Made available in DSpace on 2015-03-26T13:42:09Z (GMT). No. of bitstreams: 1 texto completo.pdf: 164176 bytes, checksum: b14dc96758addd4c516b427d913d7a6c (MD5) Previous issue date: 2009-05-29 / Conselho Nacional de Desenvolvimento Científico e Tecnológico / The BLUP methodology, which is widely used in animal and forestry genetic evaluation, can also be applied to annual crop breeding. The objective of this study was to compare the accuracy and efficiency of among- and within-half-sib family selection through the use of multi-trait BLUP, single-trait BLUP and phenotypic selection. Expansion volume and yield data from two recurrent selection cycles of a popcorn population were analyzed. Progeny tests were designed as a lattice. In order to maximize accuracy of the prediction of breeding values, the BLUP analyses included phenotypic values of the two cycles. All statistical analyses were performed using the ASREML software. The multi-trait BLUP method demonstrated greater accuracy and efficiency in family selection. In the case of within-family selection, both accuracy and efficiency of multi-trait or single-trait BLUP methods were equivalent. The selection efficiency of the multi-trait BLUP was dependent on the estimated genetic parameters, particularly the difference between the genetic and environmental correlations of the traits. / A metodologia BLUP, que é amplamente utilizada na avaliação genética animal e florestal também pode ser aplicada no melhoramento de culturas anuais. O objetivo deste estudo foi comparar a acurácia e a eficiência da seleção entre e dentro de famílias de meios-irmãos através da utilização do BLUP multicaracterística, BLUP unicaracterística e seleção fenotípica. Dados de capacidade de expansão e produção de dois ciclos de seleção recorrente em uma população de milho-pipoca foram analisados. Os testes de progênies foram delineados como um látice. Visando maximizar a acurácia da predição dos valores genéticos as análises BLUP incluíram valores fenotípicos dos dois ciclos. Todas as análises estatísticas foram realizadas utilizando o software ASREML. O método BLUP multicaracterística apresentou maior acurácia e eficiência de seleção de famílias. No caso da seleção dentro de famílias a acurácia e a eficiência dos métodos BLUP multicaracterística e BLUP unicaracterística foram equivalentes. A eficiência de seleção do BLUP multicaracterística foi dependente dos parâmetros genéticos estimados, particularmente da diferença entre as correlações genéticas e ambientais das características.

Neste trabalho apresentamos uma versão do Teorema de Poincaré-Bendixson para campos vetoriais contínuos na garrafa de Klein. Como conseqüência, mostramos que a garrafa de Klein não possui campo vetorial contínuo com trajetória injetiva recorrente / We present a version of the Poincaré-Bendixson Theorem on the Klein bottle for continuous vector fields. As a consequence, we obtain the fact that the Klein bottle does not admit continuous vector fields having a recurrent injective trajectory

The author investigates the performance of a time series based approach in predicting the risk of patients abandoning treatment in a treatment program for childhood obesity. The time series based approach is compared and contrasted to an approach based on static features (which has been applied in similar problems). Four machine learning models are constructed; one ‘Main model’ using both time series forecasting and three ‘reference models’ created by removing or exchanging parts of the main model to test the performance of using only time series forecasting or only static features in the prediction. The main model achieves an ROC-AUC of 0.77 on the data set. ANOVA testing is used to determine whether the four models perform differently. A difference cannot be verified at the significance level of 0.05, and thus, the author concludes that the project cannot show either an advantage or a disadvantage to employing a time series based approach over static features in this problem. / Författaren jämför modeller baserade på tidsserieförutsägelser med modeller baserade på statiska, fasta värden, till syfte att identifera patienter som riskerar att lämna ett behandlingsprogram för barnfetma. Fyra maskininlärningsmodeller konstrueras, en ‘Huvudmodell’ som använder sig av både tidsserieförutsägelser och statiska värden, och tre modeller som bryter ut delar av huvudmodellen för undersöka beteendet i modeller baserade enbart på statiska värden respektive enbart baserade på tidsserieförutsägelser. Huvudmodellen uppnår ROC-AUC0.77 på datasetet. ANOVA(variansanalys) används för att avgöra huruvida de fyra modellernas resultat skiljer sig, och en skillnad kan ej verieras vid P = 0:05. Följaktligen drar författaren slutsatsen att projektet inte har kunnat visa vare sig en signifikant fördel eller nackdel med att använda sig av tidsserieförutsägelser inom den aktuella problemdomänen.

Background. This thesis focuses on the task of historical document semantic segmentation with recurrent neural networks. Document semantic segmentation involves the segmentation of a page into different meaningful regions and is an important prerequisite step of automated document analysis and digitisation with optical character recognition. At the time of writing, convolutional neural network based solutions are the state-of-the-art for analyzing document images while the use of recurrent neural networks in document semantic segmentation has not yet been studied. Considering the nature of a recurrent neural network and the recent success of recurrent neural networks in document image binarization, it should be possible to employ a recurrent neural network for document semantic segmentation and further achieve high performance results. Objectives. The main objective of this thesis is to investigate if recurrent neural networks are a viable alternative to convolutional neural networks in document semantic segmentation. By using a combination of a convolutional neural network and a recurrent neural network, another objective is also to determine if the performance of the combination can improve upon the existing case of only using the recurrent neural network. Methods. To investigate the impact of recurrent neural networks in document semantic segmentation, three different recurrent neural network architectures are implemented and trained while their performance are further evaluated with Intersection over Union. Afterwards their segmentation result are compared to a convolutional neural network. By performing pre-processing on training images and multi-class labeling, prediction images are ultimately produced by the employed models. Results. The results from the gathered performance data shows a 2.7% performance difference between the best recurrent neural network model and the convolutional neural network. Notably, it can be observed that this recurrent neural network model has a more consistent performance than the convolutional neural network but comparable performance results overall. For the other recurrent neural network architectures lower performance results are observed which is connected to the complexity of these models. Furthermore, by analyzing the performance results of a model using a combination of a convolutional neural network and a recurrent neural network, it can be noticed that the combination performs significantly better with a 4.9% performance increase compared to the case with only using the recurrent neural network. Conclusions. This thesis concludes that recurrent neural networks are likely a viable alternative to convolutional neural networks in document semantic segmentation but that further investigation is required. Furthermore, by combining a convolutional neural network with a recurrent neural network it is concluded that the performance of a recurrent neural network model is significantly increased. / Bakgrund. Detta arbete handlar om semantisk segmentering av historiska dokument med recurrent neural network. Semantisk segmentering av dokument inbegriper att dela in ett dokument i olika regioner, något som är viktigt för att i efterhand kunna utföra automatisk dokument analys och digitalisering med optisk teckenläsning. Vidare är convolutional neural network det främsta alternativet för bearbetning av dokument bilder medan recurrent neural network aldrig har använts för semantisk segmentering av dokument. Detta är intressant eftersom om vi tar hänsyn till hur ett recurrent neural network fungerar och att recurrent neural network har uppnått mycket bra resultat inom binär bearbetning av dokument, borde det likväl vara möjligt att använda ett recurrent neural network för semantisk segmentering av dokument och även här uppnå bra resultat. Syfte. Syftet med arbetet är att undersöka om ett recurrent neural network kan uppnå ett likvärdigt resultat jämfört med ett convolutional neural network för semantisk segmentering av dokument. Vidare är syftet även att undersöka om en kombination av ett convolutional neural network och ett recurrent neural network kan ge ett bättre resultat än att bara endast använda ett recurrent neural network. Metod. För att kunna avgöra om ett recurrent neural network är ett lämpligt alternativ för semantisk segmentering av dokument utvärderas prestanda resultatet för tre olika modeller av recurrent neural network. Därefter jämförs dessa resultat med prestanda resultatet för ett convolutional neural network. Vidare utförs förbehandling av bilder och multi klassificering för att modellerna i slutändan ska kunna producera mätbara resultat av uppskattnings bilder. Resultat. Genom att utvärdera prestanda resultaten för modellerna kan vi i en jämförelse med den bästa modellen och ett convolutional neural network uppmäta en prestanda skillnad på 2.7%. Noterbart i det här fallet är att den bästa modellen uppvisar en jämnare fördelning av prestanda. För de två modellerna som uppvisade en lägre prestanda kan slutsatsen dras att deras utfall beror på en lägre modell komplexitet. Vidare vid en jämförelse av dessa två modeller, där den ena har en kombination av ett convolutional neural network och ett recurrent neural network medan den andra endast har ett recurrent neural network uppmäts en prestanda skillnad på 4.9%. Slutsatser. Resultatet antyder att ett recurrent neural network förmodligen är ett lämpligt alternativ till ett convolutional neural network för semantisk segmentering av dokument. Vidare dras slutsatsen att en kombination av de båda varianterna bidrar till ett bättre prestanda resultat.

No description available.

The Transformer, an attention-based deep learning architecture, has shown promising capabilities in both Natural Language Processing and Computer Vision. Recently, it has also been applied to time series classification, which has traditionally used statistical methods or the Gated Recurrent Unit (GRU). The aim of this project was to apply multivariate time series classification to evaluate Transformer-based models, in comparison with the traditional GRUs. The evaluation was done within the problem of startup success prediction at a venture and private equity firm called EQT. Four different Machine Learning (ML) models – the Univariate GRU, Multivariate GRU, Transformer Encoder, and an already existing implementation, the Time Series Transformer (TST) – were benchmarked using two public datasets and the EQT dataset which utilized an investor-centric data split. The results suggest that the TST is the best-performing model on EQT’s dataset within the scope of this project, with a 47% increase in performance – measured by the Area Under the Curve (AUC) metric – compared to the Univariate GRU, and a 12% increase compared to the Multivariate GRU. It was also the best, and third-best, performing model on the two public datasets. Additionally, the model also demonstrated the highest training stability out of all four models, and 15 times shorter training times than the Univariate GRU. The TST also presented several potential qualitative advantages such as utilizing its embeddings for downstream tasks, an unsupervised learning technique, higher explainability, and improved multi-modal compatibility. The project results, therefore, suggest that the TST is a viable alternative to the GRU architecture for multivariate time series classification within the investment domain. With its performance, stability, and added benefits, the TST is certainly worth considering for time series modeling tasks. / Transformern är en attention-baserad arkitektur skapad för djupinlärning som har demonsterat lovande kapacitet inom både naturlig språkbehandling och datorseende. Nyligen har det även tillämpats på tidsserieklassificering, som traditionellt har använt statistiska metoder eller GRU. Syftet med detta projekt var att tillämpa multivariat tidsserieklassificering för att utvärdera transformer-baserade modeller, i jämförelse med de traditionella GRUerna. Jämförelsen gjordes inom problemet med att klassificera vilka startup-företag som är potentiellt framgångsrika eller inte, och gjordes på ett risk- och privatkapitalbolag som heter EQT. Fyra olika maskininlärningsmodeller – Univariat GRU, Multivariat GRU, Transformer Encoder och en redan existerande implementering, TST – jämfördes med hjälp av två offentliga datamängder och EQT-datamängden som använde sig av en investerarcentrerad datauppdelning. Resultaten tyder på att TST är den modellen som presterar bäst på EQT:s datauppsättning inom ramen för detta projekt, med en 47% ökning i prestanda – mätt med AUC – jämfört med den univariata GRUn och en ökning på 12% jämfört med den multivariata GRUn. Det var också den bäst och tredje bäst presterande modellen på de två offentliga datamängderna. Modellen visade även den högsta träningsstabiliteten av alla fyra modellerna och 15 gånger kortare träningstider än den univariata GRUn. TST visade även flera potentiella kvalitativa fördelar som att använda dess inbäddningar för nedströmsuppgifter, en oövervakad inlärningsteknik, högre förklarabarhet och förbättrad multimodal kompatibilitet. Projektresultaten tyder därför på att TST är ett gångbart alternativ till GRUarkitekturen för multivariat tidsserieklassificering inom investeringsdomänen. Med sin prestanda, stabilitet och extra fördelar är TST verkligen värt att överväga för tidsseriemodelleringsproblem.

Tracab’s optical tracking system allows to track the 2-dimensional trajectories of players and ball during a football game. Using this data it is possible to train machine learning models to identify events that happen during the match. In this thesis, we explore the detection of corners, free kicks, and throw-in events by means of neural networks. Training a model to solve this task is not easy; the neural network needs to model the spatio-temporal interactions between different agents moving in a 2-dimensional space. We decided to address this problem using graph neural networks in combination with recurrent neural networks, which allow us to model respectively the spatial and temporal components of the data. Tracking the position of the ball is difficult, which makes the dataset noisy. In this thesis, we mainly work with a version of the dataset where the position of the ball has been manually corrected. However, to study how the noisy position of the ball affects the results we also train the models on the original data. The results show that detecting the corner and the throw-in is much easier than detecting the free kick. Moreover, the noisy position of the ball affects significantly the performance of the model. We conclude that to train the model on the original data it is necessary to use a much larger training set. Since the amount of training data for these events is limited, we also train the model on the more generic ball-dead-to-alive event, for which much more data is available, and we observe that by increasing the amount of training data the results can improve significantly. In this report, we also provide an in-depth discussion about all the challenges faced during the project and how different hyperparameters and design choices can affect the results. / Tracabs optiska spårningssystem gör det möjligt att spåra de 2-dimensionella banorna för spelare och boll under en fotbollsmatch. Med hjälp av dessa data är det möjligt att träna maskininlärningsmodeller för att identifiera händelser som inträffar under matchen. I denna avhandling utforskar vi upptäckten av hörnor, frisparkar och inkastningshändelser med hjälp av neurala nätverk. Att träna en modell för att lösa denna uppgift är inte lätt; det neurala nätverket behöver modellera de rums-temporala interaktionerna mellan olika agenter som rör sig i ett 2-dimensionellt rum. Vi bestämde oss för att ta itu med detta problem med hjälp av grafiska neurala nätverk i kombination med återkommande neurala nätverk, vilket gör att vi kan modellera de rumsliga respektive temporala komponenterna i datan. Det är svårt att spåra bollens position, vilket gör datauppsättningen bullrig. I detta examensarbete arbetar vi främst med en version av datamängden där bollens position har korrigerats manuellt. Men för att studera hur bollens bullriga position påverkar resultaten tränar vi också modellerna på originaldata. Resultaten visar att det är mycket lättare att upptäcka hörna och inkastet än att upptäcka frisparken. Dessutom påverkar bollens bullriga position avsevärt modellens prestanda. Vi drar slutsatsen att för att träna modellen på originaldata är det nödvändigt att använda en mycket större träningsuppsättning. Eftersom mängden träningsdata för dessa evenemang är begränsad, tränar vi också modellen på den mer generiska bollen död-till-levande-händelsen, för vilken mycket mer data finns tillgänglig, och vi observerar att genom att öka mängden träningsdata resultaten kan förbättras avsevärt. I denna rapport ger vi också en fördjupad diskussion om alla utmaningar som ställs inför under projektet och hur olika hyperparametrar och designval kan påverka resultaten.

Yes / Human activity recognition from sensor data is a critical research topic to achieve remote health monitoring and ambient assisted living (AAL). In AAL, sensors are integrated into conventional objects aimed to support targets capabilities through digital environments that are sensitive, responsive and adaptive to human activities. Emerging technological paradigms to support AAL within the home or community setting offers people the prospect of a more individually focused care and improved quality of living. In the present work, an ambient human activity classification framework that augments information from the received signal strength indicator (RSSI) of passive RFID tags to obtain detailed activity profiling is proposed. Key indices of position, orientation, mobility, and degree of activities which are critical to guide reliable clinical management decisions using 4 volunteers are employed to simulate the research objective. A two-layer, fully connected sequence long short-term memory recurrent neural network model (LSTM RNN) is employed. The LSTM RNN model extracts the feature of RSS from the sensor data and classifies the sampled activities using SoftMax. The performance of the LSTM model is evaluated for different data size and the hyper-parameters of the RNN are adjusted to optimal states, which results in an accuracy of 98.18%. The proposed framework suits well for smart health and smart homes which offers pervasive sensing environment for the elderly, persons with disability and chronic illness.

ITC/USA 2008 Conference Proceedings / The Forty-Fourth Annual International Telemetering Conference and Technical Exhibition / October 27-30, 2008 / Town and Country Resort & Convention Center, San Diego, California / Adaptive modulation is a communication technique capable of maximizing throughput while guaranteeing a fixed symbol error rate (SER). However, this technique requires instantaneous channel state information at the transmitter. This can be obtained by predicting channel states at the receiver and feeding them back to the transmitter. Existing algorithms used to predict single-input single-output (SISO) channels with recurrent neural networks (RNN) are extended to multiple-input multiple-output (MIMO) channels for use with adaptive modulation and their performance is demonstrated in several examples.

Bankruptcy prediction has been of great interest to academics in the fields of accounting and finance for decades. Prior literatures focus mostly on investigating the covariates that lead to bankruptcy. In this thesis, however, we extend the issue of interest to what are the possible covariates that cause significant jumps in bankruptcy probability for a company. We consider the BSM-probability measure examined by Hillegeist, Keating, Cram, and Lundsedt (2004) to help us calculate the variation in bankruptcy probabilities for companies. In addition, recurrent event data analysis is applied to explore these jumps in bankruptcy intensity. By investigating the S&P500 constituents with sample consists of 343 S&P500-listed companies and 17,836 quarter observations starting from 1994 to 2007, we find that, in three of our models, all of these six covariates are negatively related to the recurrences of event that a company will suffer significant jumps in its bankruptcy probability during the next quarter. Additionally, macroeconomic covariates have greater explanatory power as factors affecting the probability of these jumps, while company-specific covariates contribute less to these recurrences of events. In comparison, we conduct another estimation based on the observation of slight increases in bankruptcy probability for companies. Contrary to what we find on the prior dataset, our empirical results suggest the factors that evoke these events are less prominent and their influences on the event recurrence are mixed.