Abstract Electrocardiogram (ECG) signals can be monitored from many patients based on healthcare systems. To enhance these systems, the ECG signals should be collected and then stored in a cloud platform for later analysis. Hence, ECG signals can be utilized to diagnose heart diseases. However, the ECG signals require great internet capacity. So, compression techniques can be implemented to reduce a memory storage capacity for these signals. One of the potential compression techniques is the compressive sensing (CS). This paper proposes a CS technique to compress ECG signals. This technique is used to reduce sampling rates of the ECG signals to be less than the Nyquist rate. Moreover, a framework is suggested for the compression of maternal and fetal ECG signals. The compression of these signals is based on the curvelet transform (CT) to produce sparsity in ECG signals. The MIT-BIH database are utilized for testing the ECG signals. This database includes several ECG signals with various sampling rates, such as aberrant and normal signals. The proposed CS technique achieved a compression ratio (CR) of 15.7 with an accuracy of 98.2%. Also, a percentage root mean difference (PRD) is utilized to calculate the performance of the reconstructed ECG signals. The achieved value of the PRD is 2.0.

Abstract Smart hospitals should equip patients with wearable devices capable of monitoring and predicting brain strokes using deep learning (DL) techniques. The latest advancements in the accuracy of DL have the potential to make a substantial impact in addressing the issues associated with predicting brain strokes. However, further enhancements are required to achieve even higher levels of precision in DL methods. This research proposes an innovative intelligent healthcare system (IHS) that utilizes a real-time web application. The IHS is specifically engineered to monitor and forecast cerebral stroke occurrences in individuals. Also, this work presents three DL models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional long short-term memory (BiLSTM), which are used to predict brain stroke. The three models are trained using a dataset collected from 4,981 individuals. This dataset consists of two categories—normal and stroke, and it comprises eleven distinct characteristics: gender, age, heart disease (HD), hypertension, marital status (MS), type of residence (RT), average glucose level (AGL), type of work (TW), body mass index (BMI), smoking status (SS), and stroke. The DL models suggested in this study are constructed using the Keras library, employing a hyperparameter tuning technique to maximize accuracy. The effectiveness of the three models is evaluated using precision-recall (PR) curves and a normalized error matrix (NEM). The results indicate that the BiLSTM model outperforms both the GRU and LSTM models in terms of efficiency for predicting brain stroke. The BiLSTM achieves the most efficiency, with a testing accuracy (TA) of 100%, followed by the LSTM with a TA of 99.90%. However, the GRU exhibits the lowest TA of 99.80%. The testing loss (TL) rates for the LSTM, GRU, and BiLSTM models are 0.0075, 0.022, and 0.0001, respectively. Additionally, the BiLSTM model achieves sensitivity, accuracy, F1-score, and area under the PR curves of 100%. The proposed DL models with IHS can assist physicians in efficiently and precisely diagnosing persons with brain strokes, enabling them to make prompt and accurate decisions.

Abstract Human activity recognition (HAR) is a challenging issue in several fields, such as medical diagnosis. Recent advances in the accuracy of deep learning have contributed to solving the HAR issues. Thus, it is necessary to implement deep learning algorithms that have high performance and greater accuracy. In this paper, a gated recurrent unit (GRU) algorithm is proposed to classify human activities. This algorithm is applied to the Wireless Sensor Data Mining (WISDM) dataset gathered from many individuals with six classes of various activities – walking, sitting, downstairs, jogging, standing, and upstairs. The proposed algorithm is tested and trained via a hyper-parameter tuning method with TensorFlow framework to achieve high accuracy. Experiments are conducted to evaluate the performance of the GRU algorithm using receiver operating characteristic (ROC) curves and confusion matrices. The results demonstrate that the GRU algorithm provides high performance in the recognition of human activities. The GRU algorithm achieves a testing accuracy of 97.08%. The rate of testing loss for the GRU is 0.221, while the precision, sensitivity, and F1-score for the GRU are 97.11%, 97.09%, and 97.10%, respectively. Experimentally, the area under the ROC curves (AUC S ) is 100%.