Proceedings ArticleDOI
Graph Signal Processing of EEG signals for Detection of Epilepsy
TLDR
Simulation results show that the proposed GDFT based features from Gaussian Weighted Visibility Graph (VG) can detect epileptic seizure with 100 % accuracy.Abstract:
Epileptic Seizure is a chronic nervous system disorder which is analyzed using Electroencephalogram (EEG) signals. This paper proposes a Graph Signal Processing technique called Graph Discrete Fourier Transform (GDFT) for the detection of epilepsy. EEG data points are projected on the Eigen space of Laplacian matrix of graph to produce GDFT coefficients. The Laplacian matrix is generated from weighted visibility graph constructed from EEG signals. It proposes Gaussian kernel based edge weights between the nodes. The proposed GDFT based feature vectors are then used to detect the seizure class from the given EEG signal using a crisp rule based classification. Simulation results show that the proposed GDFT based features from Gaussian Weighted Visibility Graph (VG) can detect epileptic seizure with 100 % accuracy.read more
Citations
More filters
Journal ArticleDOI
Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
TL;DR: A survey of different types of graph architectures and their applications in healthcare can be found in this article, where the authors provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure and electrical-based analysis.
Journal ArticleDOI
Graph Signal Processing, Graph Neural Network and Graph Learning on Biological Data: A Systematic Review
TL;DR: In this paper , the authors systematically review graph-based analysis methods of Graph Signal Processing (GSP), Graph Neural Networks (GNNs) and graph topology inference, and their applications to biological data.
Journal ArticleDOI
Graph-signal Reconstruction and Blind Deconvolution for Structured Inputs
TL;DR: In this paper, the authors provide a comprehensive and unifying view of several sampling, reconstruction, and recovery problems for signals defined on irregular domains that can be accurately represented by a graph and leverage those priors, the shift operator of the supporting graph, and the samples of the signal of interest to recover: the signal at the non-sampled nodes, the input (deconvolution), the filter coefficients (system identification), or any combination thereof (blind deconvolution).
Journal ArticleDOI
EEG decoding method based on multi-feature information fusion for spinal cord injury
Fang Zhou Xu,Jincheng Li,Gege Dong,Jianfei Li,Xinyi Chen,Jian-guo Zhu,Jinglu Hu,Yang Zhang,Shouwei Yue,Dong Wen,Jia Leng +10 more
TL;DR: In this paper , a deep learning framework based on a modified graph convolution neural network (M-GCN) is proposed, in which temporal-frequency processing is performed on the data through modified S-transform (MST) to improve the decoding performance of original EEG signals in different types of MI recognition.
Journal ArticleDOI
Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
David Ahmedt-Aristizabal,David Ahmedt-Aristizabal,Mohammad Ali Armin,Simon Denman,Clinton Fookes,Lars Petersson +5 more
TL;DR: A comprehensive survey of different types of graph architectures and their applications in healthcare can be found in this article, where the authors provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure and electrical-based analysis.
References
More filters
Journal ArticleDOI
The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
TL;DR: The field of signal processing on graphs merges algebraic and spectral graph theoretic concepts with computational harmonic analysis to process high-dimensional data on graphs as discussed by the authors, which are the analogs to the classical frequency domain and highlight the importance of incorporating the irregular structures of graph data domains when processing signals on graphs.
Journal ArticleDOI
Discrete Signal Processing on Graphs
TL;DR: This paper extends to signals on graphs DSP and its basic tenets, including filters, convolution, z-transform, impulse response, spectral representation, Fourier transform, frequency response, and illustrates DSP on graphs by classifying blogs, linear predicting and compressing data from irregularly located weather stations, or predicting behavior of customers of a mobile service provider.
Journal ArticleDOI
From time series to complex networks: The visibility graph
TL;DR: A simple and fast computational method, the visibility algorithm, that converts a time series into a graph, which inherits several properties of the series in its structure, enhancing the fact that power law degree distributions are related to fractality.
Journal ArticleDOI
Graph Frequency Analysis of Brain Signals
Weiyu Huang,Leah Goldsberry,Nicholas F. Wymbs,Scott T. Grafton,Danielle S. Bassett,Alejandro Ribeiro +5 more
TL;DR: It is observed that brain signals corresponding to different graph frequencies exhibit different levels of adaptability throughout learning, and a strong association between graph spectral properties of brain networks and the level of exposure to tasks performed is noticed.
Journal ArticleDOI
Weighted Visibility Graph With Complex Network Features in the Detection of Epilepsy
TL;DR: The experimental results demonstrate that the combined effect of both features is valuable for network metrics to characterize the EEG time series signals in case of weighted complex network generating up to 100% classification accuracy.