在這份研究中，我們提出一個類分散式神經網路框架，此框架為高頻交易系統研究下之子專案。在系統中，我們透過資料探勘程序發掘財務時間序列中的模式，其中所採用的資料探勘演算法之一即為類神經網路。我們實作一個在分散式平台上訓練類神經網路的框架。我們採用Apache Spark來建立底層的運算叢集，因為它提供高效能的記憶體內運算（in-memory computing）。我們分析一些分散式後向傳導演算法（特別是用來預測財務時間序列的），加以調整，並將其用於我們的框架。我們提供了許多細部的選項，讓使用者在進行類神經網路建模時有很高的彈性。 / In this research, we introduce a distributed framework of artificial neural network (ANN) as a subproject under the research of a high-frequency trading (HFT) system. In the system, ANNs are used in the data mining process for identifying patterns in financial time series. We implement a framework for training ANNs on a distributed computing platform. We adopt Apache Spark to build the base computing cluster because it is capable of high performance in-memory computing. We investigate a number of distributed backpropagation algorithms and techniques, especially ones for time series prediction, and incorporate them into our framework with some modifications. With various options for the details, we provide the user with flexibility in neural network modeling.

In this dissertation, generalized additive neural networks (GANNs) and multilayer perceptrons (MLPs) are studied and compared as prediction techniques. MLPs are the most widely used type of artificial neural network (ANN), but are considered black boxes with regard to interpretability. There is currently no simple a priori method to determine the number of hidden neurons in each of the hidden layers of ANNs. Guidelines exist that are either heuristic or based on simulations that are derived from limited experiments. A modified version of the neural network construction with cross–validation samples (N2C2S) algorithm is therefore implemented and utilized to construct good MLP models. This algorithm enables the comparison with GANN models. GANNs are a relatively new type of ANN, based on the generalized additive model. The architecture of a GANN is less complex compared to MLPs and results can be interpreted with a graphical method, called the partial residual plot. A GANN consists of an input layer where each of the input nodes has its own MLP with one hidden layer. Originally, GANNs were constructed by interpreting partial residual plots. This method is time consuming and subjective, which may lead to the creation of suboptimal models. Consequently, an automated construction algorithm for GANNs was created and implemented in the SAS R statistical language. This system was called AutoGANN and is used to create good GANN models. A number of experiments are conducted on five publicly available data sets to gain insight into the similarities and differences between GANN and MLP models. The data sets include regression and classification tasks. In–sample model selection with the SBC model selection criterion and out–of–sample model selection with the average validation error as model selection criterion are performed. The models created are compared in terms of predictive accuracy, model complexity, comprehensibility, ease of construction and utility. The results show that the choice of model is highly dependent on the problem, as no single model always outperforms the other in terms of predictive accuracy. GANNs may be suggested for problems where interpretability of the results is important. The time taken to construct good MLP models by the modified N2C2S algorithm may be shorter than the time to build good GANN models by the automated construction algorithm / Thesis (M.Sc. (Computer Science))--North-West University, Potchefstroom Campus, 2011.

In this dissertation, generalized additive neural networks (GANNs) and multilayer perceptrons (MLPs) are studied and compared as prediction techniques. MLPs are the most widely used type of artificial neural network (ANN), but are considered black boxes with regard to interpretability. There is currently no simple a priori method to determine the number of hidden neurons in each of the hidden layers of ANNs. Guidelines exist that are either heuristic or based on simulations that are derived from limited experiments. A modified version of the neural network construction with cross–validation samples (N2C2S) algorithm is therefore implemented and utilized to construct good MLP models. This algorithm enables the comparison with GANN models. GANNs are a relatively new type of ANN, based on the generalized additive model. The architecture of a GANN is less complex compared to MLPs and results can be interpreted with a graphical method, called the partial residual plot. A GANN consists of an input layer where each of the input nodes has its own MLP with one hidden layer. Originally, GANNs were constructed by interpreting partial residual plots. This method is time consuming and subjective, which may lead to the creation of suboptimal models. Consequently, an automated construction algorithm for GANNs was created and implemented in the SAS R statistical language. This system was called AutoGANN and is used to create good GANN models. A number of experiments are conducted on five publicly available data sets to gain insight into the similarities and differences between GANN and MLP models. The data sets include regression and classification tasks. In–sample model selection with the SBC model selection criterion and out–of–sample model selection with the average validation error as model selection criterion are performed. The models created are compared in terms of predictive accuracy, model complexity, comprehensibility, ease of construction and utility. The results show that the choice of model is highly dependent on the problem, as no single model always outperforms the other in terms of predictive accuracy. GANNs may be suggested for problems where interpretability of the results is important. The time taken to construct good MLP models by the modified N2C2S algorithm may be shorter than the time to build good GANN models by the automated construction algorithm / Thesis (M.Sc. (Computer Science))--North-West University, Potchefstroom Campus, 2011.

Värme står för det största energibehovet inom hushåll och andra byggnader i samhället och olika tekniker används för att kunna reducera mängden energi som går åt för att spara på både miljö och pengar. Ett angreppssätt på detta problem är genom informatiken, där maskininlärning kan användas för att analysera och förutspå värmebehovet. I denna studie används maskininlärning för att prognostisera framtida energiförbrukning för fjärrvärme utifrån historisk fjärrvärmedata från ett fjärrvärmebolag tillsammans med exogena variabler i form av väderdata från Sveriges meteorologiska och hydrologiska institut. Studien är skriven på svenska och utforskar effekter av preprocessering hos prediktionsmodeller som använder tidsseriedata för att prognostisera framtida datapunkter. Stegen som utförs i studien är normalisering, interpolering, hantering av numeric outliers och missing values, datetime feature engineering, säsongsmässighet, feature selection, samt korsvalidering. Maskininlärningsmodellen som används i studien är Multilayer Perceptron som är en subkategori av artificiellt neuralt nätverk. Forskningsfrågan som besvaras fokuserar på effekter av preprocessering och feature selection för prediktiva modellers prestanda inom olika datamängder och kombinationer av preprocesseringsmetoder. Modellerna delades upp i tre olika datamängder utifrån datumintervall: 2009, 2007–2011, samt 2007–2017, där de olika kombinationerna utgörs av preprocesseringssteg som kombineras inom en iterativ process. Procentuella ökningar på R2-värden för dessa olika intervall har uppnått 47,45% för ett år, 9,97% för fem år och 32,44% för 11 år. I stora drag bekräftar och förstärker resultatet befintlig teori som menar på att preprocessering kan förbättra prediktionsmodeller. Ett antal mindre observationer kring enskilda preprocesseringsmetoders effekter har identifierats och diskuterats i studien, såsom DateTime Feature Engineerings negativa effekter på modeller som tränats med ett mindre antal iterationer. / Heat accounts for the greatest energy needs in households and other buildings in society. Effective production and distribution of heat energy require techniques for minimising economic and environmental costs. One approach to this problem is through informatics where machine learning is used to analyze and predict the heating needs with the help of historical data from a district heating company and exogenous variables in the form of weather data from Sweden's Meteorological and Hydrological Institute (SMHI). This study is written in Swedish and explores the importance of preprocessing practices before training and using prediction models which utilizes time-series data to predict future energy consumption. The preprocessing steps explored in this study consists of normalization, interpolation, identification and management of numerical outliers and missing values, datetime feature engineering, seasonality, feature selection and cross-validation. The machine learning model used in this study is Multilayer Perceptron which is a subcategory of artificial neural network. The research question focuses on the effects of preprocessing and feature selection for predictive model performance within different datasets and combinations of preprocessing methods. The models were divided into three different data sets based on date ranges: 2009, 2007–2011, and 2007–2017, where the different combinations consist of preprocessing steps that are combined within an iterative process. Percentage increases in R2 values for these different ranges have reached 47,45% for one year, 9,97% for five years and 32,44% for 11 years. The results broadly confirm and reinforce the existing theory that preprocessing can improve prediction models. A few minor observations about the effects of individual preprocessing methods have been identified and discussed in the study, such as DateTime Feature Engineering having a detrimental effect on models with very few training iterations.

This thesis discusses the utilization of the artificial neural networks (ANN) for detection of coronary artery disease (CAD) in frequency area. The first part of this thesis is orientated towards the theoretical knowledge. Describes the issue of ECG pathological changes. ECQ are converted to frequency area. Described statistical methods and methods for automatic detection of CAD and MI. Explained the issue of the perceptron and ANN. The second deals with use of Neural Network Toolbox MATLAB®. This part focuses on counting and finding suitable parameters and making connection of band. At the end of the thesis UNS is used to detect ischemic parameters and the results are discussed. Average values for the best settings are 100% accuracy.

No description available.

Agriculture is becoming more dependent on computerized solutions to make thefarmer’s job easier. The big step that many companies are working towards is fullyautonomous vehicles that work the fields. To that end, the equipment fitted to saidvehicles must also adapt and become autonomous. Making this equipment autonomoustakes many incremental steps, one of which is developing an accurate and reliable tanklevel measurement system. In this thesis, a system for tank level measurement in a seedplanting machine is evaluated. Traditional systems use load cells to measure the weightof the tank however, these types of systems are expensive to build and cumbersome torepair. They also add a lot of weight to the equipment which increases the fuel consump-tion of the tractor. Thus, this thesis investigates the use of radar sensors together witha number of Machine Learning algorithms. Fourteen radar sensors are fitted to a tankat different positions, data is collected, and a preprocessing method is developed. Then,the data is used to test the following Machine Learning algorithms: Bagged RegressionTrees (BG), Random Forest Regression (RF), Boosted Regression Trees (BRT), LinearRegression (LR), Linear Support Vector Machine (L-SVM), Multi-Layer Perceptron Re-gressor (MLPR). The model with the best 5-fold crossvalidation scores was Random For-est, closely followed by Boosted Regression Trees. A robustness test, using 5 previouslyunseen scenarios, revealed that the Boosted Regression Trees model was the most robust.The radar position analysis showed that 6 sensors together with the MLPR model gavethe best RMSE scores.In conclusion, the models performed well on this type of system which shows thatthey might be a competitive alternative to load cell based systems.

Keyword spotting is one of the many applications of automatic speech recognition. Its purpose is determining spots in given utterance in which some of the specified words were spoken. Keyword spotting has a great potential to enhance performance of new applications as well as the existing ones. An example could be a mobile phone voice control. Due to OS Symbian's coming to the market it is even possible for end user to implement a keyword spotting for a mobile phone on his or her own. The thesis describes theoretical prerequisites for keyword spotting and its implementation. Firstly the OS Symbian is presented with respect to the given task. Secondly each step of keyword spotting process is described. Finally the object design of keyword spotter is presented followed by implementation description. The thesis concludes with results review and notes on possible improvements.

Collaborative filtering is a popular technique to use behavior data in the form of user’s interactions with, or ratings of, items in a system to provide personalized recommendations of items to the user. This study compares three different state-of-the-art Recommendation System models that implement this technique, Matrix Factorization, Multi-layer Perceptron and Neural Matrix Factorization, using behavior data from a digital book platform for children. The field of Recommendation Systems is growing, and many platforms can benefit of personalizing the user experience and simplifying the use of the platforms. To perform a more complex comparison and introduce a new take on the models, this study proposes a new way to represent the behavior data as input to the models, i.e., to use the Term Frequency-Inverse Document Frequency (TFIDF) of occurrences of interactions between users and books, as opposed to the traditional binary representation (positive if there has been any interaction and negative otherwise). The performance is measured by extracting the last book read for each user, and evaluating how the models would rank that book for recommendations to the user. To assess the value of the models for the children’s reading platform, the models are also compared to the existing Recommendation System on the digital book platform. The results indicate that the Matrix Factorization model performs best out of the three models when using children’s reading behavior data. However, due to the long training process and larger set of hyperparameters to tune for the other two models, these may not have reached an optimal hyperparameter tuning, thereby affecting the comparison among the three state-of-the-art models. This limitation is further discussed in the study. All three models perform significantly better than the current system on the digital book platform. The models with the proposed representation using TF-IDF values show notable promise, performing better than the binary representation in almost all numerical metrics for all models. These results can suggest future research work on more ways of representing behavior data as input to these types of models. / Kollaborativ filtrering är en populär teknik för att använda beteendedata från användare i form av t.ex. interaktioner med, eller betygsättning av, objekt i ett system för att ge användaren personliga rekommendationer om objekt. I den här studien jämförs tre olika modeller av moderna rekommendationssystem som tillämpar denna teknik, matrisfaktorisering, flerlagersperceptron och neural matrisfaktorisering, med hjälp av beteendedata från en digital läsplattform för barn. Rekommendationssystem är ett växande område, och många plattformar kan dra nytta av att anpassa användarupplevelsen utifrån individen och förenkla användningen av plattformen. För att utföra en mer komplex jämförelse och introducera en ny variant av modellerna, föreslår denna studie ett nytt sätt att representera beteendedata som indata till modellerna, d.v.s. att använda termfrekvens med omvänd dokumentfrekvens (TF- IDF) av förekomster av interaktioner mellan användare och böcker, i motsats till den traditionella binära representationen (positiv om en tidigare interaktion existerar och negativ i annat fall). Prestandan mäts genom att extrahera den senaste boken som lästs för varje användare, och utvärdera hur högt modellerna skulle rangordna den boken i rekommendationer till användaren. För att värdesätta modellerna för plattformen med digitala böcker, så jämförs modellerna också med det befintliga rekommendationssystemet på plattformen. Resultaten tyder på att matrisfaktorisering-modellen presterar bäst utav de tre modellerna när man använder data från barns läsbeteende. På grund av den långa träningstiden och fler hyperparametrar att optimera för de andra två modellerna, kan det dock vara så att de inte har nått en optimal hyperparameterinställning, vilket påverkar jämförelsen mellan de tre moderna modellerna. Denna begränsning diskuteras ytterligare i studien. Alla tre modellerna presterar betydligt bättre än det nuvarande systemet på läsplattformen. Modellerna med den föreslagna representationen av TFIDF-värden visar sig mycket lovande och presterar bättre än den binära representationen i nästan alla numeriska mått för alla modeller. Dessa resultat kan ge skäl för framtida forskning av fler sätt att representera beteendedata som indata till denna typ av modeller.

The field of crisis management and humanitarian assistance has been one of the major fields of development for governmental and common best European practices in the last decades. The European Union as a major humanitarian stakeholder has taken great effort to strengthen the response in case of humanitarian disasters. This work addresses the feasibility and possible benefits of using machine learning in the prediction of the impact severity of a disaster as a model-driven data analysis in comparison to data-driven reference models for early response coordination and preparedness. In comparison to classical data analysis systems the feasibility of earthquake impact prediction based on machine learning models is evaluated and further debated.