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.
Due to the increasing aging of the world’s population, the welfare and safety of the elderly are a concern. Moreover, 28%–35% of people aged 65 years or older fall at least once a year, and 20%–30% of falls result in moderate to severe injury or even death [
Based on the sensors used, FDSs can be divided into contextual and wearable systems [
In recent years, numerous studies have been conducted to clarify this challenge by shifting the focus from post-impact fall detection to pre-impact falls. Most relevant work on pre-impact FDS has been done using threshold-based and machine learning (ML) techniques. However, determining the correct threshold has not been straightforward. Although additional features could help to categorize falls and non-falls more accurately, computing the values of the salient features would be too time-consuming and waste too much operating time of the ML algorithm. With the development of deep learning (DL) techniques, a few early experiments have demonstrated the effectiveness of the generated algorithms on moderately small datasets (limited number of human participants and movements).
Therefore, this study investigated the use of pre-impact FDS utilizing wearable sensors and DL techniques. To accomplish our study objective, we proposed a deep residual network for pre-impact FDS that would effectively detect pre-impact falls. The proposed model was trained and evaluated using KFall, a large-scale movement dataset. The following is a summary of our contributions: FDSNeXt, a novel deep residual network with aggregated transformation, was proposed in this study, which included many multikernel blocks throughout the main convolution procedure to provide reliable predictions for pre-impact and impact fall detection. Different DL networks (CNN, LSTM, and CNN-LSTM) were implemented to analyze and detect the pre-impact and impact fall events. On the same pre-impact fall dataset, we compared the performance of the proposed FDSNeXt.
The following specifics highlight the paper’s organization: The related study is discussed in Section 2. Section 3 explains the approach, which consists of a sensor-based FDS structure and a proposed DL model. Then, in Section 4, the experiments and results of the DL model are analyzed and compared. The research results are discussed in Section 5. In Section 6, we conclude with a description of our results, limitations, and potential research challenges.
In this section, we briefly discuss the studies on sensor-based fall detection. The following sections contain further information on the related studies in this study.
Vision-based, ambient, and wearable sensors are three possible classifications for current fall detection strategies [
There are post-fall and pre-impact fall detection systems based on wearable inertial sensors. Post-fall detection would perceive falls and alert caregivers to avoid prolonged recumbency [
Due to the cheap affordability of sensors in latest years, wearable sensors have gained increasing popularity. To achieve the three-axis acceleration at various points and the three-axis rotation angular velocity in a gyroscope, the most popular locations for wearable sensors have been the calf, spine, head, pelvis, and feet [
Conventional pattern classification and recognition based on DL are the two primary categories of ML techniques [
In this section, the procedure for developing a DL model and detecting falls using wearable sensing devices is explained.
The KFall [
Activity | Class |
---|---|
Stand for 30 s | ADL |
Stand with a slow bend on the back | ADL |
Take up an object | ADL |
Take a jump | ADL |
Stand and sit, and get up | ADL |
Regular walk with a turn | ADL |
Fast walk with a turn | ADL |
Regular jog with a turn | ADL |
Fast jog with a turn | ADL |
Fall down while walking | ADL |
Thirty seconds of sitting on a chair | ADL |
Thirty seconds while seated on the sofa (back angled toward the support) | ADL |
Sit down on a chair, and get up | ADL |
Sit down on a chair, and get up quickly | ADL |
Sit down on a chair, attempt to stand, and collapse | ADL |
Stand and sit down on the couch (back is inclined), and stand up again | ADL |
Lay down on the bed for 30 s. | ADL |
Perform usually sitting, lying down on the bed, and getting up | ADL |
Perform quickly sitting, lying down on the bed, and getting up | ADL |
Regular walk upstairs and downstairs | ADL |
Fast walk upstairs and downstairs | ADL |
Sit down and forward fall | Fall |
Sit down and backward fall | Fall |
Sit down and lateral fall | Fall |
Get up and forward fall | Fall |
Get up and lateral fall | Fall |
Sit and forward fall (fainting) | Fall |
Sit and lateral fall (fainting) | Fall |
Sit and backward fall (fainting) | Fall |
Walk with vertical fall (fainting) | Fall |
Walk with a fall (hands to dampen fall, fainting) | Fall |
Walk and forward fall (caused a trip) | Fall |
Jogging and forward fall (caused a trip) | Fall |
Walk and forward fall (caused a slip) | Fall |
Walk and lateral fall (caused a slip) | Fall |
Walk and backward fall (caused a slip) | Fall |
The raw sensor data from the waist contained the measurement noise and additional unpredicted noise resulting from the active movements of the participants during the data acquisition. A noisy signal obliterated the relevant information. Therefore, it was important to limit the impact of the noise on the mobility in order to collect the user’s data for subsequent processing. Mean, low-pass, and wavelet filtering were the most common filtering methods [
There were three reasons about the selection of the window size of 0.5 s and the overlapping proportion of 50% as follows: (1) the 0.5 s window size in the sliding windows were sufficient to achieve the high detection rates for the fall detection problems as suggested by Liu et al. [
This study addressed a convolution-based DL technique to overcome the FDS challenge. We proposed a multi-branch aggregation model called FDSNeXt that was influenced by Xie et al. [
The FDSNeXt model contained four units with convolutional kernels of differing sizes. Each multikernel unit had three kernel sizes: 1 × 3, 1 × 5, and 1 × 7. In addition, the 1 × 1 convolution was used before applying these kernels to decrease the model’s complication and the number of parameters.
In this work, the evaluation metrics of accuracy, precision, recall, and F1-score were used to evaluate the DL models and the proposed models for pre-impact and impact fall detection. These four evaluation metrics are most commonly used in fall detection research to evaluate the overall success. The detection is a true positive (TP) for the category under consideration and a true negative (TN) for all others. If sensor data from one category is incorrectly classified as belonging to another, this will result in a false positive (FP) detection. Sensor data from another category may be incorrectly classified as belonging to this category, resulting in a false negative (FP) detection.
Accuracy is the sum of correctly detected issues divided by the total number of classifications. The mathematical formula of the accuracy is shown in
In the field of fall detection, the precision rate is the proportion of instances that represent a positive class out of all instances that are predicted to be positive classes. According to the definition, the mathematical formula for calculating the precision rate is presented in
The recall rate is the proportion of the number of instances of all positive classes of which the number is correctly predicted to be positive. According to the definition, the recall metric is calculated mathematically as shown in
The F1-score is the weighted summed average of the precision rate and the recall rate. The F1-score takes into account both the precision and recall metrics. When the F1-score is higher, this metric can indicate that the experimental method is effective. The F1-score formula is shown in
For this study, the Google Colab-Pro+ platform was deployed. The 16 GB graphics processor unit of Tesla V100-SXM2 was used to accelerate the training of the DL models with excellent performance. It was decided to include FDSNeXt and other standard DL models in the Python library using the Tensorflow backend v.3.9.1 [ Numpy and Pandas were used to access, process, and analyze sensor data. Matplotlib and Seaborn were used to display and report the results of the data discovery and model evaluation. In the study, Sklearn was used to perform the sampling and data generation. Models for DL were created and trained using Keras, TensorFlow, and TensorBoard.
The hyperparameter settings in the DL model were used to drive the learning experience. For the proposed model, the relevant hyperparameters used were: (1) epochs, (2) batch size, (3) learning rate, (4) optimization, and (5) loss function (shown in
Stage | Hyperparameter | Values | |
---|---|---|---|
Conv1D | Kernel Size | 5 | |
Filters | 64 | ||
Batch Normalization | – | ||
Activation | ReLU | ||
Max Pooling | 2 | ||
Conv1D | Kernel Size | 1 | |
Filters | 16 | ||
Conv1D | Kernel Size | 3 | |
Filters | 16 | ||
Conv1D | Kernel Size | 1 | |
Filters | 16 | ||
Conv1D | Kernel Size | 5 | |
Filters | 16 | ||
Conv1D | Kernel Size | 1 | |
Filters | 16 | ||
Conv1D | Kernel Size | 7 | |
Filters | 16 | ||
Kernel Size | 1 | ||
Conv1D | Stride | 1 | |
Filters | 64 | ||
Kernel Size | 1 | ||
Conv1D | Stride | 1 | |
Filters | 64 | ||
Global Average Pooling | – | ||
Flatten | – | ||
Dense | 128 | ||
Loss Function | Cross-entropy | ||
Optimizer | Adam | ||
Batch Size | 128 | ||
Number of Epochs | 200 |
In this research, the two main experiments were conducted utilizing sensor data from the KFall dataset: Scenario I: Detected falls using data from wearable sensors Scenario II: Utilized data from wearable sensors to identify falls before impact.
Considering a five-fold cross-validation procedure, experimental movement signal data were obtained. This study evaluated the identification effectiveness of three standard DL models (CNN, LSTM, and CNN-LSTM) and the proposed FDSNeXt model via a series of experiments. The experimental results were evaluated by the Accuracy, Loss, and F1-score, as shown in
Model | Performance | ||
---|---|---|---|
Accuracy | Loss | F1-score | |
CNN | 86.19% (±0.541%) | 0.40% (±0.054%) | 85.57% (±0.578%) |
LSTM | 90.56% (±1.564%) | 0.23% (± 0.032%) | 90.30% (±1.676%) |
CNN-LSTM | 83.69% (±0.866%) | 0.35% (± 0.013%) | 83.22% (±0.898%) |
FDSNeXt | 92.52% (±0.208%) | 0.23% (± 0.010%) | 92.34% (±0.208%) |
Model | Performance | ||
---|---|---|---|
Accuracy | Loss | F1-score | |
CNN | 85.69% (±0.700%) | 0.49% (±0.048%) | 82.37% (±0.765%) |
LSTM | 90.12% (±0.412%) | 0.25% (±0.004%) | 87.68% (±0.406%) |
CNN-LSTM | 84.04% (±0.417%) | 0.35% (±0.008%) | 79.29% (±0.659%) |
FDSNeXt | 91.87% (±0.306%) | 0.27% (±0.009%) | 89.92% (±0.375%) |
From the results of the fall detection, the proposed FDSNeXt model achieved the highest accuracy and F1-score in the experiment. The proposed model was achieved the best interpretations of the operating motion signals from the waist position with the highest accuracy of 92.52% and the highest F1-score of 92.34%.
The proposed FDSNeXt model achieved the highest accuracy and F1-score in the performed investigation for the pre-impact fall identification. Considering motion data from the waist location, the proposed model achieved the highest accuracy of 91.87% and the highest F1-score of 89.92%.
To evaluate the effectiveness of the proposed FDSNeXt model, three standard DL models were evaluated as the benchmarks. In this work, the models were evaluated using five-fold cross-validation procedures, and the average performance indicators (Accuracy, Loss, and F1-score) were used as the indices to evaluate the effectiveness.
Several baseline models were used to evaluate the proposed model, including CNN, LSTM, and CNN-LSTM.
As illustrated in
To show the efficiency of the proposed fall detection approach, we showed the confusion matrices of each DL model used in this work.
The proposed FDSNeXt model was compared to previously trained models on the same dataset (KFall dataset). Previous research [
Model | Performance | |
---|---|---|
Sensitivity | Specificity | |
Threshold | 95.50 | 83.43 |
SVM | 99.77 | 94.87 |
FDSNeXt | 99.78 | 95.02 |
In this study, we investigated a DL model that depended on the inputs from wearable sensors compared to other models. According to the experimental results, the proposed FDSNeXt model significantly outperformed the other baseline models (CNN, LSTM, and CNN-LSTM). The proposed model was achieved the detection accuracies of 92.52 and 91.87% for fall detection and pre-impact fall detection, respectively.
The proposed DL network in this paper benefited from the repeated topology of the InceptionNet, which enabled it to have a very high accuracy rate while slightly increasing the amount of the network calculations, while also greatly reducing the number of hyperparameters. Moreover, the FDSNeXt network was based on the design concept of the residual connection and combined the aggregation transformation. The structure of the residual connection improved the shortcomings of the degradation for multi-layer DL networks. Moreover, the convolution modules of the transformation set were all the same. The FDSNeXt used a transformation set to replace the transformation structure of the Inception network. Because each aggregated topology was the same, the network no longer needed to modify too many hyperparameters on the different data sets, which had better robustness.
For future studies, we plan to collect elderly fall data and train the model to improve the detection accuracy. Moreover, the proposed model would be used on wearable devices such as smartphones and smartwatches.
The authors gratefully acknowledge the financial support provided by
The authors declare that they have no conflicts of interest to report regarding the present study.