Enhanced Algorithm for the Detection of Preimpact Fall for Wearable Airbags

Jung, Haneul; Koo, Bummo; Kim, Jong Man; Kim, Tae-Hee; Nam, Yejin; Kim, Young‐Ho

doi:10.3390/s20051277

Cited by 28 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While some studies extracted handcrafted features and constructed fixed-threshold algorithms for real-world use, Jung et al [ 17 ] obtained 100% sensitivity, 97.54% specificity, and 98.33% accuracy on their private dataset, and achieved relatively high performance in comparison to some similar studies on the SisFall dataset. However, as shown in Table 1 , when evaluating Jung’s algorithm with our experimental data, 87.16% accuracy and 77.36% specificity were achieved, due to the diversity of individuals, behaviors, and environments.…”

Section: Discussionmentioning

confidence: 99%

Pre-Impact Fall Detection with CNN-Based Class Activation Mapping Method

Shi

Chen

Wang

2020

Sensors

View full text Add to dashboard Cite

In this paper, we report our improvement on the prediction accuracy of pre-impact fall detection by applying a learning-based method on the real-time data from an IMU (inertial measurement unit)-sensor mounted on the waist, making it possible to achieve a high accuracy on a wearable device with the extracted features. Using the fixed threshold method is difficult for achieving satisfactory detection accuracy, due to various characteristics and behaviors in the movement of different individuals. In contrast, one could realize high-accuracy detection with machine learning-based methods, but it is difficult to apply them in the wearable devices due to the high hardware requirement. Our method merges the two methods above. We build a convolutional neural network (CNN) with a class activation mapping (CAM) method, which could highlight the class-specific region in the data and obtain a hot map of the fall data. After training on the MobiAct dataset, the model could achieve high-accuracy detection (95.55%) and obtain the region with high contributions to the classification. Then, we manually extract effective features and characteristics of this region and form our special threshold method, achieving pre-impact fall detection in real-world data. Consequently, our method achieves accuracy of 95.33% and a detection time of within 400 ms.

show abstract

Section: Discussionmentioning

confidence: 99%

Pre-Impact Fall Detection with CNN-Based Class Activation Mapping Method

Shi

Chen

Wang

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The VA was calculated using a complementary filter with a PI controller [ 34 ] to minimize integration errors and the effect of external impacts. Figure 5 shows the flowchart of a complementary filter with the PI controller.…”

Section: Methodsmentioning

confidence: 99%

“…Their algorithm achieved 100% sensitivity, three false alarms (the number of non-falls detected as falls), and a lead time of over 70 ms. Nyan et al [ 32 ] also developed a threshold-based pre-impact fall detection algorithm using angles calculated from the torso and thigh (with two IMUs), as well as the correlation coefficients of the torso and thigh angles. The algorithm achieved 100% specificity, 95.2% specificity, and a lead time of 700 ms. Sabatini et al [ 33 ] estimated the vertical velocity and height change using an IMU with a barometric altimeter to detect fall and achieved 80% sensitivity, 100% specificity, and an average lead time of 157 ms. Jung et al [ 34 ] performed experiments on 30 healthy young males and obtained inertial data from the back waist. A fall detection algorithm was developed using acceleration RMS, angular velocity RMS, and vertical angle (VA).…”

Section: Introductionmentioning

confidence: 99%

Detection of Pre-Impact Falls from Heights Using an Inertial Measurement Unit Sensor

Kim

Jung

Koo

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Many safety accidents can occur in industrial sites. Among them, falls from heights (FFHs) are the most frequent accidents and have the highest fatality rate. Therefore, some existing studies have developed personal wearable airbags to mitigate the damage caused by FFHs. To utilize these airbags effectively, it is essential to detect FFHs before collision with the floor. In this study, an inertial measurement unit (IMU) sensor attached to the seventh thoracic vertebrae (T7) was used to develop an FFH detection algorithm. The vertical angle and vertical velocity were calculated using the inertial data obtained from the IMU sensor. Forty young and healthy males were recruited to perform non-FFH and FFH motions. In addition, experiments using a human mannequin and dynamics simulations were performed to obtain FFH data at heights above 2 m. The developed algorithm achieved 100% FFH detection accuracy and provided sufficient lead time such that the airbags could be inflated completely before collision with the floor.

show abstract

“…In recent years, researchers have begun to shift their focus from post-fall detection to pre-impact fall detection and shed some light on this topic. Jung et al (2020) developed a threshold-based algorithm, which combined multiple thresholds (magnitude of acceleration, magnitude of angular velocity, and vertical angle) based on inertial sensors for pre-impact fall detection and achieved 100% sensitivity and 97.54% specificity with an average lead time of 280 ms. This algorithm was developed based on their own simulated dataset with six types of falls and 14 types of activities of daily living (ADLs) by 30 young subjects.…”

Section: Introductionmentioning

confidence: 99%

“…This poses a challenge to fairly evaluate the performance of different algorithms on a common basis and their generalizability to different datasets. A few preliminary studies showed that algorithms based on a specific database with good performance had poor external validity on other databases (Sabatini et al, 2015;Jung et al, 2020). For instance, when Jung et al (2020) applied their thresholds to the SisFall dataset (Sucerquia et al, 2017), both sensitivity and specificity dropped considerably by 4 and 7%, respectively.…”

Section: Introductionmentioning

confidence: 99%

A Large-Scale Open Motion Dataset (KFall) and Benchmark Algorithms for Detecting Pre-impact Fall of the Elderly Using Wearable Inertial Sensors

Jang

Xiong

2021

Front. Aging Neurosci.

View full text Add to dashboard Cite

Research on pre-impact fall detection with wearable inertial sensors (detecting fall accidents prior to body-ground impacts) has grown rapidly in the past decade due to its great potential for developing an on-demand fall-related injury prevention system. However, most researchers use their own datasets to develop fall detection algorithms and rarely make these datasets publicly available, which poses a challenge to fairly evaluate the performance of different algorithms on a common basis. Even though some open datasets have been established recently, most of them are impractical for pre-impact fall detection due to the lack of temporal labels for fall time and limited types of motions. In order to overcome these limitations, in this study, we proposed and publicly provided a large-scale motion dataset called “KFall,” which was developed from 32 Korean participants while wearing an inertial sensor on the low back and performing 21 types of activities of daily living and 15 types of simulated falls. In addition, ready-to-use temporal labels of the fall time based on synchronized motion videos were published along with the dataset. Those enhancements make KFall the first public dataset suitable for pre-impact fall detection, not just for post-fall detection. Importantly, we have also developed three different types of latest algorithms (threshold based, support-vector machine, and deep learning), using the KFall dataset for pre-impact fall detection so that researchers and practitioners can flexibly choose the corresponding algorithm. Deep learning algorithm achieved both high overall accuracy and balanced sensitivity (99.32%) and specificity (99.01%) for pre-impact fall detection. Support vector machine also demonstrated a good performance with a sensitivity of 99.77% and specificity of 94.87%. However, the threshold-based algorithm showed relatively poor results, especially the specificity (83.43%) was much lower than the sensitivity (95.50%). The performance of these algorithms could be regarded as a benchmark for further development of better algorithms with this new dataset. This large-scale motion dataset and benchmark algorithms could provide researchers and practitioners with valuable data and references to develop new technologies and strategies for pre-impact fall detection and proactive injury prevention for the elderly.

show abstract

Enhanced Algorithm for the Detection of Preimpact Fall for Wearable Airbags

Cited by 28 publications

References 30 publications

Pre-Impact Fall Detection with CNN-Based Class Activation Mapping Method

Pre-Impact Fall Detection with CNN-Based Class Activation Mapping Method

Detection of Pre-Impact Falls from Heights Using an Inertial Measurement Unit Sensor

A Large-Scale Open Motion Dataset (KFall) and Benchmark Algorithms for Detecting Pre-impact Fall of the Elderly Using Wearable Inertial Sensors

Contact Info

Product

Resources

About