TY - GEN
T1 - Eigen Vector Method with Swarm and Non Swarm Intelligence Techniques for Epileptic Seizure Classification
AU - Prabhakar, Sunil Kumar
AU - Rajaguru, Harikumar
AU - Lee, Seong Whan
N1 - Funding Information:
This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (No. 2017-0-00451, Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - One of the most commonly occurring neurological disorder in the human brain is epilepsy. It is a long-term chaos in the Central Nervous System (CNS) that severely affects the life of an individual due to repeated seizures. In the electrical activity of the brain, a seizure is nothing but a slight or serious transient irregularity that tends to disturb the cortical regions of the brain and produces symptoms such as muscle spasms, sensory illusion, fatigueness, memory lapse, attention lapse etc. For the diagnosis of epilepsy, Electroencephalography (EEG) signals is used widely. In this work, Eigen vector method utilizing Pisarenko's technique is utilized to extract the features from EEG signals. Then the extracted features are optimized with two techniques, one is a swarm intelligence technique and the other is a non-swarm intelligence technique. The swarm intelligence technique used here is a Bat optimization algorithm and the non-swarm intelligence technique used here is a Biogeography based optimization algorithm. Finally, it is classified with the help of Decision Trees, Multilayer Perceptron (MLP) and Random Forest (RF) classifiers. Results show that a highest classification accuracy of 95.57% is obtained when Eigen Vector technique is utilized with Bat optimization algorithm and classified with Random Forest (RF) classifier.
AB - One of the most commonly occurring neurological disorder in the human brain is epilepsy. It is a long-term chaos in the Central Nervous System (CNS) that severely affects the life of an individual due to repeated seizures. In the electrical activity of the brain, a seizure is nothing but a slight or serious transient irregularity that tends to disturb the cortical regions of the brain and produces symptoms such as muscle spasms, sensory illusion, fatigueness, memory lapse, attention lapse etc. For the diagnosis of epilepsy, Electroencephalography (EEG) signals is used widely. In this work, Eigen vector method utilizing Pisarenko's technique is utilized to extract the features from EEG signals. Then the extracted features are optimized with two techniques, one is a swarm intelligence technique and the other is a non-swarm intelligence technique. The swarm intelligence technique used here is a Bat optimization algorithm and the non-swarm intelligence technique used here is a Biogeography based optimization algorithm. Finally, it is classified with the help of Decision Trees, Multilayer Perceptron (MLP) and Random Forest (RF) classifiers. Results show that a highest classification accuracy of 95.57% is obtained when Eigen Vector technique is utilized with Bat optimization algorithm and classified with Random Forest (RF) classifier.
KW - CNS
KW - Classification
KW - Epilepsy
KW - Optimization
UR - http://www.scopus.com/inward/record.url?scp=85084068157&partnerID=8YFLogxK
U2 - 10.1109/BCI48061.2020.9061653
DO - 10.1109/BCI48061.2020.9061653
M3 - Conference contribution
AN - SCOPUS:85084068157
T3 - 8th International Winter Conference on Brain-Computer Interface, BCI 2020
BT - 8th International Winter Conference on Brain-Computer Interface, BCI 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th International Winter Conference on Brain-Computer Interface, BCI 2020
Y2 - 26 February 2020 through 28 February 2020
ER -