A Weighted Overlook Graph Representation of EEG Data for Absence Epilepsy Detection

Wang, Jialin; Shen, Liang; Wang, Ye; Zhang, Yanchun; He, Di; Ma, Jiangang; Ruan, Chunyang; Wu, Yingcheng; Hong, X. C.; Shen, Jiaqiu

doi:10.1109/icdm50108.2020.00067

Cited by 9 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For epilepsy detection, this restriction is usually too strict, resulting in too few edges to be created, which makes it difficult to distinguish between epileptic seizures and nonepileptic seizures. Therefore, the weighted overlook graph (WOG) method [29] enhances the ability of the graph representation method to distinguish EEG limit numbers by improving the connection criterion. Since these graph structures have many redundant edges, such graph representation occupies large computation space to store redundancy of weights.…”

Section: A Eeg Signal Data Representation Methodsmentioning

confidence: 99%

“…In this section, we evaluate our method on the Bonn dataset [54] and the spikes and slow waves (SSW) dataset [29]. We conduct experiments on graph representation, model classification performance, and pruning methods to estimate the performance of our proposed method in three parts.…”

Section: Methodsmentioning

confidence: 99%

“…The method we proposed is based on the classical graph representation [23], [25], [29]. Considering two arbitrary data points x i and x j (i < j) in an EEG signal x, an weighted, directed edge α i, j is created.…”

Section: B Weighted Neighbor Field Graphmentioning

confidence: 99%

“…The sampling frequency is 200 Hz. Usually, the duration of an SSW was less than 1 s. See [29] for details. Therefore, we divide the signal into 1 s (containing 200 data points) and mark the signal by clinical experts from famous local hospitals.…”

Section: A Datasetsmentioning

confidence: 99%

See 3 more Smart Citations

SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification

Wang

Gao

Zheng

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

In this article, we propose a sparse spectra graph convolutional network (SSGCNet) for epileptic electroencephalogram (EEG) signal classification. The goal is to develop a lightweighted deep learning model while retaining a high level of classification accuracy. To do so, we propose a weighted neighborhood field graph (WNFG) to represent EEG signals. The WNFG reduces redundant edges between graph nodes and has lower graph generation time and memory usage than the baseline solution. The sequential graph convolutional network is further developed from a WNFG by combining sparse weight pruning and the alternating direction method of multipliers (ADMM). Compared with the state-of-the-art method, our method has the same classification accuracy on the Bonn public dataset and the spikes and slow waves (SSW) clinical real dataset when the connection rate is ten times smaller.

show abstract

Section: A Eeg Signal Data Representation Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: B Weighted Neighbor Field Graphmentioning

confidence: 99%

Section: A Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification

Wang

Gao

Zheng

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Representation Learning for Unstructured Data: Combining feature representations of unstructured data (like text, images and genome sequences) with features extracted from graphs proved beneficial in multiple applications like rumor detection [12], social community detection [13], disease identification in medical images [14], and metagenome classification [15]. Learning low-dimensional feature representations from metagenome sequences are key aspects of existing deep learning algorithms for metagenome classification.…”

Section: Related Workmentioning

confidence: 99%

Metagenome2Vec: Building Contextualized Representations for Scalable Metagenome Analysis

Aakur¹,

Indla²,

Indla³

et al. 2021

Preprint

View full text Add to dashboard Cite

Advances in next-generation metagenome sequencing have the potential to revolutionize the point-of-care diagnosis of novel pathogen infections, which could help prevent potential widespread transmission of diseases. Given the high volume of metagenome sequences, there is a need for scalable frameworks to analyze and segment metagenome sequences from clinical samples, which can be highly imbalanced. There is an increased need for learning robust representations from metagenome reads since pathogens within a family can have highly similar genome structures (some more than 90%) and hence enable the segmentation and identification of novel pathogen sequences with limited labeled data. In this work, we propose Metagenome2Vec -a contextualized representation that captures the global structural properties inherent in metagenome data and local contextualized properties through self-supervised representation learning. We show that the learned representations can help detect six (6) related pathogens from clinical samples with less than 100 labeled sequences. Extensive experiments on simulated and clinical metagenome data show that the proposed representation encodes compositional properties that can generalize beyond annotations to segment novel pathogens in an unsupervised setting.

show abstract

Detection and explanation of anomalies in healthcare data

Samariya

Aryal

et al. 2023

Health Inf Sci Syst

Self Cite

View full text Add to dashboard Cite

The growth of databases in the healthcare domain opens multiple doors for machine learning and artificial intelligence technology. Many medical devices are available in the medical field; however, medical errors remain a severe challenge. Different algorithms are developed to identify and solve medical errors, such as detecting anomalous readings, anomalous health conditions of a patient, etc. However, they fail to answer why those entries are considered an anomaly. This research gap leads to an outlying aspect mining problem. The problem of outlying aspect mining aims to discover the set of features (a.k.a subspace) in which the given data point is dramatically different than others. In this paper, we present a framework that detects anomalies in healthcare data and then provides an explanation of anomalies. This paper aims to effectively and efficiently detect anomalies and explain why they are considered anomalies by detecting outlying aspects. First, we re-introduced four anomaly detection techniques and outlying aspect mining algorithms. Then, we evaluate the performance of anomaly detection techniques and choose the best anomaly detection algorithm. Later, we detect the top k anomaly as a query and detect their outlying aspect. Lastly, we evaluate their performance on 16 real-world healthcare datasets. The experimental results show that the latest isolation-based outlying aspect mining measure, SiNNE, has outstanding performance on this task and has promising results.

show abstract

A Weighted Overlook Graph Representation of EEG Data for Absence Epilepsy Detection

Cited by 9 publications

References 27 publications

SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification

SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification

Metagenome2Vec: Building Contextualized Representations for Scalable Metagenome Analysis

Detection and explanation of anomalies in healthcare data

Contact Info

Product

Resources

About