Performance comparison of CNN and LSTM algorithms for arrhythmia classification

Hassan, Shahab Ul; Zahid, Mohd Soperi Mohd; Husain, Khaleel

doi:10.1109/icci51257.2020.9247636

Cited by 11 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, machine learning methods-particularly neural networks-perform exceptionally well at identifying patterns and correlations in massive volumes of data and have succeeded in various fields, including recommendation systems, picture recognition, and natural language processing [4]. However, standalone neural networks are less suited to modelling physical systems and adhering to fundamental principles because of the lack of explicit knowledge of physical laws.…”

Section: Introductionmentioning

confidence: 99%

“…The most straightforward network is a feedforward network, in which information moves from the input layer to the output layer in one direction without needing feedback loops. Recurrent networks can recognize temporal relationships in data because of feedback connections [4]. Convolutional networks are made to perform image recognition tasks by extracting information from pictures using convolutional and pooling layers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Neural Networks Solutions for Solving Differential Equations: A Focus and Example for Flow of Viscoelastic Fluid with Microrotation

Abdullah,

Ibrahima Faye,

Laila Amera Aziz

2024

ARFMTS

View full text Add to dashboard Cite

Physics-informed neural networks (PINN) are an artificial neural network (ANN) approach for solving differential equations. PINN offers an alternative to classical numerical methods. The paper discusses the applications of PINN in various domains by highlighting the advantages, challenges, limitations, and some future directions. For example, PINN is implemented to solve the differential equations describing the Flow of Viscoelastic Fluid with Microrotation at a Horizontal Circular Cylinder Boundary Layer. The differential equations resulting from a nondimensionalization process of the governing equations and the associated boundary conditions are solved using PINN. The obtained results using PINN are discussed and compared to other state-of-the-art methods. Future research might aim to increase the precision and effectiveness of PINN models for solving differential equations, either by adding more physics-based restrictions or multi-scale methods to expand their capabilities. Additionally, investigating new application domains like linked multi-physics issues or real-time simulation situations may help to increase the reach and significance of PINN approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial Neural Networks Solutions for Solving Differential Equations: A Focus and Example for Flow of Viscoelastic Fluid with Microrotation

Abdullah,

Ibrahima Faye,

Laila Amera Aziz

2024

ARFMTS

View full text Add to dashboard Cite

show abstract

“…Many existing studies have integrated CNN and LSTM to create a hybrid model that combined their respective strengths. [33][34][35][36][37][38][39] Additionally, Hassan et al 40 systematically compared the detection efficiency of CNN and LSTM, suggesting that CNN performs better than LSTM. Moreover, there are other studies mainly focuses on the use of CNN, RNN, LSTM and the combination of these models, as well as classic architectures such as Stacked Auto-encoders (SAE) [41][42][43][44][45][46] and deep belief network (DBN).…”

Section: Introductionmentioning

confidence: 99%

“…Many existing studies have integrated CNN and LSTM to create a hybrid model that combined their respective strengths 33–39 . Additionally, Hassan et al 40 . systematically compared the detection efficiency of CNN and LSTM, suggesting that CNN performs better than LSTM.…”

Section: Introductionmentioning

confidence: 99%

A novel transformer‐based ECG dimensionality reduction stacked auto‐encoders for arrhythmia beat detection

et al. 2023

View full text Add to dashboard Cite

BackgroundElectrocardiogram (ECG) is a powerful tool for studying cardiac activity and diagnosing various cardiovascular diseases, including arrhythmia. While machine learning and deep learning algorithms have been applied to ECG interpretation, there is still room for improvement. For instance, the commonly used Recurrent Neural Networks (RNNs), reply on its previous state to update and is therefore ineffective for parallel computing. RNN also struggles to efficiently address the issue of long‐distance reliance.PurposeTo reduce computational complexity by dimensionality reduction of ECG signals we constructed a Stacked Auto‐encoders model using Transformer for ECG‐based arrhythmia detection. And overcome the challenges of long‐term dependencies and limited parallelizability in traditional RNNs when applied to ECG signal processing.MethodsIn this paper, a Transformer‐Based ECG Dimensionality Reduction Stacked Auto‐encoders model is proposed for ECG‐based arrhythmia detection. The transformer is used to encode ECG signals into a feature matrix, which is then dimensionally reduced using unsupervised greedy training through the four linear layers. This resulted in a low‐dimensional representation of ECG features, which are subsequently classified using support vector machines (SVM) to minimize overfitting.ResultsThe proposed method is benchmarked on the MIT‐BIH Arrhythmia database. In the 10‐fold cross validation of beat‐based arrhythmia detection, the average accuracy, sensitivity, specificity and F1 score of the proposed method are 99.83%, 98.84%, 99.84% and 99.13%, respectively, for the record‐based arrhythmia detection which refers to the approach where the training and testing sets use ECG data from independent recorded patients are 88.10%, 49.79%, 91.56% and 39.95%, respectively.ConclusionsCompared to other existing ECG‐based arrhythmia detection methods, our proposed approach exhibits improved detection accuracy and stronger generalization for arrhythmia beats. Additionally, the use of the record‐based data division method makes our approach more suitable for clinical practice.

show abstract

“…Moreover, LSTM is a kind of artificial RNN, 19 , 20 which is suitable for classifying sequences and time-series data. LSTM only preserves the previous data because the only inputs it has received are from the past.…”

Section: Introductionmentioning

confidence: 99%

Classification of cardiac arrhythmia using a convolutional neural network and bi-directional long short-term memory

et al. 2022

Self Cite

View full text Add to dashboard Cite

Cardiac arrhythmia is a leading cause of cardiovascular disease, with a high fatality rate worldwide. The timely diagnosis of cardiac arrhythmias, determined by irregular and fast heart rate, may help lower the risk of strokes. Electrocardiogram signals have been widely used to identify arrhythmias due to their non-invasive approach. However, the manual process is error-prone and time-consuming. A better alternative is to utilize deep learning models for early automatic identification of cardiac arrhythmia, thereby enhancing diagnosis and treatment. In this article, a novel deep learning model, combining convolutional neural network and bi-directional long short-term memory, is proposed for arrhythmia classification. Specifically, the classification comprises five different classes: non-ectopic (N), supraventricular ectopic (S), ventricular ectopic (V), fusion (F), and unknown (Q) beats. The proposed model is trained, validated, and tested using MIT-BIH and St-Petersburg data sets separately. Also, the performance was measured in terms of precision, accuracy, recall, specificity, and f1-score. The results show that the proposed model achieves training, validation, and testing accuracies of 100%, 98%, and 98%, respectively with the MIT-BIH data set. Lower accuracies were shown for the St-Petersburg data set. The performance of the proposed model based on the MIT-BIH data set is also compared with the performance of existing models based on the MIT-BIH data set.

show abstract

Performance comparison of CNN and LSTM algorithms for arrhythmia classification

Cited by 11 publications

References 15 publications

Artificial Neural Networks Solutions for Solving Differential Equations: A Focus and Example for Flow of Viscoelastic Fluid with Microrotation

Artificial Neural Networks Solutions for Solving Differential Equations: A Focus and Example for Flow of Viscoelastic Fluid with Microrotation

A novel transformer‐based ECG dimensionality reduction stacked auto‐encoders for arrhythmia beat detection

Classification of cardiac arrhythmia using a convolutional neural network and bi-directional long short-term memory

Contact Info

Product

Resources

About