Hereditary hemorrhagic telangiectasia (HHT), also known as Osler-Weber-Rendu syndrome, is a rare genetic blood disorder that leads to abnormal bleeding due to absent capillaries and multiple abnormal blood vessels known as arteriovenous malformations. A feature of HHT is high-output heart failure due to multiple arteriovenous malformations. High-output heart failure can lead to recurrent epistaxis Kiesselbach area syndrome (REKAS), further exacerbating heart failure through increased blood loss and resultant anemia. We report a patient with HHT who presented with high-output heart failure contributing to REKAS. In patients with REKAS, we propose if anemia is present, REKAS can be avoided by correcting the anemia by increasing the hemoglobin level to greater than 9 to 10 g/dL. This decreases hyperdynamic circulation and reduces pressure in the blood vessels of the nose.

Deception detection has always been of subject of interest. After all, determining if a person is telling the truth or not could be detrimental in many real-world cases. Current methods to discern deceptions require expensive equipment that need specialists to read and interpret them. In this article, we carry out an exhaustive comparison between 9 different facial landmark recognition based recurrent deep learning models trained on a recent man-made database used to determine lies, comparing them by accuracy and AUC. We also propose two new metrics that represent the validity of each prediction. The results of a 5-fold cross validation show that out of all the tested models, the Stacked GRU neural model has the highest AUC of.9853 and the highest accuracy of 93.69% between the trained models. Then, a comparison is done between other machine and deep learning methods and our proposed Stacked GRU architecture where the latter surpasses them in the AUC metric. These results indicate that we are not that far away from a future where deception detection could be accessible throughout computers or smart devices. / Revisión por pares

The anterior approach to cervical spine surgery is associated with many possible complications. Dysphagia has commonly been reported as one of these complications. A closer examination of the reports of dysphagia following anterior cervical spine surgery, however, reveals that while new onset transient dysphagia is often mentioned, long-term (greater than 48 hours) dysphagia has not been well described. In this article, we report the case of a 29-year-old female with long-term recurrent dysphagia following cervical spine surgery using the anterior approach. The important point about this case is that our patient's symptoms suddenly recurred for the first time after, nearly a two-month period of normal swallowing. Consequently, this patient has required multiple dilations. As a result, despite an initial lack of swallowing dysfunction or the return of normal swallowing, clinicians should be aware of the importance of reassessing swallowing in patients who have undergone cervical spine surgery using the anterior approach.

For different input contexts (sequence of previous words), to predict the next word, a neural word-level language model outputs a probability distribution over all the words in the vocabulary using a softmax function. When the log of probability outputs for all such contexts are stacked together, the resulting matrix is a log probability matrix which can be denoted as Q_theta, where theta denotes the model parameters. When language modeling is formulated as a matrix factorization problem, the matrix to be factorized Q_theta is expected to be high-rank as natural language is highly context-dependent. But existing softmax based word-level language models have a limitation of not being able to produce such matrices; this is known as the softmax bottleneck. There are several works that attempted to overcome the limitations introduced by softmax bottleneck, such as the models that can produce high-rank Q_theta. During the process of reproducing the results of these works, we observed that the rank of Q_theta does not always positively correlate with better performance (i.e., lower test perplexity). This puzzling observation triggered us to conduct a systematic investigation to check the influence of rank of Q_theta on better performance of a language model. We first introduce a new family of activation functions called the Generalized SigSoftmax (GSS). By controlling the parameters of GSS, we were able to construct language models that can produce Q_theta with diverse ranks (i.e., low, medium, and high ranks). For models that use GSS with different parameters, we observe that rank does not have a strong positive correlation with perplexity on the test data, reinforcing the support of our initial observation. By inspecting the top-5 predictions made by different models for a selected set of input contexts, we observe that a high-rank Q_theta does not guarantee a strong qualitative performance. Then, we conduct experiments to check if there are any other additional benefits in having models that can produce high-rank Q_theta. We expose that Q_theta rather suffers from the phenomenon of fast singular value decay. Additionally, we also propose an alternative metric to denote the rank of any matrix known as epsilon-effective rank, which can be useful to approximately quantify the singular value distribution when different values for epsilon are used. We conclude by showing that it is the regularization which has played a positive role in the performance of these high-rank models in comparison to the chosen baselines, and there is no single model yet which truly gains improved expressiveness just because of breaking the softmax bottleneck.

Thesis (M.Sc. (Statistics)) -- University of Limpopo, 2019 / Recurrent peritonitis is a major problem of peritoneal dialysis (PD) due to its association with technique failure in the dialysis process. The literature on peritonitis focused only on investigating major risk factors associated with the first episode of peritonitis. However, this dissertation investigates factors associated to multiple episodes of peritonitis, to a maximum of 6 episodes. The correlation of recurrent episodes of a patient is considered. The univariate counting process, stratified, gap-time and marginal hazard regression models are applied to select the significant covariates to the multivariate regression hazard models. Regression coefficient for covariates are found to be statistically significant at 5% level. The application of Akaike information criterion (AIC) and Schwarz bayesian criterion (SBC) assisted to filter out the best method which is the stratified regression hazard model. The major risk factors associated with recurrent episodes of peritonitis are examined from the selected good fitting model. In conclusion, the selected model identified two independent risk factors to be significantly associated with recurrent episodes of peritonitis: marital status and glomerularfiltrationrate. Twocategoriesofmaritalstatus, divorceandwidowerare the significant factors compared to married patients (when taking married patients as the reference category). / VLIROUC Programme

The process of energy consumption and monitoring of a buildingis time-consuming. Therefore, an feasible approach for using trans-fer learning is presented to decrease the necessary time to extract re-quired large dataset. The technique applies a bidirectional long shortterm memory recurrent neural network using sequence to sequenceprediction. The idea involves a training phase that extracts informa-tion and patterns of a building that is presented with a reasonablysized dataset. The validation phase uses a dataset that is not sufficientin size. This dataset was acquired through a related paper, the resultscan therefore be validated accordingly. The conducted experimentsinclude four cases that involve different strategies in training and val-idation phases and percentages of fine-tuning. Our proposed modelgenerated better scores in terms of prediction performance comparedto the related paper.

Indiana University-Purdue University Indianapolis (IUPUI) / Action recognition has been an active research topic for over three decades. There are various applications of action recognition, such as surveillance, human-computer interaction, and content-based retrieval. Recently, research focuses on movies, web videos, and TV shows datasets. The nature of these datasets make action recognition very challenging due to scene variability and complexity, namely background clutter, occlusions, viewpoint changes, fast irregular motion, and large spatio-temporal search space (articulation configurations and motions). The use of local space and time image features shows promising results, avoiding the cumbersome and often inaccurate frame-by-frame segmentation (boundary estimation). We focus on two state of the art methods for the action classification problem: dense trajectories and recurrent neural networks (RNN). Dense trajectories use typical supervised training (e.g., with Support Vector Machines) of features such as 3D-SIFT, extended SURF, HOG3D, and local trinary patterns; the main idea is to densely sample these features in each frame and track them in the sequence based on optical flow. On the other hand, the deep neural network uses the input frames to detect action and produce part proposals, i.e., estimate information on body parts (shapes and locations). We compare qualitatively and numerically these two approaches, indicative to what is used today, and describe our conclusions with respect to accuracy and efficiency.

京都大学 / 0048 / 新制・課程博士 / 博士(医学) / 甲第18163号 / 医博第3883号 / 新制||医||1003(附属図書館) / 31021 / 京都大学大学院医学研究科医学専攻 / (主査)教授 福山 秀直, 教授 富樫 かおり, 教授 増永 慎一郎 / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DFAM

京都大学 / 0048 / 新制・課程博士 / 博士(教育学) / 甲第19214号 / 教博第177号 / 新制||教||154(附属図書館) / 32213 / 京都大学大学院教育学研究科教育科学専攻 / (主査)准教授 齊藤 智, 教授 楠見 孝, 教授 Emmanuel MANALO / 学位規則第4条第1項該当 / Doctor of Philosophy (Education) / Kyoto University / DGAM

No description available.