The current advancement in cloud computing, Artificial Intelligence (AI), and the Internet of Things (IoT) transformed the traditional healthcare system into smart healthcare. Healthcare services could be enhanced by incorporating key techniques like AI and IoT. The convergence of AI and IoT provides distinct opportunities in the medical field. Fall is regarded as a primary cause of death or post-traumatic complication for the ageing population. Therefore, earlier detection of older person falls in smart homes is required to improve the survival rate of an individual or provide the necessary support. Lately, the emergence of IoT, AI, smartphones, wearables, and so on making it possible to design fall detection (FD) systems for smart home care. This article introduces a new Teamwork Optimization with Deep Learning based Fall Detection for IoT Enabled Smart Healthcare Systems (TWODL-FDSHS). The TWODL-FDSHS technique’s goal is to detect fall events for a smart healthcare system. Initially, the presented TWODL-FDSHS technique exploits IoT devices for the data collection process. Next, the TWODL-FDSHS technique applies the TWO with Capsule Network (CapsNet) model for feature extraction. At last, a deep random vector functional link network (DRVFLN) with an Adam optimizer is exploited for fall event detection. A wide range of simulations took place to exhibit the enhanced performance of the presented TWODL-FDSHS technique. The experimental outcomes stated the enhancements of the TWODL-FDSHS method over other models with increased accuracy of 98.30% on the URFD dataset.
The Healthcare sector recently began to use information technology for formulating contemporary applications and improving the treatment and diagnostic process [
The data, captured through incorporated, portable, and ingestible sensors, mobile paradigms, and device-used paradigms, allow the author to know users’ habits [
Falling will is a common issue faced by older adults. For elder ones, a fall is highly risky and may cause severe health problems [
This article introduces a new Teamwork Optimization with DL-based Fall Detection for IoT Enabled Smart Healthcare Systems (TWODL-FDSHS). The TWODL-FDSHS technique’s goal is to detect fall events for a smart healthcare system. Initially, the presented TWODL-FDSHS technique exploits IoT devices for the data collection process. Next, the TWODL-FDSHS technique applies the TWO with Capsule Network (CapsNet) model for feature extraction. At last, a deep random vector functional link network (DRVFLN) with Adam optimizer was exploited for fall event detection. A wide range of simulations was conducted to exhibit the enhanced performance of the presented TWODL-FDSHS technique.
Qian et al. [
Vaiyapuri et al. [
In [
In this article, a new TWODL-FDSHS approach was devised for smart healthcare. The major intention of the presented TWODL-FDSHS technique lies in detecting fall events for a smart healthcare system. Primarily, the presented TWODL-FDSHS technique exploited the IoT devices for the data collection. Then, the TWODL-FDSHS technique encompasses CapsNet feature extraction, TWO-based hyperparameter tuning, DRVFLN-based fall detection, and Adam optimizer.
The TWODL-FDSHS technique applies TWO with the CapsNet model for feature extraction in this work. Capsule networks can encode spatial information and discriminate between different poses, textures, and orientations [
Initially, the predictive vector is calculated by,
In
The coupling coefficient is calculated using the
where
At last, a squashing function will combine squashing, and unit scaling is employed for confining output values within [0,1] as,
The loss function is related to the capsule in the final layer, whereas
where value
For the hyperparameter tuning procedure, TWO algorithms are used. The main idea is to design a TWO algorithm comprised of reactions, activities, and behaviours amongst the team members to accomplish the team’s major objective [
Solitary Activity: Every team member, based on personal efforts and behaviours, strives to contribute to the achievement of the whole group. In a mathematical model, every member of the population is determined by the vector, and the number of problem parameters is precisely similar to the component count. From the expression, the algorithm population makes use of the matrixes where the column count is equivalent to the number of variables, along with the row count is being similar to the population member.
From the expression,
F indicates the FF from the equation, and
Supervisor:
Phase1: leadership of a supervisor
In these phases, the group individual has been rehabilitated based on the supervisor’s guidelines. Meanwhile, the supervisor reported their data to be the residual group individual and led the individual towards the team. The following equation has demonstrated these steps of the upgrade in the presented technique.
Now,
Phase2: Sharing information
For increased team performance, every team member is struggling to employ the other team member data that works better than others and it is formulated in the subsequent equation.
Now,
Phase 3: Solitary activity
Every member of the team strives to improve their own functioning based on the upgraded location:
Now,
The TWO approaches derived a FF to accomplish better classifier performance. It sets a positive value to characterize the good performance of the candidate solution. The reduction of the classifier error rate was regarded as a FF as follows.
Finally, the DRVFLN model with Adam optimizer is exploited for fall event detection. The presented method is an expanded edition of shallow RVFL networks from the context of DL or representation learning [
In
This design approach is like the shallow RVFL network where input-output layers have non-linear features under stacked hidden layers and novel features:
The resulting weight
Note that the proposed method splits themselves under the deep ESN under the following characteristics: the significant difference between deeper ESN and DRVFLN goes to the class of randomized RNN, but DRVFLN should randomize the feedforward technique. Hence, it has dissimilar target problems. It inspected the effectiveness of DRVFLN from classifier issue however deep ESN discovered a time-series issue. Moreover, DRVFLN is based on a shallow RVFL network with a resulting layer encompassing nonlinearly changed features and novel features using a direct connection. Conversely, deep ESN doesn’t consider original features under resulting weight computation.
At last, the DL structure, DRVFLN was generic and is employed by few RVFL variances. The Adam optimizer is utilized for the optimum selection of the hyperparameter of the DRVFLN method [
This section examines the performance of the TWODL-FDSHS method on MCF [
Sample size (%) | Accuracy | Precision | Sensitivity | Specificity | F-score |
---|---|---|---|---|---|
80:20 | 99.87 | 99.54 | 99.82 | 99.60 | 99.87 |
70:30 | 99.78 | 100.00 | 99.88 | 99.70 | 99.97 |
60:40 | 99.76 | 99.82 | 99.87 | 99.86 | 99.32 |
50:50 | 99.74 | 99.86 | 99.90 | 99.55 | 99.88 |
40:60 | 99.82 | 99.70 | 99.88 | 99.45 | 99.54 |
Average | 99.79 | 99.78 | 99.87 | 99.63 | 99.72 |
The training accuracy (TRA) and validation accuracy (VLA) obtained by the TWODL-FDSHS technique under the MCF database is depicted in
The training loss (TRL) and validation loss (VLL) attained by the TWODL-FDSHS method under the MCF dataset are displayed in
Sample size (%) | Accuracy | Precision | Sensitivity | Specificity | F-score |
---|---|---|---|---|---|
80:20 | 99.89 | 99.76 | 99.95 | 99.97 | 99.87 |
70:30 | 99.61 | 99.80 | 99.64 | 99.68 | 99.87 |
60:40 | 99.55 | 99.99 | 99.51 | 99.47 | 99.66 |
50:50 | 99.55 | 99.92 | 99.82 | 99.91 | 99.58 |
40:60 | 99.49 | 99.72 | 99.89 | 99.73 | 99.56 |
Average | 99.62 | 99.84 | 99.76 | 99.75 | 99.71 |
The TRA and VLA gained by the TWODL-FDSHS method under the URFD dataset are shown in
The TRL and VLL obtained by the TWODL-FDSHS method under the URFD dataset are shown in
Methods | Accuracy (%) |
---|---|
Depthwise | 97.51 |
1D-CNN | 94.53 |
2D-CNN | 95.75 |
ResNet-50 | 96.11 |
ResNet-101 | 96.65 |
IMEFD-ODCNN | 99.71 |
TWODL-FDSHS | 99.79 |
Methods | Accuracy (%) |
---|---|
Depthwise Model | 98.30 |
1D-CNN Model | 92.99 |
2D-CNN Model | 95.07 |
ResNet-50 Model | 95.65 |
ResNet-101 Model | 95.96 |
IMEFD-ODCNN | 99.32 |
TWODL-FDSHS | 99.62 |
Methods | TRT (min) | TST (min) |
---|---|---|
Depthwise Model | 49.60 | 19.57 |
1D-CNN Model | 34.26 | 13.78 |
2D-CNN Model | 33.17 | 15.36 |
ResNet-50 Model | 20.74 | 17.69 |
ResNet-101 Model | 25.80 | 18.17 |
IMEFD-ODCNN | 21.98 | 8.07 |
TWODL-FDSHS | 20.50 | 7.80 |
Methods | TRT (min) | TST (min) |
---|---|---|
Depthwise Model | 21.10 | 10.22 |
1D-CNN Model | 17.38 | 10.02 |
2D-CNN Model | 20.95 | 9.82 |
ResNet-50 Model | 26.58 | 12.27 |
ResNet-101 Model | 26.83 | 18.05 |
IMEFD-ODCNN | 13.52 | 13.17 |
TWODL-FDSHS | 13.24 | 9.52 |
These results ensured the enhanced performance of the TWODL-FDSHS model over other DL models.
In this article, a new TWODL-FDSHS algorithm was devised for smart healthcare. The major intention of the presented TWODL-FDSHS technique lies in the detection of fall events for a smart healthcare system. Primarily, the presented TWODL-FDSHS technique exploited the IoT devices for the data collection process. Followed by, the TWODL-FDSHS technique applied TWO with the CapsNet model for feature extraction. At last, the DRVFLN model with Adam optimizer is exploited for fall event detection. In order to exhibit the enhanced performance of the presented TWODL-FDSHS technique, a wide range of simulations were carried out. The experimental outcomes stated the enhancements of the TWODL-FDSHS algorithm over other models. In the future, the presented TWODL-FDSHS technique can be extended by utilizing advanced DL techniques for classifying purposes.
The
The authors declare that they have no conflicts of interest to report regarding the present study.