Orientador: Ibiara Correia de Lima Almeida Paz / Resumo: A avicultura de corte é caracterizada pelos ciclos de produção muito curtos, com rápido crescimento dos frangos. Em contrapartida, essa característica se reflete na composição mineral dos ossos e cartilagens, estando inaptos para sustentar seu peso, resultando em queda no desempenho e na produtividade, além de prejudicar o bem-estar animal. A hipótese dessa pesquisa foi de que os distúrbios ósseos causam prejuízo ao desenvolvimento do frango de corte e a qualidade de sua carcaça, e esses problemas começam a surgir com o aumento exponencial do ganho de peso. O objetivo desse trabalho foi correlacionar as metodologias de avaliação de bem-estar em frangos de corte por meio da capacidade de manter-se em pé em caixas plásticas (versão adaptada do latency to lie) e caminhar no trajeto em um metro linear (gait score), delineando a idade e o peso que se iniciam os distúrbios locomotores. Somado a isso, foi verificado a incidência de miopatia dorsal cranial, pododermatite e distúrbios locomotores nas aves. Para tanto, foram utilizadas 1000 aves da linhagem Cobb® Slow, adquiridas de um incubatório comercial, com 1 dia de idade, e alojadas em um sistema totalmente automatizado com ventilação em pressão negativa, utilização de exaustores e painéis evaporativos de celulose. Para este estudo, não houve tratamento, delineamento e repetição, assim, avaliou-se os animais em condições semelhantes às comerciais de criação. O bem-estar foi avaliado por dois métodos distintos, o gait score e o la... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Poultry farming is characterized by very short production cycles, with rapid growth of chickens. In contrast, this characteristic is reflect in the mineral composition of bones and cartilage, being unable to sustain their weight, resulting in a drop in performance and productivity, as well as impairing animal welfare. The hypothesis of this research was that the bone problems cause damage to the development of the broiler chicken and the quality of its carcass, and these problems begin to appear with the exponential increase of the weight gain. The objective of this study was to correlate welfare methodologies in broiler chickens through the ability to stand in plastic boxes (adapted version of latency to lie) and walk on a linear meter (gait score), delineating the age and weight that locomotion problems begin. In addition, the incidence of dorsal cranial myopathy, pododermatitis and locomotion problems in birds was verified. For this purpose, 1000 birds of the Cobb® Slow lineage were used, acquired from a commercial hatchery, at 1 day of age, housed in a fully automated system with negative pressure ventilation, use of hoods and evaporative cellulose panels. For this study, there was no treatment, delineation and repetition, thus, the animals were evaluated under conditions similar to commercial ones. The welfare was evaluated by two distinct methods, gait score and latency to lie, and later these methods were compared and correlated. The birds were weighed weekly, in order... (Complete abstract click electronic access below) / Mestre

Analyzing a person's gait is important in determining their physical and neurological health. However, typical motion analysis laboratories are only in urban specialty care facilities and can be expensive due to the specialized personnel and technology needed for these examinations. Many patients, especially those who reside in underdeveloped or isolated locations, find it impractical to go to such facilities. With the help of recent developments in high-performance computing and artificial intelligence models, it is now feasible to evaluate human movement using digital video. Over the past 20 years, various visual gait analysis tools and scales have been developed. A study of the literature and discussions with physicians who are domain experts revealed that the Edinburgh Visual Gait Score (EVGS) is one of the most effective scales currently available. Clinical implementations of EVGS currently rely on human scoring of videos. In this thesis, an algorithmic implementation of EVGS scoring based on hand-held smart phone video was implemented. Walking gait was recorded using a handheld smartphone at 60Hz as participants walked along a hallway. Body keypoints representing joints and limb segments were then identified using the OpenPose - Body 25 pose estimation model. A new algorithm was developed to identify foot events and strides from the keypoints and determine EVGS parameters at relevant strides. The stride identification results were compared with ground truth foot events that were manually labeled through direct observation, and the EVGS results were compared with evaluations by human scorers. Stride detection was accurate within 2 to 5 frames. The level of agreement between the scorers and the algorithmic EVGS score was strong for 14 of 17 parameters. The algorithm EVGS results were highly correlated to scorers' scores (r>0.80) for eight of the 17 factors. Smartphone-based remote motion analysis with automated implementation of the EVGS may be employed in a patient's neighborhood, eliminating the need to travel. These results demonstrated the viability of automated EVGS for remote human motion analysis.