Fig 1.
The sensing layer gathers data and sends it to the data layer, while the control layer acts as the infrastructure’s central intelligence, overseeing the whole SDN-IoT network.
An example of an SDN-IoMT infrastructure consists of these three layers.
Table 1.
A description of CTG and clinical features, including the types of sensors used to capture these features and the normal range for each feature.
Fig 2.
To monitor fetal distress monitoring, many CTG devices are placed in rooms within a distributed SDN-IoT architecture.
After this, the control layer receives the data gathered from these devices for additional processing. We apply a Deep Learning model in this three-layered architecture to identify and categorize anomalies
Fig 3.
An actual CTG recording was acquired from a Pakistani hospital located in Islamabad.
Three important data are shown on this CTG: acceleration, baseline variability, and fetal heart rate. All three are within the normal range.
Fig 4.
The architecture of the proposed framework.
Fig 5.
Creation of a model for tracking fetal health monitoring utilizing an imbalanced CTG dataset, Generative Adversarial Network, and Autoencoder for anomaly detection and classification.
Fig 6.
The pre-processing of CTG raw signals [26].
Fig 7.
The CNN classifier architecture used in our suggested framework to categorize CTG imbalance data into three groups: abnormal, non-abnormal, and reassuring.
Table 2.
A description of CTG features reassuring and non-reassuring values.
Table 3.
CTG imbalance dataset distribution.
Table 4.
Performance of classifiers for normal and abnormal task detection using Recall (R), Precision (P), and F1-score (F1). G.LSTM, G.DNN, and G.CNN denote proposed models with Noise-Aware Encoder (NAE).
Fig 8.
Using the Accuracy metric, three model types—naive deep learning models, advanced deep learning models, and the proposed framework—are compared for the binary classification of normal and abnormal classes in an unbalanced CTG test dataset.
Fig 9.
Using the Recall, Precision, and F1-score metrics, three model types are compared: naïve deep learning models, advanced deep learning models, and the proposed framework for binary classification of normal class in an imbalanced CTG test dataset.
Fig 10.
Using the Recall, Precision, and F1-score metrics, three model types are compared: naïve deep learning models, advanced deep learning models, and the proposed framework for binary classification of abnormal class in an imbalanced CTG test dataset.
Fig 11.
The proposed framework’s confusion matrix on the unbalanced CTG dataset.
Fig 12.
ROC analysis of the proposed framework on the imabalnace CTG dataset.
Table 5.
Evaluating the proposed framework’s accuracy in binary and multiclassification scenarios against the baseline DL models.
Table 6.
Performance comparison of classifiers for Suspicious and Pathological categories.
Fig 13.
Three types of models are compared using the Accuracy metric for multiclassification in an imbalanced CTG test dataset: basic deep learning models, advanced deep learning models, and the proposed framework.
Fig 14.
Using the Recall, Precision, and F1-score metrics, three model types are compared: naïve deep learning models, advanced deep learning models, and the proposed framework for multiclassification of Suspicious minor class in an imbalanced CTG test dataset.
Fig 15.
Using the Recall, Precision, and F1-score metrics, three model types—naive deep learning models, advanced deep learning models, and the proposed framework—are compared for multiclassification of the Pathological minor class in an imbalanced CTG test dataset.
The Proposed Framework is indicated here by P.F.
Fig 16.
Speed efficiency of the proposed technique in comparison with the baseline deep learning models.
Table 7.
Performance metrics with mean, standard deviation, and 95% confidence interval.
Table 8.
Statistical comparison of model performance.
Table 9.
Comparison of the proposed framework with the existing literature.