RESUMEN
Automatic fall detection will reduce the consequences of falls in the elderly and promote independent living, ensuring people can confidently live safely at home. Inertial sensor technology can distinguish falls from normal activities. However, <;7% of studies have used fall data recorded from elderly people in real life. The FARSEEING project has compiled a database of real life falls from elderly people, to gain new knowledge about fall events. We have extracted temporal and kinematic parameters to further improve the development of fall detection algorithms. A total of 100 real-world falls were analysed. Subjects with a known fall history were recruited, inertial sensors were attached to L5 and a fall report, following a fall, was used to extract the fall signal. This data-set was examined, and variables were extracted that include upper and lower impact peak values, posture angle change during the fall and time of occurrence. These extracted parameters, can be used to inform the design of fall-detection algorithms for real-world falls detection in the elderly.
Asunto(s)
Accidentes por Caídas , Vértebras Lumbares/fisiopatología , Monitoreo Ambulatorio/instrumentación , Anciano , Algoritmos , Fenómenos Biomecánicos , Humanos , Postura , Factores de TiempoRESUMEN
Physical activity has a positive impact on people's well-being and it had been shown to decrease the occurrence of chronic diseases in the older adult population. To date, a substantial amount of research studies exist, which focus on activity recognition using inertial sensors. Many of these studies adopt a single sensor approach and focus on proposing novel features combined with complex classifiers to improve the overall recognition accuracy. In addition, the implementation of the advanced feature extraction algorithms and the complex classifiers exceed the computing ability of most current wearable sensor platforms. This paper proposes a method to adopt multiple sensors on distributed body locations to overcome this problem. The objective of the proposed system is to achieve higher recognition accuracy with "light-weight" signal processing algorithms, which run on a distributed computing based sensor system comprised of computationally efficient nodes. For analysing and evaluating the multi-sensor system, eight subjects were recruited to perform eight normal scripted activities in different life scenarios, each repeated three times. Thus a total of 192 activities were recorded resulting in 864 separate annotated activity states. The methods for designing such a multi-sensor system required consideration of the following: signal pre-processing algorithms, sampling rate, feature selection and classifier selection. Each has been investigated and the most appropriate approach is selected to achieve a trade-off between recognition accuracy and computing execution time. A comparison of six different systems, which employ single or multiple sensors, is presented. The experimental results illustrate that the proposed multi-sensor system can achieve an overall recognition accuracy of 96.4% by adopting the mean and variance features, using the Decision Tree classifier. The results demonstrate that elaborate classifiers and feature sets are not required to achieve high recognition accuracies on a multi-sensor system.
Asunto(s)
Acelerometría/instrumentación , Acelerometría/métodos , Monitoreo Ambulatorio/instrumentación , Monitoreo Ambulatorio/métodos , Movimiento/fisiología , Reconocimiento de Normas Patrones Automatizadas/métodos , Actividades Cotidianas , Anciano , Anciano de 80 o más Años , Algoritmos , Diseño de Equipo , Humanos , Postura/fisiología , Procesamiento de Señales Asistido por Computador , Muslo , Tórax , Tiempo , Caminata/fisiologíaRESUMEN
Despite its medical relevance, accurate recognition of sedentary (sitting and lying) and dynamic activities (e.g. standing and walking) remains challenging using a single wearable device. Currently, trunk-worn wearable systems can differentiate sitting from standing with moderate success, as activity classifiers often rely on inertial signals at the transition period (e.g. from sitting to standing) which contains limited information. Discriminating sitting from standing thus requires additional sources of information such as elevation change. The aim of this study is to demonstrate the suitability of barometric pressure, providing an absolute estimate of elevation, for evaluating sitting and standing periods during daily activities. Three sensors were evaluated in both calm laboratory conditions and a pilot study involving seven healthy subjects performing 322 sitting and standing transitions, both indoor and outdoor, in real-world conditions. The MS5611-BA01 barometric pressure sensor (Measurement Specialties, USA) demonstrated superior performance to counterparts. It discriminates actual sitting and standing transitions from stationary postures with 99.5% accuracy and is also capable to completely dissociate Sit-to-Stand from Stand-to-Sit transitions.
Asunto(s)
Acelerometría/instrumentación , Presión Atmosférica , Monitoreo Ambulatorio/instrumentación , Movimiento/fisiología , Postura/fisiología , Actividades Cotidianas , Adulto , Ambiente , Femenino , Humanos , Masculino , Proyectos Piloto , Caminata/fisiologíaRESUMEN
Accelerometer-based activity monitoring sensors have become the most suitable means for objective assessment of mobility trends within patient study groups. The use of minimal, low power, IC (integrated circuit) components within these sensors enable continuous (long-term) monitoring which provides more accurate mobility trends (over days or weeks), reduced cost, longer battery life, reduced size and weight of sensor. Using scripted activities of daily living (ADL) such as sitting, standing, walking, and numerous postural transitions performed under supervised conditions by young and elderly subjects, the ability to discriminate these ADL were investigated using a single tri-axial accelerometer, mounted on the trunk. Data analysis was performed using Matlab® to determine the accelerations performed during eight different ADL. Transitions and transition types were detected using the scalar (dot) product technique and vertical velocity estimates on a single tri-axial accelerometer was compared to a proven discrete wavelet transform method that incorporated accelerometers and gyroscopes. Activities and postural transitions were accurately detected by this simplified low-power kinematic sensor and activity detection algorithm with a sensitivity and specificity of 86-92% for young healthy subjects in a controlled setting and 83-89% for elderly healthy subjects in a home environment.
Asunto(s)
Aceleración , Monitoreo Ambulatorio/instrumentación , Actividad Motora/fisiología , Tórax , Accidentes por Caídas , Actividades Cotidianas , Adulto , Anciano , Anciano de 80 o más Años , Algoritmos , Femenino , Humanos , Masculino , Proyectos Piloto , Postura/fisiología , Adulto JovenRESUMEN
It is estimated that by 2050 more than one in five people will be aged 65 or over. In this age group, falls are one of the most serious life-threatening events that can occur. Their automatic detection would help reduce the time of arrival of medical attention, thus reducing the mortality rate and in turn promoting independent living. This study evaluated a variety of existing and novel fall-detection algorithms for a waist-mounted accelerometer based system. In total, 21 algorithms of varying degrees of complexity were tested against a comprehensive data-set recorded from 10 young healthy volunteers performing 240 falls and 120 activities of daily living (ADL) and 10 elderly healthy volunteers performing 240 scripted ADL and 52.4 waking hours of continuous unscripted normal ADL. Results show that using an algorithm that employs thresholds in velocity, impact and posture (velocity+impact+posture) achieves 100% specificity and sensitivity with a false-positive rate of less than 1 false-positive (0.6 false-positives) per day of waking hours. This algorithm is the most suitable method of fall-detection, when tested using continuous unscripted activities performed by elderly healthy volunteers, which is the target environment for a fall-detection device.
Asunto(s)
Accidentes por Caídas , Algoritmos , Ingeniería Biomédica/instrumentación , Modelos Biológicos , Aceleración , Accidentes por Caídas/prevención & control , Actividades Cotidianas , Adulto , Anciano , Anciano de 80 o más Años , Fenómenos Biomecánicos , Ingeniería Biomédica/estadística & datos numéricos , Bases de Datos Factuales , Reacciones Falso Positivas , Femenino , Humanos , Masculino , Monitoreo Fisiológico/instrumentación , Monitoreo Fisiológico/estadística & datos numéricos , Equilibrio Postural/fisiología , Adulto JovenRESUMEN
This study investigates distinguishing falls from normal Activities of Daily Living (ADL) by thresholding of the vertical velocity of the trunk. Also presented is the design and evaluation of a wearable inertial sensor, capable of accurately measuring these vertical velocity profiles, thus providing an alternative to optical motion capture systems. Five young healthy subjects performed a number of simulated falls and normal ADL and their trunk vertical velocities were measured by both the optical motion capture system and the inertial sensor. Through vertical velocity thresholding (VVT) of the trunk, obtained from the optical motion capture system, at -1.3 m/s, falls can be distinguished from normal ADL, with 100% accuracy and with an average of 323 ms prior to trunk impact and 140 ms prior to knee impact, in this subject group. The vertical velocity profiles obtained using the inertial sensor, were then compared to those obtained using the optical motion capture system. The signals from the inertial sensor were combined to produce vertical velocity profiles using rotational mathematics and integration. Results show high mean correlation (0.941: Coefficient of Multiple Correlations) and low mean percentage error (6.74%) between the signals generated from the inertial sensor to those from the optical motion capture system. The proposed system enables vertical velocity profiles to be measured from elderly subjects in a home environment where as this has previously been impractical.
Asunto(s)
Accidentes por Caídas/prevención & control , Interpretación de Imagen Asistida por Computador/métodos , Monitoreo Ambulatorio/métodos , Movimiento/fisiología , Actividades Cotidianas , Algoritmos , Fenómenos Biomecánicos , Calibración , Biología Computacional , Simulación por Computador , Diagnóstico Diferencial , Diseño de Equipo , Humanos , Reproducibilidad de los Resultados , Programas InformáticosRESUMEN
A threshold-based algorithm, to distinguish between Activities of Daily Living (ADL) and falls is described. A gyroscope based fall-detection sensor array is used. Using simulated-falls performed by young volunteers under supervised conditions onto crash mats and ADL performed by elderly subjects, the ability to discriminate between falls and ADL was achieved using a bi-axial gyroscope sensor mounted on the trunk, measuring pitch and roll angular velocities, and a threshold-based algorithm. Data analysis was performed using Matlab to determine the angular accelerations, angular velocities and changes in trunk angle recorded, during eight different fall and ADL types. Three thresholds were identified so that a fall could be distinguished from an ADL: if the resultant angular velocity is greater than 3.1 rads/s (Fall Threshold 1), the resultant angular acceleration is greater than 0.05 rads/s(2) (Fall Threshold 2), and the resultant change in trunk-angle is greater than 0.59 rad (Fall Threshold 3), a fall is detected. Results show that falls can be distinguished from ADL with 100% accuracy, for a total data set of 480 movements.
Asunto(s)
Accidentes por Caídas , Monitoreo Ambulatorio/métodos , Actividades Cotidianas , Adulto , Anciano , Anciano de 80 o más Años , Algoritmos , Marcha , Humanos , Monitoreo Ambulatorio/instrumentación , Movimiento , Equilibrio Postural , Postura , Estándares de Referencia , Rotación , Sensibilidad y Especificidad , TransductoresRESUMEN
Fall detection of the elderly is a major public health problem. Thus it has generated a wide range of applied research and prompted the development of telemonitoring systems to enable the early diagnosis of fall conditions. This article is a survey of systems, algorithms and sensors, for the automatic early detection of the fall of elderly persons. It points out the difficulty to compare the performances of the different systems due to the lack of a common framework. It then proposes a procedure for this evaluation.
Asunto(s)
Accidentes por Caídas/prevención & control , Actividades Cotidianas , Algoritmos , Monitoreo Ambulatorio/instrumentación , Monitoreo Ambulatorio/métodos , Movimiento , Transductores , Diseño de Equipo , Humanos , Evaluación de la Tecnología BiomédicaRESUMEN
Using simulated falls performed under supervised conditions and activities of daily living (ADL) performed by elderly subjects, the ability to discriminate between falls and ADL was investigated using tri-axial accelerometer sensors, mounted on the trunk and thigh. Data analysis was performed using MATLAB to determine the peak accelerations recorded during eight different types of falls. These included; forward falls, backward falls and lateral falls left and right, performed with legs straight and flexed. Falls detection algorithms were devised using thresholding techniques. Falls could be distinguished from ADL for a total data set from 480 movements. This was accomplished using a single threshold determined by the fall-event data-set, applied to the resultant-magnitude acceleration signal from a tri-axial accelerometer located at the trunk.