The main goal of this thesis was to increase reconstruction quality of sparse sampled microscopic images by using neural networks. The thesis will cover various approaches for image reconstruction and will also include descriptions of implementations, which were used. Implementations will be evaluated based on quality of reconstruction, but also based on segmentation, which could be their main possible application.

This thesis investigates the use of Generative Adversarial Networks (GANs) for detecting images containing non-natural objects in natural environments and if the introduction of stereo data can improve the performance. The state-of-the-art GAN-based anomaly detection method presented by A. Berget al. in [5] (BergGAN) was the base of this thesis. By modifiying BergGAN to not only accept three channel input, but also four and six channel input, it was possible to investigate the effect of introducing stereo data in the method. The input to the four channel network was an RGB image and its corresponding disparity map, and the input to the six channel network was a stereo pair consistingof two RGB images. The three datasets used in the thesis were constructed froma dataset of aerial video sequences provided by SAAB Dynamics, where the scene was mostly wooded areas. The datasets were divided into training and validation data, where the latter was used for the performance evaluation of the respective network. The evaluation method suggested in [5] was used in the thesis, where each sample was scored on the likelihood of it containing anomalies, Receiver Operating Characteristics (ROC) analysis was then applied and the area under the ROC-curve was calculated. The results showed that BergGAN was successfully able to detect images containing non-natural objects in natural environments using the dataset provided by SAAB Dynamics. The adaption of BergGAN to also accept four and six input channels increased the performance of the method, showing that there is information in stereo data that is relevant for GAN-based anomaly detection. There was however no substantial performance difference between the network trained with two RGB images versus the one trained with an RGB image and its corresponding disparity map.

ermal desorption spectroscopy (TDS) is a common method for surface analysis of adsorbed molecules. In chapter 1 the work deals with the theoretical background of this method and shows the principles of a desorption process influenced by subsurface diffusion. Chapter 2 first shows application of TDS for detection of surface molecules and determination of binding energy.Experiments were mainly focused on ditermination of surface adsorbents and impurities on Si wafers. The second part of chapter 2 describes desorption of atoms of a Ga layer on Si surface and their subsurface diffusion. A Ga diffusion process was also observed by with secondary ion mass spectrometry (SIMS) and numerically simulated.

京都大学 / 0048 / 新制・課程博士 / 博士(工学) / 甲第21108号 / 工博第4472号 / 新制||工||1695(附属図書館) / 京都大学大学院工学研究科電気工学専攻 / (主査)教授 篠原 真毅, 教授 山川 宏, 教授 木本 恒暢 / 学位規則第4条第1項該当 / Doctor of Philosophy (Engineering) / Kyoto University / DFAM

No description available.

<p>  </p> <p>Research that seeks to understand and develop the growth of III-nitride materials by molecular beam epitaxy (MBE) is beneficial to a broad range of the device community. MBE and the III-nitrides have been used to develop transistors, diodes, electroacoustic devices, solar cells, LEDs, LDs, intersubband devices, and quantum-cascade lasers. In this work we focus on the growth of III-nitride materials specifically for applications in near-infrared intersubband (NIR ISB) optical devices, however all this work is broadly applicable. </p> <p><br></p> <p>We begin by investigating the reduced indium incorporation in non-polar m-plane InGaN films. We find that InGaN grown on m-plane GaN has an effective activation energy for thermal decomposition of 1 eV, nearly half that reported for similar c-plane films. We produce high quality m-plane In0.16Ga0.84N and utilize it in AlGaN/InGaN devices designed for near-infrared ISB absorption measurements. We continue this work by exploring the growth of low-temperature AlGaN, necessary for these devices. We find that the utilization of an indium surfactant during low-temperature AlGaN growth enhances adatom diffusion, resulting in smoother surface morphologies, sharper interfaces, and reduced defects within the material. This growth method also prevents the anomalous suppression of the AlGaN growth rate, which we link to a reduction in the formation of high-aluminum containing defects. These investigations result in the demonstration of an Al0.24Ga0.76N/In0.16Ga0.84N heterostructure with a conduction band offset large enough to enable NIR ISB transitions.</p> <p><br></p> <p>Lastly, we explore the novel material ScAlN. This material’s large bandgap, large spontaneous polarization, ferroelectricity, and ability to be lattice matched to GaN at ~18% scandium composition make it an ideal candidate for a variety of devices, including NIR ISB devices. We investigate the reported temperature dependence of ScAlN’s <em>c</em>-lattice constant and confirm this dependence is present for high growth-temperature ScxAl1-xN with 0.11 < x < 0.23. We find that this temperature dependence is no longer present below a certain composition-dependent growth temperature. This finding, coupled with observations that samples grown at lower temperatures exhibit lower defect densities, smoother surfaces, and homogeneous chemical compositions suggest that high growth temperatures lead to defect generation that may cause the observed change in lattice parameters. We demonstrate lattice-matched, 50 repeat Sc0.18Al1-xN/GaN heterostructures with ISB absorption in excess of 500 meV with FWHM as little as 45 meV. </p>

Central Clearing Counterparties play a crucial role in financial markets, requiring robust risk management practices to ensure operational stability. A growing emphasis on risk analysis and stress testing from regulators has led to the need for sophisticated tools that can model extreme but plausible market scenarios. This thesis presents a method leveraging Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to construct an independent scenario generator capable of modeling and generating return distributions for financial markets. The developed method utilizes two primary components: the WGAN-GP model and a novel scenario selection strategy. The WGAN-GP model approximates the multivariate return distribution of stocks, generating plausible return scenarios. The scenario selection strategy employs lower and upper bounds on Euclidean distance calculated from the return vector to identify, and select, extreme scenarios suitable for stress testing clearing members' portfolios. This approach enables the extraction of extreme yet plausible returns. This method was evaluated using 25 years of historical stock return data from the S&amp;P 500. Results demonstrate that the WGAN-GP model effectively approximates the multivariate return distribution of several stocks, facilitating the generation of new plausible returns. However, the model requires extensive training to fully capture the tails of the distribution. The Euclidean distance-based scenario selection strategy shows promise in identifying extreme scenarios, with the generated scenarios demonstrating comparable portfolio impact to historical scenarios. These results suggest that the proposed method offers valuable tools for Central Clearing Counterparties to enhance their risk management. / Centrala motparter spelar en avgörande roll i dagens finansmarknad, vilket innebär att robusta riskhanteringsrutiner är nödvändiga för att säkerställa operativ stabilitet. Ökande regulatoriskt tryck för riskanalys och stresstestning från tillsynsmyndigheter har lett till behovet av avancerade verktyg som kan modellera extrema men troliga marknadsscenarier. I denna uppsats presenteras en metod som använder Wasserstein Generative Adversarial Networks med Gradient Penalty (WGAN-GP) för att skapa en oberoende scenariogenerator som kan modellera och generera avkastningsfördelningar för finansmarknader. Den framtagna metoden består av två huvudkomponenter: WGAN-GP-modellen och en scenariourvalstrategi. WGAN-GP-modellen approximerar den multivariata avkastningsfördelningen för aktier och genererar möjliga avkastningsscenarier. Urvalsstrategin för scenarier använder nedre och övre gränser för euklidiskt avstånd, beräknat från avkastningsvektorn, för att identifiera och välja extrema scenarier som kan användas för att stresstesta clearingmedlemmars portföljer. Denna strategi gör det möjligt att erhålla nya extrema men troliga avkastningar. Metoden utvärderas med 25 års historisk aktieavkastningsdata från S&amp;P 500. Resultaten visar att WGAN-GP-modellen effektivt kan approximera den multivariata avkastningsfördelningen för flera aktier och därmed generera nya möjliga avkastningar. Modellen kan dock kräva en omfattande mängd träningscykler (epochs) för att fullt ut fånga fördelningens svansar. Scenariurvalet baserat på euklidiskt avstånd visade lovande resultat som ett urvalskriterium för extrema scenarier. De genererade scenarierna visar en jämförbar påverkan på portföljer i förhållande till de historiska scenarierna. Dessa resultat tyder på att den föreslagna metoden kan erbjuda värdefulla verktyg för centrala motparter att förbättra sin riskhantering.

<p>High-throughput phenotyping has emerged as a powerful approach to expedite crop breeding programs. Modern remote sensing systems, including manned aircraft, unmanned aerial vehicles (UAVs), and terrestrial platforms equipped with multiple sensors, such as RGB cameras, multispectral, hyperspectral, and infrared thermal sensors, as well as light detection and ranging (LiDAR) scanners are now widely used technologies in advancing high throughput phenotyping. These systems can collect high spatial, spectral, and temporal resolution data on various phenotypic traits, such as plant height, canopy cover, and leaf area. Enhancing the capability of utilizing such remote sensing data for automated phenotyping is crucial in advancing crop breeding. This dissertation focuses on developing deep learning and transfer learning methodologies for crop phenotyping using multi-modality remote sensing and environmental data. The techniques address two main areas: multi-temporal/across-field biomass prediction and multi-scale remote sensing data fusion.</p> <p><br></p> <p>Biomass is a plant characteristic that strongly correlates with biofuel production, but is also influenced by genetic and environmental factors. Previous studies have shown that deep learning-based models are effective in predicting end-of-season biomass for a single year and field. This dissertation includes development of transfer learning methodologies for multiyear,</p> <p>across-field biomass prediction. Feature importance analysis was performed to identify and remove redundant features. The proposed model can incorporate high-dimensional genetic marker data, along with other features representing phenotypic information, environmental conditions, or management practices. It can also predict end-of-season biomass using mid-season remote sensing and environmental data to provide early rankings. The framework was evaluated using experimental trials conducted from 2017 to 2021 at the Agronomy Center for Research and Education (ACRE) at Purdue University. The proposed transfer learning techniques effectively selected the most informative training samples in the target domain, resulting in significant improvements in end-of-season yield prediction and ranking. Furthermore, the importance of input remote sensing features was assessed at different growth stages.</p> <p><br></p> <p>Remote sensing technology enables multi-scale, multi-temporal data acquisition. However, to fully exploit the potential of the acquired data, data fusion techniques that leverage the strengths of different sensors and platforms are necessary. In this dissertation, a generative adversarial network (GAN) based multiscale RGB-guided model and domain adaptation framework were developed to enhance the spatial resolution of multispectral images. The model was trained on limited high spatial resolution images from a wheel-based platform and then applied to low spatial resolution images acquired by UAV and airborne platforms.</p> <p>The strategy was tested in two distinct scenarios, sorghum plant breeding, and urban areas, to evaluate its effectiveness.</p>

This thesis aims to evaluate the current state of the art for unconditional text generation and compare established models with novel approaches in the task of generating texts, after being trained on texts written by political parties from the Swedish Riksdag. First, the progression of language modeling from n-gram models and statistical models to neural network models is presented. This is followed by theoretical arguments for the development of adversarial training methods,where a generator neural network tries to fool a discriminator network, trained to distinguish between real and generated sentences. One of the methods in the research frontier diverges from the adversarial idea and instead uses cooperative training, where a mediator network is trained instead of a discriminator. The mediator is then used to estimate a symmetric divergence measure between the true distribution and the generator’s distribution, which is to be minimized in training. A set of experiments evaluates the performance of cooperative training and adversarial training, and finds that they both have advantages and disadvantages. In the experiments, the adversarial training increases the quality of generated texts, while the cooperative training increases the diversity. The findings are in line with the theoretical expectation. / Denna uppsats utvärderar några nyligen föreslagna metoder för obetingad textgenerering, baserade på s.k. “Generative Adversarial Networks” (GANs). Den jämför etablerade modeller med nya metoder för att generera text, efter att ha tränats på texter från de svenska Riksdagspartierna. Utvecklingen av språkmodellering från n-gram-modeller och statistiska modeller till modeller av neurala nätverk presenteras. Detta följs upp av teoretiska argument för utvecklingen av GANs, för vilka ett generatornätverk försöker överlista ett diskriminatornätverk, som tränas skilja mellan riktiga och genererade meningar. En av de senaste metoderna avviker från detta angreppssätt och introducerar istället kooperativ träning, där ett mediatornätverk tränas istället för en diskriminator. Mediatorn används sedan till att uppskatta ett symmetriskt divergensmått mellan den sanna distributionen och generatorns distribution, vilket träningen syftar till att minimera. En serie experiment utvärderar hur GANs och kooperativ träning presterar i förhållande till varandra, och finner att de båda har för- och nackdelar. I experimenten ökar GANs kvaliteten på texterna som genereras, medan kooperativ träning ökar mångfalden. Resultaten motsvarar vad som kan förväntas teoretiskt.

The Generative Adversarial Network framework has shown success in implicitly modeling data distributions and is able to generate realistic samples. Its architecture is comprised of a generator, which produces fake data that superficially seem to belong to the real data distribution, and a discriminator which is to distinguish fake from genuine samples. The Noiseless Joint Plug &amp; Play model offers an extension to the framework by simultaneously training autoencoders. This model uses a pre-trained encoder as a feature extractor, feeding the generator with global information. Using the Plug &amp; Play network as baseline, we design a new model by adding discriminators to the Plug &amp; Play architecture. These additional discriminators are trained to discern real and fake latent codes, which are the output of the encoder using genuine and generated inputs, respectively. We proceed to investigate whether this approach is viable. Experiments conducted for the MNIST manifold show that this indeed is the case. / Generative Adversarial Network är ett ramverk vilket implicit modellerar en datamängds sannolikhetsfördelning och är kapabel till att producera realistisk exempel. Dess arkitektur utgörs av en generator, vilken kan fabricera datapunkter liggandes nära den verkliga sannolikhetsfördelning, och en diskriminator vars syfte är att urskilja oäkta punkter från genuina. Noiseless Joint Plug &amp; Play modellen är en vidareutveckling av ramverket som samtidigt tränar autoencoders. Denna modell använder sig utav en inlärd enkoder som förser generatorn med data. Genom att använda Plug &amp; Play modellen som referens, skapar vi en ny modell genom att addera diskriminatorer till Plug &amp; Play architekturen. Dessa diskriminatorer är tränade att särskilja genuina och falska latenta koder, vilka har producerats av enkodern genom att ha använt genuina och oäkta datapunkter som inputs. Vi undersöker huruvida denna metod är gynnsam. Experiment utförda för MNIST datamängden visar att så är fallet.