This thesis explores the use of machine learning (ML) and smartphone sensors to improve indoordistance estimation, a critical aspect of healthcare tests like the 6-minute walk test (6MWT). In order to make tests like the 6MWT more available, and lower the barrier for a patient toget tested, there are multiple problems which need to be solved: How can the distance data needed for these tests be collected reliably and remotely, and without having to rely on the patient reporting correct data; How can these tests be performed indoors, without relying on GPS or other GNSS, which are unreliable indoors. To tackle these challenges a convolutional neural network (CNN) trained on a dataset containing continuous ground truth was employed. An enhancement of an existing CNN model was done by collecting more training data, tuning hyper parameters, and testing it on a diverse dataset. The results of this thesis shows that when predicting distance walked on data from participants the CNN model has seen before, the precision meets clinical minimum for being able to show a change in the health condition. On real world data the performance suffers. Despite limitations due to the scope of data collection, the results still underscores the potential of ML for accurate and efficient indoor distance estimation and points to future research directions. / <p></p><p></p><p></p>

No description available.

Tyrimo tikslas. Palyginti eisenos atsigavimą asmenims, patyrusiems trauminį galvos smegenų sužalojimą (TGSS) ar galvos smegenų infarktą (GSI), pirmajame reabilitacijos etape taikant kineziterapiją. Tyrimo uždaviniai.1) Įvertinti asmenų, patyrusių TGSS ar GSI, protinę būklę ir mobilumą prieš ir po kineziterapijos; 2) Įvertinti asmenų, patyrusių TGSS, eiseną taikant kineziterapiją pirmojo reabilitacijos etapo pradžioje ir pabaigoje; 3) Įvertinti asmenų, patyrusių GSI, eiseną taikant kineziterapiją pirmojo reabilitacijos etapo pradžioje ir pabaigoje; 4) Įvertinti asmenų, patyrusių TGSS ar GSI, proto būklės ir mobilumo atsigavimo įtaką eisenos atsigavimui, taikant kineziterapiją. Tyrimo metodai. Tyrime dalyvavo 60 asmenų: 30 asmenų, patyrusių TGSS, ir 30 asmenų, patyrusių GSI. Visiems tiriamiesiems buvo sutrikusi eisena. Vertinome tiriamųjų proto būklę pagal Trumpą Proto Būklės Tyrimo Testą, (TPBVT), mobilumą pagal Rivermead’o mobilumo indeksą (Rivermead Mobility Index) ir eiseną pagal Dinaminį Eisenos Indeksą (Dynamic Gait Index). Rezultatai skaičiuoti atliekant matematinę statistinę analizę. Visiems tiriamiesiems buvo taikoma kineziterapija siekiant eisenos atsigavimo. Tyrimo rezultatai. Tyrimo rezultatai parodė, kad taikant kineziterapiją pagerėjo proto būklė, mobilumas ir eisena abiejose tiriamųjų grupėse. Atlikus asmenų po TGSS ar GSI proto būklės, mobilumo ir eisenos palyginamąją analizę, gavome, kad kineziterapija turi teigiamą įtaką abiejų grupių proto būklės, mobilumo... [toliau žr. visą tekstą] / The aim. To compare gait recovery of individuals after Traumatic Brain Injury (TBI) or Ischemic Brain Stroke (IBS) using Physical Therapy during first rehabilitation stage. The tasks were: 1) To evaluate individuals after TBI or IBS mental state and mobility before and after Physical Therapy. 2) To evaluate individuals gait after TBI before and after Physical Therapy during first rehabilitation state. 3) To evaluate individuals gait after IBS before and after Physical Therapy during first rehabilitation state. 4) To find correlation between mental state, mobility and gait recovery of individuals after TBI or IBS using Physical Therapy. Methods and Material. In this study there were 60 persons participated: 30 after TBI and 30 after IBS. All patients had gait disorders. We evaluated mental state using Mini Mental State Examine (MMSE), mobility using Rivermead Mobility Index (RMI) and gait using Dynamic Gait Index. The results were calculated using mathematical statistical analysis. All patients received Physical Therapy to improve their gait. Results. The results showed significant mental state, mobility and gait recovery after Physical Therapy in both groups. Comparative analysis of persons after TBI or IBS mental state, mobility and gait showed that Physical Therapy has a statistically significant influence on mental state, mobility and gait recovery in both groups. We found correlation between mental state, mobility and gait recovery for patients after TBI or IBS. Gait... [to full text]

Este trabalho propõe um novo enfoque em visão computacional aplicado a sequências de vídeo, de pessoas em movimento, para reconhecê-las por meio da marcha. O movimento humano carrega diferentes informações, considerando-se diferentes maneiras de analisá-lo. O esqueleto carrega as informações do movimento global de articulações do corpo humano e como se comportam durante a caminhada e a silhueta carreia informações referentes ao comportamento global do contorno do corpo humano. Além disso, imagens binárias e em escala de cinza possuem diferentes informações sobre o movimento humano. O método proposto considera o conjunto de frames segmentados de cada indivíduo como uma classe e cada frame como um objeto desta classe. A metodologia aplica o Modelo de Mistura de Gaussianas (GMM) para subtração de fundo, redução de escala realizada por meio de técnicas de multiresolução baseadas na Transformada Wavelet (TW) e a extração dos padrões por meio da Análise dos Componentes Principais (PCA). São propostos e ensaiados quatro novos modelos de captura de movimentos globais do corpo humano durante a marcha: o modelo Silhouette-Gray-Wavelet (SGW) captura o movimento baseado nas variações em nível de cinza; o modelo Silhouette-Binary-Wavelet (SBW) captura o movimento baseado nas informações binárias da silhueta; o modelo Silhouette-Edge-Wavelet (SEW) captura o movimento baseado nas informações contidas na borda das silhuetas e o modelo Silhouette-Skeleton-Wavelet (SSW) captura o movimento baseado do esqueleto humano. As taxas de classificações corretas obtidas separadamente a partir destes quatro diferentes modelos são então combinadas utilizando-se uma nova técnica de fusão. Os resultados demonstram excelente desempenho e mostraram a viabilidade para reconhecimento de pessoas. / This paper proposes a novel computer vision approach that processes video sequences of people walking and then recognises those people by their gait. Human motion carries different information that can be analysed in various ways. The skeleton carries motion information about human joints, and the silhouette carries information about boundary motion of the human body. Moreover, binary and gray-level images contain different information about human movements. Our proposed method considers the set of the segmented frames of each individual as a distinct class and each frame as an object of this class. The methodology applies background extraction using the Gaussian Mixture Model (GMM), a scale reduction based on the Wavelet Transform (WT) and feature extraction by Principal Component Analysis (PCA). We propose four new schemas for motion information capture: the Silhouette-Gray-Wavelet model (SGW) captures motion based on grey level variations; the Silhouette-Binary-Wavelet model (SBW) captures motion based on binary information; the Silhouette-Edge-Binary model (SEW) captures motion based on edge information and the Silhouette-Skeleton-Wavelet model (SSW) captures motion based on skeleton movement. The classification rates obtained separately from these four different models are then merged using a new proposed fusion technique. The results suggest excellent performance in terms of recognising people by their gait.

Le vieillissement de la population est un enjeu majeur pour les prochaines années en raison, notamment, de l'augmentation du nombre de personnes dépendantes. La question du maintien à domicile de ces personnes se pose alors, du fait de l'impossibilité pour les instituts spécialisés de les accueillir toutes et, surtout, de la volonté des personnes âgées de rester chez elles le plus longtemps possible. Or, le développement de systèmes technologiques peut aider à résoudre certains problèmes comme celui de la sécurisation en détectant les chutes, et de l'évaluation du degré d'autonomie pour prévenir les accidents. Plus particulièrement, nous nous intéressons au développement des systèmes ambiants, peu coûteux, pour l'équipement du domicile. Les caméras de profondeur permettent d'analyser en temps réel les déplacements de la personne. Nous montrons dans cette thèse qu'il est possible de reconnaître l'activité de la personne et de mesurer des paramètres de sa marche à partir de l'analyse de caractéristiques simples extraites des images de profondeur. La reconnaissance d'activité est réalisée à partir des modèles de Markov cachés, et permet en particulier de détecter les chutes et des activités à risque. Lorsque la personne marche, l'analyse de la trajectoire du centre de masse nous permet de mesurer les paramètres spatio-temporels pertinents pour l'évaluation de la fragilité de la personne. Ce travail a été réalisé sur la base d'expérimentations menées en laboratoire, d'une part, pour la construction des modèles par apprentissage automatique et, d'autre part, pour évaluer la validité des résultats. Les expérimentations ont montré que certains modèles de Markov cachés, développés pour ce travail, sont assez robustes pour classifier les différentes activités. Nous donnons, également dans cette thèse, la précision, obtenue avec notre système, des paramètres de la marche en comparaison avec un tapis actimètrique. Nous pensons qu'un tel système pourrait facilement être installé au domicile de personnes âgées, car il repose sur un traitement local des images. Il fournit, au quotidien, des informations sur l'analyse de l'activité et sur l'évolution des paramètres de la marche qui sont utiles pour sécuriser et évaluer le degré de fragilité de la personne. / Population ageing is a major issue for society in the next years, especially because of the increase of dependent people. The limits in specialized institutes capacity and the wish of the elderly to stay at home as long as possible explain a growing need for new specific at home services. Technologies can help securing the person at home by detecting falls. They can also help in the evaluation of the frailty for preventing future accidents. This work concerns the development of low cost ambient systems for helping the stay at home of elderly. Depth cameras allow analysing in real time the displacement of the person. We show that it is possible to recognize the activity of the person and to measure gait parameters from the analysis of simple feature extracted from depth images. Activity recognition is based on Hidden Markov Models and allows detecting at risk behaviours and falls. When the person is walking, the analysis of the trajectory of her centre of mass allows measuring gait parameters that can be used for frailty evaluation. This work is based on laboratory experimentations for the acquisition of data used for models training and for the evaluation of the results. We show that some of the developed Hidden Markov Models are robust enough for classifying the activities. We also evaluate de precision of the gait parameters measurement in comparison to the measures provided by an actimetric carpet. We believe that such a system could be installed in the home of the elderly because it relies on a local processing of the depth images. It would be able to provide daily information on the person activity and on the evolution of her gait parameters that are useful for securing her and evaluating her frailty

Hauptziel der Arbeit war es einen Ganganalyse-Meßplatz zu entwickeln, der es ermöglicht, sowohl die Kinematik als auch die Kinetik des Ganges zu messen. Für den praktischen Einsatz ist dabei die "online" - Fähigkeit des Meßsystems von Bedeutung. Wichtige Entwicklungskriterien waren auch die Nutzerfreundlichkeit und geringe Kosten. Nicht zuletzt sollte der modulare Aufbau des Systems eine nachträgliche Integration zusätzlicher Meßkomponenten ermöglichen. Die Wahl des Meßprinzips für die Kinetik des Ganges fiel auf den Einsatz von Druckmeßsohlen. Folgende Gründe führten u.a. zu dieser Entscheidung: · Eine Messung mit Druckmeßsohlen erlaubt die Bestimmung der örtlichen Druckverteilung unter dem Fuß beim Gehen, d.h. man erkennt an welcher Stelle des Fußes der Druck auftritt, ob an der Ferse oder am Vorfuß. · Die Auswertung kann anhand einer großen Zahl aufeinanderfolgender Schritte erfolgen. · Bei Messungen mit Sohlen ist man nicht ortsgebunden. Sowohl Untersuchungen auf dem Laufband, als auch im Laufgang sind möglich. Ebenso kann die Messung im beliebigen Gelän-de (z.B. auf dem Sportplatz oder auf der Treppe) durchgeführt werden. Für die Messung der Kinematik finden Goniometer Verwendung. Ebenso wie bei den Druckmeß-sohlen, sind Goniometermessungen nicht ortsgebunden. Wichtig für die Entscheidung zugunsten der Goniometrie ist auch, daß diese preiswerter ist als die meisten anderen kinematischen Meß-verfahren. An das Meßsystem können noch weitere Sensoren angeschlossen werden. Mögliche Sensoren sind zum Beispiel aktive Oberflächenelektroden für Elektromyographie-Messungen oder Beschleu-nigungssensoren. Die Datenübertragung erfolgt über Funk. Eine wesentliche Aufgabe zum Erreichen des Hauptziels, bestand darin, aufbauend auf dem all-gemein anerkannten Erkenntnisstand, Gangparameter zu entwickeln, welche die verschiedenen Einzelaspekte des menschlichen Ganges hinreichend genau beschreiben. Wichtig für die Datenre-duktion war dabei die Berechnung eines für den zu Untersuchenden typischen mittleren Schrittes. Insbesondere aus der Sicht der Nutzerfreundlichkeit ist eine Datenbank für die Charakterisierung des unauffälligen Ganges erstellt worden. Der Nutzer erhält damit die Möglichkeit, seine gemesse-nen Daten mit den Daten einer gangunauffälligen Probandengruppe zu vergleichen. / Main goal of the thesis was the development of a gait analysis measurement system, supporting the measurement of kinetics and kinematics of the gait. For practical application were important the online-abilities of the measuring system. Criteria for development were user friendliness and low cost. The modular build of the system is meant to provide the ability for later integration of other sensors. The choice of measuring principle for the kinetics of gait were pressure measuring insoles. The following reasons led to this decision: · The measurement with insoles allows locating the pressure distribution under the foot during walking, i.e. the point of pressure can be allocated to the forefoot or heel. · The evaluation can be based on many consecutive steps. · The measurement with insoles is not bound to a place. Measurement on a tread mill as well as on a defined stretch of hall. The measurement can take place in the surrounding of choice (for example in a sporting arena or on a stairway). For the kinematic measurements were used goniometers. As with the measurements with insoles the goniometer measurements are not bound to one place. An important reason for the decision to use goniometers rather than other kinematic measurement devices was amongst others it cost effectiveness. A number of different sensors can be attached to the measurement system. Other possible sensors could be active surface electrodes for electromyographic measurements or accelerometers. The data transmission is wireless. A main task on the way to reaching the main goal, was to develop gait parameters basing on the current knowledge which describe the different aspects of human gait appropriately. An important step towards data reduction was the calculation of a typical average step for the examinee. With view towards user friendliness a data base was developed in order to facilitate the characterisation of normal gait. The user can compare his measured data to the data of a group with normal gait.

A fisioterapia motora vem sendo empregada como terapia de suporte para as distrofias musculares, porém, seu efeito no músculo distrófico e na função motora global precisa ser melhor compreendida para direcionar os tratamentos. Esta pesquisa objetiva elucidar o papel da fisioterapia motora na deposição de colágeno muscular, bem como em alguns parâmetros cinemáticos e dinâmicos da marcha do modelo Golden Retriever Muscular Dystrophy (GRMD). Fragmentos do músculo bíceps femoralis foram coletados por biópsia de cinco animais GRMD de mesma idade para análises por microscopia de luz e imuno-histoquímica. A marcha dos animais foi registrada por câmeras de vídeo e as Forças de Reação do Solo (FRS) nos sentidos vertical (Fy), craniocaudal (Fx) e mediolateral (Fz) coletadas utilizando uma plataforma de força Kistler AG (9287A/100Hz) com os valores normalizados pelo peso corporal. Dois animais (tratados: TD) participaram do protocolo de fisioterapia que consistiu de atividade de marcha com velocidade controlada em área de 288 metros, 3 vezes/semana durante 12 semanas. Os animais controles (CD) mantiveram sua rotina de atividades diárias. A coleta I foi considerada como tempo zero (t0) com n=5 e o tempo após a fisioterapia (t1) como coleta II. As análises estatísticas consideraram p<.01. Foi realizada Imuno-histoquímica anti-colágenos tipo I, III (Calbiochem®) e IV (Bioreagents®). As características histopatológicas foram observadas no t0. Os CD apresentaram fibras hipercontraídas no t1, não observadas nos TD. Os colágenos do tipo I e III foram os mais presentes e aumentados. No t1, feixes espessos de colágeno do tipo I foram observados no endomísio dos TD, comparado ao t0. Os animais GRMD apresentaram velocidade lenta de marcha no t0 (0.64 m.s-1) com diminuição da mesma no t1 para os TD (0.45 m.s-1). No t1, os TD apresentaram diminuição da ADM do quadril (p<.0001), bem como do ombro (p<.05). O joelho e carpo dos animais foram as articulações com maiores ADM durante a marcha. Houve aumento da força vertical (Fy) dos membros torácicos e pélvicos dos TD e CD no t1 comparada ao t0. Os CD mostraram aumento do tempo de suporte dos membros torácicos no t1. A força propulsiva (Fx-) dos animais GRMD estava diminuída no t0, não mostrando sofrer influência da fisioterapia. A força medial (Fz+) do membro torácico dos TD mostrou aumento no t1 quando comparada aos CD p<.0001). Os animais tratados apresentam diminuição da flexibilidade e menor regeneração do tecido muscular em comparação aos animais não tratados. Funcionalmente, a fraqueza muscular dos animais distróficos reflete em uma marcha lenta, com característica de sobrecarga e dificuldade de avançar com o corpo. Além destas características, os TD apresentam menor amplitude de movimento articular proximal quando comparado ao t0. A fisioterapia motora aplicada acelera as alterações morfológicas no músculo distrófico sem interferir na progressão das disfunções de marcha no modelo canino da distrofia muscular. / Physiotherapy has been widely used as support treatment for muscular dystrophies. Its effect on dystrophic muscle and global function should be better understood to guide treatments. This study aims to understand the role of motor physical therapy on muscular collagen deposition and some kinematics and dynamical parameters of gait of the Golden Retriever Muscular Dystrophy (GRMD) model. Five GRMD dogs with the same age had fragments of biceps femoralis collected by biopsy for light microscopy and Immunohistochemistry analysis. Gait of the dogs were video recording for kinematics analysis and Ground Reaction Forces (GRF) in vertical (Fy), craniocaudal (Fx) and mediolateral (Fz) direction were collect using a Force Plate Kistler AG (9287A/100Hz) and normalized for body weight. Two animals (therapy dogs: TD) underwent a protocol which consisted of velocity controlled walking activity in an area of 288 meters total length, 3 times/week per 12 weeks. Control dogs (CD) maintained their daily routine. Zero time (t0) is considered at collect I (n=5) and time after therapy (t1) - collect II. Statistical analysis considered p<.01. Immunohistochemistry anticollagen types I, III (Calbiochem®) and IV (Bioreagents®) were performed. Histopathology features were observed at t0. CD presented hypercontracted fibers that were not observed on TD at t1. Collagen types I and III were the most increased ones. At t1, thicker tracts of collagen type I were observed at the endomysium of TD compared to t0. GRMD dogs presented slow velocity of gait (0.64 m.s-1) at t0 and there were a decrease of this velocity of TD at t1 (0.45 m.s-1). Hip ROM was decrease at t1 (p<.0001), as well as the shoulder ROM (p<.05) for TD. Stifle and Carpal ROM presented the highest active ROM during gait of dystrophic dogs. Fy of thoracic and pelvic limbs at t1 of TD and CD was higher than t0. CD presented increase of support time of thoracic limbs at t1 (49 to 53%). Propulsive force (Fx-) of GRMD dogs were decrease at t0, with no effect of physical therapy. Medial force (Fz+) of TD thoracic limbs were higher at t1 when compared to CD (p<.0001). TD presents less muscular flexibility and regeneration when compared to CD. Functionally, the muscular weakness of dystrophic dogs reflects a gait with slow velocity, overloaded and difficulty to goes forward. Moreover, TD presented lower range of motion of the proximal joints when compared to t0. The applied motor physical therapy accelerates the morphological alterations on dystrophic muscle without stop the gait disorders of the canine model of Duchenne muscular dystrophy.

Este trabalho propõe um novo enfoque em visão computacional aplicado a sequências de vídeo, de pessoas em movimento, para reconhecê-las por meio da marcha. O movimento humano carrega diferentes informações, considerando-se diferentes maneiras de analisá-lo. O esqueleto carrega as informações do movimento global de articulações do corpo humano e como se comportam durante a caminhada e a silhueta carreia informações referentes ao comportamento global do contorno do corpo humano. Além disso, imagens binárias e em escala de cinza possuem diferentes informações sobre o movimento humano. O método proposto considera o conjunto de frames segmentados de cada indivíduo como uma classe e cada frame como um objeto desta classe. A metodologia aplica o Modelo de Mistura de Gaussianas (GMM) para subtração de fundo, redução de escala realizada por meio de técnicas de multiresolução baseadas na Transformada Wavelet (TW) e a extração dos padrões por meio da Análise dos Componentes Principais (PCA). São propostos e ensaiados quatro novos modelos de captura de movimentos globais do corpo humano durante a marcha: o modelo Silhouette-Gray-Wavelet (SGW) captura o movimento baseado nas variações em nível de cinza; o modelo Silhouette-Binary-Wavelet (SBW) captura o movimento baseado nas informações binárias da silhueta; o modelo Silhouette-Edge-Wavelet (SEW) captura o movimento baseado nas informações contidas na borda das silhuetas e o modelo Silhouette-Skeleton-Wavelet (SSW) captura o movimento baseado do esqueleto humano. As taxas de classificações corretas obtidas separadamente a partir destes quatro diferentes modelos são então combinadas utilizando-se uma nova técnica de fusão. Os resultados demonstram excelente desempenho e mostraram a viabilidade para reconhecimento de pessoas. / This paper proposes a novel computer vision approach that processes video sequences of people walking and then recognises those people by their gait. Human motion carries different information that can be analysed in various ways. The skeleton carries motion information about human joints, and the silhouette carries information about boundary motion of the human body. Moreover, binary and gray-level images contain different information about human movements. Our proposed method considers the set of the segmented frames of each individual as a distinct class and each frame as an object of this class. The methodology applies background extraction using the Gaussian Mixture Model (GMM), a scale reduction based on the Wavelet Transform (WT) and feature extraction by Principal Component Analysis (PCA). We propose four new schemas for motion information capture: the Silhouette-Gray-Wavelet model (SGW) captures motion based on grey level variations; the Silhouette-Binary-Wavelet model (SBW) captures motion based on binary information; the Silhouette-Edge-Binary model (SEW) captures motion based on edge information and the Silhouette-Skeleton-Wavelet model (SSW) captures motion based on skeleton movement. The classification rates obtained separately from these four different models are then merged using a new proposed fusion technique. The results suggest excellent performance in terms of recognising people by their gait.

Les signaux multicanaux sont des signaux captés à travers plusieurs canaux ou capteurs, portant chacun un mélange de sources, une partie desquelles est connue alors que le reste des sources reste inconnu. Les méthodes à l’aide desquelles l’isolement ou la séparation des sources est accomplie sont connues par les méthodes de séparation de sources en général, et si le degré d’inconnu est large, par la séparation aveugle des sources (SAS). Cependant, la SAS appliquée aux signaux multicanaux est en fait plus facile de point de vue mathématique que l’application de la SAS sur des signaux monocanaux, ou un seul capteur existe et tous les signaux arrivent au même point pour enfin produire un mélange de sources inconnues. Tel est le domaine de cette thèse. Nous avons développé une nouvelle technique de SAS : une combinaison de plusieurs méthodes de séparation et d’optimisation, basée sur la factorisation non-négative des matrices (NMF). Cette méthode peut être utilisée dans de nombreux domaines comme l’analyse des sons et de la parole, les variations de la bourse, et les séismographes. Néanmoins, ici, les signaux de force de réaction de terre verticaux (VGRF) monocanaux d’un groupe d’athlètes coureurs d’ultra-marathon sont analysés et séparés pour l’extraction du peak passif du peak actif d’une nouvelle manière adaptée à la nature de ces signaux. Les signaux VGRF sont des signaux cyclo-stationnaires caractérisés par des double-peaks, chacun étant très rapide et parcimonieux, indiquant les phases de course de l’athlète. L’analyse des peaks est extrêmement importante pour déterminer et prédire la condition du coureur : problème physiologique, problème anatomique, fatigue etc. De plus, un grand nombre de chercheurs ont prouvé que l’impact du pied postérieur avec la terre d’une manière brutale, l’analyse de ce phénomène peut nous ramener à une prédiction de blessure interne. Ils essayent même d’adopter une technique de course - Non-Heel-strike Running (NHS) - par laquelle ils obligent les coureurs à courir sur le pied-antérieur seulement. Afin d'étudier ce phénomène, la séparation du peak d’impact du VGRF permet d'isoler la source portant les informations patho-physiologiques et le degré de fatigue. Nous avons introduit de nouvelles méthodes de prétraitement et de traitement des signaux VGRF pour remplacer le filtrage de bruit traditionnel utilisé partout, et qui peut parfois détruire les peaks d’impact qui sont nos sources à séparer, base sur le concept de soustraction spectrale pour le filtrage, utilisée avec les signaux de parole, après l’application d’un algorithme d’échantillonnage intelligent et adaptatif qui décompose les signaux en pas isolés. Une analyse des signaux VGRF en fonction du temps a été faite pour la détection et la quantification de la fatigue des coureurs durant les 24 heures de course. Cette analyse a été accomplie au domaine fréquentiel/spectral où nous avons détecté un décalage clair du contenu fréquentiel avec la progression de la course indiquant la progression de la fatigue. Nous avons défini les signaux cyclosparse au domaine temporel, puis traduit cette définition à son équivalent au domaine temps-fréquence utilisant la transformée Fourier a court-temps (STFT). Cette représentation a été décomposée à travers une nouvelle méthode que l’on a appelé Cyclosparse Non-negative Matrix Factorisation (Cyclosparse-NMF), basée sur l’optimisation de la minimisation de la divergence Kullback-Leibler (KL) avec pénalisation liée à la périodicité et la parcimonie des sources, ayant comme but final d’extraire les sources cyclosparse du mélange monocanal appliquée aux signaux VGRF monocanaux. La méthode a été testée sur des signaux analytiques afin de prouver l’efficacité de l’algorithme. Les résultats se sont avéré satisfaisants, et le peak impact a été séparé du mélange VGRF monocanal. / The purpose of the presented work is to develop a customized Single-channel Blind Source Separation technique that aims to separate cyclostationary and transient pulse-like patterns/sources from a linear instantaneous mixture of unknown sources. For that endeavor, synthetic signals of the mentioned characteristic were created to confirm the separation success, in addition to real life signals acquired throughout an experiment in which experienced athletes were asked to participate in a 24-hour ultra-marathon in a lab environment on an instrumented treadmill through which their VGRF, which carries a cyclosparse Impact Peak, is continuously recorded with very short discontinuities during which blood is drawn for in-run testing, short enough not to provide rest to the athletes. The synthetic and VGRF signals were then pre-processed, processed for Impact Pattern extraction via a customized Single-channel Blind Source Separation technique that we termed Cyclo-sparse Non-negative Matrix Factorization and analyzed for fatigue assessment. As a result, the Impact Patterns for all of the participating athletes were extracted at 10 different time intervals indicating the progression of the ultra-marathon for 24 hours, and further analysis and comparison of the resulting signals proved major significance in the field of fatigue assessment; the Impact Pattern power monotonically increased for 90% of the subjects by an average of 24.4 15% with the progression of the ultra-marathon during the 24-hour period. Upon computation of the Impact Pattern separation algorithm, fatigue progression showed to be manifested by an increase in reliance on heel-strike impact to push to the bodyweight as a compensation for the decrease in muscle power during propulsion at toe-off. This study among other presented work in the field of VGRF processing forms methods that could be implemented in wearable devices to assess and track runners’ gait as a part of sports performance analysis, rehabilitation phase tracking and classification of healthy vs. unhealthy gait.

Friedreich's Ataxia (FA) is an autosomal-recessive, neurodegenerative disease characterized by progressive lower extremity muscle weakness and sensory loss, balance deficits, limb and gait ataxia, and dysarthria. FA is considered a sensory ataxia because the dorsal root ganglia and spinal cord dorsal columns are involved early in the disease, whereas the cerebellum is affected later. Balance deficits and gait ataxia are often evaluated clinically and in research using clinical rating scales. Recently, quantitative tools such as the Biodex Balance System SD and the GAITRite Walkway System have become available to objectively assess balance and gait, respectively. However, there are limited studies using instrumented measures to quantitatively assess and characterize balance and gait disturbances in FA, and longitudinal, quantitative analyses of both balance and gait have not been investigated in this patient cohort. The purpose of the present study was to characterize gait patterns of adults with FA and to identify changes in gait and balance over time using clinical rating scales and quantitative measures. Additionally, this study investigated the relationship between disease duration, clinical rating scale scores and objective measures of gait and balance. This study used a longitudinal research design to investigate changes in balance and gait in 8 adults with genetically confirmed FA and 8 healthy controls matched for gender, age, height, and weight. Subjects with FA were evaluated using the Berg Balance Scale (BBS), the Friedreich's Ataxia Rating Scale (FARS) and instrumented gait and balance measures at baseline, 6 months, 12 months and 24 months. Controls underwent the same tests at baseline and 12 months. Gait parameters were measured utilizing the GAITRite Walkway system with a focus on gait velocity, cadence, step and stride lengths, step and stride length variability and percent of the gait cycle in swing, stance and double limb support. Balance was assessed using the BBS and the Biodex Balance System; the latter included tests of postural stability and limits of stability. At baseline, there were significant differences in gait and balance parameters, BBS scores and FARS total scores between FA subjects and controls as determined using paired t-tests (p This is the first longitudinal study to demonstrate changes over time in gait and balance of adults with FA using both quantitative measures and clinical rating scales. This study provided a detailed characterization of the gait pattern and balance of adults with FA. The GAITRite Walkway system proved to be a sensitive measure, and able to detect subtle changes in gait parameters over time in adults with FA. In addition, the BBS was an appropriate and sensitive assessment to detect changes in static and dynamic balance in this patient cohort. Finally, results revealed a strong and consistent relationship between clinical rating scale scores, postural stability indices, limits of stability scores, and step and stride length variability in individuals with FA.