Article

Evaluation of accelerometer-based fall detection algorithms on real-world falls.

Department of Electronics, Computer Science and Systems, University of Bologna, Bologna, Italy.
PLoS ONE (Impact Factor: 3.73). 01/2012; 7(5):e37062. DOI: 10.1371/journal.pone.0037062
Source: PubMed

ABSTRACT Despite extensive preventive efforts, falls continue to be a major source of morbidity and mortality among elderly. Real-time detection of falls and their urgent communication to a telecare center may enable rapid medical assistance, thus increasing the sense of security of the elderly and reducing some of the negative consequences of falls. Many different approaches have been explored to automatically detect a fall using inertial sensors. Although previously published algorithms report high sensitivity (SE) and high specificity (SP), they have usually been tested on simulated falls performed by healthy volunteers. We recently collected acceleration data during a number of real-world falls among a patient population with a high-fall-risk as part of the SensAction-AAL European project. The aim of the present study is to benchmark the performance of thirteen published fall-detection algorithms when they are applied to the database of 29 real-world falls. To the best of our knowledge, this is the first systematic comparison of fall detection algorithms tested on real-world falls. We found that the SP average of the thirteen algorithms, was (mean ± std) 83.0% ± 30.3% (maximum value = 98%). The SE was considerably lower (SE = 57.0% ± 27.3%, maximum value = 82.8%), much lower than the values obtained on simulated falls. The number of false alarms generated by the algorithms during 1-day monitoring of three representative fallers ranged from 3 to 85. The factors that affect the performance of the published algorithms, when they are applied to the real-world falls, are also discussed. These findings indicate the importance of testing fall-detection algorithms in real-life conditions in order to produce more effective automated alarm systems with higher acceptance. Further, the present results support the idea that a large, shared real-world fall database could, potentially, provide an enhanced understanding of the fall process and the information needed to design and evaluate a high-performance fall detector.

0 Bookmarks
 · 
183 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: With the progress of technologies of recent years, methods have become available that use wearable sensors and ambulatory systems to measure aspects of - particular axial - motor function. As Parkinson's disease (PD) can be considered a model disorder for motor impairment, a significant number of studies have already been performed with these patients using such techniques. In general, motion sensors such as accelerometers and gyroscopes are used, in combination with lightweight electronics that do not interfere with normal human motion. A fundamental advantage in comparison with usual clinical assessment is that these sensors allow a more quantitative, objective, and reliable evaluation of symptoms; they have also significant advantages compared to in-lab technologies (e.g., optoelectronic motion capture) as they allow long-term monitoring under real-life conditions. In addition, based on recent findings particularly from studies using functional imaging, we learned that non-motor symptoms, specifically cognitive aspects, may be at least indirectly assessable. It is hypothesized that ambulatory quantitative assessment strategies will allow users, clinicians, and scientists in the future to gain more quantitative, unobtrusive, and everyday relevant data out of their clinical evaluation and can also be designed as pervasive (everywhere) and intensive (anytime) tools for ambulatory assessment and even rehabilitation of motor and (partly) non-motor symptoms in PD.
    Acta Neurologica Scandinavica 04/2014; · 2.47 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a multimodal system for seamless surveillance of elderly people in their living environment. The system uses simultaneously a wearable sensor network for each individual and premise-embedded sensors specific for each environment. The paper demonstrates the benefits of using complementary information from two types of mobility sensors: visual flow-based image analysis and an accelerometer-based wearable network. The paper provides results for indoor recognition of several elementary poses and outdoor recognition of complex movements. Instead of complete system description, particular attention was drawn to a polar histogram-based method of visual pose recognition, complementary use and synchronization of the data from wearable and premise-embedded networks and an automatic danger detection algorithm driven by two premise- and subject-related databases. The novelty of our approach also consists in feeding the databases with real-life recordings from the subject, and in using the dynamic time-warping algorithm for measurements of distance between actions represented as elementary poses in behavioral records. The main results of testing our method include: 95.5% accuracy of elementary pose recognition by the video system, 96.7% accuracy of elementary pose recognition by the accelerometer-based system, 98.9% accuracy of elementary pose recognition by the combined accelerometer and video-based system, and 80% accuracy of complex outdoor activity recognition by the accelerometer-based wearable system.
    Sensors 01/2014; 14(5):7831-7856. · 2.05 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Falls are a common source of serious injury for elderly people. The harm can be mitigated by using a fall detector. However they are far from ideal and produce a large number of false alarms for every real fall detected. This paper describes an experiment to examine whether the reliability of fall detectors might be improved by using photoplethysmography, which evaluates heart rate and blood flow in microvascular tissue, to make inferences about the body position. The results show a correlation between body position and pulse shape. However the effect is small and is of similar size to the effect of the position of the arm on which the sensor is mounted. Further work is needed to better under-stand how arm position affects pulse shape and the extent to which these results may be applicable to elderly people.
    7th International Conference on PErvasive Technologies Related to Assistive Environments; 05/2014

Full-text (2 Sources)

View
70 Downloads
Available from
May 21, 2014