Limits...
Exploring sampling in the detection of multicategory EEG signals.

Siuly S, Kabir E, Wang H, Zhang Y - Comput Math Methods Med (2015)

Bottom Line: In the similar way, for the OS scheme, an OS set is obtained.Then eleven statistical features are extracted from the RS and OS set, separately.The experimental outcomes demonstrate that the RS scheme well represents the EEG signals and the k-NN with the RS is the optimum choice for detection of multicategory EEG signals.

View Article: PubMed Central - PubMed

Affiliation: Centre for Applied Informatics, College of Engineering and Science, Victoria University, P.O. Box 14428, Melbourne, VIC 8001, Australia.

ABSTRACT
The paper presents a structure based on samplings and machine leaning techniques for the detection of multicategory EEG signals where random sampling (RS) and optimal allocation sampling (OS) are explored. In the proposed framework, before using the RS and OS scheme, the entire EEG signals of each class are partitioned into several groups based on a particular time period. The RS and OS schemes are used in order to have representative observations from each group of each category of EEG data. Then all of the selected samples by the RS from the groups of each category are combined in a one set named RS set. In the similar way, for the OS scheme, an OS set is obtained. Then eleven statistical features are extracted from the RS and OS set, separately. Finally this study employs three well-known classifiers: k-nearest neighbor (k-NN), multinomial logistic regression with a ridge estimator (MLR), and support vector machine (SVM) to evaluate the performance for the RS and OS feature set. The experimental outcomes demonstrate that the RS scheme well represents the EEG signals and the k-NN with the RS is the optimum choice for detection of multicategory EEG signals.

Show MeSH

Related in: MedlinePlus

Exemplary EEG signals from each of the five sets. From top to bottom: class Z, class O, class N, class F, and class S.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4419228&req=5

fig3: Exemplary EEG signals from each of the five sets. From top to bottom: class Z, class O, class N, class F, and class S.

Mentions: We used the EEG time series database [29] which is publically available and is considered as a benchmark of testing classification techniques. The detailed descriptions of the dataset are discussed by Andrzejak et al. [30]. The whole database consists of five EEG datasets (Sets A–E), each containing 100 single channel EEG signals of 23.6 sec duration, composed for the study. Set A (denoted class Z) and Set B (denoted class O) consisted of segments taken from surface EEG recordings that were carried out on five healthy volunteers using a standardized electrode placement scheme. Volunteers were relaxed in an awake state with eyes open (class Z) and eyes closed (class O), respectively. Sets C, D, and E (denoted classes N, F, and S, resp.) originated from presurgical diagnosis. Segments in Set D (class F) were recorded from within the epileptogenic zone and those in Set C (class N) from the hippocampal formation of the opposite hemisphere of the brain. While Set C (class N) and Set D (class F) contained only activity measured during seizure free intervals, Set E (class S) only contained seizure activity. All EEG signals were recorded with the same 128-channel amplifier system, using an average common reference. After 12-bit analog-to-digital conversion, the data were written continuously onto the disk of a data acquisition computer system at a sampling rate of 173.61 Hz. Band-pass filter settings were 0.53–40 Hz (12 dB/oct.). In this work, five classes' (Z to S) classification problems, called multiclass classification, are performed from the above dataset in order to verify the performance of the proposed method. All the EEGs from the dataset are used and they are classified into five different classes: Z, O, N, F, and S, which can be denoted by Z-O-N-F-S. Exemplary EEGs of each of the five classes are depicted in Figure 3.


Exploring sampling in the detection of multicategory EEG signals.

Siuly S, Kabir E, Wang H, Zhang Y - Comput Math Methods Med (2015)

Exemplary EEG signals from each of the five sets. From top to bottom: class Z, class O, class N, class F, and class S.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4419228&req=5

fig3: Exemplary EEG signals from each of the five sets. From top to bottom: class Z, class O, class N, class F, and class S.
Mentions: We used the EEG time series database [29] which is publically available and is considered as a benchmark of testing classification techniques. The detailed descriptions of the dataset are discussed by Andrzejak et al. [30]. The whole database consists of five EEG datasets (Sets A–E), each containing 100 single channel EEG signals of 23.6 sec duration, composed for the study. Set A (denoted class Z) and Set B (denoted class O) consisted of segments taken from surface EEG recordings that were carried out on five healthy volunteers using a standardized electrode placement scheme. Volunteers were relaxed in an awake state with eyes open (class Z) and eyes closed (class O), respectively. Sets C, D, and E (denoted classes N, F, and S, resp.) originated from presurgical diagnosis. Segments in Set D (class F) were recorded from within the epileptogenic zone and those in Set C (class N) from the hippocampal formation of the opposite hemisphere of the brain. While Set C (class N) and Set D (class F) contained only activity measured during seizure free intervals, Set E (class S) only contained seizure activity. All EEG signals were recorded with the same 128-channel amplifier system, using an average common reference. After 12-bit analog-to-digital conversion, the data were written continuously onto the disk of a data acquisition computer system at a sampling rate of 173.61 Hz. Band-pass filter settings were 0.53–40 Hz (12 dB/oct.). In this work, five classes' (Z to S) classification problems, called multiclass classification, are performed from the above dataset in order to verify the performance of the proposed method. All the EEGs from the dataset are used and they are classified into five different classes: Z, O, N, F, and S, which can be denoted by Z-O-N-F-S. Exemplary EEGs of each of the five classes are depicted in Figure 3.

Bottom Line: In the similar way, for the OS scheme, an OS set is obtained.Then eleven statistical features are extracted from the RS and OS set, separately.The experimental outcomes demonstrate that the RS scheme well represents the EEG signals and the k-NN with the RS is the optimum choice for detection of multicategory EEG signals.

View Article: PubMed Central - PubMed

Affiliation: Centre for Applied Informatics, College of Engineering and Science, Victoria University, P.O. Box 14428, Melbourne, VIC 8001, Australia.

ABSTRACT
The paper presents a structure based on samplings and machine leaning techniques for the detection of multicategory EEG signals where random sampling (RS) and optimal allocation sampling (OS) are explored. In the proposed framework, before using the RS and OS scheme, the entire EEG signals of each class are partitioned into several groups based on a particular time period. The RS and OS schemes are used in order to have representative observations from each group of each category of EEG data. Then all of the selected samples by the RS from the groups of each category are combined in a one set named RS set. In the similar way, for the OS scheme, an OS set is obtained. Then eleven statistical features are extracted from the RS and OS set, separately. Finally this study employs three well-known classifiers: k-nearest neighbor (k-NN), multinomial logistic regression with a ridge estimator (MLR), and support vector machine (SVM) to evaluate the performance for the RS and OS feature set. The experimental outcomes demonstrate that the RS scheme well represents the EEG signals and the k-NN with the RS is the optimum choice for detection of multicategory EEG signals.

Show MeSH
Related in: MedlinePlus