Pre-impact Fall Research Articles

Unveiling Fall Origins: Leveraging Wearable Sensors to Detect Pre-Impact Fall Causes

Unveiling Fall Origins: Leveraging Wearable Sensors to Detect Pre-Impact Fall Causes

A novel semi-supervised model for pre-impact fall detection with limited fall data

Due to the high prevalence and severe consequences of falls among older people, pre-impact fall detection algorithms which aim to detect falls before body-ground impacts are of critical importance. The success of existing algorithms based on wearable sensors relies heavily on numerous labeled data from both falls and activities of daily living (ADLs). However, fall data is much more difficult to acquire compared with ADLs, and moreover, labeling falling period apart from ADLs is laborious and time-consuming. To this end, we proposed a novel semi-supervised model for pre-impact fall detection, called Semi-PFD, which maximizes the utilization of easily obtainable ADL data and reduces the dependency on labeled fall data. This model was evaluated on two large-scale public fall datasets (KFall and SisFall) and compared with its supervised baseline under different ratios of fall data. Cross-validation results showed that Semi-PFD outperformed the supervised baseline across all conditions on both datasets. More importantly, Semi-PFD achieved considerable improvement of 2–4% F1-score when the ratios of fall data were low (≤23.1%). Remarkably, with only 76.9% of fall data, Semi-PFD achieved comparable and even higher F1-scores than the state-of-the-art benchmark models which utilized 100% of fall data. We further observed that the incorporation of unsupervised training in Semi-PFD mitigated the typical overconfidence problem associated with supervised training without affecting lead time. These findings underscore Semi-PFD's practical potential, reducing the burden of fall data collection and labeling while maintaining superior performance.

Analyzing and Comparing Deep Learning Models on an ARM 32 Bits Microcontroller for Pre-Impact Fall Detection

Analyzing and Comparing Deep Learning Models on an ARM 32 Bits Microcontroller for Pre-Impact Fall Detection

TinyFallNet: A Lightweight Pre-Impact Fall Detection Model.

Falls represent a significant health concern for the elderly. While studies on deep learning-based preimpact fall detection have been conducted to mitigate fall-related injuries, additional efforts are needed for embedding in microcomputer units (MCUs). In this study, ConvLSTM, the state-of-the-art model, was benchmarked, and we attempted to lightweight it by leveraging features from image-classification models VGGNet and ResNet while maintaining performance for wearable airbags. The models were developed and evaluated using data from young subjects in the KFall public dataset based on an inertial measurement unit (IMU), leading to the proposal of TinyFallNet based on ResNet. Despite exhibiting higher accuracy (97.37% < 98.00%) than the benchmarked ConvLSTM, the proposed model requires lower memory (1.58 MB > 0.70 MB). Additionally, data on the elderly from the fall data of the FARSEEING dataset and activities of daily living (ADLs) data of the KFall dataset were analyzed for algorithm validation. This study demonstrated the applicability of image-classification models to preimpact fall detection using IMU and showed that additional tuning for lightweighting is possible due to the different data types. This research is expected to contribute to the lightweighting of deep learning models based on IMU and the development of applications based on IMU data.

Pre-Impact Firefighter Fall Detection Using Machine Learning on the Edge

Falling is one of the primary causes of firefighter casualties. Therefore, early fall detection, followed by reliable and timely notification, is vital to ensure the survival of firefighters. However, due to complex and diverse firefighting scenarios, current fall detection systems are inadequate, especially in terms of accuracy and real-time applications. Hence, in this study, a wearable pre-impact fall detection system for firefighters is proposed. We also evaluated the feasibility of using machine learning and ensemble learning methods deployed on the edge node to simultaneously improve the real-time performance and accuracy. Moving thresholding method is introduced to overcome the class-imbalanced issue due to fewer samples acquired during the pre-impact phase. Based on 14 firefighters’ data collection, the experimental results revealed that a Decision Tree classifier with optimized parameters (DT-ED4) outperformed other machine learning and ensemble learning methods in a trade-off between processing time and accuracy. The results also showed that our system can detect falls before the impact with an average lead time of 447.9 ms, sensitivity of 95.10%, and specificity of 97.99%. The system’s heterogeneous IoT network architecture facilitated remote monitoring and alerts that enabled the incident commander to execute the rescue mission immediately upon notification. This study enhances the practicability of PIFDS and extends the application range of PIFDS from health-care to firefighting.

Comparison of four machine learning algorithms for a pre-impact fall detection system.

In recent years, real-time health monitoring using wearable sensors has been an active area of research. This paper presents an efficient and low-cost fall detection system based on a pair of shoes equipped with inertial sensors and plantar pressure sensors. In addition, four machine learning algorithms (KNN, SVM, RF, and BP neural network) are compared in terms of their detection performance and suitability for pre-impact fall detection. The results show that KNN and BP neural network outperformed the other two algorithms, where KNN had 98.8% sensitivity, 99.8% specificity, and 99.7% accuracy, and BP neural network had 100% sensitivity, 99.8% specificity, and 99.9% accuracy. KNN outperformed BP neural network in terms of fitting ability, and their lead times were both 460.95ms. The system can provide sufficient intervention time for the wearer in the pre-impact phase and together with the touchdown fall protection device can effectively prevent fall injuries.

Data Augmentation to Address Various Rotation Errors of Wearable Sensors for Robust Pre-impact Fall Detection.

This paper proposes a novel application of data augmentation to address various rotation errors of wearable sensors for robust pre-impact fall detection. In such systems, sensor rotation errors are inevitable because of loose attachment and body movement during long deployment. Two augmented models with uniform and normal strategies were compared with a non-augmented model on the original dataset (no rotation error) and a validation dataset (with rotation error). The validation dataset was constructed with three types of rotation errors, namely, pitch, roll, and compound roll and pitch (CRP) at three levels of range (low: 15°, medium: 30°, and high: 45°). Five-fold cross validation showed the two augmented models maintained accuracy (>98.5%) as high as the non-augmented model on the original dataset but showed considerable improvements of 6.11% and 6.50% on the validation dataset, respectively. CRP error negatively affected the model accuracy the most, followed by pitch and then roll errors. In addition, the normal model had advantages over the uniform model in the low-to-medium range of error, which is expected to be the typical error range in practical applications. As for lead time, similarly, the augmented models achieved performance similar to the non-augmented model on the original dataset but showed significant improvements on the validation dataset. Data augmentation had notable capacities to address sensor rotation errors for practical applications and augmented models especially the normal model showed good potential to be embedded in a wearable system for robust pre-impact fall detection and injury prevention.

Pre-Impact and Impact Fall Detection Based on a Multimodal Sensor Using a Deep Residual Network

Falls are the contributing factor to both fatal and nonfatal injuries in the elderly. Therefore, pre-impact fall detection, which identifies a fall before the body collides with the floor, would be essential. Recently, researchers have turned their attention from post-impact fall detection to pre-impact fall detection. Pre-impact fall detection solutions typically use either a threshold-based or machine learning-based approach, although the threshold value would be difficult to accurately determine in threshold-based methods. Moreover, while additional features could sometimes assist in categorizing falls and non-falls more precisely, the estimated determination of the significant features would be too time-intensive, thus using a significant portion of the algorithm’s operating time. In this work, we developed a deep residual network with aggregation transformation called FDSNeXt for a pre-impact fall detection approach employing wearable inertial sensors. The proposed network was introduced to address the limitations of feature extraction, threshold definition, and algorithm complexity. After training on a large-scale motion dataset, the KFall dataset, and straightforward evaluation with standard metrics, the proposed approach identified pre-impact and impact falls with high accuracy of 91.87 and 92.52%, respectively. In addition, we have investigated fall detection’s performances of three state-of-the-art deep learning models such as a convolutional neural network (CNN), a long short-term memory neural network (LSTM), and a hybrid model (CNN-LSTM). The experimental results showed that the proposed FDSNeXt model outperformed these deep learning models (CNN, LSTM, and CNN-LSTM) with significant improvements.

A Novel Feature Extraction Method for Preimpact Fall Detection System Using Deep Learning and Wearable Sensors

Fall detection and prevention are crucial in elderly healthcare and humanoid robotic research as they help mitigate the damaging after-effects of falls. In this work, we have presented a deep-learning-based preimpact fall detection system (FDS) that detects a fall within 0.5 s of the fall initiation phase, thus providing a sufficient lead time of 0.5 s which is far better than the state-of-the-art. To achieve this, we have developed an automatic feature extraction methodology that can extract temporal features from all types of human fall data collected using wearable sensors. A deep neural classifier based on the ensemble of convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) is trained on the extracted temporal features. The classifier has performed exceptionally well in detecting the Fall Initiation phase with a sensitivity of 99.24% and an F1-score of 98.79% for different types of falls. A sensitivity of 99.24% signifies that the model has sufficiently reduced the occurrence of false negatives, which is far more critical for an FDS. A concept of a transitional window is introduced to improve the reaction time of the FDS. We utilized two standard fall datasets, viz. SisFall and KFall, for the experimentation. Dataset fusion is employed to increase the generalizability of the system. This work can be utilized to design and develop fall detection devices for the Internet-of-Healthcare-Things applications (IoHT) and for imparting fall detection capabilities to humanoid robots and gait rehabilitation devices such as exoskeleton robots and smart prosthetic legs.

The Pre-impact Fall Detection using the quantization based on ResNet

The Pre-impact Fall Detection using the quantization based on ResNet

A pre-impact fall detection data segmentation method based on multi-channel convolutional neural network and class activation mapping

Objective. A segmentation method for pre-impact fall detection data is investigated. Specifically, it studies how to partition data segments that are important for classification from continuous inertial sensor data for pre-impact fall detection. Approach. In this study, a trigger-based algorithm combining multi-channel convolutional neural network (CNN) and class activation mapping was proposed to solve the problem of data segmentation. First, a pre-impact fall detection training dataset was established and divided into two parts. For falls, the 1 s data was divided from the peak value of the acceleration signal magnitude vector to the starting direction. For activities of daily living, the cycle segmentation was performed for a 1 s window size. Second, a heat map of the class activation regions of the sensor data was formed using a multi-channel CNN and a class activation mapping algorithm. Finally, the data segmentation strategy was established based on the heat map, the basic law of falls and the real-time requirements. Main results. This method was verified by the SisFall dataset. The obtained segmentation strategy (i.e. to start segmenting a small data segment with a window duration of 325 ms when the acceleration signal magnitude vector is less than 9.217 m s−2) met the real-time requirements for pre-impact fall detection. Moreover, it was suitable for various machine learning algorithms, and the accuracy of the machine learning algorithms used exceeded 94.8%, with the machine learning algorithms verifying the data segmentation strategy. Significance. The proposed method can automatically identify the class activation area, save the computing resources of wearable devices, shorten the duration of segmentation window, and ensure the real-time performance of pre-impact fall detection.

A comprehensive comparison of accuracy and practicality of different types of algorithms for pre-impact fall detection using both young and old adults

This study aims to comprehensively compare the accuracy and practicality of three different types of algorithms for pre-impact fall detection using both young and old subjects. Threshold-based, conventional machine learning (SVM) and deep learning (ConvLSTM) algorithms were compared. Results showed that ConvLSTM had an accuracy of 99.16 % (sensitivity: 99.32 %, specificity: 99.01 %) and an averaged lead time of 403 ms on young subjects, which outperformed SVM (97.16 %, 385 ms) and much superior to the threshold-based algorithm (89.06 %, 333 ms). In addition, latency tests on an embedded device showed that the Lite model of ConvLSTM had a low latency of 2.1 ms, which was comparable to the threshold-based algorithm (<1 ms) but much lower than SVM (86.9 ms). The feasibility and effectiveness of applying algorithms trained on young subjects to old subjects were also validated. These findings suggested that ConvLSTM has great potential for detecting pre-impact falls and preventing fall-related injuries.

Wearable airbag technology and machine learned models to mitigate falls after stroke

BackgroundFalls are a common complication experienced after a stroke and can cause serious detriments to physical health and social mobility, necessitating a dire need for intervention. Among recent advancements, wearable airbag technology has been designed to detect and mitigate fall impact. However, these devices have not been designed nor validated for the stroke population and thus, may inadequately detect falls in individuals with stroke-related motor impairments. To address this gap, we investigated whether population-specific training data and modeling parameters are required to pre-detect falls in a chronic stroke population.MethodsWe collected data from a wearable airbag’s inertial measurement units (IMUs) from individuals with (n = 20 stroke) and without (n = 15 control) history of stroke while performing a series of falls (842 falls total) and non-falls (961 non-falls total) in a laboratory setting. A leave-one-subject-out crossvalidation was used to compare the performance of two identical machine learned models (adaptive boosting classifier) trained on cohort-dependent data (control or stroke) to pre-detect falls in the stroke cohort.ResultsThe average performance of the model trained on stroke data (recall = 0.905, precision = 0.900) had statistically significantly better recall (P = 0.0035) than the model trained on control data (recall = 0.800, precision = 0.944), while precision was not statistically significantly different. Stratifying models trained on specific fall types revealed differences in pre-detecting anterior–posterior (AP) falls (stroke-trained model’s F1-score was 35% higher, P = 0.019). Using activities of daily living as non-falls training data (compared to near-falls) significantly increased the AUC (Area under the receiver operating characteristic) for classifying AP falls for both models (P < 0.04). Preliminary analysis suggests that users with more severe stroke impairments benefit further from a stroke-trained model. The optimal lead time (time interval pre-impact to detect falls) differed between control- and stroke-trained models.ConclusionsThese results demonstrate the importance of population sensitivity, non-falls data, and optimal lead time for machine learned pre-impact fall detection specific to stroke. Existing fall mitigation technologies should be challenged to include data of neurologically impaired individuals in model development to adequately detect falls in other high fall risk populations.Trial registrationhttps://clinicaltrials.gov/ct2/show/NCT05076565; Unique Identifier: NCT05076565. Retrospectively registered on 13 October 2021

Wearable Pre-Impact Fall Detection System Based on 3D Accelerometer and Subject’s Height

This study presents a low-power wearable system able to predict a fall by detecting a pre-impact condition, performed through a simple analysis of motion data (acceleration) and height of the subject. The system can detect a fall in all directions with an average consumption of 5.91 mA; i.e., it can monitor the activity of daily living (ADL), whether or not a fall occurs. The entire detection system uses a single wearable tri-axis accelerometer placed on the waist for the comfort of the wearer during a long-term application. The algorithm is based on the following hypothesis: “A region defined as balanced boundary circle, based on the user’s height, is characterized by the fact the chance that an actual fall happening is minimal. When an activity is classified outside this circle, an acceleration analysis is performed to determine an impending fall condition”. Our threshold-based algorithm was validated experimentally, first with 9 young healthy volunteers performing both normal ADL and fall activities and then using 10 ADL and 5 falls from public SisFall dataset. The results show that falls could be detected with an average lead-time of 259 ms before the impact occurs, with minimal false alarms (97.7% specificity) and a sensitivity of 92.6%. This is a good lead-time achieved thus far in pre-impact fall detection, permitting the integration of our detection system in a wearable inflatable airbag for hip protection.

Identification of the cause of fall during the pre-impact fall period.

[Purpose] This study aimed to develop and validate a method for identifying factors that may cause a fall during the pre-impact fall period using wearable sensors. [Participants and Methods] The participants were 23 young people from the public data set (mean age, 23.4 years). Acceleration and angular velocity information obtained from sensors attached to the participant’s waist was used to generate the pre-impact fall. The cause of the fall (slip, trip, fainting, get up, sit down) was then classified with and without the addition of activity of daily living data using three different support vector machine. In addition, we investigated the influence of lead time (0–2.0s) on accuracy. [Results] The quadratic and cubic support vector machine identified the activity of daily living and fall patterns more accurately than the linear support vector machine, and the cubic support vector machine was better for classification, although the difference was slight. The greatest accuracy for predicting the cause of the fall (87.9%) was obtained when the cubic support vector machine was used, activity of daily living was factored into the analysis, and the lead time was 0.25 sec. [Conclusion] Support vector machine can identify the cause of the fall during the pre-impact fall period. Appropriate individualized interventions may be designed based on the most likely cause of fall as identified by this analysis method.

A Comprehensive Comparison of Accuracy and Practicality of Different Types of Algorithms for Pre-Impact Fall Detection Using Both Young and Old Adults

A Comprehensive Comparison of Accuracy and Practicality of Different Types of Algorithms for Pre-Impact Fall Detection Using Both Young and Old Adults

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

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.

Preimpact Fall Detection for Elderly Based on Fractional Domain

The aging population has become a growing worldwide problem. Every year, deaths and injuries caused by elderly people's falls bring huge social costs. To reduce the rate of injury and death caused by falls among the elderly and the following social cost, the elderly must be monitored. In this context, falls detecting has become a hotspot for many research institutions and enterprises at home and abroad. This paper proposes an algorithm framework to prealarm the fall based on fractional domain, using inertial data sensor as motion data collection devices, preprocessing the data by axis synthesis and mean filtering, and using fractional-order Fourier transform to convert the collected data from time domain to fractional domain. Based on the above, a multilayer dichotomy classifier is designed, and each node parameter selection method is given, which constructed a preimpact fall detection system with excellent performance. The experiment result demonstrates that the algorithm proposed in this paper can guarantee better warning effect and classification accuracy with fewer features.

Multisensing Architecture for the Balance Losses During Gait via Physiologic Signals Recognition

In this paper, we propose an innovative multi-sensor architecture operating in the field of pre-impact fall detection (PIFD). The proposed architecture jointly analyzes cortical and muscular involvement when unexpected slippages occur during steady walking. The electrophysiological signals (EEG and EMG) are acquired through wearable and wireless acquisition devices interfaced with a central control unit. The control unit consists of a hybrid architecture that exploits both an STM32L4 microcontroller and a DSP-oriented Simulink model. The EMG computation block translates EMGs into binary signals, which are used to trigger the cortical analyses, to extract a score on the revealed muscular pattern and to distinguish “standard” muscular behaviors from anomalous ones (perturbation). A Simulink model evaluates the cortical responsiveness in five bands of interest and implements a logical-based network to detect near-falls or potential ones. The proposed architecture goal is to obtain a detection time conservatively below 550 ms, which represents a strict limit for the successful application of postural recovery strategies. The system has been tested on 6 healthy subjects and demonstrated to react in ${\sf 370.62} \pm {\sf 60.85}$ ms, while keeping competitive accuracy (96.21%).

Acceleration Magnitude at Impact Following Loss of Balance Can Be Estimated Using Deep Learning Model.

Pre-impact fall detection can detect a fall before a body segment hits the ground. When it is integrated with a protective system, it can directly prevent an injury due to hitting the ground. An impact acceleration peak magnitude is one of key measurement factors that can affect the severity of an injury. It can be used as a design parameter for wearable protective devices to prevent injuries. In our study, a novel method is proposed to predict an impact acceleration magnitude after loss of balance using a single inertial measurement unit (IMU) sensor and a sequential-based deep learning model. Twenty-four healthy participants participated in this study for fall experiments. Each participant worn a single IMU sensor on the waist to collect tri-axial accelerometer and angular velocity data. A deep learning method, bi-directional long short-term memory (LSTM) regression, is applied to predict a fall’s impact acceleration magnitude prior to fall impact (a fall in five directions). To improve prediction performance, a data augmentation technique with increment of dataset is applied. Our proposed model showed a mean absolute percentage error (MAPE) of 6.69 ± 0.33% with r value of 0.93 when all three different types of data augmentation techniques are applied. Additionally, there was a significant reduction of MAPE by 45.2% when the number of training datasets was increased by 4-fold. These results show that impact acceleration magnitude can be used as an activation parameter for fall prevention such as in a wearable airbag system by optimizing deployment process to minimize fall injury in real time.