In the second environment was used the FRED data base with 130 economic variables as explanatory variables. In the third environment, the most relevant variables of environment 1 and environment 2 were used. It was observed an improvement in predicting IP against an AR model and some interpretations regarding the behavior of the American economy in the last 45 years (importance of sectors, uncertainty periods, and changes in response to risk premium, volatility and interest rate).

Noise is defined as any undesired sound. Urban noise and its effect on citizens area significant environmental problem, and the increasing level of noise has become a critical problem in some cities. Fortunately, noise pollution can be mitigated by better planning of urban areas or controlled by administrative regulations. However, the execution of such actions requires well-established systems for noise monitoring. In this thesis, we present a solution for noise measurement and classification using a low-power and inexpensive IoT unit. To measure the noise level, we implement an algorithm for calculating the sound pressure level in dB. We achieve a measurement error of less than 1 dB. Our machine learning-based method for noise classification uses Mel-frequency cepstral coefficients for audio feature extraction and four supervised classification algorithms (that is, support vector machine, k-nearest neighbors, bootstrap aggregating, and random forest). We evaluate our approach experimentally with a dataset of about 3000 sound samples grouped in eight sound classes (such as car horn, jackhammer, or street music). We explore the parameter space of the four algorithms to estimate the optimal parameter values for the classification of sound samples in the dataset under study. We achieve noise classification accuracy in the range of 88% – 94%.

Submitted by Livia Mello (liviacmello@yahoo.com.br) on 2016-09-28T18:01:55Z No. of bitstreams: 1 DissGCM.pdf: 2068084 bytes, checksum: 4d89da9569508f8b5d13a8b899ad055a (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-04T19:00:31Z (GMT) No. of bitstreams: 1 DissGCM.pdf: 2068084 bytes, checksum: 4d89da9569508f8b5d13a8b899ad055a (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-04T19:00:38Z (GMT) No. of bitstreams: 1 DissGCM.pdf: 2068084 bytes, checksum: 4d89da9569508f8b5d13a8b899ad055a (MD5) / Made available in DSpace on 2016-10-04T19:00:49Z (GMT). No. of bitstreams: 1 DissGCM.pdf: 2068084 bytes, checksum: 4d89da9569508f8b5d13a8b899ad055a (MD5) Previous issue date: 2015-12-14 / Não recebi financiamento / The quest for increased productivity has become a mantra repeated ad nauseam in many companies immersed in a globalized market. In this context, many computational techniques have becoming more popular, gaining followers, aiding and refining the process of decision-making. Among the various techniques available, the discrete event simulation stands out, as it allows studying the behavior of systems, real or not, in various conditions, allowing hypotheses to be tested without physical and financial resources are used. In the case of the animal feed industry, this technique becomes a very important tool, especially in the short term planning which involves the management of the floor operations. The animal feed industry is part of the agribusiness chain, and as such, has its inputs internationally listed, commodities, thus effectively managing its installed capacity is a strategic advantage for differentiation before the market needs in terms of cost, time and quality. In this sense, the objective of this study was to develop a discrete simulation model to assist the decision-making process on increasing the rate of bagging an animal feed industry, located in the state of São Paulo. For this study it has been used the Arena® software, Rockwell Software, and as a method of research modeling and simulation, and the simulation model development stages followed the methodology proposed by Law and Kelton (2000) and Banks (2010). Data were always collected with the same operator at the same time. As a result of simulation of the proposed model was possible to analyze different scenarios, assessing the dynamics of the system and with the performance indicators the equipment utilization rate, the amount of products produced and the consumption of electricity and natural gas per ton of product produced. Whereas the use of discrete simulation in animal feed industry belonging to the process industry and with hybrid production process, could be used due to the approach proposed by Spieckmann and Stobbe (2012). / A busca pelo aumento de produtividade tornou-se um mantra repetido à exaustão em muitas empresas imersas em um mercado globalizado. Neste contexto, muitas técnicas computacionais vêm ganhando espaço, conquistando adeptos, auxiliando e refinando o processo de tomada de decisão. Dentre as várias técnicas disponíveis, a simulação discreta se destaca, pois permite estudar o comportamento de sistemas, reais ou não, sob diversas condições, possibilitando que hipóteses sejam testadas sem que recursos físicos e financeiros sejam utilizados. No caso da indústria de nutrição animal, essa técnica se torna uma ferramenta muito relevante, principalmente no planejamento de curto prazo que envolve a gestão das operações do chão de fábrica. A indústria de nutrição animal está inserida na cadeia do agronegócio, e como tal, tem seus insumos cotados internacionalmente, commodities, assim uma gestão eficaz de sua capacidade instalada representa uma vantagem estratégica de diferenciação perante as necessidades do mercado em relação a custo, prazo e qualidade. Neste sentido, o objetivo deste trabalho foi desenvolver um modelo de simulação discreta para auxiliar o processo de tomada de decisão sobre o aumento da taxa de ensaque de uma indústria de nutrição animal, localizada no interior do estado de São Paulo. Para a realização deste estudo foi utilizado o software Arena®, da Rockwell Softwares, e como método de pesquisa a modelagem e simulação, sendo que as etapas de desenvolvimento do modelo de simulação seguiram a metodologia proposta por Law e Kelton (2000) e Banks (2010). Os dados foram coletados sempre com os mesmos operadores no mesmo horário. Como resultado da simulação do modelo proposto foi possível analisar diferentes cenários, avaliando a dinâmica do sistema e tendo como indicadores de desempenho a taxa de utilização dos equipamentos, a quantidade de produtos produzidos e o consumo de energia elétrica e gás natural por tonelada de produto produzido. Sendo que a utilização da simulação discreta na indústria de nutrição animal, pertencente à indústria de processo e com processo produtivo híbrido, foi possível devido à abordagem utilizada, proposta por Spieckmann e Stobbe (2012).

Ensemble Stream Modeling and Data-cleaning are sensor information processing systems have different training and testing methods by which their goals are cross-validated. This research examines a mechanism, which seeks to extract novel patterns by generating ensembles from data. The main goal of label-less stream processing is to process the sensed events to eliminate the noises that are uncorrelated, and choose the most likely model without over fitting thus obtaining higher model confidence. Higher quality streams can be realized by combining many short streams into an ensemble which has the desired quality. The framework for the investigation is an existing data mining tool. First, to accommodate feature extraction such as a bush or natural forest-fire event we make an assumption of the burnt area (BA*), sensed ground truth as our target variable obtained from logs. Even though this is an obvious model choice the results are disappointing. The reasons for this are two: One, the histogram of fire activity is highly skewed. Two, the measured sensor parameters are highly correlated. Since using non descriptive features does not yield good results, we resort to temporal features. By doing so we carefully eliminate the averaging effects; the resulting histogram is more satisfactory and conceptual knowledge is learned from sensor streams. Second is the process of feature induction by cross-validating attributes with single or multi-target variables to minimize training error. We use F-measure score, which combines precision and accuracy to determine the false alarm rate of fire events. The multi-target data-cleaning trees use information purity of the target leaf-nodes to learn higher order features. A sensitive variance measure such as f-test is performed during each node’s split to select the best attribute. Ensemble stream model approach proved to improve when using complicated features with a simpler tree classifier. The ensemble framework for data-cleaning and the enhancements to quantify quality of fitness (30% spatial, 10% temporal, and 90% mobility reduction) of sensor led to the formation of streams for sensor-enabled applications. Which further motivates the novelty of stream quality labeling and its importance in solving vast amounts of real-time mobile streams generated today.

No description available.