Foreign exchange market is the largest financial market in the world and thus prediction of foreign exchange rate values is of interest to millions of people. In this research, I evaluated the performance of Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Autoregressive Integrated Moving Average (ARIMA) and Moving Average (MA) on the USD/CAD and USD/AUD exchange pairs for 1-day, 1-week and 2-weeks predictions. For LSTM and GRU, twelve macroeconomic indicators along with past exchange rate values were used as features using data from January 2001 to December 2019. Predictions from each model were then integrated with uncertainty modeling to find out the chance of a model’s prediction being greater than or less than a user-defined target value using the error distribution from the test dataset, Monte-Carlo simulation trials and ChancCalc excel add-in. Results showed that ARIMA performs slightly better than LSTM and GRU for 1-day predictions for both USD/CAD and USD/AUD exchange pairs. However, when the period is increased to 1-week and 2-weeks, LSTM and GRU outperform both ARIMA and moving average for both USD/CAD and USD/AUD exchange pair.

This master thesis deals with the implementation of various types of recurrent neural networks via programming language lua using torch library. It focuses on finding optimal strategy for training recurrent neural networks and also tries to minimize the duration of the training. Furthermore various types of regularization techniques are investigated and implemented into the recurrent neural network architecture. Implemented recurrent neural networks are compared on the speech recognition task using AMI dataset, where they model the acustic information. Their performance is also compared to standard feedforward neural network. Best results are achieved using BLSTM architecture. The recurrent neural network are also trained via CTC objective function on the TIMIT dataset. Best result is again achieved using BLSTM architecture.

As the complexity of deep learning model increases, the transparency of the systems does the opposite. It may be hard to understand the predictions a deep learning model makes, but even harder to understand why these predictions are made. Using eXplainable AI (XAI), we can gain greater knowledge of how the model operates and how the input in which the model receives can change its predictions. In this thesis, we apply Integrated Gradients (IG), an XAI method primarily used on image data and on datasets containing tabular and time-series data. We also evaluate how the results of IG differ from various types of models and how the change of baseline can change the outcome. In these results, we observe that IG can be applied to both sequenced and nonsequenced data, with varying results. We can see that the gradient baseline does not affect the results of IG on models such as RNN, LSTM, and GRU, where the data contains time series, as much as it does for models like MLP with nonsequenced data. To confirm this, we also applied IG to SVM models, which gave the results that the choice of gradient baseline has a significant impact on the results of IG.

<p>  </p> <p>Advanced high temperature fluid reactors (AR), such as sodium fast reactors (SFR) and molten salt cooled reactors (MSCR) are promising nuclear energy options, which offer lower levelized electricity costs compared to existing light water reactors (LWR). Increasing economic competitiveness of ARs in the open market involves developing strategies for reducing operation and maintenance (O&M) costs. Digitization of AR’s allows to implement continuous on-line monitoring paradigm to achieve early detection of incipient problems, and thus reduce O&M costs. Machine learning (ML) algorithms offer a number of advantages for reactor monitoring through anticipation of key performance variables using data-driven process models. ML model does not require detailed knowledge of the system, which could be difficult to obtain or unavailable because of commercial privacy restrictions. In addition, any data obtained from sensors or through various ML models need to be securely transmitted under all possible conditions, including those of cyber-attacks. Quantum information processing offers promising solutions to these threats by establishing secure communications, due to unique properties of entanglement and superposition in quantum physics. More specifically, quantum key distribution (QKD) algorithms can be used to generate and transmit keys between the reactor and a remote user. In one of popular QKD communication protocols, BB84, the symmetric keys are paired with an advanced encryption standard (AES) protocol protecting the information. Another challenge in sensor measurements is the noise, which can affect the accuracy and reliability of the measured values. The presence of noise in sensor measurements can lead to incorrect interpretations of the data, and therefore, it is crucial to develop effective signal processing techniques to improve the quality of measurements. </p> <p>In this study, we develop several variations of Recurrent Neural Networks (RNN) and test their ability to predict future values of thermocouple measurements. Data obtained by a heat-up experiment conducted in a liquid sodium experimental facility is used for training and testing the RNNs. The method of extrapolation is also explored using measurements of different sensors to train and test a network. We then examine through computer simulations the potential of secure real-time communication of monitoring information using the BB84 protocol. Finally, signal analysis is performed with Discrete Fourier Transform (DFT) sensor signals to analyze and correlate the prediction results with the results obtained by the analysis of the time series in the frequency domain. Using information from the frequency analysis, we apply cutoff filters in the original time series and test again the performance of the networks. Results show that the ML models developed in this work can be efficiently used for forecasting of thermocouple measurements, as they provide Root Mean Square Error (RMSE) values lower than the measurement uncertainty of the thermocouples. Extrapolation produces good results, with performance related to the Euclidean distance between the sets of time series. Moreover, the results from the utilization of the BB84 protocol to securely transmit the measurements prove the feasibility of secure real-time communication of monitoring information. The application of the cutoff filters provided more accurate predictions of the thermocouple measurements than in the case of the unfiltered signals.</p> <p>The suit of computational tools developed in this work is shown to be efficient and promises to have a positive impact on improving performance of an AR.</p>

Ambient temperature poses a significant challenge to the performance of mobile phones, impacting their internal thermal flow and increasing the likelihood of overheating, leading to a compromised user experience. The knowledge about the ambient temperature in mobile phones is crucial as it assists engineers in correlating external factors with internal factors that might affect the mobile's performance under various conditions. Notably, these devices lack dedicated sensors to measure ambient temperature independently, underscoring the need for innovative solutions to estimate it accurately.      In response to this challenge, our research investigates the feasibility of estimating ambient temperature using machine-learning algorithms based on data from internal thermal sensors in Sony mobile phones.  Through comprehensive data collection and analysis, custom datasets were constructed to simulate different use-case scenarios, including CPU workloads, camera operation, and GPU tasks. These scenarios introduced varying levels of thermal disturbance, providing a robust basis for evaluating model performance. Feature engineering played a pivotal role in ensuring that the models could effectively interpret the internal thermal dynamics and correlate them with the ambient temperature. The results demonstrate that while simpler models like Linear Regression offer computational efficiency, they fall short in scenarios with complex thermal patterns. In contrast, deep learning models, particularly those incorporating time series analysis, showed superior accuracy and robustness. The Attention-LSTM model, in particular, excelled in generalizing across diverse and novel thermal conditions, although its complexity poses challenges for on-device deployment. This research underscores the importance of selecting appropriate sensors and incorporating a wide range of training scenarios to enhance model performance. It also highlights the potential of advanced machine learning techniques in providing advance solutions for ambient temperature estimation, thereby contributing to more effective thermal management in mobile devices.

Identifying facemasks is an important duty that affects public health and safety, especially during epidemics of communicable diseases. Many architectures of deep learning models are being investigated for their effectiveness, as they have demonstrated great potential in automating this process. The performance of four well-known deep learning architectures—VGG19, VGG16, GRU, and Fully Convolutional Neural Networks (FCNN)—for facemask identification is thoroughly compared in this thesis. The goal of the study is to assess these architectures in terms of accuracy, efficiency, and robustness in order to offer important information for the creation of efficient facemask detection systems. This study examines the advantages and disadvantages of each model in relation to facemask detection through thorough testing and analysis. The models are statistically evaluated for their ability to detect facemasks in pictures or video streams using performance metrics including precision, recall, and F1-score. Furthermore, the actual feasibility of using these models in real-world applications is assessed by analyzing computational efficiency measures like inference time and model size. Moreover, the models' resilience is assessed in a range of demanding scenarios, such as changes in illumination, facial expressions, and occlusions. The consequences of these results are discussed in the thesis along with suggestions for improving each architecture for facemask detection tasks. This study's methodology focuses on developing and evaluating deep learning models for facemask recognition that are especially suited for usage in mobile health care units. This method seeks to guarantee high accuracy, robustness, and efficiency in real-world healthcare environments, where prompt and accurate facemask detection is essential. Four well-known deep learning architectures VGG19, VGG16, Gated Recurrent Unit (GRU), and Fully Convolutional Neural Networks (FCNN) were chosen for the models' selection and development. Due to their shown effectiveness in a range of image recognition tasks and possible flexibility to facemask detection, these models were selected. / Идентификация лицевых масок является важной задачей, которая влияет на здоровье и безопасность населения, особенно во время эпидемий инфекционных заболеваний. Многие архитектуры моделей глубокого обучения исследуются на предмет их эффективности, поскольку они продемонстрировали большой потенциал в автоматизации этого процесса. В этой работе проводится тщательное сравнение производительности четырех хорошо известных архитектур глубокого обучения —VGG19, VGG16, GRU и полностью сверточных нейронных сетей (FCNN)— для идентификации лицевых масок. Цель исследования - оценить эти архитектуры с точки зрения точности, эффективности и надежности, чтобы предоставить важную информацию для создания эффективных систем обнаружения лицевых масок. В этом исследовании рассматриваются преимущества и недостатки каждой модели в отношении распознавания лицевых масок путем тщательного тестирования и анализа. Модели подвергаются статистической оценке на предмет их способности обнаруживать лицевые маски на изображениях или в видеопотоках с использованием показателей производительности, включая точность, запоминаемость и показатель F1. Кроме того, фактическая возможность использования этих моделей в реальных приложениях оценивается путем анализа показателей вычислительной эффективности, таких как время вывода и размер модели. Более того, устойчивость моделей оценивается в ряде сложных сценариев, таких как изменение освещения, выражения лица и прикуса. В диссертации обсуждаются последствия этих результатов, а также предложения по улучшению каждой архитектуры для задач обнаружения лицевых масок. Методология этого исследования направлена на разработку и оценку моделей глубокого обучения для распознавания лицевых масок, которые особенно подходят для использования в мобильных медицинских учреждениях. Этот метод призван гарантировать высокую точность, надежность и эффективность в реальных условиях здравоохранения, где важно быстрое и точное распознавание лицевых масок. Для выбора и разработки моделей были выбраны четыре хорошо известные архитектуры глубокого обучения VGG19, VGG16, Gated Recurrent Unit (GRU) и полностью сверточные нейронные сети (FCNN). Эти модели были выбраны из-за их доказанной эффективности в решении целого ряда задач распознавания изображений и возможной гибкости в обнаружении лицевых масок. Ключевые слова: Распознавание лицевых масок, глубокое обучение, VGG19, VGG16, GRU, Полностью сверточные нейронные сети, Оценка эффективности, Мобильные медицинские учреждения.

This thesis proposes a deep learning anomaly detection pipeline to detect possible anomalies during the operation of a fleet of batteries and presents its development and evaluation. The pipeline employs sensors that connect to each battery in the fleet to remotely collect real-time measurements of their operating characteristics, such as voltage, current, and temperature. The deep learning based time-series anomaly detection model was developed using Variational Autoencoder (VAE) architecture that utilizes either Long Short-Term Memory (LSTM) or, its cousin, Gated Recurrent Unit (GRU) as the encoder and the decoder networks (LSTMVAE and GRUVAE). Both variants were evaluated against three well-known conventional anomaly detection algorithms Isolation Nearest Neighbour (iNNE), Isolation Forest (iForest), and kth Nearest Neighbour (k-NN) algorithms. All five models were trained using two variations in the training dataset (full-year dataset and partial recent dataset), producing a total of 10 different model variants. The models were trained using the unsupervised method and the results were evaluated using a test dataset consisting of a few known anomaly days in the past operation of the customer’s battery fleet. The results demonstrated that k-NN and GRUVAE performed close to each other, outperforming the rest of the models with a notable margin. LSTMVAE and iForest performed moderately, while the iNNE and iForest variant trained with the full dataset, performed the worst in the evaluation. A general observation also reveals that limiting the training dataset to only a recent period produces better results nearly consistently across all models. / Detta examensarbete föreslår en pipeline för djupinlärning av avvikelser för att upptäcka möjliga anomalier under driften av en flotta av batterier och presenterar dess utveckling och utvärdering. Rörledningen använder sensorer som ansluter till varje batteri i flottan för att på distans samla in realtidsmätningar av deras driftsegenskaper, såsom spänning, ström och temperatur. Den djupinlärningsbaserade tidsserieanomalidetekteringsmodellen utvecklades med VAE-arkitektur som använder antingen LSTM eller, dess kusin, GRU som kodare och avkodarnätverk (LSTMVAE och GRU) VAE). Båda varianterna utvärderades mot tre välkända konventionella anomalidetekteringsalgoritmer -iNNE, iForest och k-NN algoritmer. Alla fem modellerna tränades med hjälp av två varianter av träningsdatauppsättningen (helårsdatauppsättning och delvis färsk datauppsättning), vilket producerade totalt 10 olika modellvarianter. Modellerna tränades med den oövervakade metoden och resultaten utvärderades med hjälp av en testdatauppsättning bestående av några kända anomalidagar under tidigare drift av kundens batteriflotta. Resultaten visade att k-NN och GRUVAE presterade nära varandra och överträffade resten av modellerna med en anmärkningsvärd marginal. LSTMVAE och iForest presterade måttligt, medan varianten iNNE och iForest tränade med hela datasetet presterade sämst i utvärderingen. En allmän observation avslöjar också att en begränsning av träningsdatauppsättningen till endast en ny period ger bättre resultat nästan konsekvent över alla modeller.

В диссертации изучается влияние аугментации данных скользящим окном на производительность различных архитектур рекуррентных нейронных сетей (RNN) для классификации временных рядов. Исследование оценивает модели на основе слоев долговременной краткосрочной памяти (LSTM), SimpleRNN, Gated Recurrent Unit (GRU) и гибридной RNN, применяемые к классификации пяти видов деятельности: езда на велосипеде, катание на роликовых лыжах (R-Skiing), бег, катание на лыжах и ходьба. Результаты показывают, что аугментация данных скользящим окном значительно повышает производительность модели, улучшая ключевые показатели, такие как точность, отзыв, F1-оценка и достоверность. Среди протестированных моделей модели гибридной RNN и GRU продемонстрировали наивысшую точность и возможности обобщения. Кроме того, мы протестировали несколько размеров окна и шага. Конфигурация с большим размером окна (256) в целом дала лучшие результаты. Эти результаты согласуются с существующей литературой, подчеркивая эффективность аугментации данных и передовых архитектур RNN в классификации временных рядов. Исследование подчеркивает важность дополнения данных для повышения надежности моделей и предоставляет ценную информацию для будущих исследований и практических приложений в различных областях. / The thesis explores the impact of sliding window data augmentation on the performance of various Recurrent Neural Network (RNN) architectures for time series classification. The study evaluates models based on Long Short-Term Memory (LSTM) layers, SimpleRNN, Gated Recurrent Unit (GRU), and a Hybrid RNN, applied to the classification of five activities: Biking, Roller Skiing (R-Skiing), Running, Skiing, and Walking. The results show that sliding window data augmentation significantly enhances model performance, improving key metrics such as precision, recall, F1-score, and accuracy. Among the models tested, the Hybrid RNN and GRU models demonstrated the highest accuracy and generalization capabilities. Additionally, we tested several window and step sizes. The configuration with a larger window size (256) generally yielded better results. These findings are consistent with existing literature, highlighting the effectiveness of data augmentation and advanced RNN architectures in time series classification. The study highlights the importance of data augmentation in improving model robustness and provides valuable insights for future research and practical applications in various fields.

<p dir="ltr">Detecting anomalies in spacecraft time-series data is a high priority, especially considering the harshness of the spacecraft operating environment. These anomalies often function as precursors for system failure. Traditionally, the time-series data channels are monitored manually by domain experts, which is time-consuming. Additionally, there are thousands of channels to monitor. Machine learning methods have proven to be useful for automatic anomaly detection, but a unique model must be trained from scratch for each time-series. This thesis proposes three approaches for reducing training costs. First, a transfer learning approach that finetunes a general pre-trained model to reduce training time and the number of unique models required for a given spacecraft. The second and third approaches both use online learning to reduce the amount of training data and time needed to identify anomalies. The second approach leverages an ensemble of extreme learning machines while the third approach uses deep learning models. All three approaches are shown to achieve reasonable anomaly detection performance with reduced training costs.</p><p dir="ltr">Measuring the phenotypes, or observable traits, of a plant enables plant scientists to understand the interaction between the growing environment and the genetic characteristics of a plant. Plant phenotyping is typically done manually, and often involves destructive sampling, making the entire process labor-intensive and difficult to replicate. In this thesis, we use image processing for characterizing two different disease progressions. Tar spot disease can be identified visually as it induces small black circular spots on the leaf surface. We propose using a Mask R-CNN to detect tar spots from RGB images of leaves, thus enabling rapid non-destructive phenotyping of afflicted plants. The second disease, bacteria-induced wilting, is measured using a visual assessment that is often subjective. We design several metrics that can be extracted from RGB images that can be used to generate consistent wilting measurements with a random forest. Both approaches ensure faster, replicable results, enabling accurate, high-throughput analysis to draw conclusions about effective disease treatments and plant breeds.</p>

This thesis is divided into two main parts. The first, comprising the three initial chapters, looks, in chapter one, at the specifically German origins of the Bildungsroman, its distinctive features, and the difficulties surrounding its transplantation into the literary contexts of other countries. Particular attention is paid to the ethical dimension of the genre, i.e. to the relation between the individual self and the exterior world, and how it affects individual formation. The focus then shifts to American literature, and the term 'narrative of initiation' is recommended as a credible alternative to 'Bildungsroman'. Allowing for similarities between them, it is none the less strongly suggested that the Bildungsroman of German origin and the American narrative of initiation should be seen as being intrinsically different, principally because of the different cultural backgrounds that shaped them. Several features of the theme of initiation are postulated as decisive factors in the discrepancies between the initiatory narrative and the Bildungsroman. Analysis of six texts - three of each literary tradition - follows, to provide support for the theoretical discussion of the terms introduced in chapter one. Three Bildungsromane are considered in the second chapter, namely Goethe's Wilhelm Meisters Lehrjahre, Stifter's Der Nachsommer and Keller's Der grune Heinrich, and three narratives of initiation in chapter three: Twain's The Adventures of Huckleberry Finn, Crane's The Red Badge of Courage and Anderson's Winesburg, Ohio. Their relevance to the tradition of German and American fiction as a whole and as precursors of Mann's Der Zauberberg and Hemingway's The Nick Adams Stories is considered. A direct comparison between Mann's and Hemingway's texts constitutes the second part of this thesis, wholly contained in chapter four. In addition to a comprehensive critical reading of both narratives, the contemporaneity of Der Zauberberg and The Nick Adams Stories is taken into account, and consequently special consideration is given to the texts' close relation with the cultural and historical realities of the early twentieth century, particularly the impact of the First World War. With the assistance of Jung's theories, an increased awareness of death and of the dark side of the psyche - though dealt with differently in both texts - is put forward as a significant factor in the deviation of Der Zauberberg and The Nick Adams Stories from the traditions of the Bildungsroman and of the narrative of initiation. This departure leads to a re-appraisal of the relation between the protagonists and their society, and to a new ethical attitude that presupposes different, more modem conceptions of what Bildung and initiation represent in the context of the early twentieth century. How and why they changed and if they survived as literary notions are questions this thesis attempts to answer.