Since the launch of the first consumer grade EEG measuring sensors ‘NeuroSky Mindset’ in 2007, the market has witnessed an introduction of at least one new product every year by competing manufacturers, which include NeuroSky, Emotiv, interaXon and OpenBCI. There are numerous variations in the make and versions, but these products clearly share the key selling points of affordability, portability, and ease of use. These features are patently well placed provided one of the main objectives for their development is to attract a new target group of commercial users. Nevertheless, with several decades of traditional EEG usage in clinical and experimental settings, the shift toward commercial and engineering sides has not been achieved without skepticism. With this in mind, researchers in related fields have been tirelessly working to ensure that these putatively novel features were not introduced at the expense of efficiency and accuracy by conducting validation studies to compare the performance of data derived from consumer grade EEG devices with ones from standard research grade counterparts. In this review, we seek to provide the detail of the products supplied by the major players, summarize studies that evaluate consumer product’s performance against research grade devices, the key areas of applications that these consumer grade devices have been employed in over the past five years or so, and finally give our perspectives on the limitations and what these innovative tools could offer going forward in terms of research and commercial applications.

Objective: Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI, EEG rhythms are specific to a subject and various changes over time. These issues point to significant challenges to enhance the classification performance, especially in a subject-independent manner. Methods: To overcome these challenges, we propose MIN2Net, a novel end-to-end multi-task learning to tackle this task. We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously. Results: This approach reduces the complexity in pre-processing, results in significant performance improvement on EEG classification. Experimental results in a subject-independent manner show that MIN2Net outperforms the state-of-the-art techniques, achieving an F1-score improvement of 6.72% and 2.23% on the SMR-BCI and OpenBMI datasets, respectively. Conclusion: We demonstrate that MIN2Net improves discriminative information in the latent representation. Significance: This study indicates the possibility and practicality of using this model to develop MI-based BCI applications for new users without calibration.

Electroencephalography (EEG) is another method for performing Person Identification (PI). Due to the nature of the EEG signals, EEG-based PI is typically done while a person is performing a mental task such as motor control. However, few studies used EEG-based PI while the person is in different mental states (affective EEG). The aim of this study is to improve the performance of affective EEG-based PI using a deep learning approach. We proposed a cascade of deep learning using a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). CNNs are used to handle the spatial information from the EEG while RNNs extract the temporal information. We evaluated two types of RNNs, namely, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The proposed method is evaluated on the state-of-the-art affective dataset DEAP. The results indicate that CNN-GRU and CNN-LSTM can perform PI from different affective states and reach up to 99.90–100% mean Correct Recognition Rate. This significantly outperformed a support vector machine baseline system that used power spectral density features. Notably, the 100% mean CRR came from 32 subjects in DEAP dataset. Even after the reduction of the number of EEG electrodes from thirty-two to five for more practical applications, the model could still maintain an optimal result obtained from the frontal region, reaching up to 99.17%. Amongst the two deep learning models, we found that CNN-GRU and CNN-LSTM performed similarly while CNN-GRU expended faster training time. In conclusion, the studied DL approaches overcame the influence of affective states in EEG-Based PI reported in the previous works.

The detection of seizures in epileptic patients via Electroencephalography (EEG) is an essential key to medical treatment. With the advances in deep learning, many approaches are proposed to tackle this problem. However, concerns such as performance, speed, and subject-independency should still be considered for practical application. Thus, we propose EEGWaveNet, a novel end-to-end multiscale convolutional neural network designed to address epileptic seizure detection. Our network utilizes trainable depth-wise convolutions as discriminative filters to simultaneously gather features from each EEG channel and separate the signal into multiscale resolution. Then, the spatial-temporal features are extracted from each scale for further classification. To demonstrate the effectiveness of EEGWaveNet, we evaluate the model in three datasets: CHB-MIT, TUSZ, and BONN. From the results, EEGWaveNet’s performance is comparable to other baseline methods in the subject-dependent approach and outperforms the others in subject-independent approaches. EEGWaveNet also has time complexity comparable to the compact EEGNet-8,2. Moreover, we transfer the model trained from the subject-independent approach and fine-tune it with a 1-h recording, significantly improving sensitivity and F1-score (Binary) compared to without fine-tuning. This article indicates the possibility of further developing this model and the fine-tuning methodology toward healthcare 5.0, where the AI aid clinicians in a manner of man–machine collaboration.

Since, cancer is curable when diagnosed at an early stage, lung cancer screening plays an important role in preventive care. Although both low dose computed tomography (LDCT) and computed tomography (CT) scans provide greater medical information than normal chest x-rays, access to these technologies in rural areas is very limited. There is a recent trend toward using computer-aided diagnosis (CADx) to assist in the screening and diagnosis of cancer from biomedical images. In this study, the 121-layer convolutional neural network, also known as DenseNet-121 by G. Huang et. al., along with the transfer learning scheme is explored as a means of classifying lung cancer using chest x-ray images. The model was trained on a lung nodule dataset before training on the lung cancer dataset to alleviate the problem of using a small dataset. The proposed model yields 74.43±6.01% of mean accuracy, 74.96±9.85% of mean specificity, and 74.68±15.33% of mean sensitivity. The proposed model also provides a heatmap for identifying the location of the lung nodule. These findings are promising for further development of chest x-ray-based lung cancer diagnosis using the deep learning approach. Moreover, they solve the problem of a small dataset.

Event-related desynchronization and synchronization (ERD/S) and movement-related cortical potential (MRCP) play an important role in brain-computer interfaces (BCI) for lower limb rehabilitation, particularly in standing and sitting. However, little is known about the differences in the cortical activation between standing and sitting, especially how the brain’s intention modulates the pre-movement sensorimotor rhythm as they do for switching movements. In this study, we aim to investigate the decoding of continuous EEG rhythms during action observation (AO), motor imagery (MI), and motor execution (ME) for the actions of standing and sitting. We developed a behavioral task in which participants were instructed to perform both AO and MI/ME in regard to the transitioning actions of sit-to-stand and stand-to-sit. Our results demonstrated that the ERD was prominent during AO, whereas ERS was typical during MI at the alpha band across the sensorimotor area. A combination of the filter bank common spatial pattern (FBCSP) and support vector machine (SVM) for classification was used for both offline and classifier testing analyses. The offline analysis indicated the classification of AO and MI providing the highest mean accuracy at 82.73±2.54% in the stand-to-sit transition. By applying the classifier testing analysis, we demonstrated the higher performance of decoding neural intentions from the MI paradigm in comparison to the ME paradigm. These observations led us to the promising aspect of using our developed tasks based on the integration of both AO and MI to build future exoskeleton-based rehabilitation systems.