2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2019
DOI: 10.1109/globalsip45357.2019.8969309
|View full text |Cite
|
Sign up to set email alerts
|

A Deep Convolutional-Recurrent Neural Network Architecture for Parkinson’s Disease EEG Classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

2
17
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 41 publications
(27 citation statements)
references
References 16 publications
2
17
0
Order By: Relevance
“…Around half of the included studies used convolution neural networks ( n = 37); afterward, other neural networks ( n = 31) were implemented in the included studies, followed by artificial neural networks (ANNs) ( n = 10), recurrent neural networks (RNNs) ( n = 9), and fuzzy neural networks (FNNs), as shown in Table 3 . In the end, the most imitated neural network architecture in the included studies was LSTM ( n = 11) [ 6 , 34 , 36 , 38 , 40 , 65 , 70 , 74 , 77 , 80 , 83 ], VGG ( n = 3) [ 18 , 27 , 58 ], and DNN ( n = 6) [ 34 , 35 , 60 , 91 , 92 , 103 ]. Recently, with the developments of new techniques such as convolutional neural network [ 101 ] and transfer learning [ 63 ], deep learning gained significant advances in the computer vision tasks, e.g., ImageNet [ 77 ].…”
Section: Resultsmentioning
confidence: 99%
See 3 more Smart Citations
“…Around half of the included studies used convolution neural networks ( n = 37); afterward, other neural networks ( n = 31) were implemented in the included studies, followed by artificial neural networks (ANNs) ( n = 10), recurrent neural networks (RNNs) ( n = 9), and fuzzy neural networks (FNNs), as shown in Table 3 . In the end, the most imitated neural network architecture in the included studies was LSTM ( n = 11) [ 6 , 34 , 36 , 38 , 40 , 65 , 70 , 74 , 77 , 80 , 83 ], VGG ( n = 3) [ 18 , 27 , 58 ], and DNN ( n = 6) [ 34 , 35 , 60 , 91 , 92 , 103 ]. Recently, with the developments of new techniques such as convolutional neural network [ 101 ] and transfer learning [ 63 ], deep learning gained significant advances in the computer vision tasks, e.g., ImageNet [ 77 ].…”
Section: Resultsmentioning
confidence: 99%
“…However, CNN and transfer learning techniques were not limited to imaging data; they also learn complex features from voices and signal data [ 29 ]. Numerous studies used the biomedical voice ( n = 21) [ 4 , 6 , 22 , 23 , 29 , 33 , 44 , 48 , 50 , 52 , 53 , 55 , 60 , 61 , 73 , 74 , 84 , 93 , 100 , 104 , 105 ] and biometric signal ( n = 14) [ 26 , 31 , 34 , 36 , 45 , 46 , 57 , 62 , 64 , 65 , 68 , 89 , 96 , 98 ]; a few of the included studies used EEG and EMG signals ( n = 5) [ 32 , 39 , 51 , 83 , 85 ].…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…Deep learning models have been applied to PD EEG to perform a range of tasks such as discriminating on-medication from offmedication conditions (Shah et al, 2020) and classification between PD and healthy controls (HC) based on EEG collected during a specific task (Shi et al, 2019). However, there are only three studies (Lee et al, 2019a;Oh et al, 2018;Xu et al, 2020) that have deployed deep learning to discriminate between PD and HC using resting-state EEG. In (Oh et al, 2018), a thirteen-layer convolutional neural network (CNN) structure was proposed, which achieved 88.3% accuracy, 84.7% sensitivity, and 91.8% specificity using raw resting EEG data collected from 20 PD and 20 HC.…”
Section: Introductionmentioning
confidence: 99%