Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 14

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  fall detection
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
With the increasing prevalence of smartphones, they now come equipped with a multitude of sensors such as GPS, microphones, cameras, magnetometers, accelerators, and more, which can simplify our daily lives. When it comes to healthcare, smartphones can become indispensable.The detection of geriatric falls is crucial as even the slightest injury can havefatal consequences. Therefore, we proposed the use of accelerometers in our research to detect falls in the elderly. Our project involved the development of an automated, continuous, and reliable monitoring system that would generate a list of elderly people at risk of falling and present it on a webpage for emergency services. This approach aimed to minimize the long-term impacts and save lives promptly. We started by developing a mobile application and used MATLAB to classify the falls as either "fall" or "not fall." Finally, we created a webpage that would facilitate communication between the mobile application and MATLAB.
PL
Wraz z rosnącąpopularnością smartfonów są one wyposażone w wiele czujników, takich jak GPS, mikrofony, kamery, magnetometry, akceleratory i inne, które mogą uprościć nasze codzienne życie. Jeśli chodzi o opiekę zdrowotną, smartfony mogą stać się niezastąpione. Wykrywanie upadków geriatrycznych ma kluczowe znaczenie, ponieważ nawet najmniejszy uraz może mieć śmiertelne konsekwencje. Dlatego zaproponowanowykorzystanie w naszych badaniach akcelerometrów do wykrywania upadków osób starszych. Nasz projekt polegał na opracowaniu zautomatyzowanego, ciągłego i niezawodnego systemu monitoringu, który generowałby listę osób starszych zagrożonych upadkiem i prezentował ją na stronie internetowej służb ratowniczych. Podejście to miało na celu zminimalizowanie długoterminowych skutków i szybkie ratowanie życia. Rozpoczęto od opracowania aplikacji mobilnej i za pomocą MATLABa sklasyfikowano upadki jako „upadek” lub „nie upadek”. Ostatecznie stworzono stronę internetową, która ułatwiłaby komunikację między aplikacją mobilną a MATLABem.
EN
The problem of fall is still unsolved even though it is a serious problem, especially in group of elderly. Also, another difficulty is to analyse falls that occur in day-to-day life. Those events are hard to observe by specialists and so it is hard to analyse them. Following work contains a description of experimental process for external force-caused fall observation with the use of motion capture system and dynamometric platforms. Data collected according to this protocol were later used for time series neural networks. Obtained results of analysis were compared to popular model of human stability. Conducted inquiry proves that it is possible to detect fall even before it occurs and while it is external force-caused fall the loss of stability develops earlier than it was assumed.
EN
Falls are one of the leading causes of disability and premature death among the elderly. Technical solutions designed to automatically detect a fall event may mitigate fall-related health consequences by immediate medical assistance. This paper presents a wearable device called TTXFD based on MPU6050 which can collect triaxial acceleration signals. We have also designed a two-step fall detection algorithm that fuses threshold-based method (TBM) and machine learning (ML). The TTXFD exploits the TBM stage with low computational complexity to pick out and transmit suspected fall data (triaxial acceleration data). The ML stage of the two-step algorithm is implemented on a server which encodes the data into an image and exploits a fall detection algorithm based on convolutional neural network to identify a fall on the basis of the image. The experimental results show that the proposed algorithm achieves high sensitivity (97.83%), specificity (96.64%) and accuracy (97.02%) on the open dataset. In conclusion, this paper proposes a reliable solution for fall detection, which combines the advantages of threshold-based method and machine learning technology to reduce power consumption and improve classification ability.
4
Content available Remote health monitoring: fall detection
EN
Falling is a serious health issue among the elderly population; it can result in critical injuries like hip fractures. Immobilization caused by injury or unconsciousness means that the victim cannot summon help themselves. With elderly who live alone, not being found for hours after a fall is quite common and drastically increases the significance of fall-induced injuries. With an aging Baby Boomer population, the incidence of falls will only rise in the next few decades. The objective of this paper is to design and create a fall detection system. The system consists of a monitoring device that links wirelessly with a laptop. The device is able to accurately distinguish between fall and non-fall.
PL
Systemy lokalizacyjne pełnią ważną rolę w procesie wspomagania i diagnostyki osób z zaburzeniami poznawczymi. W referacie przedstawiono system zrealizowany w ramach projektu IONIS. Opisano architekturę systemu, budowę węzłów i etykiet, przedstawiono wymianę informacji pomiędzy urządzeniami. System umożliwia wykorzystanie do wyznaczania położenia wyników pomiarów wykonanych w interfejsach UWB i Bluetooth Low Energy. Ilustracją działania systemu są przykładowe wyniki lokalizacji osób w domu opieki.
EN
Localization systems are important component of platforms supporting persons with cognitive impairments. The paper presents a positioning system developed within IONIS project. System's architecture, design of anchor nodes and tags, exchange of data between devices are briefly described. Localization algorithms implemented in the system utilize results of measurements carried out in UWB and Bluetooth Low Energy interfaces. Exemplary results illustrating system operation are also included.
6
Content available Fall detection of the elderly using a smartphone
EN
Fall detection of the elderly is a major public health problem. The probability of falls makes them dependent on others and restricts their freedom of movement. Although many fall detection methods have been developed to recognize falls in a real-time, most are inaccurate and inconvenient to use. In this paper we describe two methods for detecting the fall of a human body that can be implemented for the smartphones with built-in accelerometer. The first one used the raw data obtained from the sensor, and the second one - filtered data. In addition to the measuring a load factor, an important role in the algorithms has also a mobile device orientation to the ground. The assumption for the study was the localization of the smartphone in a right pocket of trousers - common in right-handed people. The experiment consisted in simulation the falls from different initial postures (standing, sitting, kneeling) in four directions (front, back, left, right). The results are satisfactory for detection of falls from a standing position. In conclusion, correct detection of falls based on the accelerometer built into the smartphone is possible after the filtration of the raw data, although the location of this device, the initial body position and direction of the fall have significant impact.
EN
This paper presents the design process and the results of a novel fall detector designed and constructed at the Faculty of Electronics, Military University of Technology. High sensitivity and low false alarm rates were achieved by using four independent sensors of varying physical quantities and sophisticated methods of signal processing and data mining. The manuscript discusses the study background, hardware development, alternative algorithms used for the sensor data processing and fusion for identification of the most efficient solution and the final results from testing the Android application on smartphone. The test was performed in four 6-h sessions (two sessions with female participants at the age of 28 years, one session with male participants aged 28 years and one involving a man at the age of 49 years) and showed correct detection of all 40 simulated falls with only three false alarms. Our results confirmed the sensitivity of the proposed algorithm to be 100% with a nominal false alarm rate (one false alarm per 8 h).
PL
W artykule zaprezentowano wyniki badań opracowanego mechanizmu detekcji upadków. Wysoką niezawodność oraz niski poziom fałszywych alarmów uzyskano w wyniku zastosowania czterech niezależnych sensorów różnych wielkości fizycznych oraz wyrafinowanych metod przetwarzania sygnałów i eksploracji danych. Przeprowadzone badania pozwalają na stwierdzenie, że pominięcie znaku deskryptorów znacznie poprawia skuteczność prawidłowej klasyfikacji upadków. Z tego powodu w dalszych pracach zostanie przyjęty algorytm wykorzystujący wartości bezwzględne wyznaczanych cech. W trakcie badań zaobserwowano, że zwiększanie liczby cech użytych w procesie uczenia oraz testowania nie prowadzi do zwiększenia jakości klasyfikacji. Wynika stąd potrzeba dobrania optymalnej liczby deskryptorów. Dlatego istotnym warunkiem poprawy skuteczności systemu jest przeprowadzenie właściwej selekcji cech, co jest głównym celem kolejnego etapu badań.
EN
The paper presents the results of research on a fall detection algorithm. The high reliability and a low level of false alarms were obtained by the use of four independent sensors of various physical quantities as well as sophisticated methods of signal processing and data mining. The algorithm was implemented and tested in Matlab. It was based on the discrete wavelet transform and a support vectors machine. The source of the data was processed by the detector presented in [5, 6]. The device integrates four MEMS sensors. It includes an atmospheric pressure sensor and three triaxial sensors, such as an accelerometer, a gyroscope and a magnetometer. The signal from each of the available sensors was sampled at a frequency of 25 Hz. The processed and analyzed frame had the length of 100 samples, which equaled four-second registration. The scheme of the measurement system is shown in Figure 3. The obtained findings were the basis for the presentation of each sensor in the field of ROC curves in two variants (taking into account an extracted feature with the sign and with its omission). Definitely, better results were obtained using the absolute values of the descriptors in the process of learning/testing. The best results of fall detection were received for a gyroscope and an accelerometer, followed by a magnetometer and a barometric pressure sensor. From the studies one can draw a conclusion that the omission of the sign descriptors significantly improves the correct classification of falls. For this reason, in further work there will be adopted an algorithm using the absolute values of extracted features. During the study it was observed that the increase in the number of features used in learning and testing did not lead to the increase in the quality of classification. This calls for the selection of the optimum number of descriptors. Therefore, an important prerequisite to improve the efficiency of the system is a proper feature selection, which is the main objective of the next stage of investigations. In further research, we plan to implement the data fusion algorithm in order to increase the effectiveness of the mechanisms developed.
EN
The evaluation in technical invention is important because it tests functionality of the intervention and it forms an overall point of view of a user. This study aims to introduce an approach for collecting user expectations with Q methodology in Safe Private Home for Elderly Persons (CARE), which is a new development in ambient assisted living. CARE is a sophisticated fall detection system used in elderly homes to monitor elderly people and the staff. Expectations of elderly people and the staff were collected with Q sorting. Requirements of examined groups were explored successfully on the basis of the sorting and the differences in their opinions were appointed.
PL
Artykuł prezentuje algorytm do detekcji niekontrolowanych upadków człowieka. Wiele dostępnych rozwiązań bazuje na pojedynczych sensorach, a uzyskiwane rezultaty są zazwyczaj wynikiem implementacji algorytmów bazujących na progach, po przekroczeniu których uruchamiana jest procedura alarmowa. W odróżnieniu do takiego podejścia w artykule zaprezentowano i przebadano algorytm detekcji upadków bazujący na dekompozycji falkowej oraz liniowej sieci wektorów nośnych. Uzyskane wyniki dały w rezultacie poprawną klasyfikację wszystkich badanych zdarzeń upadków, z niewielką liczbą zgłaszanych fałszywych alarmów. Zaprezentowane badania są kontynuacja prac mających na celu opracowanie mobilnego detektora upadków.
EN
This article presents an algorithm for the detection of uncontrolled falls. Many of the available solutions are based on data from individual sensors. The results obtained through them are usually based on thresholds algorithms beyond which the alarm is triggered. In contrast to this approach, in this article falls detection algorithm based on wavelet decomposition and linear support vector machine has been presented and tested. The results have given the correct classification of all fall events, with a small number of false positives. The presented study is the continuation of the work to develop a mobile fall detector.
PL
Artykuł przedstawia nową metodę wykrywania zmian w położeniu ludzkiego ciała, w szczególności upadków, na podstawie sygnałów odczytywanych z czujników umieszczonych na monitorowanej osobie. Przekształcenie sekwencji danych zebranych z czujników pozwala odróżnić upadek od normalnego ruchu. Opracowana metoda może być stosowana w domowych systemach nadzoru i opieki telemedycznej.
EN
This paper presents new method to detect abrupt changes in the position of the human body, in particular falling, based on the signals acquired from sensors placed on the monitored person. The transformation of data sequence collected from sensors allows to distinguish between fall and normal movement. The method can be used in domestic telemedic systems.
12
Content available remote A solution to detect and prevent the falls of geriatric patients
EN
Advanced technologies are effectively used in healthcare applications. One of areas is support of taking care of older adults, which is a growing problem in contemporary societies. The research results in designing new systems and solutions, dedicated to solve particular problems or to cover the caretaking problem in general. Among such systems and solutions, the special ones are systems designed to help to solve the fall detection problem. In this paper, the review of such solutions is presented, advantages and disadvantages are discussed. The novel conception of such system is presented and discussed and conclusion is drawn.
PL
Ochrona zdrowia coraz efektywniej wykorzystuje rozwiązania, oparte na nowoczesnych technologiach. Jednym z obszarów ich stosowania są systemy wspierania opieki nad osobami starszymi, które to zagadnienie stanowi narastający problem współczesnych społeczeństw. Wyniki badań pozwalają na projektowanie różnorodnych systemów i urządzeń, zarówno przeznaczonych do rozwiązywania określonego problemu opieki, jak też wspierających cały proces. Pośród nich szczególną klasę stanowią rozwiązania przeznaczone do wspomagania nadzorowania możliwości wystąpienia upadku. W niniejszym artykule zaprezentowano przegląd istniejących rozwiązań w tej klasie i omówiono ich charakterystykę. Przedstawiono także nowatorską koncepcję systemu tej klasy.
PL
Co trzeci człowiek powyżej 65. roku życia przynajmniej raz do roku narażony jest na upadek [1, 2]. W roku 2002 z powodu upadków zmarło 391 tysięcy ludzi [1]. Upadki oraz urazy nimi spowodowane stanowią istotny problem zdrowia publicznego i często wymagają natychmiastowej pomocy medycznej. Bardzo szybka detekcja niekontrolowanego upadku pozwala na skrócenie czasu hospitalizacji, a przede wszystkim zmniejszenie potencjalnego ryzyka wystąpienia groźnych powikłań pourazowych. W niniejszym artykule zaprezentowano projekt bezprzewodowego urządzenia do detekcji niekontrolowanych upadków. Zaprojektowane urządzenie zaopatrzone jest w cztery sensory: żyroskop, akcelerometr, magnetometr oraz sensor ciśnienia. Dane z sensorów przetwarzane są w mikrokontrolerze, który w pierwszym etapie dokonuje operacji związanych z fuzją i integracją danych. Następnie w module decyzyjno-wnioskującym podejmowana jest decyzja o detekcji upadku i wyzwoleniu procedury alarmowej. Zgłoszenie alarmu odbywa się za pośrednictwem sieci bezprzewodowej, umożliwiającej podłączenie urządzenia do integratora sensorycznego, którym może być np. telefon komórkowy z dedykowaną aplikacją.
EN
At least once a year every third person over 65 years of age is exposed to a fall [1, 2]. 391,000 people died due to falls in 2002 [1]. Falls and injuries caused by them are an important public health problem and often require immediate medical attention. Very fast detection of uncontrolled falls shortens the duration of hospitalization and reduces the potential risk of serious complications of injuries. This paper presents the design of a wireless device for the detection of uncontrolled falls. The device consists of four sensors: a gyroscope, an accelerometer, a magnetometer, and a pressure sensor. Data from the sensors are processed in the microcontroller, which performs the operations of data fusion and integration. The decision about the fall detection is made in the next step and if it is needed, it triggers an alarm. Alarm notification is sent via wireless network. The device can be connected to the sensor integrator, i.e. a mobile phone with the dedicated application, which can call for help.
EN
This paper presents a new method for detection of changes in alignment of the human body, particularly the fall, on the basis of signals acquired from the position sensors placed on the body of the monitored person. The sensors are located on the cuffs, waist and chest. Transformation of data sequence collected from sensors is proposed in order to best distinguish between the collapse from the normal movement. It is based on nonlinear combination of the first two derivatives of the signals being read. Because data from the sensors is sent asynchronously, a numerical algorithm for unevenly sampled data differentiation is proposed. Derivative values are calculated in equidistant nodes through differentiation of a polynomial, which is adjusted by minimizing the mean square error. The developed method can be used in home care telemedicine systems, where it is necessary to long term monitor of multiple vital parameters of people under care.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.