Multi-class time series classification of EEG signals with Recurrent Neural Networks

Dutta, Kusumika Krori

doi:10.1109/confluence.2019.8776889

Cited by 15 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose of this experiment is to evaluate the performance of the ASGCN model, compared with GRU (Dutta, 2019), CGCRN (Xu et al, 2019), Graph wavenet (Wu et al, 2019) models. Each experiment used the fNIRS data of whole brain region as the input of model.…”

Section: Identification Ability Comparison Of DI Erent Classification...mentioning

confidence: 99%

Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network

Zhang

Xu²,

Yu³

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

The accurate diagnosis of autism spectrum disorder (ASD) is of great practical significance in clinical practice. The spontaneous hemodynamic fluctuations were collected by functional near-infrared spectroscopy (fNIRS) from the bilateral frontal and temporal cortices of typically developing (TD) children and children with ASD. Since traditional machine learning and deep learning methods cannot make full use of the potential spatial dependence between variable pairs, and require a long time series to diagnose ASD. Therefore, we use adaptive spatiotemporal graph convolution network (ASGCN) and short time series to classify ASD and TD. To capture spatial and temporal features of fNIRS multivariable time series without the pre-defined graph, we combined the improved adaptive graph convolution network (GCN) and gated recurrent units (GRU). We conducted a series of experiments on the fNIRS dataset, and found that only using 2.1 s short time series could achieve high precision classification, with an accuracy of 95.4%. This suggests that our approach may have the potential to detect pathological signals in autism patients within 2.1 s. In different brain regions, the left frontal lobe has the best classification effect, and the abnormalities occur more frequently in left hemisphere and frontal lobe region. Moreover, we also found that there were correlations between multiple channels, which had different degrees of influence on the classification of ASD. From this, we can also generalize to a wider range, there may be potential correlations between different brain regions. This may help to better understand the cortical mechanism of ASD.

show abstract

Section: Identification Ability Comparison Of DI Erent Classification...mentioning

confidence: 99%

Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network

Zhang

Xu²,

Yu³

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Recurrent neural networks (RNNs) [ 13 , 14 ] are the most commonly used method. Modelling of time-series data by an RNN considers the time correlation of data, which is reflected in the connection of nodes between hidden layers; that is, the input of the hidden layer includes not only the output of the input layer but also the output of the hidden layer at the previous time.…”

Section: Related Workmentioning

confidence: 99%

“…To maintain the memory and dependence on the data, RNN’s variants, LSTM and the GRU were proposed in turn. Dutta [ 13 ], compared the simple RNN, LSTM, and GRU with EEG signal data. As the number of layers increases, although it takes longer, the accuracy of the latter two is significantly higher than that of the former.…”

Section: Related Workmentioning

confidence: 99%

Multi-Channel Fusion Classification Method Based on Time-Series Data

Yang

Kong

et al. 2021

Sensors

View full text Add to dashboard Cite

Time-series data generally exists in many application fields, and the classification of time-series data is one of the important research directions in time-series data mining. In this paper, univariate time-series data are taken as the research object, deep learning and broad learning systems (BLSs) are the basic methods used to explore the classification of multi-modal time-series data features. Long short-term memory (LSTM), gated recurrent unit, and bidirectional LSTM networks are used to learn and test the original time-series data, and a Gramian angular field and recurrence plot are used to encode time-series data to images, and a BLS is employed for image learning and testing. Finally, to obtain the final classification results, Dempster–Shafer evidence theory (D–S evidence theory) is considered to fuse the probability outputs of the two categories. Through the testing of public datasets, the method proposed in this paper obtains competitive results, compensating for the deficiencies of using only time-series data or images for different types of datasets.

show abstract

“…are used as feature extractor based on their energy compaction, using recurrence plots, based on dictionary learning and sparse representations, using Random forest (RF) classifier, using different layers of CNN, transfer learning, using deep batch normalization, using neural memory networks, etc. are tried out with different researcher using cleaned and raw data from different datasets [30][31][32][33][34][35][36][37][38][39][40][41][42]. Slowly real time clinical diagnostics is tried out [43].…”

Section: Introductionmentioning

confidence: 99%

Untitled

2023

AMLAI

View full text Add to dashboard Cite

Background: Epileptic Seizure type diagnosis is done by clinician based on the symptoms during the episode and the Electroencephalograph (EEG) recording taken during inter-ictal period. But main challenge is, most of the time with the absence of any attendee, the patients are unable to explain the symptoms and not possible to find signature in inter-ictal EEG signal. Aims: This paper aims to analyze epileptic seizure Electro-encephalograph (EEG) signals to diagnose seizure in pre-ictal, ictal and inter-ictal stages and to classify into seven different classes. Methods: Temple University Hospital licensed dataset is used for study. From the seizure corpus, seven seizure types are pre-processed and segregated into pre-ictal, ictal and inter-ictal stages. The multi class classification performed using different machine and deep learning techniques such as K-Nearest Neighbor (KNN) and Random Forest, etc.Results: Multiclass classification of seven type of epileptic seizure with 20 channels, with 80-20 train-test ratio, is achieved 94. 7%, 94.7%, 69.0% training accuracy and 94.46%, 94.46% 71.11% test accuracy by weighted KNN for pre-ictal, ictal and inter-ictal stages respectively. Conclusion:Seven epileptic seizure type classification using machine learning techniques carried out with MATLAB software and weighted KNN shows better accuracy comparatively.

show abstract

Multi-class time series classification of EEG signals with Recurrent Neural Networks

Cited by 15 publications

References 16 publications

Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network

Identification of autism spectrum disorder based on functional near-infrared spectroscopy using adaptive spatiotemporal graph convolution network

Multi-Channel Fusion Classification Method Based on Time-Series Data

Untitled

Contact Info

Product

Resources

About