Glioblastoma Multiforme (GBM) is a very aggressive brain tumour. Previous studies have suggested that the morphological distribution of single GBM cells may hold information about the severity. This study aims to find if there is a potential for automated morphological qualification and clustering of GBM cells and what it shows. In this context, phase-contrast images from 10 different GBMcell cultures were analyzed. To test the hypothesis that morphological differences exist between the cell cultures, images of single GBM cells images were created from an image over the well using CellProfiler and Python. Singlecellimages were passed through multiple different feature extraction models to identify the model showing the most promise for this dataset. The features were then clustered and quantified to see if any differentiation exists between the cell cultures. The results suggest morphological feature differences exist between GBM cell cultures when using automated models. The siamese network managed to construct clusters of cells having very similar morphology. I conclude that the 10 cell cultures seem to have cells with morphological differences. This highlights the importance of future studies to find what these morphological differences imply for the patients' survivability and choice of treatment.

Gaze tracking has already shown to be a popular technology for desktop devices. When it comes to gaze tracking for mobile devices, however, there is still a lot of progress to be made. There’s still no high accuracy gaze tracking available that works in an unconstrained setting for mobile devices. This work makes contributions in the area of appearance-based unconstrained gaze estimation. Artificial neural networks are trained on GazeCapture, a publicly available dataset for mobile gaze estimation containing over 2 million face images and corresponding gaze labels. In this work, Siamese neural networks are trained to learn linear distances between face images for different gaze points. Then, during inference, calibration points are used to estimate gaze points. This approach is shown to be an effective way of utilizing calibration points in order to improve the result of gaze estimation. / Ögonblickspårning har redan etablerat sig som en populär teknologi för stationära enheter. När det dock gäller mobila enheter så finns det framsteg att göra. Det saknas fortfarande en lösning för ögonblickspårning som fungerar i en undantagsfri miljö för mobila enheter. Detta examensarbete ämnar att bidra till en sådan lösning. Artificiella neurala nätverk tränas på GazeCapture, en allmänt tillgänglig datasamling som består av över 2 miljoner ansiktsbilder samt korresponderande etikett för ögonblickspunkt. I detta examensarbete tränas Siamesiska neurala nätverk för att lära sig det linjära avståndet mellan två ögonblickspunkter. Sedan utnyttjas en samling med kalibreringsbilder för att estimera ögonblickspunkter. Denna teknik visar sig vara ett effektivt sätt att nyttja kalibreringsbilder med målet att förbättra resultatet för ögonblicksestimering.

Submitted by PPG Ci?ncia da Computa??o (ppgcc@pucrs.br) on 2017-11-21T17:02:34Z No. of bitstreams: 1 Alan_Diego_dos_Santos_dis.pdf: 1881856 bytes, checksum: cf0113b0b67e0771e4b2920440d41e2b (MD5) / Rejected by Caroline Xavier (caroline.xavier@pucrs.br), reason: Devolvido devido ? falta da folha de rosto (p?gina com as principais informa??es) no arquivo PDF, passando direto da capa para a ficha catalogr?fica. on 2017-11-29T19:03:08Z (GMT) / Submitted by PPG Ci?ncia da Computa??o (ppgcc@pucrs.br) on 2017-11-30T15:50:58Z No. of bitstreams: 1 Alan_Diego_dos_Santos_dis.pdf: 1884320 bytes, checksum: 6e508a972289e66527fd4b76cbae3586 (MD5) / Approved for entry into archive by Caroline Xavier (caroline.xavier@pucrs.br) on 2017-12-04T16:14:52Z (GMT) No. of bitstreams: 1 Alan_Diego_dos_Santos_dis.pdf: 1884320 bytes, checksum: 6e508a972289e66527fd4b76cbae3586 (MD5) / Made available in DSpace on 2017-12-04T16:18:35Z (GMT). No. of bitstreams: 1 Alan_Diego_dos_Santos_dis.pdf: 1884320 bytes, checksum: 6e508a972289e66527fd4b76cbae3586 (MD5) Previous issue date: 2017-03-29 / Triagem virtual de bancos de dados de ligantes ? amplamente utilizada nos est?gios iniciais do processo de descoberta de f?rmacos. Abordagens computacionais ?docam? uma pequena mol?cula dentro do s?tio ativo de um estrutura biol?gica alvo e avaliam a afinidade das intera??es entre a mol?cula e a estrutura. Todavia, os custos envolvidos ao aplicar algoritmos de docagem molecular em grandes bancos de ligantes s?o proibitivos, dado a quantidade de recursos computacionais necess?rios para essa execu??o. Nesse contexto, estrat?gias de aprendizagem de m?quina podem ser aplicadas para ranquear ligantes baseadas na afinidade com determinada estrutura biol?gica e, dessa forma, reduzir o n?mero de compostos qu?micos a serem testados. Nesse trabalho, propomos um modelo para ranquear ligantes baseados na arquitetura de redes neurais siamesas. Esse modelo calcula a compatibilidade entre receptor e ligante usando grades de propriedades bioqu?micas. N?s tamb?m mostramos que esse modelo pode aprender a identificar intera??es moleculares importantes entre ligante e receptor. A compatibilidade ? calculada baseada em rela??o ? conforma??o do ligante, independente de sua posi??o e orienta??o em rela??o ao receptor. O modelo proposto foi treinado usando ligantes ativos previamente conhecidos e mol?culas chamarizes (decoys) em um modelo de receptor totalmente flex?vel (Fully Flexible Receptor - FFR) do complexo InhA-NADH da Mycobacterium tuberculosis, encontrando ?timos resultados. / Structure-based virtual screening (SBVS) on compounds databases has been widely applied in early stage of the drug discovery on drug target with known 3D structure. In SBVS, computational approaches usually ?dock? small molecules into binding site of drug target and ?score? their binding affinity. However, the costs involved in applying docking algorithms into huge compounds databases are prohibitive, due to the computational resources required by this operation. In this context,different types of machine learning strategies can be applied to rank ligands, based on binding affinity,and to reduce the number of compounds to be tested. In this work, we propose a deep learning energy-based model using siamese neural networks to rank ligands. This model takes as inputs grids of biochemical properties of ligands and receptors and calculates their compatibility. We show that the model can learn to identify important biochemical interactions between ligands and receptors. Besides, we demonstrate that the compatibility score is computed based only on conformation of small molecule, independent of its position and orientation in relation to the receptor. The proposed model was trained using known ligands and decoys in a Fully Flexible Receptor model of InhA-NADH complex (PDB ID: 1ENY), having achieved outstanding results.

One of the things augmented reality depends on is object tracking, which is a problem classically found in cinematography and security. However, the algorithms designed for the classical application are often too expensive computationally or too complex to run on simpler mobile hardware. One of the methods to do object tracking is with a trained neural network, this has already led to great results but is unfortunately still running into some of the same problems as the classical algorithms. For this reason a neural network designed specifically for object tracking on mobile hardware needs to be developed. This thesis will propose two di erent neural networks designed for object tracking on mobile hardware. Both are based on a siamese network structure and methods to improve their accuracy using filtering are also introduced. The first network is a modified version of “CNN architecture for geometric matching” that utilizes an a ne regression to perform object tracking. This network was shown to underperform in the MOT benchmark as-well as the VOT benchmark and therefore not further developed. The second network is an object detector based on “SqueezeDet” in a siamese network structure utilizing the performance optimized layers of “MobileNets”. The accuracy of the object detector network is shown to be competitive in the VOT benchmark, placing at the 16th place compared to trackers from the 2016 challenge. It was also shown to run in real-time on mobile hardware. Thus the one shot object detection network used for a tracking application can improve the experience of augmented reality applications on mobile hardware.

Trouble and bug reports are essential in software maintenance and for identifying faults—a challenging and time-consuming task. In cases when the fault and reports are similar or identical to previous and already resolved ones, the effort can be reduced significantly making the prospect of automatically detecting duplicates very compelling. In this work, common methods and techniques in the literature are evaluated and compared on domain-specific and multimodal trouble reports from Ericsson software. The number of samples is few, which is a case not so well-studied in the area. On this basis, both traditional and more recent techniques based on deep learning are considered with the goal of accurately detecting duplicates. Firstly, the more traditional approach based on natural language processing and machine learning is evaluated using different vectorization techniques and similarity measures adapted and customized to the domain-specific trouble reports. The multimodality and many fields of the trouble reports call for a wide range of techniques, including term frequency-inverse document frequency, BM25, and latent semantic analysis. A pipeline processing each data field of the trouble reports independently and automatically weighing the importance of each data field is proposed. The best performing model achieves a recall rate of 89% for a duplicate candidate list size of 10. Further, obtaining knowledge on which types of data are most important for duplicate detection is explored through what is known as Shapley values. Results indicate that utilizing all types of data indeed improve performance, and that date and code parameters are strong indicators. Secondly, a Siamese network based on Transformer-encoders is evaluated on data fields believed to have some underlying representation of the semantic meaning or sequentially important information, which a deep model can capture. To alleviate the issues when having few samples, pre-training through automatic data labeling is studied. Results show an increase in performance compared to not pre-training the Siamese network. However, compared to the more traditional model it performs on par, indicating that traditional models may perform equally well when having few samples besides also being simpler, more robust, and faster. / Buggrapporter är kritiska för underhåll av mjukvara och för att identifiera fel — en utmanande och tidskrävande uppgift. I de fall då felet och rapporterna liknar eller är identiska med tidigare och redan lösta ärenden, kan tiden som krävs minskas avsevärt, vilket gör automatiskt detektering av dubbletter mycket önskvärd. I detta arbete utvärderas och jämförs vanliga metoder och tekniker i litteraturen på domänspecifika och multimodala buggrapporter från Ericssons mjukvara. Antalet tillgängliga träningsexempel är få, vilket inte är ett så välstuderat fall. Utifrån detta utvärderas både traditionella samt nyare tekniker baserade på djupinlärning med målet att detektera dubbletter så bra som möjligt. Först utvärderas det mer traditionella tillvägagångssättet baserat på naturlig språkbearbetning och maskininlärning med hjälp av olika vektoriseringstekniker och likhetsmått specialanpassade till buggrapporterna. Multimodaliteten och de många datafälten i buggrapporterna kräver en rad av tekniker, så som termfrekvens-invers dokumentfrekvens, BM25 och latent semantisk analys. I detta arbete föreslås en modell som behandlar varje datafält i buggrapporterna separat och automatiskt sammanväger varje datafälts betydelse. Den bäst presterande modellen uppnår en återkallningsfrekvens på 89% för en lista med 10 dubblettkandidater. Vidare undersöks vilka datafält som är mest viktiga för dubblettdetektering genom Shapley-värden. Resultaten tyder på att utnyttja alla tillgängliga datafält förbättrar prestandan, och att datum och kodparametrar är starka indikatorer. Sedan utvärderas ett siamesiskt nätverk baserat på Transformator-kodare på datafält som tros ha en underliggande representation av semantisk betydelse eller sekventiellt viktig information, vilket en djup modell kan utnyttja. För att lindra de problem som uppstår med få träningssexempel, studeras det hur den djupa modellen kan förtränas genom automatisk datamärkning. Resultaten visar på en ökning i prestanda jämfört med att inte förträna det siamesiska nätverket. Men jämfört med den mer traditionella modellen presterar den likvärdigt, vilket indikerar att mer traditionella modeller kan prestera lika bra när antalet träningsexempel är få, förutom att också vara enklare, mer robusta, och snabbare.