Abstract:Two of the biggest challenges in building models for detecting emotions from electroencephalography (EEG) devices are the relatively small amount of labeled samples and the strong variability of signal feature distributions between different subjects. In this study, we propose a context-generalized model that tackles the data constraints and subject variability simultaneously using a deep neural network architecture optimized for normally distributed subject-independent feature embeddings. Variational autoenco… Show more
“…Numerous ConvNets with end-to-end architecture have been proposed to learn informative features and deal with the variation of noises in EEG analysis automatically and efficiently. For instance, attention classification using Shallow ConvNet and long short-term memory (LSTM) network on a three-back task [ 30 ], and emotion classification using subject-invariant bilateral variational domain adversarial neural network [ 31 ]. However, EEG features need to be extracted into various representations that improve the learning effect, especially for EEG analysis.…”
Deep learning using an end-to-end convolutional neural network (ConvNet) has been applied to several electroencephalography (EEG)-based brain–computer interface tasks to extract feature maps and classify the target output. However, the EEG analysis remains challenging since it requires consideration of various architectural design components that influence the representational ability of extracted features. This study proposes an EEG-based emotion classification model called the multi-kernel temporal and spatial convolution network (MultiT-S ConvNet). The multi-scale kernel is used in the model to learn various time resolutions, and separable convolutions are applied to find related spatial patterns. In addition, we enhanced both the temporal and spatial filters with a lightweight gating mechanism. To validate the performance and classification accuracy of MultiT-S ConvNet, we conduct subject-dependent and subject-independent experiments on EEG-based emotion datasets: DEAP and SEED. Compared with existing methods, MultiT-S ConvNet outperforms with higher accuracy results and a few trainable parameters. Moreover, the proposed multi-scale module in temporal filtering enables extracting a wide range of EEG representations, covering short- to long-wavelength components. This module could be further implemented in any model of EEG-based convolution networks, and its ability potentially improves the model’s learning capacity.
“…Numerous ConvNets with end-to-end architecture have been proposed to learn informative features and deal with the variation of noises in EEG analysis automatically and efficiently. For instance, attention classification using Shallow ConvNet and long short-term memory (LSTM) network on a three-back task [ 30 ], and emotion classification using subject-invariant bilateral variational domain adversarial neural network [ 31 ]. However, EEG features need to be extracted into various representations that improve the learning effect, especially for EEG analysis.…”
Deep learning using an end-to-end convolutional neural network (ConvNet) has been applied to several electroencephalography (EEG)-based brain–computer interface tasks to extract feature maps and classify the target output. However, the EEG analysis remains challenging since it requires consideration of various architectural design components that influence the representational ability of extracted features. This study proposes an EEG-based emotion classification model called the multi-kernel temporal and spatial convolution network (MultiT-S ConvNet). The multi-scale kernel is used in the model to learn various time resolutions, and separable convolutions are applied to find related spatial patterns. In addition, we enhanced both the temporal and spatial filters with a lightweight gating mechanism. To validate the performance and classification accuracy of MultiT-S ConvNet, we conduct subject-dependent and subject-independent experiments on EEG-based emotion datasets: DEAP and SEED. Compared with existing methods, MultiT-S ConvNet outperforms with higher accuracy results and a few trainable parameters. Moreover, the proposed multi-scale module in temporal filtering enables extracting a wide range of EEG representations, covering short- to long-wavelength components. This module could be further implemented in any model of EEG-based convolution networks, and its ability potentially improves the model’s learning capacity.
“…For these reasons, newer studies tried to overcome the Dataset Shift problem in EEG-based BCIs [32]. In particular, Domain Adaptation (DA) strategies try to construct models able to generalize on unseen data exploiting knowledge given by available unlabelled data.…”
This work addresses the employment of Machine Learning (ML) and Domain Adaptation (DA) in the framework of Brain-Computer Interfaces (BCIs) based on Steady-State Visually Evoked Potentials (SSVEPs). Currently, all the state-of-the-art classification strategies do not consider the high non-stationarity typical of brain signals. This can lead to poor performance, expecially when short-time signals have to be considered to allow real-time human-environment interaction. In this regard, ML and DA techniques can represent a suitable strategy to enhance the performance of SSVEPs classification pipelines. In particular, the employment of a two-step DA technique is proposed: first, the standardization of the data per subject is performed by exploiting a part of unlabeled test data during the training stage; second, a similarity measure between subjects is considered in the selection of the validation sets. The proposal was applied to three classifiers to verify the statistical significance of the improvements over the standard approaches. These classifiers were validated and comparatively tested on a well-known public benchmark dataset. An appropriate validation method was used in order to simulate real-world usage. The experimental results show that the proposed approach significantly improves the classification accuracy of SSVEPs. In fact, up to 62.27 % accuracy was achieved also in the case of short-time signals (i.e., 1.0 s). This represents a further confirmation of the suitability of advanced ML to improve the performance of BCIs for daily-life applications.
“…VAE often employs Kullback-Leibler (KL) divergence, which is a measure of how the probability distribution of the latent space differs from that generated by sampling data from it [20]. A special version of the VAE was proposed in [21], focused on learning a generalised model of emotion by concurrently optimizing the goal or learning normally distributed and subjectindependent feature representations, via the use of spectral topography data. The ultimate objective was to maximize dataset inter-compatibility, improve robustness to localized electrode noise, and provide a more generally applicable method within neuroscience.…”
Section: B Variational Autoencoders For Feature Representationmentioning
Dimensionality reduction and the automatic learning of key features from electroencephalographic (EEG) signals have always been challenging tasks. Variational autoencoders (VAEs) have been used for EEG data generation and augmentation, denoising, and automatic feature extraction. However, investigations of the optimal shape of their latent space have been neglected. This research tried to understand the minimal size of the latent space of convolutional VAEs, trained with spectral topographic EEG head-maps of different frequency bands, that leads to the maximum reconstruction capacity of the input and maximum utility for classification tasks. Head-maps are generated employing a sliding window technique with a 125ms shift. Person-specific convolutional VAEs are trained to learn latent spaces of varying dimensions while a dense neural network is trained to investigate their utility on a classification task. The empirical results suggest that when VAEs are deployed on spectral topographic maps with shape 32x32, deployed for 32 electrodes from 2 seconds cerebral activity, they were capable of reducing the input up to almost 99%, with a latent space of 28 means and standard deviations. This did not compromise the salient information, as confirmed by a structural similarity index, and mean squared error between the input and reconstructed maps. Additionally, along the 28 means maximized the utility of latent spaces in the classification task, with an average 0.93% accuracy. This study contributes to the body of knowledge by offering a pipeline for effective dimensionality reduction of EEG data by employing convolutional variational autoencoders.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.