The integration of brain monitoring based on electroencephalography (EEG) into everyday life has been hindered by the limited portability and long setup time of current wearable systems as well as by the invasiveness of implanted systems (e.g. intracranial EEG). We explore the potential to record EEG in the ear canal, leading to a discreet, unobtrusive, and user-centered approach to brain monitoring. The in-the-ear EEG (Ear-EEG) recording concept is tested using several standard EEG paradigms, benchmarked against standard onscalp EEG, and its feasibility proven. Such a system promises a number of advantages, including fixed electrode positions, user comfort, robustness to electromagnetic interference, feedback to the user, and ease of use. The Ear-EEG platform could also support additional biosensors, extending its reach beyond EEG to provide a powerful health-monitoring system for those applications that require long recording periods in a natural environment.

Abstract-Brain electrical activity recorded via electroencephalogram (EEG) is the most convenient means for brain-computer interface (BCI), and is notoriously noisy. The information of interest is located in well defined frequency bands, and a number of standard frequency estimation algorithms have been used for feature extraction. To deal with data nonstationarity, low signal-to-noise ratio, and closely spaced frequency bands of interest, we investigate the effectiveness of recently introduced multivariate extensions of empirical mode decomposition (MEMD) in motor imagery BCI. We show that direct multichannel processing via MEMD allows for enhanced localization of the frequency information in EEG, and, in particular, its noise-assisted mode of operation (NA-MEMD) provides a highly localized time-frequency representation. Comparative analysis with other state of the art methods on both synthetic benchmark examples and a well established BCI motor imagery dataset support the analysis.Index Terms-Brain-computer interface (BCI), electroencephalogram (EEG), empirical mode decomposition, motor imagery paradigm, noise assisted multivariate extensions of empirical mode decomposition (NA-MEMD).

A noise-assisted approach in conjunction with multivariate empirical mode decomposition (MEMD) algorithm is proposed for the computation of empirical mode decomposition (EMD), in order to produce localized frequency estimates at the accuracy level of instantaneous frequency. Despite many advantages of EMD, such as its data driven nature, a compact decomposition, and its inherent ability to process nonstationary data, it only caters for signals with a sufficient number of local extrema. In addition, EMD is prone to mode-mixing and is designed for univariate data. We show that the noiseassisted MEMD (NA-MEMD) approach, which utilizes the dyadic filter bank property of MEMD, provides a solution to the above problems when used to calculate standard EMD. The method is also shown to alleviate the effects of noise interference in univariate noise-assisted EMD algorithms which directly add noise to the data. The efficacy of * Corresponding author. 1350007-1 N. ur Rehman et al.the proposed method, in terms of improved frequency localization and reduced modemixing, is demonstrated via simulations on electroencephalogram (EEG) data sets, over two paradigms in brain-computer interface (BCI).

We proposed an optimal deep learning architecture and its parameters for stress recognition, and the theoretical consideration on how to design the deep learning structure based on the periodic patterns of the raw ECG data. Experimental results in this study have proved that the proposed deep learning model, the Deep ECGNet, is an optimal structure to recognize the stress conditions using ultra short-term ECG data.

A novel augmented complex-valued common spatial pattern (CSP) algorithm is introduced in order to cater for general complex signals with noncircular probability distributions. This is a typical case in multichannel electroencephalogram (EEG), due to the power difference or correlation between the data channels, yet current methods only cater for a very restrictive class of circular data. The proposed complex-valued CSP algorithms account for the generality of complex noncircular data, by virtue of the use of augmented complex statistics and the strong-uncorrelating transform (SUT). Depending on the degree of power difference of complex signals, the analysis and simulations show that the SUT based algorithm maximizes the inter-class difference between two motor imagery tasks. Simulations on both synthetic noncircular sources and motor imagery experiments using real-world EEG support the approach.

No abstract

Blood pressure (BP) is a vital sign that provides fundamental health information regarding patients. Continuous BP monitoring is important for patients with hypertension. Various studies have proposed cuff-less BP monitoring methods using pulse transit time. We propose an end-to-end deep learning architecture using only raw signals without the process of extracting features to improve the BP estimation performance using the attention mechanism. The proposed model consisted of a convolutional neural network, a bidirectional gated recurrent unit, and an attention mechanism. The model was trained by a calibration-based method, using the data of each subject. The performance of the model was compared to the model that used each combination of the three signals, and the model with the attention mechanism showed better performance than other state-of-the-art methods, including conventional linear regression method using pulse transit time (PTT). A total of 15 subjects were recruited, and electrocardiogram, ballistocardiogram, and photoplethysmogram levels were measured. The 95% confidence interval of the reference BP was [86.34, 143.74] and [51.28, 88.74] for systolic BP (SBP) and diastolic BP (DBP), respectively. The R 2 values were 0.52 and 0.49, and the mean-absolute-error values were 4.06 ± 4.04 and 3.33 ± 3.42 for SBP and DBP, respectively. In addition, the results complied with global standards. The results show the applicability of the proposed model as an analytical metric for BP estimation.

Recent studies have demonstrated the disassociation between the mu and beta rhythms of electroencephalogram (EEG) during motor imagery tasks. The proposed algorithm in this paper uses a fully data-driven multivariate empirical mode decomposition (MEMD) in order to obtain the mu and beta rhythms from the nonlinear EEG signals. Then, the strong uncorrelating transform complex common spatial patterns (SUTCCSP) algorithm is applied to the rhythms so that the complex data, constructed with the mu and beta rhythms, becomes uncorrelated and its pseudocovariance provides supplementary power difference information between the two rhythms. The extracted features using SUTCCSP that maximize the interclass variances are classified using various classification algorithms for the separation of the left- and right-hand motor imagery EEG acquired from the Physionet database. This paper shows that the supplementary information of the power difference between mu and beta rhythms obtained using SUTCCSP provides an important feature for the classification of the left- and right-hand motor imagery tasks. In addition, MEMD is proved to be a preferred preprocessing method for the nonlinear and nonstationary EEG signals compared to the conventional IIR filtering. Finally, the random forest classifier yielded a high performance for the classification of the motor imagery tasks.