2020
DOI: 10.18280/ts.370214
|View full text |Cite
|
Sign up to set email alerts
|

Comparison of Classification Models Using Entropy Based Features from Sub-bands of EEG

Abstract: The purpose of this study is to distinguish between different epileptic states automatically in an EEG. The work focuses on distinguishing activity of a controlled patient from interictal and ictal activity and also from each other. Publically available Bonn database is used in this study. Seven such cases are considered. For this study three entropy features: approximate entropy, sample entropy and fuzzy approximate entropy are extracted from frequency sub-bands and are used with six classification algorithms… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 26 publications
0
4
0
Order By: Relevance
“…ApEn increases as the time series becomes more complex. In recent decades, ApEn has been developed and widely used for mechanical fault diagnosis, power system fault signal analysis, biomedicine, and electroencephalograms, owing to its adaptability, robustness, and strong antinoise capability [15][16][17]. In recent years, ApEn has also been applied for the analysis of the regularity and complexity of soil moisture movements and temperature variations under various conditions.…”
Section: Introductionmentioning
confidence: 99%
“…ApEn increases as the time series becomes more complex. In recent decades, ApEn has been developed and widely used for mechanical fault diagnosis, power system fault signal analysis, biomedicine, and electroencephalograms, owing to its adaptability, robustness, and strong antinoise capability [15][16][17]. In recent years, ApEn has also been applied for the analysis of the regularity and complexity of soil moisture movements and temperature variations under various conditions.…”
Section: Introductionmentioning
confidence: 99%
“…Higher probabilities of new pattern emergence correspond to greater sequence complexity and, consequently, to higher approximate entropy [22]. Compared with approximate entropy, SE offers two main advantages [23]: (1) it does not include comparisons with its own data segments, providing an exact value of the negative average natural logarithm of conditional probabilities and thus making SE calculations independent of data length; and (2) it exhibits better consistency, meaning if one time series has a higher value, it also tends to have higher values in other measures [24]. The more complex a time series, the higher the SE calculation value, and vice versa [25].…”
Section: Introductionmentioning
confidence: 99%
“…And following the continuous development of modern society, the training objectives, and requirements of modern higher education for the English professionals are constantly changing, and the existing evaluation systems and strategies for college English teaching quality also have certain limitations. To this end, based on the existing research results, this paper analyzes the current status of English teaching in colleges, and discuss an improved method for evaluating the quality of college English teaching using the gray system theory [14][15] and the entropy weight method [16][17][18][19].…”
Section: Introductionmentioning
confidence: 99%