FallAllD: An Open Dataset of Human Falls and Activities of Daily Living for Classical and Deep Learning Applications

Saleh, Majd; Abbas, Manuel; Jeannes, Regine Bouquin Le

doi:10.1109/jsen.2020.3018335

Cited by 73 publications

(92 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Thresholdbased algorithms are less sensitive to the sampling frequency since their working principle is usually based on a single frame of data, not multiple frames. Even for post-fall detection, Saleh et al (2021) found that the detection accuracy was always improved by increasing the sensor sampling frequency from 20 to 40 Hz in three different sensor locations. In this study, KFall with a sensor sampling frequency of 100 Hz achieved promising accuracy and lead time in three benchmark algorithms, which also provides some flexibility for interested readers to evaluate the performance of different algorithms if downsampling is required.…”

Section: Discussionmentioning

confidence: 96%

“…Compared with the existing public fall datasets (Casilari et al, 2017a;Saleh et al, 2021) in the literature, the biggest advantage of the KFall dataset is that it is constructed with the synchronized video reference and motion sensor data. This enables accurate temporal labels for the fall time and allows the dataset to be further used for pre-impact fall detection, not just post-fall detection.…”

Section: Discussionmentioning

confidence: 99%

“…(2) the dataset should include various types of falls and ADLs with a sufficient number of subjects; (3) sensor orientation measurement should also be provided, which allows more flexibility to the interested researchers when designing their algorithms; and (4) the sampling frequency and measurement range of the inertial sensor should be sufficient (Saleh et al, 2021).…”

Section: Kfall Dataset Constructionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Discussionmentioning

confidence: 96%

Section: Discussionmentioning

confidence: 99%

Section: Kfall Dataset Constructionmentioning

confidence: 99%

See 1 more Smart Citation

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

show abstract

“…Three publicly available datasets that contain acceleration measurements of falls and ADL were used in this research: ErciyesUni [ 17 ], FallAllD [ 31 ], and SisFall [ 32 ]. For all three datasets, young subjects performed a variety of simulated falls and ADL in a controlled environment while wearing accelerometer sensors attached to different body parts.…”

Section: Methodsmentioning

confidence: 99%

Event-Centered Data Segmentation in Accelerometer-Based Fall Detection Algorithms

Šeketa

Pavlaković

Džaja

et al. 2021

Sensors

View full text Add to dashboard Cite

Automatic fall detection systems ensure that elderly people get prompt assistance after experiencing a fall. Fall detection systems based on accelerometer measurements are widely used because of their portability and low cost. However, the ability of these systems to differentiate falls from Activities of Daily Living (ADL) is still not acceptable for everyday usage at a large scale. More work is still needed to raise the performance of these systems. In our research, we explored an essential but often neglected part of accelerometer-based fall detection systems—data segmentation. The aim of our work was to explore how different configurations of windows for data segmentation affect detection accuracy of a fall detection system and to find the best-performing configuration. For this purpose, we designed a testing environment for fall detection based on a Support Vector Machine (SVM) classifier and evaluated the influence of the number and duration of segmentation windows on the overall detection accuracy. Thereby, an event-centered approach for data segmentation was used, where windows are set relative to a potential fall event detected in the input data. Fall and ADL data records from three publicly available datasets were utilized for the test. We found that a configuration of three sequential windows (pre-impact, impact, and post-impact) provided the highest detection accuracy on all three datasets. The best results were obtained when either a 0.5 s or a 1 s long impact window was used, combined with pre- and post-impact windows of 3.5 s or 3.75 s.

show abstract

“…Various machine learning (ML) techniques [12] have been applied to improve the detection performance of the typical FD systems [25] as they mainly rely on human knowledge to build rule-based FD classifiers, including k-nearest-neighbors and support vector machines. Furthermore, the advanced deep learning (DL) techniques have shown superiority in the detection ability, such as convolutional neural networks and long short-term memory [26]. However, previous works [19,20] have reported the performance of ML-based FD systems is sensitive to the sampling rates.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Signal Enhancement of Low-Resolution Accelerometer for Fall Detection Systems

Liu

Hung

Hsieh

et al. 2022

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

In the last two decades, fall detection (FD) systems have been developed as a popular assistive technology. To support long-term FD services, various power-saving strategies have been implemented. Among them, a reduced sampling rate is a common approach for an energy-efficient system in the real world. However, the performance of FD systems is diminished owing to low-resolution (LR) accelerometer signals. To improve the detection accuracy with LR accelerometer signals, several technical challenges must be considered, including mismatch of effective features and the degradation effects. In this work, a deeplearning-based accelerometer signal enhancement (ASE) model is proposed as a front-end processor to help typical LR-FD systems achieve better detection performance. The proposed ASE model based on a deep denoising convolutional autoencoder architecture reconstructs high-resolution (HR) signals from the LR signals by learning the relationship between the LR and HR signals. The results show that the FD system using support vector machine and the proposed ASE model at an extremely low sampling rate (sampling rate < 2 Hz) achieved 97.34% and 90.52% accuracies in the SisFall and FallAllD datasets, respectively, while those without ASE models only achieved 95.92% and 87.47% accuracies in the SisFall and FallAllD datasets, respectively. The results also demonstrate that the proposed ASE mode can be suitably combined with deep-learning-based FD systems.

show abstract

FallAllD: An Open Dataset of Human Falls and Activities of Daily Living for Classical and Deep Learning Applications

Cited by 73 publications

References 19 publications

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

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

Event-Centered Data Segmentation in Accelerometer-Based Fall Detection Algorithms

Deep-Learning-Based Signal Enhancement of Low-Resolution Accelerometer for Fall Detection Systems

Contact Info

Product

Resources

About