PMID- 29765477
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240325
IS  - 1871-4080 (Print)
IS  - 1871-4099 (Electronic)
IS  - 1871-4080 (Linking)
VI  - 12
IP  - 3
DP  - 2018 Jun
TI  - Detecting epileptic seizure with different feature extracting strategies using 
      robust machine learning classification techniques by applying advance parameter 
      optimization approach.
PG  - 271-294
LID - 10.1007/s11571-018-9477-1 [doi]
AB  - Epilepsy is a neurological disorder produced due to abnormal excitability of 
      neurons in the brain. The research reveals that brain activity is monitored 
      through electroencephalogram (EEG) of patients suffered from seizure to detect 
      the epileptic seizure. The performance of EEG detection based epilepsy require 
      feature extracting strategies. In this research, we have extracted varying 
      features extracting strategies based on time and frequency domain 
      characteristics, nonlinear, wavelet based entropy and few statistical features. A 
      deeper study was undertaken using novel machine learning classifiers by 
      considering multiple factors. The support vector machine kernels are evaluated 
      based on multiclass kernel and box constraint level. Likewise, for K-nearest 
      neighbors (KNN), we computed the different distance metrics, Neighbor weights and 
      Neighbors. Similarly, the decision trees we tuned the paramours based on maximum 
      splits and split criteria and ensemble classifiers are evaluated based on 
      different ensemble methods and learning rate. For training/testing tenfold Cross 
      validation was employed and performance was evaluated in form of TPR, NPR, PPV, 
      accuracy and AUC. In this research, a deeper analysis approach was performed 
      using diverse features extracting strategies using robust machine learning 
      classifiers with more advanced optimal options. Support Vector Machine linear 
      kernel and KNN with City block distance metric give the overall highest accuracy 
      of 99.5% which was higher than using the default parameters for these 
      classifiers. Moreover, highest separation (AUC = 0.9991, 0.9990) were obtained at 
      different kernel scales using SVM. Additionally, the K-nearest neighbors with 
      inverse squared distance weight give higher performance at different Neighbors. 
      Moreover, to distinguish the postictal heart rate oscillations from epileptic 
      ictal subjects, and highest performance of 100% was obtained using different 
      machine learning classifiers.
FAU - Hussain, Lal
AU  - Hussain L
AUID- ORCID: 0000-0003-1103-4938
AD  - 1Quality Enhancement Cell (QEC), The University of Azad Jammu and Kashmir, City 
      Campus, Muzaffarabad, Azad Kashmir 13100 Pakistan. ISNI: 0000 0001 0699 3419. 
      GRID: grid.413058.b
AD  - 2Department of Computer Science and IT, The University of Azad Jammu and Kashmir, 
      City Campus, Muzaffarabad, 13100 Pakistan. ISNI: 0000 0001 0699 3419. GRID: 
      grid.413058.b
LA  - eng
PT  - Journal Article
DEP - 20180125
PL  - Netherlands
TA  - Cogn Neurodyn
JT  - Cognitive neurodynamics
JID - 101306907
PMC - PMC5943212
OTO - NOTNLM
OT  - Classification
OT  - Decision tree
OT  - Ensemble classifier
OT  - Epilepsy
OT  - K-nearest neighbors
OT  - Seizure detection
OT  - Support vector machine
EDAT- 2018/05/17 06:00
MHDA- 2018/05/17 06:01
PMCR- 2019/06/01
CRDT- 2018/05/17 06:00
PHST- 2017/10/09 00:00 [received]
PHST- 2017/12/01 00:00 [revised]
PHST- 2018/01/18 00:00 [accepted]
PHST- 2018/05/17 06:00 [entrez]
PHST- 2018/05/17 06:00 [pubmed]
PHST- 2018/05/17 06:01 [medline]
PHST- 2019/06/01 00:00 [pmc-release]
AID - 9477 [pii]
AID - 10.1007/s11571-018-9477-1 [doi]
PST - ppublish
SO  - Cogn Neurodyn. 2018 Jun;12(3):271-294. doi: 10.1007/s11571-018-9477-1. Epub 2018 
      Jan 25.