Boosting Generalization in Bio-signal Classification by Learning the Phase-Amplitude Coupling

@article{Lemkhenter2020BoostingGI,
  title={Boosting Generalization in Bio-signal Classification by Learning the Phase-Amplitude Coupling},
  author={Abdelhak Lemkhenter and P. Favaro},
  journal={Pattern Recognition},
  year={2020},
  volume={12544},
  pages={72 - 85}
}
Various hand-crafted feature representations of bio-signals rely primarily on the amplitude or power of the signal in specific frequency bands. The phase component is often discarded as it is more sample specific, and thus more sensitive to noise, than the amplitude. However, in general, the phase component also carries information relevant to the underlying biological processes. In fact, in this paper we show the benefits of learning the coupling of both phase and amplitude components of a bio… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 32 REFERENCES
Self-Supervised Representation Learning from Electroencephalography Signals
TLDR
This work presents self-supervision strategies that can be used to learn informative representations from multivariate time series and demonstrates that this approach outperforms a purely supervised approach in low data regimes, while capturing important physiological information without any access to labels. Expand
Deep learning-based electroencephalography analysis: a systematic review
TLDR
This work reviews 156 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain-computer interfacing, and cognitive and affective monitoring, to extract trends and highlight interesting approaches in order to inform future research and formulate recommendations. Expand
EEG phase patterns reflect the selectivity of neural firing.
TLDR
These findings support a neural basis for stimulus selective and entrained EEG phase patterns and reveal a level of interrelation between encephalographic signals and neural firing beyond simple amplitude covariations in both signals. Expand
Advanced Biosignal Processing
TLDR
Through 17 chapters, this book presents the principle of many advanced biosignal processing techniques by means of various advanced signal processing approaches, namely wavelets, Empirical Modal Decomposition, Neural networks, Markov models, Metaheuristics as well as hybrid approaches including wavelet networks and neuro-fuzzy networks. Expand
The Phase of Ongoing EEG Oscillations Predicts Visual Perception
TLDR
The results support the notion that ongoing oscillations shape perception by providing a temporal reference frame for neural codes that rely on precise spike timing, and indicate that the visual detection threshold fluctuates over time along with the phase of ongoing EEG activity. Expand
Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG
TLDR
Slow-wave microcontinuity, being based on a physiological model of sleep, reflects sleep depth more closely than SWP does, and confirms earlier reports that gender affects SWP but not sleep depth. Expand
Dynamic low frequency EEG phase synchronization patterns during proactive control of task switching
TLDR
It is confirmed that proactive control during a task switch was associated with frontoparietal theta connectivity, and a distinct role of delta band oscillatory synchronization in proactive control is found, engaging more posterior frontotemporal regions as opposed to fronto‐theta connectivity. Expand
Time series classification from scratch with deep neural networks: A strong baseline
TLDR
The proposed Fully Convolutional Network (FCN) achieves premium performance to other state-of-the-art approaches and the exploration of the very deep neural networks with the ResNet structure is also competitive. Expand
End-to-end Sleep Staging with Raw Single Channel EEG using Deep Residual ConvNets
TLDR
A 34-layer deep residual ConvNet architecture for end-to-end sleep staging is proposed, which takes raw single channel electroencephalogram signal as input and yields hypnogram annotations for each 30s segments as output. Expand
Age and gender affect different characteristics of slow waves in the sleep EEG.
TLDR
The notion that gender-related anatomical differences have a general effect on EEG amplitude, including during slow-wave sleep, supports the notion that aging affects the neurophysiologicalSlow-wave-generating mechanism. Expand
...
1
2
3
4
...