619 results found
Tonoyan Y, Looney D, Mandic DP, et al., 2014, PREDICTING SUBJECT PERFORMANCE LEVEL FROM EEG SIGNAL COMPLEXITY WHEN ENGAGED IN BCI PARADIGM, IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Publisher: IEEE, ISSN: 2161-0363
Xia Y, Jahanchahi C, Xu D, et al., 2014, The ℍℂ calculus, quaternion derivatives and caylay-hamilton form of quaternion adaptive filters and learning systems, Pages: 3395-3401
© 2014 IEEE. We introduce a novel and unifying framework for the calculation of gradients of both quaternion holomorphic functions and nonholomorphic real functions of quaternion variables. This is achieved by considering the isomorphism between the quaternion domain ℍ and the bivariate complex domain ℂ× ℂ, and by exploiting complex calculus to simplify the quaternion gradient calculation. The validation of the proposed ℍℂ calculus is performed against the existing HR calculus, and its convenience is illustrated in the context of gradient-based quaternion optimisation as well as in adaptive learning systems. Quaternion adaptive filtering algorithms and a dynamical perceptron update are next derived based on the bivariate complex representation of quaternions and the HC calculus. Simulations on both synthetic and real-world multidimensional signals support the analysis.
Looney D, Kidmose P, Mandic DP, 2014, Ear-EEg: User-centered and wearable BCI, Biosystems and Biorobotics, Pages: 41-50
© Springer-Verlag Berlin Heidelberg 2014. We present a radically new solution for EEG-based brain computer interface (BCI) where electrodes are embedded on a customized earpiece, as typically used in hearing aids (Ear-EEG). This provides a noninvasive, minimally intrusive and user-friendly EEG platform suitable for long-term use (days) in natural environments. The operation of Ear-EEG is illustrated for al-pha-attenuation and responses to auditory stimuli, and its potential in BCI is evaluated on an SSVEP study. We show that Ear-EEG bitrate performances are comparable with those of on-scalp electrodes, thus promising a quantum step forward for wearable BCI.
Xia Y, Mandic DP, 2014, A widely linear least mean phase algorithm for adaptive frequency estimation of unbalanced power systems, INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, Vol: 54, Pages: 367-375, ISSN: 0142-0615
Li L, Witon A, Marcora S, et al., 2014, EEG-based brain connectivity analysis of states of unawareness., Pages: 1002-1005
This work investigates phase synchrony as a neuro-marker for the identification of two brain states: coma and quasi-brain-death. Scalp electroencephalography (EEG) data of 34 patients were recorded in an intensive care unit (ICU), with 17 recordings for patients in a coma state, and 17 recordings for patients in a quasi-brain-death state. Phase synchrony was used for feature extraction from EEG recording by comparing the phase value between pairs of electrodes using an entropy based measure. In particular, we performed phase synchrony analysis in five standard frequency bands and provide visualization of the phase synchronies in matrices. The effectiveness of the phase synchrony features in each of the frequency bands are evaluated with statistical analysis. Results suggest phase synchrony for coma patients has a significant increase in the theta / alpha band compared to quasi-brain-death patients. Hence, we propose phase synchrony as a candidate for the identification of consciousness states between coma and quasi-brain-death.
Ujang BC, Jahanchahi C, Took CC, et al., 2013, Adaptive Convex Combination Approach for the Identification of Improper Quaternion Processes, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, Vol: 25, Pages: 172-182, ISSN: 2162-237X
Williamon A, Aufegger L, Wasley D, et al., 2013, Complexity of physiological responses decreases in high-stress musical performance, JOURNAL OF THE ROYAL SOCIETY INTERFACE, Vol: 10, ISSN: 1742-5689
Peng B, Liu W, Mandic DP, 2013, Design of oversampled generalised discrete Fourier transform filter banks for application to subband-based blind source separation, IET SIGNAL PROCESSING, Vol: 7, Pages: 843-853, ISSN: 1751-9675
Mandic DP, Rehman NU, Wu Z, et al., 2013, Empirical Mode Decomposition-Based Time-Frequency Analysis of Multivariate Signals, IEEE SIGNAL PROCESSING MAGAZINE, Vol: 30, Pages: 74-86, ISSN: 1053-5888
Took CC, Douglas SC, Mandic D, 2013, On intraference and its implications in complex-valued signal processing, Pages: 3934-3937, ISSN: 1520-6149
We introduce the concept of intra-ference in order to quantify the degree to which the integrity of bivariate (or complex) sources is preserved in applications based on matrix decompositions of bivariate data. This is achieved by examining the pseudocovariancematrix of noncircular complex sources, and by recognising that the pseudocovariance is intrinsically complex valued. We illuminate how the existing decompositions such as the strong uncorrelating transform (SUT) not only decorrelate the bivariate sources from one another, but also decorrelate and scatter the data channels within each bivariate source, thus violating source integrity. Examples showing that the intra-ference arises due to the phase ambiguity in the existing matrix decompositions support the approach. © 2013 IEEE.
Dini DH, Djuric PM, Mandic DP, 2013, The Augmented Complex Particle Filter, IEEE TRANSACTIONS ON SIGNAL PROCESSING, Vol: 61, Pages: 4341-4346, ISSN: 1053-587X
Navarro-Moreno J, Fernandez-Alcala RM, Took CC, et al., 2013, Prediction of wide-sense stationary quaternion random signals, SIGNAL PROCESSING, Vol: 93, Pages: 2573-2580, ISSN: 0165-1684
Peng B, Liu W, Mandic DP, 2013, Subband-based joint blind source separation for convolutive mixtures employing M-CCA
This paper addresses the source separation problem for convolutive mixtures by employing the joint blind source separation (BSS) technique in the subband domain. The key to the proposed method is to decompose the time-domain mixed signals into subbands to generate the required related multiple data sets for the operation of joint BSS. To reduce the aliasing error after subband decimation, the oversampled generalized DFT filter banks are employed to maintain a sufficient level of correlation between the data sets. A recently proposed correlation optimisation method for the design of filter banks is adopted to enhance the correlation between adjacent subband signals, which leads to further improved separation results in terms of both signal to interference ratio and subband permutation alignment.
Aguilera P, Cruces S, Duran-Diaz I, et al., 2013, Blind Separation of Dependent Sources With a Bounded Component Analysis Deflationary Algorithm, IEEE SIGNAL PROCESSING LETTERS, Vol: 20, Pages: 709-712, ISSN: 1070-9908
Xia Y, Mandic DP, 2013, Augmented MVDR Spectrum-Based Frequency Estimation for Unbalanced Power Systems, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, Vol: 62, Pages: 1917-1926, ISSN: 0018-9456
Mostafanezhad I, Yavari E, Boric-Lubecke O, et al., 2013, Cancellation of Unwanted Doppler Radar Sensor Motion Using Empirical Mode Decomposition, IEEE SENSORS JOURNAL, Vol: 13, Pages: 1897-1904, ISSN: 1530-437X
Ahrabian A, Rehman NU, Mandic D, 2013, Bivariate Empirical Mode Decomposition for Unbalanced Real-World Signals, IEEE SIGNAL PROCESSING LETTERS, Vol: 20, Pages: 245-248, ISSN: 1070-9908
Kidmose P, Mandic D, Ungstrup M, et al., 2013, A Hearing Aid Adapted for Detection Brain Waves and a Method for Adapting Such a Hearing Aid
Dini DH, Mandic DP, 2013, Widely Linear Modeling for Frequency Estimation in Unbalanced Three-Phase Power Systems, IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, Vol: 62, Pages: 353-363, ISSN: 0018-9456
Er W, Mandic DP, 2013, DYNAMICAL COMPLEXITY ANALYSIS OF MULTIVARIATE FINANCIAL DATA, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Publisher: IEEE, Pages: 8732-8736, ISSN: 1520-6149
Tobar FA, Mandic DP, 2013, THE QUATERNION KERNEL LEAST SQUARES, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Publisher: IEEE, Pages: 6128-6132, ISSN: 1520-6149
Zhao Q, Caiafa CF, Mandic D, et al., 2013, Higher-Order Partial Least Squares (HOPLS): A Generalized Multi-Linear Regression Method, IEEE Transactions on Pattern Analysis and Machine Intelligence, Pages: 1-1, ISSN: 0162-8828
Park C, Looney D, Rehman NU, et al., 2013, Classification of Motor Imagery BCI Using Multivariate Empirical Mode Decomposition, IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, Vol: 21, Pages: 10-22, ISSN: 1534-4320
Rutkowski TM, Struzik ZR, Mandic DP, 2013, EEG Epileptic Seizures Separation with Multivariate Empirical Mode Decomposition for Diagnostic Purposes, 35th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC), Publisher: IEEE, Pages: 7128-7131, ISSN: 1557-170X
Dini DH, Mandic DP, 2013, Exploiting sparsity in widely linear estimation, Pages: 808-812, ISSN: 2154-0217
The distribution of complex random signals is typically improper. It has recently been established that conventional strictly linear models are only second order optimum for signals with proper distributions, while so called "widelylinear models" are optimum for the generality of complex signals, both proper and improper. Widely-linear models, however, are over-parameterised when the underlying system is strictly-linear, requiring twice the number of parameters to be estimated compared to strictly-linear models. This effects widely-linear adaptive algorithms, such as the augmented complex least mean square (ACLMS) and augmented complex recursive least squares (ACRLS), and leads to slow convergence. We here address the problem of the over-parameterisation of the ACLMS through the use of regularised cost error functions, and illustrate its effects through analysis and simulations. © VDE Verlag GMBH.
Jahanchahi C, Mandic DP, 2013, AN ADAPTIVE DIFFUSION QUATERNION LMS ALGORITHM FOR DISTRIBUTED NETWORKS OF 3D AND 4D VECTOR SENSORS, 21st European Signal Processing Conference (EUSIPCO), Publisher: IEEE
Took CC, Douglas SC, Mandic D, 2013, u ON INTRAFERENCE AND ITS IMPLICATIONS IN COMPLEX-VALUED SIGNAL PROCESSING, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Publisher: IEEE, Pages: 3934-3937, ISSN: 1520-6149
Jahanchahi C, Cheong Took C, Mandic DP, 2013, A class of quaternion valued affine projection algorithms, Signal Processing, ISSN: 0165-1684
Kidmose P, Looney D, Jochumsen L, et al., 2013, Ear-EEG from generic earpieces: a feasibility study., Annu Int Conf IEEE Eng Med Biol Soc, Vol: 2013, Pages: 543-546
The use of brain monitoring based on EEG, in natural environments and over long time periods, is hindered by the limited portability of current wearable systems, and the invasiveness of implanted systems. To that end, we introduce an ear-EEG recording device based on generic earpieces which meets key patient needs (discreet, unobstrusive, user-friendly, robust) and that is low-cost and suitable for off-the-shelf use; thus promising great advantages for healthcare applications. Its feasibility is validated in a comprehensive comparative study with our established prototype, based on a personalized earpiece, for a key EEG paradigm.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.