[pt] Dores no pé e joelho estão relacionadas com patologias ortopédicas e lesões nos membros inferiores. Desde a corrida de rua até o treinamento funcional CrossFit, estas dores e lesões estão correlacionadas com a distribuição iregular da pressão plantar e o posicionamento inadequado do joelho durante a prática física de longo prazo, e podem levar a lesões ortopédicas graves se o padrão de movimento não for corrigido. Portanto, o monitoramento da distribuição da pressão plantar do pé e das características espaciais e temporais das irregularidades no posicionamento dos pés e joelhos são de extrema importância para a prevenção de lesões. Este trabalho propõe uma plataforma, composta de uma rede de sensores vestíveis e um classificador de Reconhecimento de Atividade Humana (HAR), para fornecer feedback em tempo real de exercícios funcionais, visando auxiliar educadores físicos a reduzir a probabilidade de lesões durante o treinamento. Realizamos um experimento com 12 voluntários diversos para construir um classificador HAR com aproximadamente de 87 porcento de precisão geral na classificação, e um segundo experimento para validar nosso modelo de avaliação física. Por fim, realizamos uma entrevista semi estruturada para avaliar questões de usabilidade e experiência do usuário da plataforma proposta.Visando uma pesquisa replicável, fornecemos informações completas sobre o hardware e o código fonte do sistema, e disponibilizamos o conjunto de dados do experimento. / [en] Foot and knee pain fave been associated with numerous orthopedic pathologies and injuries of the lower limbs. From street running to CrossFitTM functional training, these common pains and injuries correlate highly with unevenly distributed plantar pressure and knee positioning during long-term physical practice and can lead to severe orthopedic injuries if the movement pattern is not amended. Therefore, the monitoring of foot plantar pressure distribution and the spatial and temporal characteristics of foot and knee positioning abnomalities is of utmost importance for injury prevention. This work proposes a platform, composed af an lot wearable body sensor network and a Human Activity Recognition (HAR), to provide realtime feedback of functional exercises, aiming to enhace physical educators capability to mitigate the probability of injuries during training. We conducted an experiment with 12 diverse volunteers to build a HAR classifier that achieved about 87 percent overall classification accuracy, and a second experiment to validate our physical evaluation model. Finally, we performed a semi-structured interview to evaluate usability and user experience issues regarding the proposed platform. Aiming at a replicable research, we provide full hardware information, system source code and a public domain dataset.

Lake Tanganyika is a complex, tropical ecosystem in East Africa, harboring an estimated 2,100 species. Extensive watershed deforestation threatens the biodiversity and ecological integrity of the lake. In this dissertation, ecological and paleoecological methods were employed to study the distribution of invertebrate biodiversity through space and time, with particular emphasis on linkages between biodiversity and land –use patterns. Ecological surveys of fish, mollusc, and ostracod crustacean diversity at sites in northern Lake Tanganyika representing different levels of watershed disturbance revealed a negative correlation between biodiversity and intensity of watershed disturbance. To elucidate the long -term relationship between disturbance and biodiversity, paleoecological records of invertebrates offshore from watersheds experiencing different degrees of anthropogenic disturbance were examined. Life, death, and fossil assemblages of ostracod valves were compared to assess the reliability and natural variability inherent to the paleoecological record. These comparisons indicated that paleoecological (i.e. death and fossil) assemblages reliably preserve information on species richness, abundance, and occurrence frequency at comparable -to- annual resolution. Unlike life assemblages, species composition of paleoecological assemblages reflects input of species from multiple habitat types. Ostracod paleoecological assemblages are characterized by spatiotemporal averaging that renders them representative of larger areas and longer time spans than life assemblages. Thus, paleoecological assemblages provide an efficient means of characterizing longer -term, site -average conditions. Natural variability in ostracod fossil assemblages from a sediment core representing the Late Glacial to the present indicates that abundance of individual ostracod species is highly variable. Ostracod assemblages were preserved in only the most recent 2,500 years of sediment. Species composition of ostracod assemblages reflects lake water depth. Core geochemical data indicate that the coring site may have been below the oxycline for ~2,000 years, inhibiting ostracod survival and preservation. Paleoecological, sedimentological, and stable isotope data revealed differences in biodiversity and watershed disturbance through time offshore from a pair of sites. The protected site is offshore from Gombe Stream National Park (Tanzania), the other offshore from a deforested watershed outside the park. Offshore from the deforested watershed, sedimentation rates increased, and turnover in ostracod species composition occurred during the past 50 years. Comparable changes were not observed offshore from the park.

Orientador: Alexandre César Rodrigues da Silva / Resumo: O reconhecimento de atividades humanas abrange diversas técnicas de classificação que permitem identificar padrões específicos do comportamento humano no momento da ocorrência. A identificação é realizada analisando dados gerados por diversos sensores corporais, entre os quais destaca-se o acelerômetro, pois responde tanto à frequência como à intensidade dos movimentos. A identificação de atividades é uma área bastante explorada. Porém, existem desafios que necessitam ser superados, podendo-se mencionar a necessidade de sistemas leves, de fácil uso e aceitação por parte dos usuários e que cumpram com requerimentos de consumo de energia e de processamento de grandes quantidades de dados. Neste trabalho apresenta-se o desenvolvimento do Sistema de Reconhecimento de atividades Humanas e Avaliação do Equilíbrio Postural, denominado SIRAH. O sistema está baseado no uso de um acelerômetro localizado na cintura do usuário. As duas fases do reconhecimento de atividades são apresentadas, fase Offline e fase Online. A fase Offline trata do treinamento de uma rede neural artificial do tipo perceptron de três camadas. No treinamento foram avaliados três estudos de caso com conjuntos de atributos diferentes, visando medir o desempenho do classificador na diferenciação de 3 posturas e 4 atividades. No primeiro caso o treinamento foi realizado com 15 atributos, gerados no domínio do tempo, com os que a rede neural artificial alcançou uma precisão de 94,40%. No segundo caso foram gerados 34 ... (Resumo completo, clicar acesso eletrônico abaixo) / Doutor

Menschliche Systeme werden seit einiger Zeit modelliert und analysiert auf der Basis der Theorie komplexer Netzwerke. Dies erlaubt es quantitativ zu untersuchen, welche strukturellen und zeitlichen Merkmale eines Systems Ausbreitungsprozesse beeinflussen, z.B. von Informationen oder von Infektionskrankheiten. Im ersten Teil der Arbeit wird untersucht, wie eine modular-hierarchische Struktur von statischen Netzwerken eine schnelle Verbreitung von Signalen ermöglicht. Es werden neue Heuristiken entwickelt um die Random-Walk-Observablen “First Passage Time” und “Cover Time” auf lokal geclusterten Netzwerken zu ermitteln. Vergleiche mit der Approximation eines gemittelten Mediums zeigen, dass das Auftreten der beobachteten Minima der Observablen ein reiner Netzwerkeffekt ist. Es wird weiterhin dargelegt, dass nicht alle modular-hierarchischen Netzwerkmodelle dieses Phänomen aufweisen. Im zweiten Teil werden zeitlich veränderliche face-to-face Kontaktnetzwerke auf ihre Anfälligkeit für Infektionskrankheiten untersucht. Mehrere Studien belegen, dass Menschen vornehmlich Zeit in Isolation oder kleinen, stark verbundenen Gruppen verbringen, und dass ihre Kontaktaktivität einem zirkadianen Rhythmus folgt. Inwieweit diese beiden Merkmale die Ausbreitung von Krankheiten beeinflussen, ist noch unklar. Basierend auf einem neuen Modell wird erstmals gezeigt, dass zirkadian variierende Netzwerke Trajektorien folgen in einem Zustandsraum mit einer strukturellen und einer zeitlichen Dimension. Weiterhin wird dargelegt, dass mit zunehmender Annäherung der zeitlichen Dimension von System und Krankheit die systemische Infektionsanfälligkeit sinkt. Dies steht in direktem Widerspruch zu Ergebnissen anderer Studien, die eine zunehmende Anfälligkeit vorhersagen, eine Diskrepanz, die auf die Ungültigkeit einer weit verbreiteten Approximation zurückzuführen ist. Die hier vorgestellten Ergebnisse implizieren, dass auf dem Gebiet die Entwicklung neuer theoretischer Methoden notwendig ist. / Human systems have been modeled and analyzed on the basis of complex networks theory in recent time. This abstraction allows for thorough quantitative analyses to investigate which structural and temporal features of a system influence the evolution of spreading processes, such as the passage of information or of infectious diseases. The first part of this work investigates how the ubiquitous modular hierarchical structure of static real-world networks allows for fast delivery of messages. New heuristics are developed to evaluate random walk mean first passage times and cover times on locally clustered networks. A comparison to average medium approximations shows that the emergence of these minima are pure network phenomena. It is further found that not all modular hierarchical network models provide optimal message delivery structure. In the second part, temporally varying face-to-face contact networks are investigated for their susceptibility to infection. Several studies have shown that people tend to spend time in small, densely-connected groups or in isolation, and that their connection behavior follows a circadian rhythm. To what extent both of these features influence the spread of diseases is as yet unclear. Therefore, a new temporal network model is devised here. Based on this model, circadially varying networks can for the first time be interpreted as following trajectories through a newly defined systemic state space. It is further revealed that in many temporally varying networks the system becomes less susceptible to infection when the time-scale of the disease approaches the time-scale of the network variation. This is in direct conflict with findings of other studies that predict increasing susceptibility of temporal networks, a discrepancy which is attributed to the invalidity of a widely applied approximation. The results presented here imply that new theoretical advances are necessary to study the spread of diseases in temporally varying networks.

The ability of human beings to perceive the environment around them with their visual system is called motion perception. This means that the attention of our visual system is primarily focused on those objects that are moving. The property of human motion perception is used in this dissertation to infer human activity from data using artificial neural networks. One of the main aims of this thesis is to discover which modalities, namely RGB images, optical flow and human keypoints, are best suited for HAR in omnidirectional data. Since these modalities are not yet available for omnidirectional cameras, they are synthetically generated and captured with an omnidirectional camera. During data generation, a distinction is made between synthetically generated omnidirectional data and a real omnidirectional dataset that was recorded in a Living Lab at Chemnitz University of Technology and subsequently annotated by hand. The synthetically generated dataset, called OmniFlow, consists of RGB images, optical flow in forward and backward directions, segmentation masks, bounding boxes for the class people, as well as human keypoints. The real-world dataset, OmniLab, contains RGB images from two top-view scenes as well as manually annotated human keypoints and estimated forward optical flow. In this thesis, the generation of the synthetic and real-world datasets is explained. The OmniFlow dataset is generated using the 3D rendering engine Blender, in which a fully configurable 3D indoor environment is created with artificially textured rooms, human activities, objects and different lighting scenarios. A randomly placed virtual camera following the omnidirectional camera model renders the RGB images, all other modalities and 15 predefined activities. The result of modelling the 3D indoor environment is the OmniFlow dataset. Due to the lack of omnidirectional optical flow data, the OmniFlow dataset is validated using Test-Time Augmentation (TTA). Compared to the baseline, which contains Recurrent All-Pairs Field Transforms (RAFT) trained on the FlyingChairs and FlyingThings3D datasets, it was found that only about 1000 images need to be used for fine-tuning to obtain a very low End-point Error (EE). Furthermore, it was shown that the influence of TTA on the test dataset of OmniFlow affects EE by about a factor of three. As a basis for generating artificial keypoints on OmniFlow with action labels, the Carnegie Mellon University motion capture database is used with a large number of sports and household activities as skeletal data defined in the BVH format. From the BVH-skeletal data, the skeletal points of the people performing the activities can be directly derived or extrapolated by projecting these points from the 3D world into an omnidirectional 2D image. The real-world dataset, OmniLab, was recorded in two rooms of the Living Lab with five different people mimicking the 15 actions of OmniFlow. Human keypoint annotations were added manually in two iterations to reduce the error rate of incorrect annotations. The activity-level evaluation was investigated using a TSN and a PoseC3D network. The TSN consists of two CNNs, a spatial component trained on RGB images and a temporal component trained on the dense optical flow fields of OmniFlow. The PoseC3D network, an approach to skeleton-based activity recognition, uses a heatmap stack of keypoints in combination with 3D convolution, making the network more effective at learning spatio-temporal features than methods based on 2D convolution. In the first step, the networks were trained and validated on the synthetically generated dataset OmniFlow. In the second step, the training was performed on OmniFlow and the validation on the real-world dataset OmniLab. For both networks, TSN and PoseC3D, three hyperparameters were varied and the top-1, top-5 and mean accuracy given. First, the learning rate of the stochastic gradient descent (Stochastic Gradient Descent (SGD)) was varied. Secondly, the clip length, which indicates the number of consecutive frames for learning the network, was varied, and thirdly, the spatial resolution of the input data was varied. For the spatial resolution variation, five different image sizes were generated from the original dataset by cropping from the original dataset of OmniFlow and OmniLab. It was found that keypoint-based HAR with PoseC3D performed best compared to human activity classification based on optical flow and RGB images. This means that the top-1 accuracy was 0.3636, the top-5 accuracy was 0.7273 and the mean accuracy was 0.3750, showing that the most appropriate output resolution is 128px × 128px and the clip length is at least 24 consecutive frames. The best results could be achieved with a learning rate of PoseC3D of 10-3. In addition, confusion matrices indicating the class-wise accuracy of the 15 activity classes have been given for the modalities RGB images, optical flow and human keypoints. The confusion matrix for the modality RGB images shows the best classification result of the TSN for the action walk with an accuracy of 1.00, but almost all other actions are also classified as walking in real-world data. The classification of human actions based on optical flow works best on the action sit in chair and stand up with an accuracy of 1.00 and walk with 0.50. Furthermore, it is noticeable that almost all actions are classified as sit in chair and stand up, which indicates that the intra-class variance is low, so that the TSN is not able to distinguish between the selected action classes. Validated on real-world data for the modality keypoint the actions rugpull (1.00) and cleaning windows (0.75) performs best. Therefore, the PoseC3D network on a time-series of human keypoints is less sensitive to variations in the image angle between the synthetic and real-world data than for the modalities RGB images and optical flow. The pipeline for the generation of synthetic data with regard to a more uniform distribution of the motion magnitudes needs to be investigated in future work. Random placement of the person and other objects is not sufficient for a complete coverage of all movement magnitudes. An additional improvement of the synthetic data could be the rotation of the person around their own axis, so that the person moves in a different direction while performing the activity and thus the movement magnitudes contain more variance. Furthermore, the domain transition between synthetic and real-world data should be considered further in terms of viewpoint invariance and augmentation methods. It may be necessary to generate a new synthetic dataset with only top-view data and re-train the TSN and PoseC3D. As an augmentation method, for example, the Fourier Domain Adaption (FDA) could reduce the domain gap between the synthetically generated and the real-world dataset.:1 Introduction 2 Theoretical Background 3 Related Work 4 Omnidirectional Synthetic Human Optical Flow 5 Human Keypoints for Pose in Omnidirectional Images 6 Human Activity Recognition in Indoor Scenarios 7 Conclusion and Future Work A Chapter 4: Flow Dataset Statistics B Chapter 5: 3D Rotation Matrices C Chapter 6: Network Training Parameters