Artificial Metaplasticity: Application to MIT-BIH Arrhythmias Database

Torres-Alegre, Santiago; Fombellida, Juan; Piñuela, J. A.; Andina, Diego

doi:10.1007/978-3-319-18914-7_14

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alonso et al use 13 parameters training patterns that can be divided into three types: time-morfological parameters, frequency parameters and complex parameters. Eljah et al generates 28 components training patterns using Discrete Wavelet Table 3 Classification accuracies obtained with our method and other classifiers from the literature References Minami et al [15] Owis et al [16] Yu et al [17] Benchaib et al [18] Ghorbanian et al [19] Benchaib et al [9] Alonso et al [20] Torres et al [11] Elhaj et al [21] Kyranyaz et al [22] Shanshan et al [23] In this study…”

Section: Performance Evaluationmentioning

confidence: 92%

“…In Table 2, results are presented, and SOM, AMSOM, AMMLPl and AMMLP2 stand, respectively, for standard self-organizing map, artificial metaplasticity SOM, MLP implementing Gaussian function to modify the weights of the network and MLP implementing the output of the network to modify the weights. AMMLPl and AMMLP2 results were presented in [9,11]. The models are evaluated based on the accuracy measures discussed above (classification accuracy, sensitivity and specificity).…”

Section: Performance Evaluationmentioning

confidence: 99%

“…Notice that to apply the proposed f£ function patterns are normalized. As the outputs of an MLP are approximations of the a posteriori probability of the different classes [10], another option of implementing AMMLP was presented by the authors of this contribution [11] based on the estimation of a posteriori probability density function considering f£ as follows:…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

AMSOM: artificial metaplasticity in SOM neural networks—application to MIT-BIH arrhythmias database

Torres-Alegre

Fombellida

Piñuela

et al. 2018

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Artificial metaplasticity is the machine learning algorithm inspired in the biological metaplasticity of neural synapses. Metaplasticity stands for plasticity of plasticity, and as long as plasticity is related to memory, metaplasticity is related to learning. Implemented in supervised learning assuming input patterns distribution or a related function, it has proved to be very efficient in performance and in training convergence for multidisciplinary applications. Now, for the first time, this kind of artificial metaplasticity is implemented in an unsupervised neural network, achieving also excellent results that are presented in this paper. To compare results, a modified self-organization map is applied to the classification of MIT-BIH cardiac arrhythmias database.

show abstract

Section: Performance Evaluationmentioning

confidence: 92%

Section: Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AMSOM: artificial metaplasticity in SOM neural networks—application to MIT-BIH arrhythmias database

Torres-Alegre

Fombellida

Piñuela

et al. 2018

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

show abstract

Application of Koniocortex-Like Networks to Cardiac Arrhythmias Classification

Torres-Alegre

Benchaib

Vicente

et al. 2019

From Bioinspired Systems and Biomedical Applications to Machine Learning

View full text Add to dashboard Cite

Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network

Zhu

et al. 2019

Sci Rep

178

123

View full text Add to dashboard Cite

Heart disease is a malignant threat to human health. Electrocardiogram (ECG) tests are used to help diagnose heart disease by recording the heart’s activity. However, automated medical-aided diagnosis with computers usually requires a large volume of labeled clinical data without patients' privacy to train the model, which is an empirical problem that still needs to be solved. To address this problem, we propose a generative adversarial network (GAN), which is composed of a bidirectional long short-term memory(LSTM) and convolutional neural network(CNN), referred as BiLSTM-CNN,to generate synthetic ECG data that agree with existing clinical data so that the features of patients with heart disease can be retained. The model includes a generator and a discriminator, where the generator employs the two layers of the BiLSTM networks and the discriminator is based on convolutional neural networks. The 48 ECG records from individuals of the MIT-BIH database were used to train the model. We compared the performance of our model with two other generative models, the recurrent neural network autoencoder(RNN-AE) and the recurrent neural network variational autoencoder (RNN-VAE). The results showed that the loss function of our model converged to zero the fastest. We also evaluated the loss of the discriminator of GANs with different combinations of generator and discriminator. The results indicated that BiLSTM-CNN GAN could generate ECG data with high morphological similarity to real ECG recordings.

show abstract

Artificial Metaplasticity: Application to MIT-BIH Arrhythmias Database

Cited by 4 publications

References 12 publications

AMSOM: artificial metaplasticity in SOM neural networks—application to MIT-BIH arrhythmias database

AMSOM: artificial metaplasticity in SOM neural networks—application to MIT-BIH arrhythmias database

Application of Koniocortex-Like Networks to Cardiac Arrhythmias Classification

Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network

Contact Info

Product

Resources

About