2020
DOI: 10.1007/978-981-15-2317-5_47
|View full text |Cite
|
Sign up to set email alerts
|

kNN and SVM Classification for EEG: A Review

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
24
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 67 publications
(24 citation statements)
references
References 32 publications
0
24
0
Order By: Relevance
“…In this way, a demonstration of the continuous duration of the patient’s stay in the hospital is described as a series of sequential steps that the patient leaves until the hospital leaves ( 30 ). A conditional multi-stage distribution was used for the model of patient length of stay ( 31 ). Time Slicing Cox regression, an extended form of Cox regression, was used to predict mortality in the ICU ( 32 ).…”
Section: Discussionmentioning
confidence: 99%
“…In this way, a demonstration of the continuous duration of the patient’s stay in the hospital is described as a series of sequential steps that the patient leaves until the hospital leaves ( 30 ). A conditional multi-stage distribution was used for the model of patient length of stay ( 31 ). Time Slicing Cox regression, an extended form of Cox regression, was used to predict mortality in the ICU ( 32 ).…”
Section: Discussionmentioning
confidence: 99%
“…The SVM maps data into a higher dimensional space and separates classes using an optimal hyperplane. In this study, the scikit-learn library [ 77 ] was used to implement the SVM with a Radial Basis Function (RBF), and the parameters were determined heuristically [ 78 ].…”
Section: Methodsmentioning
confidence: 99%
“…There are numerous machine learning classifiers [ 69 ] such as k-nearest neighbor (kNN), SVM, Bayesian, as well as deep learning networks [ 70 ], such as the convolutional neural network (CNN) and long short-term memory (LSTM), though we chose the SVM with the radial basis function kernel, due to its popular use and in consideration of our relatively small sample data size for each participant (2250 samples). To classify each 0.8 s EEG segment as “in the zone” or “out of the zone”, a different SVM model was trained for each participant.…”
Section: Methodsmentioning
confidence: 99%