Pre-impact and Impact Detection of Falls Using Built-In Tri-accelerometer of Smartphone

Mao, Liyu; Ding, Lixin; Ning, Yunkun; Ma, Yingnan; Gao, Xing; Zhao, Guoru

doi:10.1007/978-3-319-06269-3_18

Cited by 12 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… The best results are always achieved when the detection algorithm employs the acceleration measurements captured on the chest (or trunk) or waist, the two points that are closest to the gravity center of the human body. This conclusion is coherent with the results of previous works [ 17 , 33 , 61 , 62 , 63 , 64 , 65 , 66 ] that compared the performance of the FDS when operating on two or more positions. In this regard, we cannot forget that ergonomics is a key aspect in the design of any wearable system.…”

Section: Resultssupporting

confidence: 91%

Analysis of a Smartphone-Based Architecture with Multiple Mobility Sensors for Fall Detection with Supervised Learning

Santoyo-Ramón

Casilari

Cano-García

2018

Sensors

View full text Add to dashboard Cite

This paper describes a wearable Fall Detection System (FDS) based on a body-area network consisting of four nodes provided with inertial sensors and Bluetooth wireless interfaces. The signals captured by the nodes are sent to a smartphone which simultaneously acts as another sensing point. In contrast to many FDSs proposed by the literature (which only consider a single sensor), the multisensory nature of the prototype is utilized to investigate the impact of the number and the positions of the sensors on the effectiveness of the production of the fall detection decision. In particular, the study assesses the capability of four popular machine learning algorithms to discriminate the dynamics of the Activities of Daily Living (ADLs) and falls generated by a set of experimental subjects, when the combined use of the sensors located on different parts of the body is considered. Prior to this, the election of the statistics that optimize the characterization of the acceleration signals and the efficacy of the FDS is also investigated. As another important methodological novelty in this field, the statistical significance of all the results (an aspect which is usually neglected by other works) is validated by an analysis of variance (ANOVA).

show abstract

Section: Resultssupporting

confidence: 91%

Analysis of a Smartphone-Based Architecture with Multiple Mobility Sensors for Fall Detection with Supervised Learning

Santoyo-Ramón

Casilari

Cano-García

2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Mao et al [8] and Aguiar et al [9] proposed a fall detection system based on smartphones, which enables detection and early fall warning depending on the pre-impact and post-fall phase based on the impact phase. However, those only flags an event that already occurred.…”

Section: Introductionmentioning

confidence: 99%

Accelerometry data analysis for identification of fallers using the six-minute walk test

Bet

Castro

Chagas

et al. 2019

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Background Methods for faller classification and gait patterns using portable and reliable equipment are still a challenge when considered an active and healthy aging population, in particular for large-scale applications. In this study, we investigated the patterns that could identify elderly faller by means of the acceleration gait data. Method Gait frequency pattern study of active older than 60 years participants divided into three groups according to the fall history in the last year: 10 non-fallers, 10 sporadic fallers and 10 recurrent fallers. The subjects performed 6MWT, with a triaxial accelerometer allocated at the waist, with 200 Hz sampling rate. Magnitude information was extracted to analyze the acceleration curves. The comparison between the groups was performed through the chi-squared test, ANOVA and Kruskal-Wallis test. Results Average age of the participants was 75.13±6.37 years (76.6% women). While it was not possible to differentiate fallers through the 6MWT, statistical differences were found in variables extracted from segmented acceleration curves. The first and third largest frequency amplitudes measured when participants are turning during the test showed discriminative capability between sporadic fallers and the other groups (p=0.018; 0.014, respectively). Statistical difference was found also from the difference between the maximum magnitude in frequency of the complete signal in relation to the turning movement between recurrent fallers and the remaining groups (p=0.035), while the third main frequency magnitude difference between walking and turning showed significant difference between sporadic fallers and the others (p=0.030). The best result considering ROC analysis achieved AUC of 0.807, sensitivity of 0.80 and specificity of 0.75. Conclusion and Relevance Frequency features extracted from the combination of the accelerometer and the test can contribute to clinical practice and to scientific area, providing a low-cost diagnosis with a wearable sensor, allowing large-scale applications. Considering specific gait events are important for this task since our results indicate there is more discriminative capability when comparing the turning movement with other gait patterns.

show abstract

“…Wearable biomedical tri-axial accelerometerbased fall detection devices transmit monitored data to a base station receiver for signal processing and fall detection. Accelerometer-based fall detection systems frequently detect fall occurrences through thresholding a parameter, such as absolute acceleration magnitude [13] or wavelet acceleration sum-vector [14] against an arbitrary value. This arbitrary threshold value within literature is frequently determined from analysis of preknown user-sepcific fall signals [15], where accuracy and false positives are significant issues [16].…”

Section: Introductionmentioning

confidence: 99%

Matching pursuit-based compressive sensing in a wearable biomedical accelerometer fall diagnosis device

Gibson

Amira

Ramzan

et al. 2017

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

There is a significant high fall risk population, where individuals are susceptible to frequent falls and obtaining significant injury, where quick medical response and fall information are critical to providing efficient aid. This article presents an evaluation of compressive sensing techniques in an accelerometer-based intelligent fall detection system modelled on a wearable Shimmer biomedical embedded computing device with Matlab. The presented fall detection system utilises a database of fall and activities of daily living signals evaluated with discrete wavelet transforms and principal component analysis to obtain binary tree classifiers for fall evaluation. 14 test subjects undertook various fall and activities of daily living experiments with a Shimmer device to generate data for principal component analysis-based fall classifiers and evaluate the proposed fall analysis system. The presented system obtains highly accurate fall detection results, demonstrating significant advantages in comparison with the thresholding method presented. Additionally, the presented approach offers advantageous fall diagnostic information. Furthermore, transmitted data accounts for over 80% battery current usage of the Shimmer device, hence it is critical the acceleration data is reduced to increase transmission efficiency and in-turn improve

show abstract

Pre-impact and Impact Detection of Falls Using Built-In Tri-accelerometer of Smartphone

Cited by 12 publications

References 14 publications

Analysis of a Smartphone-Based Architecture with Multiple Mobility Sensors for Fall Detection with Supervised Learning

Analysis of a Smartphone-Based Architecture with Multiple Mobility Sensors for Fall Detection with Supervised Learning

Accelerometry data analysis for identification of fallers using the six-minute walk test

Matching pursuit-based compressive sensing in a wearable biomedical accelerometer fall diagnosis device

Contact Info

Product

Resources

About