The recent embedding of electroencephalographic (EEG) electrodes in wearable devices raises the problem of the quality of the data recorded in such uncontrolled environments. These recordings are often obtained with dry single-channel EEG devices, and may be contaminated by many sources of noise which can compromise the detection and characterization of the brain state studied. In this paper, we propose a classification-based approach to effectively quantify artefact contamination in EEG segments, and discriminate muscular artefacts. The performance of our method were assessed on different databases containing either artificially contaminated or real artefacts recorded with different type of sensors, including wet and dry EEG electrodes. Furthermore, the quality of unlabelled databases was evaluated. For all the studied databases, the proposed method is able to rapidly assess the quality of the EEG signals with an accuracy higher than 90%. The obtained performance suggests that our approach provide an efficient, fast and automated quality assessment of EEG signals from low-cost wearable devices typically composed of a dry single EEG channel.
We consider the problem of resource allocation for a Direct Sequence Code Division Multiple Access (DS-CDMA) wireless visual sensor network (VSN). We use the Nash Bargaining Solution (NBS) from game theory in order to determine the transmission power and source and channel coding rate for each node. The NBS assumes that the nodes negotiate (using the help of a centralized control unit) in order to jointly determine their transmission parameters. The transmission powers are allowed to take continuous values, whereas the source and channel coding rate combination can only assume discrete values. Thus, the resulting optimization problem is a mixedinteger optimization task and is solved using Particle Swarm Optimization (PSO). Experimental results are provided and conclusions are drawn.
In this work, we propose a No-Reference (NR) bitstream-based model for predicting the quality of H.264/AVC video sequences, affected by both compression artifacts and transmission impairments. The proposed model is based on a feature extraction procedure, where a large number of features are calculated from the packet-loss impaired bitstream. Many of the features are firstly proposed in this work, and the specific set of the features as a whole is applied for the first time for making NR video quality predictions. All feature observations are taken as input to the Least Absolute Shrinkage and Selection Operator (LASSO) regression method. LASSO indicates the most important features, and using only them, it is possible to estimate the Mean Opinion Score (MOS) with high accuracy. Indicatively, we point out that only 13 features are able to produce a Pearson Correlation Coefficient of 0.92 with the MOS. Interestingly, the performance statistics we computed in order to assess our method for predicting the Structural Similarity Index and the Video Quality Metric are equally good. Thus, the obtained experimental results verified the suitability of the features selected by LASSO as well as the ability of LASSO in making accurate predictions through sparse modeling.
Keywords:Electroencephalography (EEG) melomind TM P300 SSVEPs quality assessment wearable systems Spinelli et al. Running title: Melomind™ signal quality 2 Abstract Wearable EEG systems have become accessible to researchers and clinicians over the last decade, thus requiring neurotechnology companies to seek for outstanding EEG signal quality. Here, weshow that the melomind TM headset equipped with dry electrodes (myBrain Technologies, Paris, France) allows the recording of reliable electro-cortical dynamics as compared to a wet-based standard-EEG system (actiCAP, Brain Products GmbH, Gilching, Germany). EEGs were acquired simultaneously from the two systems while thirteen subjects underwent a visual oddball, a steadystate visually-evoked potentials (SSVEPs) and two resting-state (RS) tasks. RS were acquired with eyes-closed and eyes-open (2 minutes each) and repeated twice (before and after the cognitive tasks).During the oddball task, participants responded on a gamepad when a target-stimulus was displayed.In the SSVEPs, visual responses were elicited at 15 and 20 Hz through a series of 15-second stimuli presented 5 times each. The power of theta- [4][5][6][7][8], and beta-[13-30 Hz] band was extracted from the two RS. The signal-to-noise-ratio in the 15 (± 1) and 20 (± 1) Hz range was computed from the SSVEPs. The shape of the N2/P300 complex was analysed from the oddball task. Strong correlations resulted between the parameters obtained from the two EEG systems (0.53 < Pearson's r < 0.97). Bland and Altman analysis revealed small dissimilarities between the two systems, with values laying in the 95% confidence interval in all the tasks. Our results demonstrate that the melomind TM is an affordable solution to reliably assess humans' electro-cortical dynamics atrest and during cognitive tasks, thus paving the way to its use in neuroscience studies and braincomputer interfaces. Spinelli et al. Running title: Melomind™ signal quality 3
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.