My work focuses on taking a single person as input and predicting the intentional movement of one dance partner based on the other dance partner's movement. Human pose estimation has been applied to dance and computer vision, but many existing applications focus on a single individual or multiple individuals performing. Currently there are very few works that focus specifically on dance couples combined with pose prediction. This thesis is applicable to the entertainment and gaming industry by training people to dance with a virtual dance partner. Many existing interactive or virtual dance partners require a motion capture system, multiple cameras or a robot which creates an expensive cost. This thesis does not use a motion capture system and combines OpenPose with swing dance YouTube videos to create a virtual dance partner. By taking in the current dancer's moves as input, the system predicts the dance partner's corresponding moves in the video frames. In order to create a virtual dance partner, datasets that contain information about the skeleton keypoints are necessary to predict a dance partner's pose. There are existing dance datasets for a specific type of dance, but these datasets do not cover swing dance. Furthermore, the dance datasets that do include swing have a limited number of videos. The contribution of this thesis is a large swing dataset that contains three different types of swing dance: East Coast, Lindy Hop and West Coast. I also provide a basic framework to extend the work to create a real-time and interactive dance partner.

No description available.

The mining industry is driven by performance and intense working environments, accompanied by high demands, hazardous working conditions and socially undesirable working hours. These factors could impact on the interaction between work and home, as well as contributing to health problems of employees. The objectives of this research were to test the construct validity, construct equivalence and reliability of a work-home interaction measuring instrument, the Survey Work-Home Interaction - Nijmegen (SWING), to determine if work-home interaction differences exist between different demographical groups, and to test a structural model of job characteristics (job demands and job resources), ill health and negative work-home interference. Random samples (n = 320) were taken from employees working in the mining industry (gold, platinum and phosphate mines) in the Gauteng, North West and Northern provinces. The SWING, a self-developed job characteristics questionnaire and an adapted version of the General Health Questionnaire were administered. Structural equation modelling, descriptive statistics, Cronbach alpha coefficients, Pearson product-moment correlations, multivariate analysis of variance (MANOVA) and one-way analysis of variance (ANOVA) were used to analyse the data. Structural equation modelling confirmed the four-factor structure of the SWING and the construct equivalence for two language and ethnic groups. The four factors showed acceptable internal consistencies. Statistically significant differences were found based on age, ethnicity, gender, qualification, marital and parental status, language, flexibility at work and whether individuals had a partner with a paid job. Regarding the structural model, the results showed that job demands and job resources have an impact on ill health, and that ill health is associated with negative WHI. It was also found that job demands and job resources have a direct relationship with negative WHI on their own, but when both high demands and a lack of resources are present, only an indirect relationship with negative WHI exists though ill health. / Thesis (M.Com. (Industrial Psychology))--North-West University, Potchefstroom Campus, 2007

Title: Physiotherapy with golf players having vertebrogenic disorders Objectives: The goal of the work is to find out and analyze, from selected foreign studies, the causes of the development of the most common pathologies in the lumbar area of the spine in adults, professionals and amateurs and based on the evaluation of the studies suggest appropriate physiotherapeutic procedures to be used as a prevention against low back pain (further LBP). Methods: The work is structured as a research, which has been created on the basis of an analysis of relevant sources. The literature, printed and electronic monographs, textbooks and specialized periodical were obtained from bibliographical databases, library catalogues and the Internet. The work contains foreign studies from USA, Canada, England and Australia. The studies were obtained from specialized medical databases: PubMed, PEDro, EBSCO. Results: The main cause of the development of LBP in golf players is the full golf swing, especially the modern type of swing. The following pathologies mainly develop in the lumbar area of the spine within the golf players: hypertonus paravertebral muscles, prolapses of intervertebral disc, fatigue vertebrae fracture and artrophaty of facet joints. In the prevention of LBP we use physiotherapeutic processes based on...

O problema de transferir uma carga ao se movimentar num plano em tempo mínimo e sem oscilação no ponto de descarga, num guindaste portuário tipo pórtico é investigado neste trabalho. Assume-se que a carga esteja inicialmente em repouso na posição vertical no ponto de carga acima do navio e igualmente em repouso no ponto de descarga na moega de alimentação no porto. Assume-se também que o carro do guindaste esteja em repouso em ambos os pontos. Um modelo completo é apresentado para o sistema do guindaste onde as equações dinâmicas não-lineares são linearizadas para ângulos de oscilação pequenos o suficiente e reescritas para a forma adimensional. A solução de tempo mínimo é buscada considerando como variáveis de controle as funções do tempo que descrevem tanto a força aplicada no carro para produzir seu deslocamento horizontal, como a velocidade de içamento da carga. Um método iterativo preditor-corretor usando a Programação Linear (PL) é proposto, baseado no modelo do sistema de tempo discreto onde as variáveis de controle são tomadas constantes por trechos. Na etapa corretora, assume-se que o movimento de içamento é dado e uma solução de tempo mínimo é obtida resolvendo-se uma seqüência de problemas de PL de tempo fixo e máximo deslocamento. Na etapa preditora, um modelo linearizado é empregado para obter-se uma correção ótima do movimento de içamento usando a PL. O problema de controle de tempo mínimo é formulado levando-se em consideração restrições práticas na velocidade do carro do guindaste, velocidade máxima de içamento, assim como na máxima força que pode ser aplicada ao carro. Resultados numéricos são apresentados e mostram a efetividade do método. / The problem of minimum-time anti-swing transfer of a load in a ship-to-pier gantry crane is investigated in this work. The load is assumed to be initially at rest at the vertical position at the loading point above the ship and equally at rest at the unloading point above the hopper. The trolley is also assumed to be at rest at both points. A complete model is presented for the crane system where the nonlinear dynamic equations are linearized for sufficiently small swing angles and then rewritten in dimensionless form. The minimum-time solution is sought by considering as control variables both the force applied on the trolley that produces its horizontal motion and the hoisting speed of the load as functions of time. A predictor-corrector iterative method using Linear Programming (LP) is proposed based on a discretetime model of the system where the control variables are taken as stepwise constants. At the corrector step, the hoisting motion is assumed given and a minimum-time solution is obtained by solving a sequence of LP problems representing fixed-time maximum-range problems. At the predictor step, a linearized model is employed to obtain an optimal correction of the hoisting motion using LP. The minimum-time control problem is formulated by taking into account practical constraints on the maximum speeds of both the trolley and the load hoisting, as well as on the maximum force that can be applied to the trolley. Numerical results are presented and show the effectiveness of the method.

Cette thèse porte sur la conception de trajectoires interplanétaires, à poussée faible. Les systèmes de propulsion électriques, à poussée faible ou continue, ont permis d'accroître significativement les possibilités de trajectoires, au détriment de mission plus longues. La poussée faible limite également la manoeuvrabilité du système. Afin de parer à ces inconvénients, on utilise généralement des manoeuvres d'assistances gravitationnelles, pour ainsi réduire la consommation et la durée de transfert de la sonde. Le rôle de l'analyste mission est donc de déterminer le meilleur scénario (la séquence de planètes à visiter). De nos jours, ce problème est résolu de manière expérimentale et heuristique. Cependant, bien que la trajectoire produite soit optimale à scénario donné, il n'y a aucune garantie que le scénario en lui-même soit optimal. De plus, cette approche est relativement fastidieuse. Notre objectif a donc été de mettre en place des outils et méthodes permettant de trouver des scénario optimaux pour un objectif fixé. Durant cette thèse, nous avons suivit 2 approches. La première approche consiste à considérer le problème comme étant un problème d'optimisation globale, à variables discrètes. Un ensemble de scénario est étudié à priori. Pour simplifier et faciliter la recherche de séquences, on a modélisé le problème de transfert à poussée faible, en utilisant un principe d'inversion dynamique. Ce modèle utilise des arcs balistiques pour minimiser la consommation, et introduire des degrés de liberté supplémentaires pour satisfaire des contraintes terminales. On a mis au point un algorithme de complexité polynomiale pour résoudre le problème. Afin de réduire le coût calculatoire, nous avons mis en place des contraintes de " pruning " permettant de réduire l'espace de recherche. La deuxième approche consiste à formuler le problème comme un problème de commande optimale, où la dynamique inclut les principaux corps perturbateurs. Le scénario est alors déterminé à postériori. On résoud numériquement le problème au N corps. On montre que les méthodes indirectes (Pontryaguin) et directes (Collocation, Transcription) ne nous permettent pas de résoudre ce problème. On a donc mis au point un solveur de deuxième ordre respectant à la fois les conditions d'optimalité et de précision connues des méthodes indirectes, et des propriétés de robustesse généralement attribué aux méthodes directes.

Thesis (M.Com. (Industrial Psychology))--North-West University, Potchefstroom Campus, 2007.

The mining industry is driven by performance and intense working environments, accompanied by high demands, hazardous working conditions and socially undesirable working hours. These factors could impact on the interaction between work and home, as well as contributing to health problems of employees. The objectives of this research were to test the construct validity, construct equivalence and reliability of a work-home interaction measuring instrument, the Survey Work-Home Interaction - Nijmegen (SWING), to determine if work-home interaction differences exist between different demographical groups, and to test a structural model of job characteristics (job demands and job resources), ill health and negative work-home interference. Random samples (n = 320) were taken from employees working in the mining industry (gold, platinum and phosphate mines) in the Gauteng, North West and Northern provinces. The SWING, a self-developed job characteristics questionnaire and an adapted version of the General Health Questionnaire were administered. Structural equation modelling, descriptive statistics, Cronbach alpha coefficients, Pearson product-moment correlations, multivariate analysis of variance (MANOVA) and one-way analysis of variance (ANOVA) were used to analyse the data. Structural equation modelling confirmed the four-factor structure of the SWING and the construct equivalence for two language and ethnic groups. The four factors showed acceptable internal consistencies. Statistically significant differences were found based on age, ethnicity, gender, qualification, marital and parental status, language, flexibility at work and whether individuals had a partner with a paid job. Regarding the structural model, the results showed that job demands and job resources have an impact on ill health, and that ill health is associated with negative WHI. It was also found that job demands and job resources have a direct relationship with negative WHI on their own, but when both high demands and a lack of resources are present, only an indirect relationship with negative WHI exists though ill health. / Thesis (M.Com. (Industrial Psychology))--North-West University, Potchefstroom Campus, 2007

Background Although trainers and athletes consider ‘good timing skills’ to be critical for optimal sport performance, little is known in regard to how sport-specific skills may benefit from timing training. Thus, assuming that all motor performances are mediated by an internal timing mechanism, enhanced motor timing is expected to have positive effects on both planning and execution of movement performance, and consequently on complex sports actions as golf or soccer. Accordingly, in order to increase our knowledge of the importance of motor timing and possible effects of timing training, this thesis examines the effects of synchronized metronome training (SMT), thought to improve the execution of motor programs and to enhance motor skills in golf and soccer players. Methods Study I examined the effects of SMT on motor timing abilities and its potential effect on golf shot accuracy and consistency in 25 experienced male golfers. Additionally, Study II examined the effects of SMT on the spatiotemporal movement organisation and dynamics of the golf swing performance, as captured by kinematic measurements and analyses in thirteen male golfers. Study III examined the effect of SMT on accuracy and variability in a soccer specific, cross-pass task in elite and sub-elite female soccer players. Moreover, the underlying brain activity was assessed by means of functional magnetic resonance imaging (fMRI) to investigate the corresponding neural activity when passively observing the cross-pass task, and the possible pre- to post training effects. Results SMT was shown to improve motor timing ability, by means of less timing asynchrony and with associated changes in timing variability, in both golf- and soccer-players. Additionally, significant improvements in golf shot and soccer cross-pass performance, by means of significant increase in outcome accuracy combined with a decrease in outcome variability was found. From the kinematic investigation in Study II, results indicate that improved motor timing, as an effect of SMT, lead to a more coordinated and dynamic swing performance, and with decreased variability in the temporal structure of the swing motion. Finally, it was found that SMT induces changes in the activity of the action observation network (AON), underpinning action observation and action prediction, by means of decreased activation within bilateral cerebellum, fusiform gyrus and superior temporal gyrus. These findings hint at a more efficient pattern of neural recruitment during action observation, after SMT. Conclusion In summary, this thesis provides evidence that four weeks of SMT improved the participant’s motor timing and synchronization abilities, and showed influence on both behavioral and neurophysiological motor programs and skill performance in golf and soccer players. Thus, by improved outcome accuracy and decreased variability, affecting the coordinated movement pattern and organisation, as well as affecting the associated underlying brain activation.

Aquesta dissertació tracta del ritme musical. Més exactamente, tracta de programes informàtics que extreuen automàticament descripcions rítmiques a partir de senyals musicals d'àudio.Presentem nous algorismes per a la inducció del tempo, la estimació del "tatum," la determinació del compàs, la estimació de "swing," transformacions de "swing" i la classificació d'estils de música de ball. Aquests algorismes processen directament gravacions digitalitzades de senyals acústiques de música. La base d'aquests algorismes son funcions de periodicitat rítmica: es a dir, funcions que mesuren la importància d'una pulsació rítmica en funció del període (o la freqüència) de la mateixa, calculades a partir d'atributs físics instantanis seleccionats per a posar en evidència aspectes rítmics del só. Aquests atributs es calculen amb una freqüència de mostreig constant sobre segments curts de la senyal d'àudio. Els nostres algorismes determinen el tempo i el "tatum" de música de diferents estils musicals, amb tempo constant, amb una precisió de més del 80% si no insistim en trobar el nivell mètric específic. Indentifiquen el compàs amb una precisió del 90%, si es coneixen nivells mètrics més ràpits. Classifiquen música de ball en 8 categories amb una precisió del 80% tenint en compte únicament aspectes rítmics de la música. Finalment, afegeixen (o substreuen) el "swing" de senyals musicals d'àudio de manera automàtica, conservant una alta qualitat de só.Des d'un punt de vista més general, aquesta dissertació contribueix de manera significativa al camp de la descripció computacional del ritme a) en proposar un entorn unificador d'analisi funcional; b) en revisar l'arquitectura de molts sistemes existent respecte els blocs funcionals d'aquest entorn; c) en organitzar la primera evaluació pública d'algorismes d'inducció de tempo; i d) en identificar direccions de recerca prometedores, particularment respecte a la selecció d'atributs instantanis més adients per al càlcul de funcions de periodicitat rítmica útils i l'estrategia per a combinar i processar multiples fonts d'informació rítmica. / Esta disertación trata del ritmo musical. Más precisamente, trata de programas informáticos que extraen automáticamente descripciones rítmicas a partir de señales musicales de audio.Presentamos nuevos algoritmos para la inducción del tempo, la estimación del "tatum," la determinación del compás, la estimación del "swing," transformaciones de "swing" y la clasificación de estilos de música de baile. Estos algoritmos procesan directamente grabaciones digitalizadas de señales acústicas de música. La base de estos algoritmos son funciones de periodicidad rítmica: funciones que miden la importancia de una pulsación rítmica en función del periodo (o la frecuencia) de la misma, calculadas a partir de atributos físicos instantáneos seleccionados para poner en evidencia aspectos rítmicos del sonido. Estos atributos se calculan con una frecuencia de muestreo constante sobre segmentos cortos de la señal de audio.Nuestros algoritmos determinan el tempo y el "tatum" de música de diferentes géneros, con tempo casi constante, con una precisión de más de 80% si no insistimos en encontrar un nivel métrico específico. Identifican el compás con una precisión de 90%, si se conocen niveles métricos más rápidos. Clasifican música de baile en 8 categorías con una precisión de 80% tomando en cuenta solamente aspectos rítmicos de la música. Finalmente, añaden (o sustraen) el "swing" de señales musicales de audio de manera automática, conservando una cualidad de sonido muy buena.De un punto de vista más general, está disertación contribuye de manera significativa al campo de la descripción computacional del ritmo a) en proponer un entorno unificador de análisis funcional; b) en revisar la arquitectura de muchos sistemas existentes respecto a los bloques funcionales de este entorno; c) en organizar la primera evaluación pública de algoritmos de inducción del tempo; y d) en identificar direcciones de investigación prometedoras, particularmente respecto a la selección de los mejores atributos instantáneos para el cálculo de funciones de periodicidad rítmica útiles y la estrategia para combinar y procesar múltiples fuentes de información rítmica.