I denna rapport kommer ämnet sentimentalitet och ensoulment att undersökas. Sentimentalitet är något väldigt personligt och svårdefinierat, och att koppla det till en designprocess är utmanande. Det engelska begreppet ensoulment, som även kommer diskuteras i arbetet, syftar på det värde som en design tar in och hur designen kan förmedla en viss känsla. Dessa två begrepp kopplat till design kan beskriva hur en användare värdesätter artefakter. Det finns ett antal artiklar som diskuterar sentimentalitet i design och hur viktigt det är att inkorporera det i en designprocess, men väldigt få har applicerat det och producerat prototyper eller produkter. Att jobba med ett begrepp kopplat till känslor och egna minnen gör att det är svårt att få ett generellt tillvägagångssätt i en designprocess. Den frågeställning som detta arbete har jobbat med ifrågasätter på vilket sätt det går att uppnå sentimentalitet i design genom att arbeta med fyra termer, engagemang, historia, förstärkning och upplevd hållbarhet. De metoder som valdes att tillämpas i detta arbete är forskning genom design, fokusgrupp, tematisk analys och en look & feel prototyp. Dessa metoder valdes för att de ansågs lämpliga för att kunna besvara frågeställningen. Två fokusgrupper utfördes med grund i detta där deltagarna uppmuntrades att diskutera deras egen syn på sentimentalitet och hur samt vad de värdesätter i objekt de håller kärt. Resultatet av studien visar att det inte aktivt går att skapa en produkt som förmedlar sentimentalitet, utan det går att trigga en sentimental känsla hos användare genom att använda sig av kopplingar till känslor och minnen. Resultatet visar att ensoulment dock är något som bättre kan inkorporeras i en designprocess för att skapa värde hos användaren. Slutsatsen som drogs är att det inte går att skapa ett sentimentalt värde i en ny produkt, men det går att trigga sentimentalitet med hjälp av olika sinnen. Att använda sig av de fyra termerna kommer att leda till att en design har större chans att bli ensouled från start. / In this paper, the topic of sentimentality and ensoulment will be explored. Sentimentality is something very personal and difficult to define and linking it to a design process is challenging. The English term ensoulment, which will also be discussed in the work, refers to the value that a design takes in and how the design can convey a certain feeling. These two concepts related to design can describe how a user values an artefact. There are several articles discussing sentimentality in design and how important it is to incorporate it into a design process, but very few have applied it and produced prototypes or products. Working with a concept linked to emotions and personal memories makes it difficult to get a general approach in a design process. The outline of this work questions in what way it is possible to achieve sentimentality in design by working with four terms: engagement, history, augmentation, and perceived durability. The methods chosen to be applied in this work are research by design, focus group, thematic analysis, and a look & feel prototype. These methods were chosen because they were considered suitable for answering the research question. Two focus groups were conducted based on this, where participants were encouraged to discuss their own views on sentimentality and how and what they value in objects they value. The results of the study show that it is not possible to actively create a product that conveys sentimentality, but it is possible to trigger a sentimental feeling in users by using links to emotions and memories. However, the results show that ensoulment is something that can be better incorporated into a design process to create value for the user. The conclusion drawn is that it is not possible to create a sentimental value in a new product, but it is possible to trigger sentimentality using different senses. Using the four terms will mean that a design has a greater chance of being ensouled from the start.

Interdisciplinary research is often at the core of scientific progress. This dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience. In particular, this thesis focuses on vision and images. The human visual system has been widely studied from both behavioural and neuroscientific points of view, as vision is the dominant sense of most people. In turn, machine vision has also been an active area of research, currently dominated by the use of artificial neural networks. This work focuses on learning representations that are more aligned with visual perception and the biological vision. For that purpose, I have studied tools and aspects from cognitive science and computational neuroscience, and attempted to incorporate them into machine learning models of vision. A central subject of this dissertation is data augmentation, a commonly used technique for training artificial neural networks to augment the size of data sets through transformations of the images. Although often overlooked, data augmentation implements transformations that are perceptually plausible, since they correspond to the transformations we see in our visual world–changes in viewpoint or illumination, for instance. Furthermore, neuroscientists have found that the brain invariantly represents objects under these transformations. Throughout this dissertation, I use these insights to analyse data augmentation as a particularly useful inductive bias, a more effective regularisation method for artificial neural networks, and as the framework to analyse and improve the invariance of vision models to perceptually plausible transformations. Overall, this work aims to shed more light on the properties of data augmentation and demonstrate the potential of interdisciplinary research.

京都大学 / 新制・課程博士 / 博士(社会健康医学) / 甲第24094号 / 社医博第125号 / 新制||社医||12(附属図書館) / 京都大学大学院医学研究科社会健康医学系専攻 / (主査)教授 佐藤 俊哉, 教授 中山 健夫, 教授 松田 秀一 / 学位規則第4条第1項該当 / Doctor of Public Health / Kyoto University / DFAM

Cities plan to revitalize sustainable transportation, with a key emphasis on cycling. However, cities need to provide safe environments for cyclists through better infrastru.cture design. education programs, or other interventions to increase cycling nwnbers, as safety concerns greatly discourage people from cycling. Thus, cities' strategies aim to protect and improve the safety ofthose who cycle. Here, cycling research con1ributes to understanding cycling and what factors related to the individua4 the bicycle, and the surrounding environm.ent, in.fluence the risk. cyclists face. Objective cycling safety goals are to i) decrease the outcome severity of accidents involving cyclists and ii) decrease the overall nwnber of accidents. lt is often based on accident records or police reports, yet most incidents are often not reported. Nevertheless, accident statistics are vital because they allow for factors such as demographic data and built environment tobe analyzed to understand cyclists' risk. ofbeing involved or injured in an accident. There is a worldwide need for more data about cycling accidents, their context, and the built environm.ent's influence. Hence complete datasets are required. We mak:e use of CYCLANDS - a collection of 30 datasets comprising 1.58M cycling accident records - to explore how other data and analysis can complement accident records. Thus, a subset of CYCLANDS was augmented to analyze circulation spaces around accident locations. We hope this takes a step in that direction, fostering the mix of authoritative and volunteered data and providing a more complete data set.

During the last few years, deep learning-based techniques have made much progress in the medical image processing field, such as segmentation and registration. The main characteristic of these methods is the large demand of medical images to do model training. However, the acquisition of these data is often difficult, due to the high expense and ethical issues. As a consequence, the lack of data may lead to poor performance and overfitting. To tackle this problem, we propose a data augmentation algorithm in this paper to inpaint the tumor on healthy pediatric brain MRI images to simulate pathological images. Since the growth of tumor may cause deformation and edema of the surrounding tissues which is called the 'mass effect', a probabilistic UNet is applied to mimic this deformation field. Then, instead of directly adding the tumor to the image, the GAN-based method is applied to transfer the mask to the image and make it more plausible, both visually and anatomically. Meanwhile, the annotations of the different brain tissues are also obtained by employing the deformation field to the original labels. Finally, the synthesized image together with the real dataset is trained to do the tumor segmentation task, and the results indicate a statistical improvement in accuracy.

Behovet av tillförlitliga, motståndskraftiga, och beständiga system är uppenbart i vårt samhälle, som i ökande grad blir allt mer beroende av mjukvarulösningar. För att uppnå tillfredsställande nivåer av säkerhet och robusthet måste alla system kontinuerligt genomgå tester. En av de största utmaningarna vid automatisering av programvarutestning är avsaknaden av tillförlitliga orakel kapabla att ge korrekta bedömningar av testfall. Metamorfisk testning är en metod som har visats möjlig att applicera för automatisering av testning, men som däremot kräver identifiering av metamorfiska relationer. Det har gjorts försök att identifiera metamorfiska relationer med hjälp av vissa maskininlärningsmodellers förmåga till mönsterigenkänning. Ett stort problem för sådana tillvägagångssätt är mängden tillgängliga och användbara data som dessa ML-modeller kan tränas på. Det huvudsakliga bidraget denna uppsats levererar är en automatiserad metod för att genomföra utökning av data genom källkodsmutation i syfte att skala befintliga datamängder. Specifikt behandlar denna uppsats producering av icke-ekvivalenta mutanter och deras inverkan på maskininlärningsassisterad identifiering av metamorfiska relationer. Resultaten visar att icke-ekvivalenta mutanter kan genereras effektivt, även om manuell granskning är nödvändig för att härleda korrekta etiketter för varje datapunkt. Det visas också att icke-ekvivalenta mutanter kan påverka klassificeringsprestandan positivt i vissa fall, även om resultaten varierar beroende på mutationsoperator och behandlad metamorfisk relation. Framgångsrika framsteg inom testautomatisering kan potentiellt påverka nuvarande standarder för programvaruutveckling genom att förbättra programvarutestningspraxis. Därmed bidrar denna studie till diskussionen om hur automatiserad programvarutestning kan påverka organisationens prestationsförmåga i ett bredare perspektiv. Diskussionen baseras på ramverket för balanserade styrkort, och slutsatsen visar att testautomatisering kan generera fördelaktiga resultat på flera fronter. Det är dock viktigt att samordna sådana initiativ med organisationens strategiska inriktning och långsiktiga mål. / The need for reliable, resilient, and persistent systems is evident in our society, which is becoming increasingly more dependent on software solutions. In order to achieve satisfactory levels of security and robustness, all systems continuously need to undergo testing to detect faults and unwanted functionality. One of the mayor issues in automating software testing is the lack of reliable oracles capable of deriving test case verdicts. Metamorphic testing has been identified as a testing technique which can be used for test automation, though it requires the identification of metamorphic relations. There have been attempts at identifying metamorphic relations using the pattern recognition capabilities of certain machine learning models. A significant problem for any such approach is obtaining a sufficiently large labeled dataset which the ML models can be trained on. The main contribution of this paper is an automated approach to performing data augmentation through a process of source code mutation with the aim of scaling existing datasets. Specifically, this paper considers the generation of non-equivalent mutants and their impact on machine learning assisted identification of metamorphic relations. The results show that non-equivalent mutants can be efficiently generated, although manual oversight is necessary to derive accurate labels for each sample. It is also shown that non-equivalent mutants can positively impact the classification performance in certain instances, though results vary depending mutation operator and considered metamorphic relation. Furthermore, successful advances in the area of test automation can potentially affect current software development standards by improving software testing practices. As such, this study adds to the discussion on how automated software testing might affect organizational performance. The discussion is based on the balanced scorecard framework, and the discussion concludes that test automation can generate beneficial performance outcomes. However, it is imperative to aligning such endeavours with the strategic direction and long-term objectives of the organization.

Task-oriented dialogue (ToD) systems need to interpret the user's input to understand the user's needs (intent) and corresponding relevant information (slots). This process is performed by a Natural Language Understanding (NLU) component, which maps the text utterance into a semantic frame representation, involving two subtasks: intent classification (text classification) and slot filling (sequence tagging). Typically, new domains and languages are regularly added to the system to support more functionalities. Collecting domain-specific data and performing fine-grained annotation of large amounts of data every time a new domain and language is introduced can be expensive. Thus, developing an NLU model that generalizes well across domains and languages with less labeled data (low-resource) is crucial and remains challenging. This thesis focuses on investigating transfer learning and data augmentation methods for low-resource NLU in ToD. Our first contribution is a study of the potential of non-conversational text as a source for transfer. Most transfer learning approaches assume labeled conversational data as the source task and adapt the NLU model to the target task. We show that leveraging similar tasks from non-conversational text improves performance on target slot filling tasks through multi-task learning in low-resource settings. Second, we propose a set of lightweight augmentation methods that apply data transformation on token and sentence levels through slot value substitution and syntactic manipulation. Despite its simplicity, the performance is comparable to deep learning-based augmentation models, and it is effective on six languages on NLU tasks. Third, we investigate the effectiveness of domain adaptive pre-training for zero-shot cross-lingual NLU. In terms of overall performance, continued pre-training in English is effective across languages. This result indicates that the domain knowledge learned in English is transferable to other languages. In addition to that, domain similarity is essential. We show that intermediate pre-training data that is more similar – in terms of data distribution – to the target dataset yields better performance.

L'objectif de ce mémoire est de comparer la méthode d'échantillonnage de Gibbs avec augmentation de données, telle que présentée par Paquet (2002) et Bernier-Martel (2005), avec celle de l'imputation multiple telle que présentée par Grégoire (2004). Le critère de comparaison sera le signe des coefficients estimés. Nous travaillerons dans le contexte de bases de données indépendantes et d'un modèle linéaire à choix discret. Le modèle sera exprimé en tenant compte du choix des modes de transport des ménages de la communauté urbaine de Toronto. Pour réaliser ce projet, nous utiliserons la base de données du TTS (Transportation Tomorrow Survey) de 1986 et de 1996. Les résultats n'ont pas tous été estimés par un signe cohérent à nos attentes. Toutefois, nous pouvons conclure que l'échantillonnage de Gibbs avec augmentation de données est une approche plus intéressante que l'imputation multiple, puisqu'elle a estimé un nombre plus élevé de bons signes.

BACKGROUND: Electronic cigarettes (e-cigarettes) are nicotine delivery systems that generate an aerosol that can be inhaled and come in a variety of attractive designs and e- liquid flavorings. E-cigarettes are the second most commonly used tobacco product in the United States and are predominantly used by youth and young adults. The cardiovascular health risk of combustible cigarette use is well-established, but whether e-cigarettes increase the risk of cardiovascular events is less clear. Evaluating the short-term vascular effects of e-cigarette use is an approach to gain insight into the cardiovascular health impact. Limited studies have shown that acute e-cigarette use in combustible cigarette users was associated with increased central hemodynamic values and arterial stiffness. Few studies have assessed the effects of chronic e-cigarette use on arterial stiffness, particularly in young adults. OBJECTIVE: To assess the effects of e-cigarette use on central hemodynamics and arterial stiffness in regular e-cigarette users in comparison to combustible cigarette users and non-users. METHODS: Combustible cigarette users, e-cigarette users, and non-users without known cardiovascular disease (CVD) or CVD risk factors between the ages of 18 and 45 were enrolled in the ongoing Cardiovascular Injury due to Tobacco Products 2.0 (CITU 2.0) study at the Boston University School of Medicine and the University of Louisville School of Medicine starting from 2019. Non-invasive arterial tonometry, using the SphygmoCor system, was performed to measure peripheral artery waveforms to obtain central hemodynamic values and arterial stiffness parameters: augmentation index (AIx), carotid-radial (CR) and carotid-femoral pulse wave velocities (CFPWV). RESULTS: We had available arterial stiffness measures in 209 study participants (mean age 26±7, 48% female) across 3 tobacco product use groups: combustible cigarette users (N=51), e-cigarette users (N=97), and non-users (N=61). Amongst the e-cigarette users, 41 were dual users (use of both e-cigarettes and combustible cigarettes), 25 were exclusive e-cigarette users who were former combustible cigarette users, and 31 were exclusive e-cigarette users who were never combustible cigarette users. The majority (87%) of e-cigarette users used a pod-based product with fruit and mint/wintergreen or menthol as the most popular e-liquid flavors. In unadjusted analyses, central systolic blood pressure, AIx, CRPWV, and CFPWV differed across the three tobacco product use categories. In multivariable regression models adjusting for age, sex, race and study site, e-cigarette users and combustible cigarette users had higher central systolic blood pressure (β=3.9±2.0, p=0.048 and β=4.8±2.4, p=0.04, respectively) whereas combustible cigarette smokers also had higher central AIx, and CRPWV compared to non-users (β=6.9±3.3, p=0.04 and β=0.97±0.31, p=0.002, respectively). In unadjusted analyses across the five groups, we found similar patterns of differences in vascular measures. In multivariable regression models comparing to combustible cigarette users, dual product users had similar measures of vascular function whereas exclusive e-cigarette users who were former smokers had lower CRPWV (β=-0.95±0.36, p=0.009), and exclusive e- cigarette users who were never combustible cigarette users had lower AIx (β=-9.0±4.2, 0.04). CONCLUSIONS: Our findings suggest that in young adults, combustible cigarette use is associated with measures of arterial stiffness. Dual e-cigarette use was largely similar to combustible cigarette use whereas exclusive e-cigarette use had a lesser degree of vascular stiffening. Further studies are needed to evaluate the long-term impact of e- cigarette use on cardiovascular health.

This study is dedicated to enhancing the effectiveness of Optical Character Recognition (OCR) systems, with a special emphasis on Arabic handwritten digit recognition. The choice to focus on Arabic handwritten digits is twofold: first, there has been relatively less research conducted in this area compared to its English counterparts; second, the recognition of Arabic handwritten digits presents more challenges due to the inherent similarities between different Arabic digits.OCR systems, engineered to decipher both printed and handwritten text, often face difficulties in accurately identifying low-quality or distorted handwritten text. The quality of the input image and the complexity of the text significantly influence their performance. However, data augmentation strategies can notably improve these systems' performance. These strategies generate new images that closely resemble the original ones, albeit with minor variations, thereby enriching the model's learning and enhancing its adaptability. The research found Conditional Variational Autoencoders (C-VAE) and Conditional Generative Adversarial Networks (C-GAN) to be particularly effective in this context. These two generative models stand out due to their superior image generation and feature extraction capabilities. A significant contribution of the study has been the formulation of the Synthetic Image Evaluation Procedure, a systematic approach designed to evaluate and amplify the generative models' image generation abilities. This procedure facilitates the extraction of meaningful features, computation of the Fréchet Inception Distance (LFID) score, and supports hyper-parameter optimization and model modifications.