Systematic reviews on diagnostic test accuracy studies provide an overview of the current literature in a systematic and transparent manner. They are the highest level of evidence in clinical research, therefore they are critical to decision-making in the healthcare setting. Cancer is the primary source of mortality in Canada, however early detection of tumors can improve the survival rates and long-term health outcomes of patients. The primary method of cancer diagnosis is histopathological assessment, however, its use remains controversial. It is an invasive procedure and requires resources and clinical expertise not readily available. Noninvasive clinical imaging has been studied as a clinically desirable method for cancer diagnosis, however its diagnostic accuracy has yet to be established in the medical setting. With the increased role of DTA research in medicine, the current literature needs to be summarized in an effective way to properly educate and influence clinical decision-making. The objective of this thesis is to address the current evidence gaps in DTA research by conducting several systematic reviews to evaluate the accuracy of diagnostic methods in cancer-related imaging. The last chapter of the thesis will provide a critical reflection on the current landscape of DTA studies in cancer-related imaging, based on the findings of the reviews in the thesis.

L'étude de la Faculté des langues (FL), telle que définie par la grammaire générative, a été principalement entreprise à travers l'examen des langues adultes, l'acquisition de la langue première, l'acquisition des langues secondes et l'acquisition bilingue. Peu de travaux ont abordé la FL à partir d'une situation d'acquisition atypique, communément appelée Trouble développemental du langage (TDL). Cette thèse est consacrée à l'étude de la façon dont FL est affectée par cette condition malheureuse. Le TDL est manifesté par certains jeunes enfants et adultes et peut être la cause de limitations importantes dans le développement du langage. La production et la compréhension langagières de ce groupe d'enfants sont atypiques par rapport au comportement linguistique d'autres enfants du même âge. Leur atypicité consiste en une grammaire non-cible en ce qui concerne ce qui est autorisé et ce qui est interdit dans la/les langue(s) à laquelle/auxquelles ils sont exposés. Les symptômes les plus communs, d'un point de vue morpho-syntaxique, sont (a) l'omission de morphèmes et de mots, (b) les commissions, c'est-à-dire la présence inadéquate de certains mots ou le remplacement inapproprié de morphèmes et (c) les redoublements, c'est-à-dire, l'apparition de mots ou de morphèmes dans plus de positions que celles autorisées dans la langue cible. Ces symptômes ont été pris comme l’indication que la FL est déficiente. Le résultat de cette défaillance est une grammaire développée par les enfants ayant le TDL qui est qualitativement différente de celle développée par leurs pairs typiques. Cette thèse examinera si la compétence linguistique sous-jacente des enfants DLD est déterminée par les mêmes traits, opérations et principes qui régissent le langage naturel en général. Extraites de la littérature expérimentale sur le TDL, les données pour l’analyse incluent la compréhension et la production par les enfants du TDL et concernent les domaines nominal, temporel/verbal et propositionnel. Les propositionsiii avancées pour rendre compte de ce disorder seront évaluées. Toutes proposent explicitement ou implicitement que la grammaire universelle (GU), c'est-à-dire l'ensemble des traits et opérations phonologiques, sémantiques et syntaxiques qui sous-tendent FL, est défectueuse: certains traits peuvent être absents, ou des opérations peuvent être inactives ou fonctionner par intermittence. Contrairement à ces propositions, l'hypothèse défendue ici est que la GU n'est pas affectée chez les enfants TDL. C'est-à-dire que malgré les nombreuses différences entre le TDL et l'acquisition typique du langage, la GU se révèle être similaire à un certain niveau dans les deux situations d'acquisition. Si la GU était altérée chez les enfants TDL, on s'attendrait à ce que les enfants affectés par cette condition produisent des phrases remarquablement différentes de celles produites par des enfants typiques. Plusieurs études ont révélé que les enfants DLD et leurs pairs typiques peuvent montrer des performances linguistiques similaires en termes de quantité et de type d'erreurs. De plus, les données révèlent que les énoncés TDL ne sont pas toujours erronés; lorsque tous les éléments et les mécanismes linguistiques sont présents, ils sont correctement utilisés. Ceci est considéré comme un signe que les traits syntaxiques, bien qu'ils ne soient pas toujours réalisés morpho-phonologiquement, sont présents dans les dérivations syntaxiques des enfants TDL, et que les opérations syntaxiques Fusion et Accord sont actives, tout comme dans les grammaires typiques. Enfin, l'analyse des énoncés non-cibles par les enfants TDL met en évidence une grammaire syntaxiquement normale et même une ressemblance avec des langues auxquelles ces enfants n'ont pas été exposés. La conclusion est que, malgré la non-convergence entre le TDL et la langue cible, la GU dans cette situation d'acquisition est intacte. / The study of the Faculty of Language (FL), as defined by generative grammar, has been mainly undertaken through the examination of adult language, first language acquisition, second language acquisition and bilingual acquisition. Few works have approached the FL from an atypical acquisitional situation, standardly called Developmental Language Disorder (DLD). This dissertation is devoted to the study of how FL is affected by this unfortunate condition. DLD is displayed by some young children and adults and can be the cause of significant limitations in language development. The linguistic production and comprehension by this group of children is atypical compared to the linguistic behaviour of other children of the same age. Their atypicality consists in a non-target-like grammar with regard to both what is allowed and what is disallowed in the language(s) to which they are exposed. The most common symptoms, from a morpho-syntactic point of view, are (a) omission of morphemes and words, (b) commissions, i.e., the inadequate presence of certain words or the inappropriate replacement of morphemes and (c) doublings, i.e., the appearance of words or morphemes in more positions than are allowed in the target language. These symptoms have been taken to indicate that the FL is deficient. The result of this deficiency is a grammar developed by children with DLD that is qualitatively different from that developed by their typical peers. This dissertation will consider whether or not the underlying linguistic competence of children with DLD is determined by the same features, operations and principles that regulate natural language in general. Drawn from the experimental literature on DLD, the data for analysis include comprehension and production by children with DLD and concern the nominal, the temporal/verbal and the propositional domains. The proposals that have been put forth to account for this impairment will be evaluated. All of them explicitly or implicitly propose that Universal Grammar (UG), i.e., the set of phonological, semantic and syntactic features and operations that underlie FL, is faulty: Some features can be absent, or operations can be inactive or function intermittently. Contrary to these proposals, the hypothesis defended here is that UG is not affected in DLD children. That is to say, despite the many differences between DLD and typical language acquisition, UG is revealed to be similar at a certain level in both acquisitional situations. If UG were impaired in DLD, children affected by this condition would be expected to produce sentences remarkably different from those produced by typical children. Several studies have shown that children with DLD and their typical peers can display similar linguistic performance in terms of both quantity and type of errors. Moreover, the data reveal that DLD utterances are not always erroneous; when all linguistic elements and mechanisms are present, they are correctly used. This is taken as a sign that syntactic features, while not always realized morpho-phonologically, are present in DLD syntactic derivations, and that the syntactic operations Merge and Agree are active, just as in typical grammars. Finally, the analysis of non-target utterances by children with DLD evinces a syntactically normal grammar and even a resemblance with languages to which these children have not been exposed. The conclusion is that, despite the non-convergence of DLD and the target language, UG in this acquisitional situation is intact.

Clinical and research practice in the context of Autism rapidly evolved in the last decades. Finer diagnostic procedures, evidence-based models of intervention and higher social inclusivity significantly improved the possibility for autistic children to participate in the fabric of social life. In terms of health best practices, gold-standard procedures still need to be improved, and bridging research and clinical practice still presents several challenges. From the clinical standpoint, the role of process variables, predictors, mechanisms, and timing of change still requires extensive investigation in order to explain response variability and design optimized interventions, tailored to individual needs and maximally effective. Observational techniques represent the elective research methods in child development, especially in clinical contexts, due to their non-invasiveness. However, they still suffer from limited objectivity and poor quantification. Further, their main disadvantage is that they are highly time-consuming and labor-intensive. The aim of this thesis was moving forward to promote translational research in clinical practice of Autism intervention with preschool children. At first, we tried to design and apply quantitative observational techniques to longitudinally study treatment response trajectories during developmental intervention. We tried to characterize different response profiles, and which baseline predictors were able to predict the response over time. Secondly, we investigated mechanisms of change. In particular, we focused on the role of the child-therapist interaction dynamics as a possible active mediator of the process of intervention, especially in the developmental framework that stresses the importance of interpersonal aspects. We also aimed at understanding whether certain time-windows during the intervention were particularly predictive of the response, as well as which specific interaction aspects played a role. Finally, to promote the translational application of observational methods and to improve objective quantification, we proposed and validated an Artificial Intelligence (AI) system to automate data annotation in unconstrained clinical contexts, remaining completely non-invasive and dealing with the specific noisy data that characterize them, for the analysis of the child-therapist acoustic interaction. This effort represents a base building block enabling to employ downstream computational techniques greatly reducing the need for human annotation that usually prevents the application of observational research to large amounts of data . We discuss our findings stressing the importance of assuming a developmental framework in Autism, the key role of the interpersonal experience also in the clinical context, the importance of focusing on trajectories of change and the important need to promote the acquisition of large amounts of quantitative data from the clinical contexts exploiting AI-based systems to assist clinicians, improving objectivity, enabling treatment monitoring, and producing precious data-driven knowledge on treatment efficacy.

In this thesis, two different architecture designs of a Multi-Layer Perceptron network have been implemented. One architecture being an ordinary MLP, and in the other adding DenseNet inspired skip connections to an MLP architecture. The models were used and evaluated on the classification task, where the goal was to classify if subjects were diagnosed with Parkinson’s disease or not based on vocal features. The models were trained on an openly available dataset for Parkinson’s classification and evaluated on a hold-out set from this dataset and on two datasets recorded in another sound recording environment than the training data. The thesis searched for the answer to two questions; How insensitive models for Parkinson’s classification are to the sound recording environment and how the proposed skip connections in an MLP model could help improve performance and generalization capacity. The thesis results show that the sound environment affects the accuracy. Nevertheless, it concludes that one would be able to overcome this with more time and allow for good accuracy when models are exposed to data from a new sound environment than the training data. As for the question, if the skip connections improve accuracy and generalization, the thesis cannot draw any broad conclusions due to the data that were used. The models had, in general, the best performance with shallow networks, and it is with deeper networks that the skip connections are argued to help improve these attributes. However, when evaluating on the data from a different sound recording environment than the training data, the skip connections had the best performance in two out of three tests. / I denna avhandling har två olika arkitektur designer för ett artificiellt flerskikts neuralt nätverk implementerats. En arkitektur som följer konventionen för ett vanlig MLP nätverk, samt en ny arkitektur som introducerar DenseNet inspirerade genvägs kopplingar i MLP nätverk. Modellerna användes och utvärderades för klassificering, vars mål var att urskilja försökspersoner som friska eller diagnostiserade med Parkinsons sjukdom baserat på röst attribut. Modellerna tränades på ett öppet tillgänglig dataset för Parkinsons klassificering och utvärderades på en delmängd av denna data som inte hade använts för träningen, samt två dataset som kommer från en annan ljudinspelnings miljö än datan för träningen. Avhandlingen sökte efter svaret på två frågor; Hur okänsliga modeller för Parkinsons klassificering är för ljudinspelnings miljön och hur de föreslagna genvägs kopplingarna i en MLP-modell kan bidra till att förbättra prestanda och generalisering kapacitet. Resultaten av avhandlingen visar att ljudmiljön påverkar noggrannheten, men drar slutsatsen att med mer tid skulle man troligen kunna övervinna detta och möjliggöra god noggrannhet i nya ljudmiljöer. När det kommer till om genvägs kopplingarna förbättrar noggrannhet och generalisering, är avhandlingen inte i stånd att dra några breda slutsatser på grund av den data som användes. Modellerna hade generellt bästa prestanda med grunda nätverk, och det är i djupare nätverk som genvägs kopplingarna argumenteras för att förbättra dessa egenskaper. Med det sagt, om man bara kollade på resultaten på datan som är ifrån en annan ljudinspelnings miljö så hade genvägs arkitekturen bättre resultat i två av de tre testerna som utfördes.

No description available.

Life on Earth is strongly related to the Sun, which makes it a vital star to study and understand. To improve our knowledge of the way the Sun works, many satellites have been launched into space to monitor the Sun‟s activities where the one of main focus is the effect of these activities on the Earth‟s climate; PICARD is one such satellite. Due to the noise associated with SODISM images, the clarity of these images and the appearance of solar features are affected. Image denoising and enhancement are the main techniques to improve the visual appearance of SODISM images. Affective de-noising algorithm methods depend on a proper detecting of noise present in the image. The aim is to identify which type of noise is present in the image. To reach this point, supervised machine-learning (ML) classifier is used to classify the type of noise present in the image. Furthermore, this work introduces a novel technique developed to enhance the quality of SODISM images. In this thesis, the Modified Undecimated Discrete Wavelet Transform (M-UDWT) technique is used to de-noise and enhance the quality of SODISM images. The proposed method is robust and effectively improves the quality of SODISM images, and produces more precise information and clear feature are brought out. In addition, the non wavelet enhancement is developed as well in this thesis. The results of this algorithm is discussed. The new methods are also assessed using two different methods: subjective (by human observation) and objective (by calculation)

No description available.

No description available.

Цель работы – разработка модели машинного обучения для автоматического сопоставления описаний продуктов, представленных в текстовом виде с внутренними кодами компании. Объект исследования – бизнес-процесс сопоставления описаний продуктов с внутренними кодами компании. Методы исследования: предварительная обработка данных, анализ данных, выбор и обучение модели машинного обучения, оценка производительности модели. Результаты работы: разработана и обучена модель машинного обучения на основе алгоритма CatBoost для автоматического сопоставления описаний продуктов с внутренними кодами компании. Модель показала высокую точность и полноту при тестировании. Созданная модель машинного обучения внедрена в продуктивное использование компании АО «Сони Электроникс» и позволяет сокращать ресурсы аналитиков в существенном объеме. Выпускная квалификационная работа выполнена в текстовом редакторе Microsoft Word и представлена в электронном и печатном виде. / The goal of the work is to develop a machine learning model for automatically comparing product descriptions presented in text form with the company’s internal codes. The object of study is the business process of comparing product descriptions with internal company codes. Research methods: data preprocessing, data analysis, selection and training of a machine learning model, evaluation of model performance. Results of the work: a machine learning model based on the CatBoost algorithm was developed and trained to automatically compare product descriptions with internal company codes. The model showed high accuracy and completeness during testing. The created machine learning model has been put into productive use by Sony Electronics JSC and makes it possible to reduce analyst resources to a significant extent. The final qualifying work was completed in the text editor Microsoft Word and presented in electronic and printed form.

Object tracking can be done in numerous ways, where the goal is to track a target through all frames in a sequence. The ground truth bounding box is used to initialize the object tracking algorithm. Object tracking can be carried out on infrared imagery suitable for military applications to execute tracking even without illumination. Objects, such as aircraft, can deploy countermeasures to impede tracking. The countermeasures most often mainly impact one wavelength band. Therefore, using two different wavelength bands for object tracking can counteract the impact of the countermeasures. The dataset was created from simulations. The countermeasures applied to the dataset are flares and Directional Infrared Countermeasures (DIRCMs). Different object tracking algorithms exist, and many are based on discriminative correlation filters (DCF). The thesis investigated the DCF-based trackers STRCF and ECO on the created dataset. The STRCF and the ECO trackers were analyzed using one and two wavelength bands. The following features were investigated for both trackers: grayscale, Histogram of Oriented Gradients (HOG), and pre-trained deep features. The results indicated that the STRCF and the ECO trackers using two wavelength bands instead of one improved performance on sequences with countermeasures. The use of HOG, deep features, or a combination of both improved the performance of the STRCF tracker using two wavelength bands. Likewise, the performance of the ECO tracker using two wavelength bands was improved by the use of deep features. However, the negative aspect of using two wavelength bands and introducing more features is that it resulted in a lower frame rate.