A Parallel Cross Convolutional Recurrent Neural Network for Automatic Imbalanced ECG Arrhythmia Detection with Continuous Wavelet Transform

Toma, Tabassum Islam; Choi, Sunwoong

doi:10.3390/s22197396

Cited by 6 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dual-channel convolution was provided by the normalized trained sample as part of pretraining. In the earlier stage of pretraining, the predictive model creates a huge loss (20). As a result, an optimizer is used for mitigating these losses and also improving the accuracy that changes the module features.…”

Section: Diabetes Detection Using Mc-blstm Modelmentioning

confidence: 99%

Binary fire hawks optimizer with deep learning driven non-invasive diabetes detection and classification

Periasamy

2024

BLL

View full text Add to dashboard Cite

Non-invasive diabetes detection refers to the utilization and development of technologies and methods that can monitor and diagnose diabetes without requiring invasive procedures, namely invasive glucose monitoring or blood sampling. The objective is to provide a more convenient and less burdensome approach to screening and management of diabetes. It is noteworthy that while non-invasive method offers promising avenues for diabetes detection, they frequently require validation through clinical studies and might have limitation in terms of reliability and accuracy than classical invasive approaches. In recent times, deep learning (DL) and feature selection (FS) are used to monitor and diagnose diabetes accurately without requiring invasive procedures. This technique combines the FS method with the DL algorithm for making accurate predictions and extracting relevant features from non-invasive data. This article introduces a new Binary Fire Hawks Optimizer with Deep Learning-Driven Non-Invasive Diabetes Detection and Classifi cation (BFHODL-NIDDC) technique. The major intention of the BFHODL-NIDDC technique focuses on the involvement of non-invasive procedures for the detection of diabetes. In the BFHODL-NIDDC technique, data preprocessing is initially performed to preprocess the input data. Next, the BFHO algorithm chooses an optimal subset of features and improves the classifi er results. For the identifi cation of diabetes, multichannel convolutional bidirectional long short-term memory (MC-BLSTM) model is used. At last, the beetle antenna search (BAS) algorithm is used for the hyperparameter selection of the MC-BLSTM method which in turn enhances the detection performance of the MC-BLSTM model. A series of simulations were conducted on the diabetes dataset to assess the diabetes detection performance of the BFHODL-NIDDC technique. The experimental outcomes illustrated better performance of the BFHODL-NIDDC method over other recent approaches in terms of different metrics (Tab. 4, Fig. 9, Ref. 23).

show abstract

Section: Diabetes Detection Using Mc-blstm Modelmentioning

confidence: 99%

Binary fire hawks optimizer with deep learning driven non-invasive diabetes detection and classification

Periasamy

2024

BLL

View full text Add to dashboard Cite

show abstract

“…In recent years, the overwhelming progress in the fields of machine learning (ML) and deep learning (DL) has accelerated its expansion in diverse application domains ranging from computer vision to natural language processing followed by predictive analysis, time-series forecasting, and digital healthcare [ 5 , 6 , 7 , 8 ]. Motivated by these unprecedented successes in different domains, ML/DL-based schemes have received considerable attention from the sleep research community.…”

Section: Introductionmentioning

confidence: 99%

An End-to-End Multi-Channel Convolutional Bi-LSTM Network for Automatic Sleep Stage Detection

Toma

Choi

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Sleep stage detection from polysomnography (PSG) recordings is a widely used method of monitoring sleep quality. Despite significant progress in the development of machine-learning (ML)-based and deep-learning (DL)-based automatic sleep stage detection schemes focusing on single-channel PSG data, such as single-channel electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG), developing a standard model is still an active subject of research. Often, the use of a single source of information suffers from data inefficiency and data-skewed problems. Instead, a multi-channel input-based classifier can mitigate the aforementioned challenges and achieve better performance. However, it requires extensive computational resources to train the model, and, hence, a tradeoff between performance and computational resources cannot be ignored. In this article, we aim to introduce a multi-channel, more specifically a four-channel, convolutional bidirectional long short-term memory (Bi-LSTM) network that can effectively exploit spatiotemporal features of data collected from multiple channels of the PSG recording (e.g., EEG Fpz-Cz, EEG Pz-Oz, EOG, and EMG) for automatic sleep stage detection. First, a dual-channel convolutional Bi-LSTM network module has been designed and pre-trained utilizing data from every two distinct channels of the PSG recording. Subsequently, we have leveraged the concept of transfer learning circuitously and have fused two dual-channel convolutional Bi-LSTM network modules to detect sleep stages. In the dual-channel convolutional Bi-LSTM module, a two-layer convolutional neural network has been utilized to extract spatial features from two channels of the PSG recordings. These extracted spatial features are subsequently coupled and given as input at every level of the Bi-LSTM network to extract and learn rich temporal correlated features. Both Sleep EDF-20 and Sleep EDF-78 (expanded version of Sleep EDF-20) datasets are used in this study to evaluate the result. The model that includes an EEG Fpz-Cz + EOG module and an EEG Fpz-Cz + EMG module can classify sleep stage with the highest value of accuracy (ACC), Kappa (Kp), and F1 score (e.g., 91.44%, 0.89, and 88.69%, respectively) on the Sleep EDF-20 dataset. On the other hand, the model consisting of an EEG Fpz-Cz + EMG module and an EEG Pz-Oz + EOG module shows the best performance (e.g., the value of ACC, Kp, and F1 score are 90.21%, 0.86, and 87.02%, respectively) compared to other combinations for the Sleep EDF-78 dataset. In addition, a comparative study with respect to other existing literature has been provided and discussed in order to exhibit the efficacy of our proposed model.

show abstract

Enhancing Arrhythmia Diagnosis with Data-Driven Methods: A 12-Lead ECG-Based Explainable AI Model

Chukwu,

Moreno-Sánchez

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Accurate and early prediction of arrhythmias using Electrocardiograms (ECG) presents significant challenges due to the non-stationary nature of ECG signals and inter-patient variability, posing difficulties even for seasoned cardiologists. Deep Learning (DL) methods offer precision in identifying diagnostic ECG patterns for arrhythmias, yet they often lack the transparency needed for clinical application, thus hindering their broader adoption in healthcare. This study introduces an explainable DL-based prediction model using ECG signals to classify nine distinct arrhythmia categories. We evaluated various DL architectures, including ResNet, DenseNet, and VGG16, using raw ECG data. The ResNet34 model emerged as the most effective, achieving an Area Under the Receiver Operating Characteristic (AUROC) of 0.98 and an F1-score of 0.826. Additionally, we explored a hybrid approach that combines raw ECG signals with Heart Rate Variability (HRV) features. Our explainability analysis, utilizing the SHAP technique, identifies the most influential ECG leads for each arrhythmia type and pinpoints critical signal segments for individual disease prediction. This study emphasizes the importance of explainability in arrhythmia prediction models, a critical aspect often overlooked in current research, and highlights its potential to enhance model acceptance and utility in clinical settings.

show abstract

A Parallel Cross Convolutional Recurrent Neural Network for Automatic Imbalanced ECG Arrhythmia Detection with Continuous Wavelet Transform

Cited by 6 publications

References 37 publications

Binary fire hawks optimizer with deep learning driven non-invasive diabetes detection and classification

Binary fire hawks optimizer with deep learning driven non-invasive diabetes detection and classification

An End-to-End Multi-Channel Convolutional Bi-LSTM Network for Automatic Sleep Stage Detection

Enhancing Arrhythmia Diagnosis with Data-Driven Methods: A 12-Lead ECG-Based Explainable AI Model

Contact Info

Product

Resources

About