No description available.

This master's thesis describes creation of prediction system. This system predicts future market development based on stock exchange data and twitter messages analysis. Tweets from two different sources are analysed by mood dictionaries or via recurrent neural networks. This analysis results and technical analysis of stock exchange data results are used in multilayer neural network for prediction. A business strategy is created and tested based on results of this prediction. Design and implementation of prediction system is described in this thesis. This system achieved revenue increase more than 25 % of some business strategies by tweets analysis. However this improvement applies for certain data and timeframe.

Heating, ventilation and air conditioning systems (HVAC) are the single largest consumer of energy in commercial and residential sectors. Minimizing its energy consumption without compromising indoor air quality (IAQ) and thermal comfort would result in environmental and financial benefits. Currently, most buildings still utilize constant air volume (CAV) systems with on/off control to meet the thermal loads. Such systems, without any consideration of occupancy, may ventilate a zone excessively and result in energy waste. Previous studies showed that CO₂-based demand-controlled ventilation (DCV) methods are the most widely used strategies to determine the optimal level of supply air volume. However, conventional CO₂ mass balanced models do not yield an optimal estimation accuracy. In this study, feed-forward neural network algorithm (FFNN) was proposed to estimate the zone occupancy using CO₂ concentrations, observed occupancy data and the zone schedule. The occupancy prediction result was then utilized to optimize supply fan operation of the air handling unit (AHU) associated with the zone. IAQ and thermal comfort standards were also taken into consideration as the active constraints of this optimization. As for the validation, the experiment was carried out in an auditorium located on a university campus. The results revealed that utilizing neural network occupancy estimation model can reduce the daily ventilation energy by 74.2% when compared to the current on/off control.

<p>3D character modeling is a crucial process of asset creation in the entertainment industry, particularly for animation and games. A fully automated pipeline via sketch-based 3D modeling (SBM) is an emerging possibility, but development is stalled by unrefined outputs and a lack of character-centered tools. This thesis proposes an improved method for constructing 3D character models with minimal user input, using only two sketch inputs  i.e., a front and side unshaded sketch. The system implements a deep convolutional neural network (CNN), a type of deep learning algorithm extending from artificial intelligence (AI), to process the input sketch and generate multi-view depth, normal and confidence maps that offer more information about the 3D surface. These are then fused into a 3D point cloud, which is a type of object representation for 3D space. This point cloud is converted into a 3D mesh via an occupancy network, involving another CNN, for a more precise 3D representation. This reconstruction step contends with non-deep learning approaches such as  Poisson reconstruction. The proposed system is evaluated for character generation on standardized quantitative metrics (i.e., Chamfer Distance [CD], Earth Mover’s Distance [EMD], F-score and Intersection of Union [IoU]), and compared to the base framework trained on the same character sketch and model database. This implementation offers a  significant improvement in the accuracy of vertex positions for the reconstructed character models. </p>

<p> Understanding the behavior of liquid hydrocarbon propellants under high pressure and temperature conditions is a crucial step towards improving the performance of modern-day combustion engines (liquid rocket engines, diesel engines, gas turbines and so on) and designing the next generation ones. Under such harsh thermodynamic conditions (high P&T) propellent droplets may experience anywhere from sub-to-trans-to-supercritical regime. The focus of this research is to explore the dynamics of the vapor-liquid two phase system formed by a liquid hydrocarbon fuel (n-heptane or n-dodecane) and ambient (nitrogen) over a wide range of P&T leading up to the mixture critical point and beyond. Molecular dynamics (MD) has been used as the primary tool in this research along with other tools like: phase stability calculations based on Gibb’s work, Peng Robinson equation of state, density gradient theory and neural networks.</p>

Indiana University-Purdue University Indianapolis (IUPUI) / This thesis proposes an artificial neural network (NN) model to predict fuel consumption in heavy vehicles. The model uses predictors derived from vehicle speed, mass, and road grade. These variables are readily available from telematics devices that are becoming an integral part of connected vehicles. The model predictors are aggregated over a fixed distance traveled (i.e., window) instead of fixed time interval. It was found that 1km windows is most appropriate for the vocations studied in this thesis. Two vocations were studied, refuse and delivery trucks. The proposed NN model was compared to two traditional models. The first is a parametric model similar to one found in the literature. The second is a linear regression model that uses the same features developed for the NN model. The confidence level of the models using these three methods were calculated in order to evaluate the models variances. It was found that the NN models produce lower point-wise error. However, the stability of the models are not as high as regression models. In order to improve the variance of the NN models, an ensemble based on the average of 5-fold models was created. Finally, the confidence level of each model is analyzed in order to understand how much error is expected from each model. The mean training error was used to correct the ensemble predictions for five K-Fold models. The ensemble K-fold model predictions are more reliable than the single NN and has lower confidence interval than both the parametric and regression models.

<p>  </p> <p>In the field of Engineering Analysis and Simulation, part simplification is often used to reduce the computational time and requirements of finite element solvers. Reducing the complexity of the model through simplification introduces error into the analysis, the amount of which depends on the engineering scenario, CAD model, and method of simplification. Expert Analysts utilize their experience and understanding to mitigate the error in analysis through intelligent simplification method selection, however, there is no formalized system of selection. Artificial Intelligence, specifically through the use of Machine Learning algorithms, has been explored as a method of capturing and automating upon this informal knowledge. One existing method which found success only explored Computational Fluid Dynamics simulations without validating the method on other kinds of engineering analysis cases. This study attempts to validate this a priori method on a new situation and directly compare the results between studies. To accomplish this, a new CAD Assembly model database was generated of over 300 simplified and non-simplified examples. Afterwards, the models were subjected to a Structural Analysis simulation, where analysis data could be generated and stored. Finally, a Regression Neural Network was utilized to create Machine Learning models to predict analysis result errors. This study examines the question of how minimal a neural network architecture will be able to make predictions with a comparable accuracy to that of the previous studies.   </p>

Recent improvements in the area of Internet of Things (IoT) has led to extensive utilization of embedded devices and sensors. Hence, along with utilization the need for safety and security of these devices also increases proportionately. In the last two decades, the side-channel attack (SCA) has become a massive threat to the interrelated embedded devices. Moreover, extensive research has led to the development of many different forms of SCA for extracting the secret key by utilizing the various leakage information. Lately, machine learning (ML) based models have been more effective in breaking complex encryption systems than the other types of SCA models. However, these ML or DL models require a lot of data for training that cannot be collected while attacking a device in a real-world situation. Thus, in this thesis, we try to solve this issue by proposing the new technique of leakage conversion. In this technique, we try to convert the high signal to noise ratio (SNR) power traces to low SNR averaged electromagnetic traces. In addition to that, we also show how artificial neural networks (ANN) can learn various non-linear dependencies of features in leakage information, which cannot be done by adaptive digital signal processing (DSP) algorithms. Initially, we successfully convert traces in the time interval of 80 to 200 as the cryptographic operations occur in that time frame. Next, we show the successful conversion of traces lying in any time frame as well as having a random key and plain text values. Finally, to validate our leakage conversion technique and the generated traces we successfully implement correlation electromagnetic analysis (CEMA) with an approximate minimum traces to disclosure (MTD) of 480.

The development of Advanced Driver Assistance Systems and autonomous driving is one of the main research fields in the area of vehicle development today. Initially the research in this area focused on analyzing and predicting driving maneuvers on highways. Nowadays, a vast amount of research focuses on urban areas as well. Driving maneuvers in urban areas are more complex and therefore more difficult to predict than driving maneuvers on highways. The goals of predicting and understanding driving maneuvers are to reduce accidents, to improve traffic density, and to develop reliable algorithms for autonomous driving. Driving behavior during different driving maneuvers such as turning at intersections, emergency braking or lane changes are analyzed. This thesis focuses on the driving behavior around lane changes and thus the prediction of lane changes in the urban area is applied with an Echo State Network. First, existing methods with a special focus on input variables and results were evaluated to derive input variables with regard to lane change and no lane change sequences. The data for this first analyses were obtained from a naturalistic driving study. Based on theses results the final set of variables (steering angle, turn signal and gazes to the left and right) was chosen for further computations. The parameters of the Echo State Network were then optimized using the data of the naturalistic driving study and the final set of variables. Finally, left and right lane changes were predicted. Furthermore, the Echo State Network was compared to a feedforward neural network. The Echo State Network could predict left and right lane changes more successful than the feedforward neural network. / Fahrerassistenzsysteme und Algorithmen zum autonomen Fahren stellen ein aktuelles Forschungsfeld im Bereich der Fahrzeugentwicklung dar. Am Anfang wurden vor allem Fahrmanöver auf der Autobahn analysiert und vorhergesagt, mittlerweile hat sich das Forschungsfeld auch auf den urbanen Verkehr ausgeweitet. Fahrmanöver im urbanen Raum sind komplexer als Fahrmanöver auf Autobahnen und daher schwieriger vorherzusagen. Ziele für die Vorhersage von Fahrmanövern sind die Reduzierung von Verkehrsunfällen, die Verbesserung des Verkehrsflusses und die Entwicklung von zuverlässigen Algorithmen für das autonome Fahren. Um diese Ziele zu erreichen, wird das Fahrverhalten bei unterschiedlichen Fahrmanövern analysiert, wie z.B. beim Abbiegevorgang an Kreuzungen, bei der Notbremsung oder beim Spurwechsel. In dieser Arbeit wird der Spurwechsel im urbanen Straßenverkehr mit einem Echo State Network vorhergesagt. Zuerst wurden existierende Methoden zur Spurwechselvorhersage bezogen auf die Eingaben und die Ergebnisse bewertet, um danach die spurwechselbezogenen Variableneigenschaften bezüglich Spurwechsel- und Nicht-Spurwechselsequenzen zu analysieren. Die Daten, die Basis für diese ersten Untersuchungen waren, stammen aus einer Realfahrstudie. Basierend auf diesen Resultaten wurden die finalen Variablen (Lenkwinkel, Blinker und Blickrichtung) für weitere Berechnungen ausgewählt. Mit den Daten aus der Realfahrstudie und den finalen Variablen wurden die Parameter des Echo State Networks optimiert und letztendlich wurden linke und rechte Spurwechsel vorhergesagt. Zusätzlich wurde das Echo State Network mit einem vorwärtsgerichteten neuronalen Netz verglichen. Das Echo State Network konnte linke und rechte Spurwechsel erfolgreicher vorhersagen als das vorwärtsgerichtete neuronale Netz.

<div> This thesis proposes an artificial neural network (NN) model to predict fuel consumption in heavy vehicles. The model uses predictors derived from vehicle speed, mass, and road grade. These variables are readily available from telematics devices that are becoming an integral part of connected vehicles. The model predictors are aggregated over a fixed distance traveled (i.e., window) instead of fixed time interval. It was found that 1km windows is most appropriate for the vocations studied in this thesis. Two vocations were studied, refuse and delivery trucks.</div><div><br></div><div> The proposed NN model was compared to two traditional models. The first is a parametric model similar to one found in the literature. The second is a linear regression model that uses the same features developed for the NN model.</div><div><br></div><div> The confidence level of the models using these three methods were calculated in order to evaluate the models variances. It was found that the NN models produce lower point-wise error. However, the stability of the models are not as high as regression models. In order to improve the variance of the NN models, an ensemble based on the average of 5-fold models was created. </div><div><br></div><div> Finally, the confidence level of each model is analyzed in order to understand how much error is expected from each model. The mean training error was used to correct the ensemble predictions for five K-Fold models. The ensemble K-fold model predictions are more reliable than the single NN and has lower confidence interval than both the parametric and regression models.</div>