Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction

A nonuniform temperature field can deteriorate the performance of sensors, especially those working in the field, such as an optical sensor for oil-tank ground settlement (GS) monitoring. In this case, the GS monitoring employs hydraulic-level-based sensors (HLBS), which are uniformly installed along with the oil-tank basement perimeter and are all connected by hydraulic tubes. Then, the cylinder structure of the oil tank itself can create a strong temperature difference between the sensors installed in the sunlit front and those in the shadow. Practically, this sunlight-dependent difference can be over 30 °C, by which the thermal expansion of the measuring liquid inside the connecting hydraulic tubes keeps on driving a movement and, thereby, leads to fluctuations in the final result of the oil-tank GS monitoring system. Now, this system can work well at night when the temperature difference becomes negligible. However, temperature uncertainty is generated in the GS sensors due to the large temperature difference between the sensors in the daytime. In this paper, we measured the temperature where the sensor was located. Then, we compared the results of the GS sensors with their corresponding temperatures and fitted them with two separate curves, respectively. After observing the similarity in the tendency of the two curves, we found that there was a qualitative correlative relationship between the change in temperature and the uncertainty in the sensor results. Then, a curve similarity analysis (CSA) principle based on the minimum mean square error (MMSE) criteria was employed to establish an algorithm, by which the temperature uncertainty in the GS sensors was reduced. A practical test proved that the standard deviation was improved by 73.4% by the algorithm. This work could be an example for reducing the temperature uncertainty from in-field sensors through the CSA method.

Section: The Csamentioning

confidence: 99%

Curve Similarity Analysis for Reducing the Temperature Uncertainty of Optical Sensor for Oil-Tank Ground Settlement Monitoring

Liu,

Jiang

et al. 2023

“…A deep convolutional neural network was employed for feature extraction, while a straightforward neural network with backpropagation was used for classification. In [ 13 ], the authors suggested a framework for machine learning to extract vital patterns from mobile ECG signals. A three-stage hybrid machine learning framework is proposed for estimating ECG duration associated with cardiovascular disease.…”

Section: Literature Reviewmentioning

confidence: 99%

“…As can be seen from Table 5 , our suggested Residual-Dense-CNN approach performs much better than the other state-of-the-art techniques in terms of the values attained for parameters, accuracy, AUC, kappa, and F1 score. We have compared the RD-CNN model with other techniques such as AlexNet-SVM [ 13 ], CNN-filtering [ 16 ], SVM [ 21 ], CNN-LSTM [ 24 ], RNN-LSTM [ 31 ], DeepCNN [ 33 ], and CNN-Pool [ 34 ]. Compared to other approaches, as mentioned in Table 1 , we have selected these studies because they are easy to implement and because these techniques detect multiclass heart disease.…”

Section: Experimental Analysismentioning

confidence: 99%

“…We have implemented these techniques as described in the corresponding studies. The AlexNet-SVM [ 13 ], CNN-filtering [ 16 ], SVM [ 21 ], CNN-LSTM [ 24 ], RNN-LSTM [ 31 ], DeepCNN [ 33 ], and CNN-Pool [ 34 ] techniques are used for comparison to detect and classify in similar training and testing configurations. The different variants of these studies have been implemented according to the methodology designed for the given dataset.…”

Section: Experimental Analysismentioning

confidence: 99%

See 1 more Smart Citation

A Residual-Dense-Based Convolutional Neural Network Architecture for Recognition of Cardiac Health Based on ECG Signals

Ahmed

Abbas

Daadaa

et al. 2023

Cardiovascular disorders are often diagnosed using an electrocardiogram (ECG). It is a painless method that mimics the cyclical contraction and relaxation of the heart’s muscles. By monitoring the heart’s electrical activity, an ECG can be used to identify irregular heartbeats, heart attacks, cardiac illnesses, or enlarged hearts. Numerous studies and analyses of ECG signals to identify cardiac problems have been conducted during the past few years. Although ECG heartbeat classification methods have been presented in the literature, especially for unbalanced datasets, they have not proven to be successful in recognizing some heartbeat categories with high performance. This study uses a convolutional neural network (CNN) model to combine the benefits of dense and residual blocks. The objective is to leverage the benefits of residual and dense connections to enhance information flow, gradient propagation, and feature reuse, ultimately improving the model’s performance. This proposed model consists of a series of residual-dense blocks interleaved with optional pooling layers for downsampling. A linear support vector machine (LSVM) classified heartbeats into five classes. This makes it easier to learn and represent features from ECG signals. We first denoised the gathered ECG data to correct issues such as baseline drift, power line interference, and motion noise. The impacts of the class imbalance are then offset by resampling techniques that denoise ECG signals. An RD-CNN algorithm is then used to categorize the ECG data for the various cardiac illnesses using the retrieved characteristics. On two benchmarked datasets, we conducted extensive simulations and assessed several performance measures. On average, we have achieved an accuracy of 98.5%, a sensitivity of 97.6%, a specificity of 96.8%, and an area under the receiver operating curve (AUC) of 0.99. The effectiveness of our suggested method for detecting heart disease from ECG data was compared with several recently presented algorithms. The results demonstrate that our method is lightweight and practical, qualifying it for continuous monitoring applications in clinical settings for automated ECG interpretation to support cardiologists.

“…In recent decades, traditional machine-learning-based abnormal detection methods have shown promise in monitoring and predicting the health conditions of humans [ 10 , 11 , 12 ]. These methods utilize machine learning algorithms such as k-nearest neighbor and support vector machines to analyze sensor data, physiological signals, or other relevant features collected from workers to identify abnormal patterns or anomalies that may indicate potential health issues or risks.…”

Section: Introductionmentioning

confidence: 99%

Long-Short-Term-Memory-Based Deep Stacked Sequence-to-Sequence Autoencoder for Health Prediction of Industrial Workers in Closed Environments Based on Wearable Devices

Xu,

He,

et al. 2023

To reduce the risks and challenges faced by frontline workers in confined workspaces, accurate real-time health monitoring of their vital signs is essential for improving safety and productivity and preventing accidents. Machine-learning-based data-driven methods have shown promise in extracting valuable information from complex monitoring data. However, practical industrial settings still struggle with the data collection difficulties and low prediction accuracy of machine learning models due to the complex work environment. To tackle these challenges, a novel approach called a long short-term memory (LSTM)-based deep stacked sequence-to-sequence autoencoder is proposed for predicting the health status of workers in confined spaces. The first step involves implementing a wireless data acquisition system using edge-cloud platforms. Smart wearable devices are used to collect data from multiple sources, like temperature, heart rate, and pressure. These comprehensive data provide insights into the workers’ health status within the closed space of a manufacturing factory. Next, a hybrid model combining deep learning and support vector machine (SVM) is constructed for anomaly detection. The LSTM-based deep stacked sequence-to-sequence autoencoder is specifically designed to learn deep discriminative features from the time-series data by reconstructing the input data and thus generating fused deep features. These features are then fed into a one-class SVM, enabling accurate recognition of workers’ health status. The effectiveness and superiority of the proposed approach are demonstrated through comparisons with other existing approaches.