Context. Electroencephalography (EEG) is a complex signal and can require several years of training, as well as advanced signal processing and feature extraction methodologies to be correctly interpreted. Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data. Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question.Objective. In this work, we review 156 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, braincomputer interfacing, and cognitive and affective monitoring. We extract trends and highlight interesting approaches from this large body of literature in order to inform future research and formulate recommendations.Methods. Major databases spanning the fields of science and engineering were queried to identify relevant studies published in scientific journals, conferences, and electronic preprint repositories. Various data items were extracted for each study pertaining to 1) the data, 2) the preprocessing methodology, 3) the DL design choices, 4) the results, and 5) the reproducibility of the experiments. These items were then analyzed one by one to uncover trends. * The first two authors contributed equally to this work.Significance. To help the community progress and share work more effectively, we provide a list of recommendations for future studies. We also make our summary table of DL and EEG papers available and invite authors of published work to contribute to it directly.

No abstract

Near-infrared spectroscopy (NIRS) has recently been investigated as a non-invasive brain-computer interface (BCI). In particular, previous research has shown that NIRS signals recorded from the motor cortex during left- and right-hand imagery can be distinguished, providing a basis for a two-choice NIRS-BCI. In this study, we investigated the feasibility of an alternative two-choice NIRS-BCI paradigm based on the classification of prefrontal activity due to two cognitive tasks, specifically mental arithmetic and music imagery. Deploying a dual-wavelength frequency domain near-infrared spectrometer, we interrogated nine sites around the frontopolar locations (International 10-20 System) while ten able-bodied adults performed mental arithmetic and music imagery within a synchronous shape-matching paradigm. With the 18 filtered AC signals, we created task- and subject-specific maximum likelihood classifiers using hidden Markov models. Mental arithmetic and music imagery were classified with an average accuracy of 77.2% +/- 7.0 across participants, with all participants significantly exceeding chance accuracies. The results suggest the potential of a two-choice NIRS-BCI based on cognitive rather than motor tasks.

No abstract

Alzheimer's disease (AD) is a neurodegenerative disorder that accounts for nearly 70% of the more than 46 million dementia cases estimated worldwide. Although there is no cure for AD, early diagnosis and an accurate characterization of the disease progression can improve the quality of life of AD patients and their caregivers. Currently, AD diagnosis is carried out using standardized mental status examinations, which are commonly assisted by expensive neuroimaging scans and invasive laboratory tests, thus rendering the diagnosis time consuming and costly. Notwithstanding, over the last decade, electroencephalography (EEG) has emerged as a noninvasive alternative technique for the study of AD, competing with more expensive neuroimaging tools, such as MRI and PET. This paper reports on the results of a systematic review on the utilization of resting-state EEG signals for AD diagnosis and progression assessment. Recent journal articles obtained from four major bibliographic databases were analyzed. A total of 112 journal articles published from January 2010 to February 2018 were meticulously reviewed, and relevant aspects of these papers were compared across articles to provide a general overview of the research on this noninvasive AD diagnosis technique. Finally, recommendations for future studies with resting-state EEG were presented to improve and facilitate the knowledge transfer among research groups.

This article presents an overview of twelve existing objective speech quality and intelligibility prediction tools. Two classes of algorithms are presented, namely intrusive and non-intrusive, with the former requiring the use of a reference signal, while the latter does not. Investigated metrics include both those developed for normal hearing listeners, as well as those tailored particularly for hearing impaired (HI) listeners who are users of assistive listening devices (i.e., hearing aids, HAs, and cochlear implants, CIs). Representative examples of those optimized for HI listeners include the speech-to-reverberation modulation energy ratio, tailored to hearing aids (SRMR-HA) and to cochlear implants (SRMR-CI); the modulation spectrum area (ModA); the hearing aid speech quality (HASQI) and perception indices (HASPI); and the PErception MOdel - hearing impairment quality (PEMO-Q-HI). The objective metrics are tested on three subjectively-rated speech datasets covering reverberation-alone, noise-alone, and reverberation-plus-noise degradation conditions, as well as degradations resultant from nonlinear frequency compression and different speech enhancement strategies. The advantages and limitations of each measure are highlighted and recommendations are given for suggested uses of the different tools under specific environmental and processing conditions.

Abstract-Stochastic properties of the binary channel that describe the successes and failures of the transmission of a modulated signal over a time-correlated flat-fading channel are considered for investigation. This analysis is employed to develop th-order Markov models for such a burst channel. The order of the Markov model that generates accurate analytical models is estimated for a broad range of fading environments. The parameterization and accuracy of an important class of hidden Markov models, known as the Gilbert-Elliott channel (GEC), are also investigated. Fading rates are identified in which the th-order Markov model and the GEC model approximate the fading channel with similar accuracy. The latter model is useful for approximating slowly fading processes, since it provides a more compact parameterization.

No abstract