2017
DOI: 10.3390/s18010020
|View full text |Cite
|
Sign up to set email alerts
|

An Event-Triggered Machine Learning Approach for Accelerometer-Based Fall Detection

Abstract: The fixed-size non-overlapping sliding window (FNSW) and fixed-size overlapping sliding window (FOSW) approaches are the most commonly used data-segmentation techniques in machine learning-based fall detection using accelerometer sensors. However, these techniques do not segment by fall stages (pre-impact, impact, and post-impact) and thus useful information is lost, which may reduce the detection rate of the classifier. Aligning the segment with the fall stage is difficult, as the segment size varies. We prop… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
68
1
2

Year Published

2018
2018
2022
2022

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 88 publications
(72 citation statements)
references
References 40 publications
1
68
1
2
Order By: Relevance
“…In any case, the obtained results (with both specificity and sensitivity near 99%) were better than those published by other studies on FDS that employed the same SisFall dataset as a benchmarking tool [36,52,56,68,69] and in which a specificity and a sensitivity superior to 0.98 were not attained simultaneously.…”
Section: Numerical Resultscontrasting
confidence: 56%
“…In any case, the obtained results (with both specificity and sensitivity near 99%) were better than those published by other studies on FDS that employed the same SisFall dataset as a benchmarking tool [36,52,56,68,69] and in which a specificity and a sensitivity superior to 0.98 were not attained simultaneously.…”
Section: Numerical Resultscontrasting
confidence: 56%
“…Nevertheless, the proposal yields better results (with values for the specificity and the sensitivity around 99%) than those achieved by other works in the literature that use the same SisFall repository as the benchmarking tool [16,103,[109][110][111]. Similarly, our system also outperforms the FDS based on a Recurrent Neural Networks (RNNs) analyzed in [112], which is tested with three different datasets.…”
Section: Number Of Filters In Each Layermentioning
confidence: 75%
“…В работе [30] представлен алгоритм обнаружения падения человека. Этот алгоритм извлекает признаки только в том случае, если человек находится в активном состоянии.…”
Section: безопасностьunclassified