Evaluating perceptual maps of asymmetries for gait symmetry quantification and pathology detection

Le mouvement de la marche est un processus essentiel de l'activité humaine et aussi le résultat de nombreuses interactions collaboratives entre les systèmes neurologiques, articulaires et musculo-squelettiques fonctionnant ensemble efficacement. Ceci explique pourquoi une analyse de la marche est aujourd'hui de plus en plus utilisée pour le diagnostic (et aussi la prévention) de différents types de maladies (neurologiques, musculaires, orthopédique, etc.). Ce rapport présente une nouvelle méthode pour visualiser rapidement les différentes parties du corps humain liées à une possible asymétrie (temporellement invariante par translation) existant dans la démarche d'un patient pour une possible utilisation clinique quotidienne. L'objectif est de fournir une méthode à la fois facile et peu dispendieuse permettant la mesure et l'affichage visuel, d'une manière intuitive et perceptive, des différentes parties asymétriques d'une démarche. La méthode proposée repose sur l'utilisation d'un capteur de profondeur peu dispendieux (la Kinect) qui est très bien adaptée pour un diagnostique rapide effectué dans de petites salles médicales car ce capteur est d'une part facile à installer et ne nécessitant aucun marqueur. L'algorithme que nous allons présenter est basé sur le fait que la marche saine possède des propriétés de symétrie (relativement à une invariance temporelle) dans le plan coronal.

Analyse quantifiée de l'asymétrie de la marche par application de Poincaré

La marche occupe un rôle important dans la vie quotidienne. Ce processus apparaît comme facile et naturel pour des gens en bonne santé. Cependant, différentes sortes de maladies (troubles neurologiques, musculaires, orthopédiques...) peuvent perturber le cycle de la marche à tel point que marcher devient fastidieux voire même impossible. Ce projet utilise l'application de Poincaré pour évaluer l'asymétrie de la marche d'un patient à partir d'une carte de profondeur acquise avec un senseur Kinect. Pour valider l'approche, 17 sujets sains ont marché sur un tapis roulant dans des conditions différentes : marche normale et semelle de 5 cm d'épaisseur placée sous l'un des pieds. Les descripteurs de Poincaré sont appliqués de façon à évaluer la variabilité entre un pas et le cycle complet de la marche. Les résultats montrent que la variabilité ainsi obtenue permet de discriminer significativement une marche normale d'une marche avec semelle. Cette méthode, à la fois simple à mettre en oeuvre et suffisamment précise pour détecter une asymétrie de la marche, semble prometteuse pour aider dans le diagnostic clinique.

Une approche moléculaire pour mieux comprendre l'infertilité chez la vache laitière

Au cours des dernières années, une sélection génétique importante a été faite pour améliorer la production de lait des bovins, ceci au détriment des performances reproductives. Cette diminution de performance n’a cependant pas été rapportée chez la génisse présentant un même potentiel génétique. Cette immense production de lait et les changements métaboliques qui l’accompagnent ont donc un impact négatif sur l’efficacité reproductive des vaches laitières qui subissent un stress métabolique supérieur à celui des génisses. Le but de l’étude était d’acquérir une meilleure connaissance des différences moléculaires et métaboliques entre ces deux groupes d’animaux pour amener à une meilleure compréhension de la pathogenèse de l’infertilité chez la vache laitière. Pour ce faire, les vagues folliculaires de vaches en lactation (30-50 jours en lait; N = 12) et de génisses (N = 10) ont été synchronisées par ablation écho guidée des follicules et par traitement hormonal avec injection de prostaglandine et insertion d’un implant de progestérone. L’aspiration du liquide folliculaire et des cellules de la granulosa du follicule dominant a été faite au jour 6. Les paramètres métaboliques mesurés chez les animaux à partir de prises de sang, faites au jour 6, confirment un plus grand stress métabolique chez la vache, les niveaux de BHBA, acides biliaires et cholestérol étant plus élevés et le niveau de glucose plus bas chez celles-ci. Un total de six échantillons a été utilisé pour le séquençage d’ARN et des analyses bio-informatiques ont été effectuées. Plusieurs gènes et voies de signalisation ont présenté des différences entre les deux groupes d’animaux incluant le cycle cellulaire et la production d’hormones. Une confirmation des résultats par PCR en temps réel a été faite, mais la grande variation intragroupe a nui à l’obtention de résultats significatifs. Conjointement, une culture primaire de cellules de la granulosa a été réalisée pour évaluer l’effet des acides biliaires sur la stéroïdogenèse suite à la détection d’une plus grande quantité de ceux-ci chez la vache laitière. La présence d’acide biliaire dans la culture cellulaire cause une diminution de l’accumulation d’estradiol ainsi que de l’expression des gènes CYP19A1 et CYP11A1. Les résultats présentés dans ce mémoire indiquent une différence potentielle au niveau métabolique et moléculaire des follicules dominants entre la vache laitière et la génisse pouvant avoir une responsabilité dans la diminution de l’efficacité reproductive observée chez la vache laitière.

A survey of human motion analysis using depth imagery

Analysis of human behaviour through visual information has been a highly active research topic in the computer vision community. This was previously achieved via images from a conventional camera, but recently depth sensors have made a new type of data available. This survey starts by explaining the advantages of depth imagery, then describes the new sensors that are available to obtain it. In particular, the Microsoft Kinect has made high-resolution real-time depth cheaply available. The main published research on the use of depth imagery for analysing human activity is reviewed. Much of the existing work focuses on body part detection and pose estimation. A growing research area addresses the recognition of human actions. The publicly available datasets that include depth imagery are listed, as are the software libraries that can acquire it from a sensor. This survey concludes by summarising the current state of work on this topic, and pointing out promising future research directions.

ReadingAct RGB-D action dataset and human action recognition from local features

For general home monitoring, a system should automatically interpret people’s actions. The system should be non-intrusive, and able to deal with a cluttered background, and loose clothes. An approach based on spatio-temporal local features and a Bag-of-Words (BoW) model is proposed for single-person action recognition from combined intensity and depth images. To restore the temporal structure lost in the traditional BoW method, a dynamic time alignment technique with temporal binning is applied in this work, which has not been previously implemented in the literature for human action recognition on depth imagery. A novel human action dataset with depth data has been created using two Microsoft Kinect sensors. The ReadingAct dataset contains 20 subjects and 19 actions for a total of 2340 videos. To investigate the effect of using depth images and the proposed method, testing was conducted on three depth datasets, and the proposed method was compared to traditional Bag-of-Words methods. Results showed that the proposed method improves recognition accuracy when adding depth to the conventional intensity data, and has advantages when dealing with long actions.

Just add water and salt: the optimisation of petrogenic hydrocarbon biodegradation in soils from semi-arid Barrow Island, Western Australia

We investigated the potential of soil moisture and nutrient amendments to enhance the biodegradation of oil in the soils from an ecologically unique semi-arid island. This was achieved using a series of controlled laboratory incubations where moisture or nutrient levels were experimentally manipulated. Respired CO2 increased sharply with moisture amendment reflecting the severe moisture limitation of these porous and semi-arid soils. The greatest levels of CO2 respiration were generally obtained with a soil pore water saturation of 50–70%. Biodegradation in these nutrient poor soils was also promoted by the moderate addition of a nitrogen fertiliser. Increased biodegradation was greater at the lowest amendment rate (100 mg N kg−1 soil) than the higher levels (500 or 1,000 mg N kg−1 soil), suggesting the higher application rates may introduce N toxicity. Addition of phosphorous alone had little effect, but a combined 500 mg N and 200 mg P kg−1 soil amendment led to a synergistic increase in CO2 respiration (3.0×), suggesting P can limit the biodegradation of hydrocarbons following exogenous N amendment.

Could in-home sensors surpass human observation of people with Parkinson’s at high risk of falling? An ethnographic study

Self-report underpins our understanding of falls among people with Parkinson’s (PwP) as they largely happen unwitnessed at home. In this qualitative study, we used an ethnographic approach to investigate which in-home sensors, in which locations, could gather useful data about fall risk. Over six weeks, we observed five independently mobile PwP at high risk of falling, at home. We made field notes about falls (prior events and concerns) and recorded movement with video, Kinect, and wearable sensors. The three women and two men (aged 71 to 79 years) having moderate or severe Parkinson’s were dependent on others and highly sedentary. We most commonly noted balance protection, loss, and restoration during chair transfers, walks across open spaces and through gaps, turns, steps up and down, and tasks in standing (all evident walking between chair and stairs, e.g.). Our unobtrusive sensors were acceptable to participants: they could detect instability during everyday activity at home and potentially guide intervention. Monitoring the route between chair and stairs is likely to give information without invading the privacy of people at high risk of falling, with very limited mobility, who spend most of the day in their sitting rooms.

Os impactos do uso de tecnologia da informação e da identificação e captura automática de dados nos processos operacionais do varejo

Este trabalho objetivou identificar as principais tecnologias disponíveis de TI (Tecnologia da Informação) e de AIDC (Identificação e Captura Automática de Dados) para a área de varejo de autosserviço, para preencher a lacuna existente na literatura, sobre os benefícios de se usar novas tecnologias no ponto de venda, com vistas a otimizar sua operação. Para tanto, foram estudados os principais processos operacionais de uma loja de varejo de autosserviço, com vistas a identificar como as Tecnologias da Informação (TI) e de Identificação e Captura Automática de Dados (AIDC), poderiam ajudar a melhorar os resultados operacionais e agregar valor ao negócio. Para analisar suas proposições (de que o uso de TI e de AIDC podem ajudar na: redução dos tempos dos processos de retaguarda; redução do número de operações no ponto de venda; prevenção de perdas; redução dos custos e dos tempos para a realização dos inventários; redução do número de funcionários nas lojas; redução do tempo de fila no caixa; redução de rupturas e no aumento da eficiência operacional da loja), foram pesquisados diversos estudos de casos mundiais de empresas do segmento de varejo, que implementaram as tecnologias de AIDC e TI, principalmente a de RFID, para saber quais foram os impactos do uso destas tecnologias em suas operações e, em seguida, foi desenvolvido um Estudo de Caso abrangente, por meio do qual se objetivou entender os benefícios empresariais reais do uso destas tecnologias para o varejo de autosserviço. Como resultado final, foi possível identificar as mudanças nos processos operacionais do varejo de autosserviço, bem como os benefícios gerados em termos de custo, produtividade, qualidade, flexibilidade e inovação. O trabalho também evidenciou os pontos críticos de sucesso para a implementação da TI e das AIDC no varejo, que são: a revisão dos processos operacionais; a correta definição do hardware; dos insumos; do software; das interferências do ambiente físico; da disponibilização dos dados/informações dos produtos; das pessoas/funcionários e dos parceiros de negócios/fornecedores. De maneira mais específica, este trabalho buscou contribuir para o enriquecimento do campo de estudos no segmento de varejo e para o uso da tecnologia da informação, no Brasil, já que o assunto sobre o uso e o impacto de novas tecnologias no ponto de vendas, ainda permanece pouco explorado academicamente.

Touch ‘n’ sketch: pen and fingers on a multi-touch sketch application for tablet PC’s

In many creative and technical areas, professionals make use of paper sketches for developing and expressing concepts and models. Paper offers an almost constraint free environment where they have as much freedom to express themselves as they need. However, paper does have some disadvantages, such as size and not being able to manipulate the content (other than remove it or scratch it), which can be overcome by creating systems that can offer the same freedom people have from paper but none of the disadvantages and limitations. Only in recent years has the technology become massively available that allows doing precisely that, with the development in touch‐sensitive screens that also have the ability to interact with a stylus. In this project a prototype was created with the objective of finding a set of the most useful and usable interactions, which are composed of combinations of multi‐touch and pen. The project selected Computer Aided Software Engineering (CASE) tools as its application domain, because it addresses a solid and well‐defined discipline with still sufficient room for new developments. This was the result from the area research conducted to find an application domain, which involved analyzing sketching tools from several possible areas and domains. User studies were conducted using Model Driven Inquiry (MDI) to have a better understanding of the human sketch creation activities and concepts devised. Then the prototype was implemented, through which it was possible to execute user evaluations of the interaction concepts created. Results validated most interactions, in the face of limited testing only being possible at the time. Users had more problems using the pen, however handwriting and ink recognition were very effective, and users quickly learned the manipulations and gestures from the Natural User Interface (NUI).

Avaliação e validação de instalações interativas para museus

Desenhar e avaliar experiências interativas digitais para museus, são processos complexos que requerem muita atenção, sobretudo nos aspectos que contribuem para que a mesma seja uma experiência de aprendizagem rica e cativante. Por outro lado, a avaliação de instalações interativas em museus é uma tarefa muito exigente devido à interseção de múltiplos campos de pesquisa, como a interação humano computador, design e multimédia, museologia, estudo de audiências e outros. Neste projeto foi criada uma plataforma com dez parâmetros específicos que permite avaliar e guiar o desenho de instalações interativas, concebidos especificamente para museus. A conceção da plataforma foi baseada em métodos e princípios de avaliação de usabilidade atuais, bem como na literatura sobre museologia. Seguidamente foi refinada de forma iterativa e, por fim, foi validada através de um estudo de longo prazo, sobre a interatividade do em todos os museus interativos da Ilha da Madeira. Além disso, e em paralelo com a criação desta plataforma de avaliação, foi criada, desenhada e desenvolvida uma instalação interativa cujo objetivo principal seria oferecer uma experiência de visita ao museu completamente diferente do que os visitantes estão habituados, na Madeira. Foi instalada na Casa-Museu Frederico de Freitas e apresentou um feedback muito positivo por parte dos visitantes do museu, que afirmaram ter gostado da experiência e ter adquirido algum conhecimento sobre a história e cultura da Madeira. A criação desta instalação permitiu aplicar a plataforma de avaliação criada, de forma iterativa ao longo de todo o processo de design e desenvolvimento, guiando e apoiando todas as fases e tomadas de decisão. Os resultados obtidos enfatizam a importância de adotar a plataforma proposta para futuras pesquisas sobre avaliação museus interativos. Além disso, demonstram a utilidade desta plataforma no design e desenvolvimento de instalações interativas que, por sua vez, revelaram ter um impacto positivo na integração nos museus da Região.

Desempenho motor de pacientes com acidente vascular cerebral em um jogo baseado em realidade virtual

The Cerebral Vascular Accident (CVA) is the leading cause of motor disability in adults and elderly and that is why it still needs effective interventions that contribute to motor recovery. Objective: This study was aimed to evaluate the performance of stroke patients in chronic stage using a virtual reality game. Method: 20 patients (10 with injury to the left and 10 to the right side), right-handed, average age 50.6 ± 9.2 years, and 20 healthy subjects with average age of 50.9 ± 8.8, also right-handed participated. The patients had a motor (Fugl-Meyer) and muscle tone assessment (Ashworth). All participants made a kinematic evaluation of the drinking water activity and then underwent training with the table tennis game on XBOX 360 Kinect®, 2 sets of 10 attempts for 45 seconds, 15 minutes rest between sets, giving a total of 30 minutes session. After training the subjects underwent another kinematic evaluation. The patients trained with the right and left hemiparect upper limb and the healthy ones with the right and left upper limb. Data were analyzed by ANOVA, t Student test and Pearson correlation. Results: There was significant difference in the number of hits between the patients and healthy groups, in which patients had a lower performance in all the attempts (p = 0.008), this performance was related to a higher level of spasticity (r = - 0.44, p = 0.04) and greater motor impairment (r = 0.59, p = 0.001). After training, patients with left hemiparesis had improved shoulder and elbow angles during the activity of drinking water, approaching the pattern of motion of the left arm of healthy subjects (p < 0.05), especially when returning the glass to the table, and patients with right hemiparesis did not obtain improved pattern of movement (p > 0.05). Conclusion: The stroke patients improved their performance over the game attempts, however, only patients with left hemiparesis were able to increase the angle of the shoulder and elbow during the functional activity execution, better responding to virtual reality game, which should be taken into consideration in motor rehabilitation

Interação gestual em ambiente residencial: estudo, concepção e desenvolvimento

Control and automation of residential environments domotics is emerging area of computing application. The development of computational systems for domotics is complex, due to the diversity of potential users, and because it is immerse in a context of emotional relationships and familiar construction. Currently, the focus of the development of this kind of system is directed, mainly, to physical and technological aspects. Due to the fact, gestural interaction in the present research is investigated under the view of Human-Computer Interaction (HCI). First, we approach the subject through the construction of a conceptual framework for discussion of challenges from the area, integrated to the dimensions: people, interaction mode and domotics. A further analysis of the domain is accomplished using the theoretical-methodological referential of Organizational Semiotics. After, we define recommendations to the diversity that base/inspire the inclusive design, guided by physical, perceptual and cognitive abilities, which aim to better represent the concerned diversity. Although developers have the support of gestural recognition technologies that help a faster development, these professionals face another difficulty by not restricting the gestural commands of the application to the standard gestures provided by development frameworks. Therefore, an abstraction of the gestural interaction was idealized through a formalization, described syntactically by construction blocks that originates a grammar of the gestural interaction and, semantically, approached under the view of the residential system. So, we define a set of metrics grounded in the recommendations that are described with information from the preestablished grammar, and still, we conceive and implement in Java, under the foundation of this grammar, a residential system based on gestural interaction for usage with Microsoft Kinect. Lastly, we accomplish an experiment with potential end users of the system, aiming to better analyze the research results

Design and evaluation of an advanced virtual reality system for visualization of dentistry structures

This paper presents the development of an application created to assist the teaching of dental structures, generate rich content information and different manners of interaction. An ontology was created to provide semantics informations for virtual models. We also used two devices gesture-based interaction: Kinect and Wii Remote. It was developed a system which use intuitive interaction, and it is able to generate three dimensional images, making the experience of teaching / learning motivating. The projection environment used by the system was called Mini CAVE. © 2012 IEEE.

A realidade virtual na intervenção motora em crianças com transtorno do desenvolvimento da coordenação

Pós-graduação em Desenvolvimento Humano e Tecnologias - IBRC

Simplificação de malhas visando representações em multirresolução

The representation of real objects in virtual environments has applications in many areas, such as cartography, mixed reality and reverse engineering. The generation of these objects can be performed through two ways: manually, with CAD (Computer Aided Design) tools, or automatically, by means of surface reconstruction techniques. The simpler the 3D model, the easier it is to process and store it. However, this methods can generate very detailed virtual elements, that can result in some problems when processing the resulting mesh, because it has a lot of edges and polygons that have to be checked at visualization. Considering this context, it can be applied simplification algorithms to eliminate polygons from resulting mesh, without change its topology, generating a lighter mesh with less irrelevant details. The project aimed the study, implementation and comparative tests of simplification algorithms applied to meshes generated through a reconstruction pipeline based on point clouds. This work proposes the realization of the simplification step, like a complement to the pipeline developed by (ONO et al., 2012), that developed reconstruction through cloud points obtained by Microsoft Kinect, and then using Poisson algorithm