EmotionalGAN

Chen, Genlang; Zhu, Yi; Hong, Zhiqing; Yang, Zaili

doi:10.1145/3349341.3349422

Cited by 25 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PPG periodicity is thus strongly correlated with ECG periodicity. They are also highly linked during episodes of arrhythmia [14,17,18]. Some of the most crucial parameters of an ECG are also linked to a pulmonary artery (PPG) pressure reading [19].…”

Section: Related Workmentioning

confidence: 99%

“…Even though deep learning has been used to process ECG for a variety of applications including biometrics [16], arrhythmia detection [18], emotion recognition [19], cognitive load analysis [20,21], and others, surprisingly few studies have addressed synthesis of ECG signals with deep neural networks [22][23][24]. Initial studies on the application of Generative Adversarial Networks (GANs) for the synthesis of electrocardiograms proposed the use of a bidirectional Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN) structure.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

ECG Signal Reconstruction from PPG Using Hybrid Deep Neural Networks

Ezzat,

Omer,

Mohamed

et al. 2024

RIA

View full text Add to dashboard Cite

Electrocardiograms (ECGs) and photoplethysmography (PPG) facilitate non-invasive cardiovascular monitoring; however, the correlation between their respective waveforms, which exhibit high cycle correlation, remains underexplored. This study aims to estimate ECG signals from PPG data using an array of Deep Neural Networks (DNNs) across varied transformation feature domains, thereby making PPG measurements a more expedient and less effort-intensive alternative to ECG acquisition. A novel, subject-specific deep learning model is introduced, combining the architectures of Convolutional Neural Networks (CNN) and bidirectional Long Short-Term Memory (BiLSTM), termed ConvBiLSTM. This hybrid model proposes an automatic method for ECG signal reconstruction. To ensure model robustness against deformation, spatial characteristics are first extracted using CNNs, followed by the extraction of temporal characteristics from the CNN output via BiLSTM. The BiLSTM approach mitigates the issues of gradient disappearance and expansion without compromising accuracy, an improvement over traditional RNN and LSTM methods. The performance of four distinct feature domains, namely the Time Domain (TD), Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), and Wavelet Scattering Transform (WST), is evaluated with regards to their efficacy in ECG signal reconstruction from PPG data using the ConvBiLSTM model. Superiority of the proposed DNN combination over individual DNNs was demonstrated through comparison of ConvBiLSTM performance. Simulation results reveal that our method achieves superior root mean square error (RMSE) in ECG signal reconstruction across all feature domains. Given the widespread application of RMSE in ECG monitoring, this metric was chosen as the key evaluation criterion. The combination of WST for PPG signals and DWT for ECG signal features demonstrated the lowest RMSE at 0.0654, indicating the potential of this approach for effective ECG signal reconstruction using PPG data.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

ECG Signal Reconstruction from PPG Using Hybrid Deep Neural Networks

Ezzat,

Omer,

Mohamed

et al. 2024

RIA

View full text Add to dashboard Cite

show abstract

“…They utilised an autoencoder network in conjunction with a Wasserstein GAN (WGAN) to enhance time series regression data. Chen et al [80] introduced EmotionalGAN, a model that utilises 1D CNNs to classify emotions from extended ECG patterns. Significant improvements were discovered when data augmentation was applied to Support Vector Machines (SVM) and Random Forests.…”

Section: Deep Learning-based Generative Modelsmentioning

confidence: 99%

Identification of Optimal Data Augmentation Techniques for Multimodal Time-Series Sensory Data: A Framework

Ashfaq,

Khan,

Nisar

2024

Information

View full text Add to dashboard Cite

Recently, the research community has shown significant interest in the continuous temporal data obtained from motion sensors in wearable devices. These data are useful for classifying and analysing different human activities in many application areas such as healthcare, sports and surveillance. The literature has presented a multitude of deep learning models that aim to derive a suitable feature representation from temporal sensory input. However, the presence of a substantial quantity of annotated training data is crucial to adequately train the deep networks. Nevertheless, the data originating from the wearable devices are vast but ineffective due to a lack of labels which hinders our ability to train the models with optimal efficiency. This phenomenon leads to the model experiencing overfitting. The contribution of the proposed research is twofold: firstly, it involves a systematic evaluation of fifteen different augmentation strategies to solve the inadequacy problem of labeled data which plays a critical role in the classification tasks. Secondly, it introduces an automatic feature-learning technique proposing a Multi-Branch Hybrid Conv-LSTM network to classify human activities of daily living using multimodal data of different wearable smart devices. The objective of this study is to introduce an ensemble deep model that effectively captures intricate patterns and interdependencies within temporal data. The term “ensemble model” pertains to fusion of distinct deep models, with the objective of leveraging their own strengths and capabilities to develop a solution that is more robust and efficient. A comprehensive assessment of ensemble models is conducted using data-augmentation techniques on two prominent benchmark datasets: CogAge and UniMiB-SHAR. The proposed network employs a range of data-augmentation methods to improve the accuracy of atomic and composite activities. This results in a 5% increase in accuracy for composite activities and a 30% increase for atomic activities.

show abstract

“…Emotional GAN [108] also applies these 1D convolutional layers to create a GAN architecture to augment an electrocardiogram (ECG) dataset improving the classification of support vector machine (SVM) and random forest models when classifying the emotions of each subject. This work used different datasets varying their frequency rate between 256 and 2048 Hz.…”

Section: D Convolutional Ganmentioning

confidence: 99%

Data Augmentation techniques in time series domain: a survey and taxonomy

Iglesias

Talavera

González-Prieto

et al. 2023

Neural Comput & Applic

View full text Add to dashboard Cite

With the latest advances in deep learning-based generative models, it has not taken long to take advantage of their remarkable performance in the area of time series. Deep neural networks used to work with time series heavily depend on the size and consistency of the datasets used in training. These features are not usually abundant in the real world, where they are usually limited and often have constraints that must be guaranteed. Therefore, an effective way to increase the amount of data is by using data augmentation techniques, either by adding noise or permutations and by generating new synthetic data. This work systematically reviews the current state of the art in the area to provide an overview of all available algorithms and proposes a taxonomy of the most relevant research. The efficiency of the different variants will be evaluated as a central part of the process, as well as the different metrics to evaluate the performance and the main problems concerning each model will be analysed. The ultimate aim of this study is to provide a summary of the evolution and performance of areas that produce better results to guide future researchers in this field.

show abstract

EmotionalGAN

Cited by 25 publications

References 23 publications

ECG Signal Reconstruction from PPG Using Hybrid Deep Neural Networks

ECG Signal Reconstruction from PPG Using Hybrid Deep Neural Networks

Identification of Optimal Data Augmentation Techniques for Multimodal Time-Series Sensory Data: A Framework

Data Augmentation techniques in time series domain: a survey and taxonomy

Contact Info

Product

Resources

About