Avec le besoin de développer un organe artificiel remplaçant le doigt humain dans le cas d'un déficit et la nécessité de comprendre le fonctionnement de ce système physiologique, un modèle physique inverse du système doigt, permettant de chercher les activations neuronales à partir du mouvement, est nécessaire. Malgré le grand nombre d'études dans la modélisation de la main humaine, presque il n'existe aucun modèle physique inverse du système doigt majeur qui s'intéresse à chercher les activations neuronales. Presque tous les modèles existants se sont intéressés à la recherche des forces et des activations musculaires. L'objectif de la thèse est de présenter un modèle neuromusculo-squelettique du système doigt majeur humain permettant d'obtenir les activations neuronales, les activations musculaires et les forces musculaires des tous les muscles agissants sur le système doigt d'après l'analyse du mouvement. Le but de ce type des modèles est de représenter les caractéristiques essentielles du mouvement avec le plus de réalisme possible. Notre travail consiste à étudier, modéliser et à simuler le mouvement du doigt humain. L'innovation du modèle proposé est le couplage entre la biomécanique et les aspects neurophysiologiques afin de simuler la chaine inverse complet du mouvement en allant des données dynamiques du doigt aux intentions neuronales qui contrôlent les activations musculaires. L'autre innovation est la conception d'un protocole expérimental spécifique qui traite à la fois les données sEMG multicanal et les données cinématiques d'après une procédure de capture de mouvement. / With the need to develop an artificial organ replacing the human finger in the case of a deficiency and the need to understand how this physiological system works, an inverse physical model of the finger system for estimating neuronal activations from the movement, is necessary. Despite the large number of studies in the human hand modeling, almost there is no inverse physical model of the middle finger system that focuses on search neuronal activations. Al most all existing models have focused on the research of the muscle forces and muscle activations. The purpose of the manuscript is to present a neuromusculoskeletal model of the human middle finger system for estimating neuronal activations, muscle activations and muscle forces of all the acting muscles after movement analysis. The aim of such models is to represent the essential characteristics of the movement with the best possible realism. Our job is to study, model and simulate the movement of the human finger. The innovation of the proposed model is the coupling between the biomechanical and neurophysiological aspects to simulate the complete inverse movement chain from dynamic finger data to neuronal intents that control muscle activations. Another innovation is the design of a specific experimental protocol that treats both the multichannel sEMG and kinematic data from a data capture procedure of the movement.

Title: Measurement of lower extremities spasticity in patients with cerebral palsy Objectives: The aim of the theoretical part of this thesis is to evaluate possibilities of lower extremities spasticity measurement in adult patients with cerebral palsy. The main focus was given to the concept of French professor J.-M. Gracies: Five- step clinical assessment in spastic paresis. This unique concept presents differentiation of three main factors of motor impairment that emerge as a result of a lesion to central motor pathways: stretch sensitive paresis, soft tissue contracture and muscle overactivity. Ability to distinguish these factors is crucial for specific treatment indication. Finding a correlation between the Five-step clinical assessment in spastic paresis and muscle activity in gait measured with polyEMG was the main objective in the practical part of the thesis. Methodology: This thesis has a theoretical-empirical character. The theoretical part is in a form of a research on the topic of spasticity diagnosis, focused on cerebral palsy patients. The empirical part of the thesis has a form of pilot quantitative research, which was attended by 6 participants with cerebral palsy (4 men and 2 women; average age 29 years). There were 2 independent measurement made for each of them. Each...

Title: Measurement of lower extremities spasticity in patients with cerebral palsy Objectives: The aim of the theoretical part of this thesis is to evaluate possibilities of lower extremities spasticity measurement in adult patients with cerebral palsy. The main focus was given to the concept of French professor J.-M. Gracies: Five-step clinical assessment in spastic paresis. This unique concept presents differentiation of three main factors of motor impairment that emerge as a result of a lesion to central motor pathways: stretch sensitive paresis, soft tissue contracture and muscle overactivity. Ability to distinguish these factors is crucial for specific treatment indication. Finding a correlation between the Five-step clinical assessment in spastic paresis and muscle activity in gait measured with sEMG was the main objective in the practical part of the thesis. Methodology: This thesis has a theoretical-empirical character. The theoretical part is in a form of a research on the topic of spasticity diagnosis, focused on cerebral palsy patients. The empirical part of the thesis has a form of pilot quantitative research, which was attended by 6 participants with cerebral palsy (4 men and 2 women; average age 29 years). There were 2 independent measurement made for each of them. Each measurement...

Muscle fatigue is a severe problem for elite athletes, and this is due to the long resting times, which can vary. Various mechanisms can cause muscle fatigue which signifies that the specific muscle has reached its maximum force and cannot continue the task. This thesis was about surveying and exploring state-of-the-art methods and systematically, theoretically, and practically testing the applicability and performance of more recent machine learning methods on an existing EMG to muscle fatigue pipeline. Several challenges within the EMG domain exist, such as inadequate data, finding the most suitable model, and how they should be addressed to achieve reliable prediction. This required approaches for addressing these problems by combining and comparing various state-of-the-art methodologies, such as data augmentation techniques for upsampling, spectrogram methods for signal processing, and transfer learning to gain a reliable prediction by various pre-trained CNN models. The approach during this study was to conduct seven experiments consisting of a classification task that aims to predict muscle fatigue in various stages. These stages are divided into 7 classes from 0-6, and higher classes represent a fatigued muscle. In the tabular part of the experiments, the Decision Tree, Random Forest, and Support Vector Machine (SVM) were trained, and the accuracy was determined. A similar approach was made for the spectrogram part, where the signals were converted to spectrogram images, and with a combination of traditional- and intelligent data augmentation techniques, such as noise and DCGAN, the limited dataset was increased. A comparison between the performance of AlexNet, VGG16, DenseNet, and InceptionV3 pre-trained CNN models was made to predict differences in jump heights. The result was evaluated by implementing baseline classifiers on tabular data and pre-trained CNN model classifiers for CWT and STFT spectrograms with and without data augmentation. The evaluation of various state-of-the-art methodologies for a classification problem showed that DenseNet and VGG16 gave a reliable accuracy of 89.8 % on intelligent data augmented CWT images. The intelligent data augmentation applied on CWT images allows the pre-trained CNN models to learn features that can generalize unseen data. Proving that the combination of state-of-the-art methods can be introduced and address the challenges within the EMG domain.