Human activity recognition by inertial signals obtained from a smartphone

Human Activity Recognition (HAR) is an emerging research field with the aim to identify the actions carried out by a person given a set of observations and the surrounding environment. The wide growth in this research field inside the scientific community is mainly explained by the high number of applications that are arising in the last years. A great part of the most promising applications are related to the healthcare field, where it is possible to track the mobility of patients with motor dysfunction as also the physical activity in patients with cardiovascular risk. Until a few years ago, by using distinct kind of sensors, a patient follow-up was possible. However, far from being a long-term solution and with the smartphone irruption, that monitoring can be achieved in a non-invasive way by using the embedded smartphone’s sensors. For these reasons this Final Degree Project arises with the main target to evaluate new feature extraction techniques in order to carry out an activity and user recognition, and also an activity segmentation. The recognition is done thanks to the inertial signals integration obtained by two widespread sensors in the greater part of smartphones: accelerometer and gyroscope. In particular, six different activities are evaluated walking, walking-upstairs, walking-downstairs, sitting, standing and lying. Furthermore, a segmentation task is carried out taking into account the activities performed by thirty users. This can be done by using Hidden Markov Models and also a set of tools tested satisfactory in speech recognition: HTK (Hidden Markov Model Toolkit).

Controle de uma plataforma inercial estabilizada com três graus de liberdade.

Esta dissertação apresenta o desenvolvimento de uma plataforma inercial autônoma com três graus de liberdade para aplicação em estabilização de sensores - por exemplo, gravimétricos estacionários e embarcados - podendo ser utilizada também para estabilização de câmeras. O sistema é formado pela Unidade de Medida Inercial, IMU, desenvolvida utilizando um sensor micro eletromecânico, MEMS - que possui acelerômetro, giroscópio e magnetômetros nos três eixos de orientação - e um microcontrolador para aquisição, processamento e envio dos dados ao sistema de controle e aquisição de dados. Para controle dos ângulos de inclinação e orientação da plataforma, foi implementado um controlador PID digital utilizando microcontrolador. Este recebe os dados da IMU e fornece os sinais de controle utilizando as saídas PWM que acionam os motores, os quais controlam a posição da plataforma. Para monitoramento da plataforma foi desenvolvido um programa para aquisição de dados em tempo real em ambiente Matlab, por meio do qual se pode visualizar e gravar os sinais da IMU, os ângulos de inclinação e a velocidade angular. Testou-se um sistema de transmissão de dados por rádio frequência entre a IMU e o sistema de aquisição de dados e controle para avaliar a possibilidade da não utilização de slip rings ou fios entre o eixo de rotação e os quadros da plataforma. Entretanto, verificou-se a inviabilidade da transmissão em razão da baixa velocidade de transmissão e dos ruídos captados pelo receptor de rádio frequência durante osmovimentos da plataforma. Sendo assim, dois pares de fios trançados foram utilizados fios para conectar o sensor inercial ao sistema de aquisição e processamento.

High speed imaging and algorithms for non invasive vibrations measurement

Comunicación presentada en EVACES 2011, 4th International Conference on Experimental Vibration Analysis for Civil Engineering Structures, Varenna (Lecco), Italy, October 3-5, 2011.

P.A.V.E.S. : Post-Accident Vehicle Emergency System

Dissertação apresentada ao Instituto Politécnico de Castelo Branco para cumprimento dos requisitos necessários à obtenção do grau de Mestre em Desenvolvimento de Software e Sistemas Interactivos, realizada sob a orientação científica do Doutor Fernando Reinaldo Silva Garcia Ribeiro, Professor Adjunto da Unidade Técnico-Científica de Informática da Escola Superior de Tecnologia do Instituto Politécnico de Castelo Branco.

Les effets de l’éclairage cyclique versus l’éclairage tamisé constant sur la stabilité physiologique et le niveau d’activité motrice de prématurés

Problématique : Les prématurés évoluent dans l’unité néonatale qui présente une intensité lumineuse parfois forte et variable, ce qui a pour effet de provoquer une instabilité physiologique, ainsi qu’une augmentation du niveau d’activité motrice chez ces derniers. Par ailleurs, le contrôle de l’éclairage à l’unité néonatale favorise la stabilité physiologique et réduit le niveau d’activité motrice des prématurés. Deux méthodes de contrôle de l’éclairage ont été étudiées, soit l’éclairage tamisé constant et l’éclairage cyclique. Or, la méthode de contrôle de l’éclairage la plus appropriée au système nerveux immature des prématurés est inconnue et il y a ambivalence en ce qui concerne les résultats des études ayant évalué ces deux modes de contrôle de l’éclairage. But : Le but de cette étude était de mesurer les effets de l’éclairage cyclique versus l’éclairage tamisé constant sur la stabilité physiologique et le niveau d’activité motrice de prématurés nés entre 28 et 32 semaines d’âge gestationnel. Méthode : Un essai clinique randomisé a été réalisé. Les 38 prématurés recrutés dans une unité néonatale de niveaux II et III d’un hôpital universitaire, ont été randomisés dans l’un des deux groupes d’intervention, soit le groupe exposé à l’éclairage tamisé constant ou celui exposé à l’éclairage cyclique. Ces deux types d’éclairage ont été appliqués pendant 24 heures. La stabilité physiologique a été mesurée par le score Stability of the Cardio Respiratory System in Premature Infants (SCRIP) et le niveau d’activité motrice a été mesuré avec un accéléromètre (Actiwatch®). L’intensité lumineuse à laquelle les prématurés ont été exposés a été mesurée de façon continue à l’intérieur de l’incubateur à l’aide d’un photomètre. Résultats : L’analyse des données révèle qu’il n’y aucune différence significative entre les deux groupes d’intervention en ce qui a trait à la stabilité physiologique (valeur-p du score SCRIP de 0,54 à 0,96) et au niveau d’activité motrice (valeur-p de 0,09 à 0,88). Les participants des deux groupes ont manifesté une stabilité physiologique et un niveau d’activité motrice comparables. Conclusion : Des interventions de contrôle de l’éclairage doivent être adoptées à l’unité néonatale, que ce soit des interventions qui permettent la mise en œuvre de l’éclairage cyclique ou de l’éclairage tamisé constant, dans le but de favoriser l’adaptation du prématuré à l’environnement de l’unité néonatale. Des recherches additionnelles sont requises afin d’identifier la méthode de contrôle de l’éclairage (éclairage cyclique ou éclairage tamisé constant) qui doit être implantée à l’unité néonatale.

Physical Health Problems and Environmental Challenges Influence Balancing Behaviour in Laying Hens

With rising public concern for animal welfare, many major food chains and restaurants are changing their policies, strictly buying their eggs from non-cage producers. However, with the additional space in these cage-free systems to perform natural behaviours and movements comes the risk of injury. We evaluated the ability to maintain balance in adult laying hens with health problems (footpad dermatitis, keel damage, poor wing feather cover; n = 15) using a series of environmental challenges and compared such abilities with those of healthy birds (n = 5). Environmental challenges consisted of visual and spatial constraints, created using a head mask, perch obstacles, and static and swaying perch states. We hypothesized that perch movement, environmental challenges, and diminished physical health would negatively impact perching performance demonstrated as balance (as measured by time spent on perch and by number of falls of the perch) and would require more exaggerated correctional movements.We measured perching stability whereby each bird underwent eight 30-second trials on a static and swaying perch: with and without disrupted vision (head mask), with and without space limitations (obstacles) and combinations thereof. Video recordings (600 Hz) and a three-axis accelerometer/gyroscope (100 Hz) were used to measure the number of jumps/falls, latencies to leave the perch, as well as magnitude and direction of both linear and rotational balance-correcting movements. Laying hens with and without physical health problems, in both challenged and unchallenged environments, managed to perch and remain off the ground. We attribute this capacity to our training of the birds. Environmental challenges and physical state had an effect on the use of accelerations and rotations to stabilize themselves on a perch. Birds with physical health problems performed a higher frequency of rotational corrections to keep the body centered over the perch, whereas, for both health categories, environmental challenges required more intense and variable movement corrections. Collectively, these results provide novel empirical support for the effectiveness of training, and highlight that overcrowding, visual constraints, and poor physical health all reduce perching performance.

Use of Extended Characteristics of Locomotion and Feeding Behavior for Automated Identification of Lame Dairy Cows.

This study was carried out to detect differences in locomotion and feeding behavior in lame (group L; n = 41; gait score ≥ 2.5) and non-lame (group C; n = 12; gait score ≤ 2) multiparous Holstein cows in a cross-sectional study design. A model for automatic lameness detection was created, using data from accelerometers attached to the hind limbs and noseband sensors attached to the head. Each cow's gait was videotaped and scored on a 5-point scale before and after a period of 3 consecutive days of behavioral data recording. The mean value of 3 independent experienced observers was taken as a definite gait score and considered to be the gold standard. For statistical analysis, data from the noseband sensor and one of two accelerometers per cow (randomly selected) of 2 out of 3 randomly selected days was used. For comparison between group L and group C, the T-test, the Aspin-Welch Test and the Wilcoxon Test were used. The sensitivity and specificity for lameness detection was determined with logistic regression and ROC-analysis. Group L compared to group C had significantly lower eating and ruminating time, fewer eating chews, ruminating chews and ruminating boluses, longer lying time and lying bout duration, lower standing time, fewer standing and walking bouts, fewer, slower and shorter strides and a lower walking speed. The model considering the number of standing bouts and walking speed was the best predictor of cows being lame with a sensitivity of 90.2% and specificity of 91.7%. Sensitivity and specificity of the lameness detection model were considered to be very high, even without the use of halter data. It was concluded that under the conditions of the study farm, accelerometer data were suitable for accurately distinguishing between lame and non-lame dairy cows, even in cases of slight lameness with a gait score of 2.5.

Les effets de l’éclairage cyclique versus l’éclairage tamisé constant sur la stabilité physiologique et le niveau d’activité motrice de prématurés

Problématique : Les prématurés évoluent dans l’unité néonatale qui présente une intensité lumineuse parfois forte et variable, ce qui a pour effet de provoquer une instabilité physiologique, ainsi qu’une augmentation du niveau d’activité motrice chez ces derniers. Par ailleurs, le contrôle de l’éclairage à l’unité néonatale favorise la stabilité physiologique et réduit le niveau d’activité motrice des prématurés. Deux méthodes de contrôle de l’éclairage ont été étudiées, soit l’éclairage tamisé constant et l’éclairage cyclique. Or, la méthode de contrôle de l’éclairage la plus appropriée au système nerveux immature des prématurés est inconnue et il y a ambivalence en ce qui concerne les résultats des études ayant évalué ces deux modes de contrôle de l’éclairage. But : Le but de cette étude était de mesurer les effets de l’éclairage cyclique versus l’éclairage tamisé constant sur la stabilité physiologique et le niveau d’activité motrice de prématurés nés entre 28 et 32 semaines d’âge gestationnel. Méthode : Un essai clinique randomisé a été réalisé. Les 38 prématurés recrutés dans une unité néonatale de niveaux II et III d’un hôpital universitaire, ont été randomisés dans l’un des deux groupes d’intervention, soit le groupe exposé à l’éclairage tamisé constant ou celui exposé à l’éclairage cyclique. Ces deux types d’éclairage ont été appliqués pendant 24 heures. La stabilité physiologique a été mesurée par le score Stability of the Cardio Respiratory System in Premature Infants (SCRIP) et le niveau d’activité motrice a été mesuré avec un accéléromètre (Actiwatch®). L’intensité lumineuse à laquelle les prématurés ont été exposés a été mesurée de façon continue à l’intérieur de l’incubateur à l’aide d’un photomètre. Résultats : L’analyse des données révèle qu’il n’y aucune différence significative entre les deux groupes d’intervention en ce qui a trait à la stabilité physiologique (valeur-p du score SCRIP de 0,54 à 0,96) et au niveau d’activité motrice (valeur-p de 0,09 à 0,88). Les participants des deux groupes ont manifesté une stabilité physiologique et un niveau d’activité motrice comparables. Conclusion : Des interventions de contrôle de l’éclairage doivent être adoptées à l’unité néonatale, que ce soit des interventions qui permettent la mise en œuvre de l’éclairage cyclique ou de l’éclairage tamisé constant, dans le but de favoriser l’adaptation du prématuré à l’environnement de l’unité néonatale. Des recherches additionnelles sont requises afin d’identifier la méthode de contrôle de l’éclairage (éclairage cyclique ou éclairage tamisé constant) qui doit être implantée à l’unité néonatale.

Heat stress, heat strain, and productivity in Washington State tree fruit harvesters

Thesis (Master's)--University of Washington, 2016-06

Screening for physical activity in family practice - Evaluation of two brief assessment tools

Background: Physical activity (PA) is relevant to the prevention and management of many health conditions in family practice. There is a need for an efficient, reliable, and valid assessment tool to identify patients in need of PA interventions. Methods: Twenty-eight family physicians in three Australian cities assessed the PA of their adult patients during 2004 using either a two- (2Q) or three-question (3Q) assessment. This was administered again approximately 3 days later to evaluate test-retest reliability. Concurrent validity was evaluated by measuring agreement with the Active Australia Questionnaire, and criterion validity by comparison with 7-day Computer Science Applications, Inc. (CSA) accelerometer counts. Results: A total of 509 patients participated, with 428 (84%) completing a repeat assessment, and 415 (82%) accelerometer monitoring. The brief assessments had moderate test-retest reliability (2Q k = 58.0%, 95% confidence interval [CI] = 47.2-68.8%; 3Q k = 55.6%, 95% CI = 43.8-67.4%); fair to moderate concurrent validity (2Q k = 46.7%, 95% CI = 35.657.9%; 3Q k = 38.7%, 95% CI = 26.4-51.1%); and poor to fair criterion validity (2Q k = 18.2%, 95% CI = 3.9-32.6%; 3Q k = 24.3%, 95% CI = 11.6-36.9%) for identifying patients as sufficiently active. A four-level scale of PA derived from the PA assessments was significantly correlated with accelerometer minutes (2Q rho = 0.39, 95% CI = 0.28-0.49; 3Q rho = 0.31, 95% CI = 0.18-0.43). Physicians reported that the assessments took I to 2 minutes to complete. Conclusions: Both PA assessments were feasible to use in family practice, and were suitable for identifying the least active patients. The 2Q assessment was preferred by clinicians and may be most appropriate for dissemination.

Validity of accelerometry for measurement of activity in people with brain injury

Purpose: To evaluate the validity of a uniaxial accelerometer (MTI Actigraph) for measuring physical activity in people with acquired brain injury (ABI) using portable indirect calorimetry (Cosmed K4b(2)) as a criterion measure. Methods: Fourteen people with ABI and related gait pattern impairment (age 32 +/- 8 yr) wore an MTI Actigraph that measured activity (counts(.)min-(1)) and a Cosmed K4b(2) that measured oxygen consumption (mL(.)kg(-1.)min(-1)) during four activities: quiet sitting (QS) and comfortable paced (CP), brisk paced (BP), and fast paced (FP) walking. MET levels were predicted from Actigraph counts using a published equation and compared with Cosmed measures. Predicted METs for each of the 56 activity bouts (14 participants X 4 bouts) were classified (light, moderate, vigorous, or very vigorous intensity) and compared with Cosmed-based classifications. Results: Repeated-measures ANOVA indicated that walking condition intensities were significantly different (P < 0.05) and the Actigraph detected the differences. Overall correlation between measured and predicted METs was positive, moderate, and significant (r = 0.74). Mean predicted METs were not significantly different from measured for CP and BP, but for FP walking, predicted METs were significantly less than measured (P < 0.05). The Actigraph correctly classified intensity for 76.8% of all activity bouts and 91.5% of light- and moderate-intensity bouts. Conclusions: Actigraph counts provide a valid index of activity across the intensities investigated in this study. For light to moderate activity, Actigraph-based estimates of METs are acceptable for group-level analysis and are a valid means of classifying activity intensity. The Actigraph significantly underestimated higher intensity activity, although, in practice, this limitation will have minimal impact on activity measurement of most community-dwelling people with ABI.

Dynamic force balances for short-duration hypersonic testing facilities

Two force balance techniques for use in hypersonic impulse facilities are compared by measuring the drag force on a 30&DEG; semi-apex-angle blunt cone model in a hypersonic shock tunnel at a free stream Mach number of 5.75. An accelerometer-based balance and a stress-wave force balance were tested simultaneously on the same model to measure the drag force. It was found that drag force measurements could be made using both techniques in a flow with a 450-μ s test period. The measured drag forces compared well with the theoretical values estimated using Newtonian theory.

Reliability and validity of a brief physical activity assessment for use by family doctors

Objective: To evaluate the reliability and validity of a brief physical activity assessment tool suitable for doctors to use to identify inactive patients in the primary care setting. Methods: Volunteer family doctors (n = 8) screened consenting patients (n = 75) for physical activity participation using a brief physical activity assessment tool. Inter-rater reliability was assessed within one week (n = 71). Validity was assessed against an objective physical activity monitor (computer science and applications accelerometer; n = 42). Results: The brief physical activity assessment tool produced repeatable estimates of sufficient total physical activity, correctly classifying over 76% of cases (kappa 0.53, 95% confidence interval (CI) 0.33 to 0.72). The validity coefficient was reasonable (kappa 0.40, 95% CI 0.12 to 0.69), with good percentage agreement (71%). Conclusions: The brief physical activity assessment tool is a reliable instrument, with validity similar to that of more detailed self report measures of physical activity. It is a tool that can be used efficiently in routine primary healthcare services to identify insufficiently active patients who may need physical activity advice.

Individual calibration for estimating free-living walking speed using the MTI monitor

Purpose: This study was conducted to devise a new individual calibration method to enhance MTI accelerometer estimation of free-living level walking speed. Method: Five female and five male middle-aged adults walked 400 m at 3.5, 4.5, and 5.5 km(.)h(-1), and 800 in at 6.5 km(.)h(-1) on an outdoor track, following a continuous protocol. Lap speed was controlled by a global positioning system (GPS) monitor. MTI counts-to-speed calibration equations were derived for each trial, for each subject for four such trials with each of four MTI, for each subject for the average MTI. and for the pooled data. Standard errors of the estimate (SEE) with and without individual calibration were compared. To assess accuracy of prediction of free-living walking speed, subjects also completed a self-paced, brisk 3-km walk wearing one of the four MTI, and differences between actual and predicted walking speed with and without individual calibration were examined. Results: Correlations between MTI counts and walking speed were 0.90 without individual calibration, 0.98 with individual calibration for the average MTI. and 0.99 with individual calibration for a specific MTI. The SEE (mean +/- SD) was 0.58 +/- 0.30 km(.)h(-1) without individual calibration, 0.19 +/- 0.09 km h(-1) with individual calibration for the average MTI monitor, and 0.16 +/- 0.08 km(.)h(-1) with individual calibration for a specific MTI monitor. The difference between actual and predicted walking speed on the brisk 3-km walk was 0.06 +/- 0.25 km(.)h(-1) using individual calibration and 0.28 +/- 0.63 km(.)h(-1) without individual calibration (for specific accelerometers). Conclusion: MTI accuracy in predicting walking speed without individual calibration might be sufficient for population-based studies but not for intervention trials. This individual calibration method will substantially increase precision of walking speed predicted from MTI counts.

Predictive validity of three ActiGraph energy expenditure equations for children

Purpose: This Study evaluated the predictive validity of three previously published ActiGraph energy expenditure (EE) prediction equations developed for children and adolescents. Methods: A total of 45 healthy children and adolescents (mean age: 13.7 +/- 2.6 yr) completed four 5-min activity trials (normal walking. brisk walking, easy running, and fast running) in ail indoor exercise facility. During each trial, participants were all ActiGraph accelerometer oil the right hip. EE was monitored breath by breath using the Cosmed K4b(2) portable indirect calorimetry system. Differences and associations between measured and predicted EE were assessed using dependent t-tests and Pearson correlations, respectively. Classification accuracy was assessed using percent agreement, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve, Results: None of the equations accurately predicted mean energy expenditure during each of the four activity trials. Each equation, however, accurately predicted mean EE in at least one activity trial. The Puyau equation accurately predicted EE during slow walking. The Trost equation accurately predicted EE during slow running. The Freedson equation accurately predicted EE during fast running. None of the three equations accurately predicted EE during brisk walking. The equations exhibited fair to excellent classification accuracy with respect to activity intensity. with the Trost equation exhibiting the highest classification accuracy and the Puyau equation exhibiting the lowest. Conclusions: These data suggest that the three accelerometer prediction equations do not accurately predict EE on a minute-by-minute basis in children and adolescents during overground walking and running. The equations maybe, however, for estimating participation in moderate and vigorous activity.