Comparative Study on Machine Learning Classifiers for Epileptic Seizure Detection in Reference to EEG Signals

Raut, Samriddhi; Rathee, Neeru

doi:10.1007/978-981-15-4992-2_18

Cited by 6 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By aggregating trees' votes, the model inference returns the input prediction picking up the class with the largest number of votes. A 99.78% accuracy was achieved by [16] on the UCI dataset.…”

Section: B Classificationmentioning

confidence: 97%

See 1 more Smart Citation

Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices

Ingolfsson

Cossettini

Wang

et al. 2021

2021 IEEE Biomedical Circuits and Systems Conference (BioCAS)

View full text Add to dashboard Cite

We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different classification approaches (Support Vector Machines, Random Forest, Extra Trees, AdaBoost) and different pre/postprocessing techniques to maximize sensitivity while guaranteeing no false alarms. We analyze global and subject-specific approaches, considering all 23-electrodes or only 4 temporal channels. For 8 s window size and subject-specific approach, we report zero false positives and 100% sensitivity. These algorithms are parallelized and optimized for a parallel ultra-low power (PULP) platform, enabling 300h of continuous monitoring on a 300 mAh battery, in a wearable form factor and power budget. These results pave the way for the implementation of affordable, wearable, long-term epilepsy monitoring solutions with low falsepositive rates and high sensitivity, meeting both patient and caregiver requirements.

show abstract

Section: B Classificationmentioning

confidence: 97%

“…During inference the SVM classifies instances based on which side of the hyperplane they lie. Referring to the UCI epileptic dataset [15], a 98.18% classification accuracy was achieved by [16] when applying SVM.…”

Section: B Classificationmentioning

confidence: 99%

Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices

Ingolfsson

Cossettini

Wang

et al. 2021

2021 IEEE Biomedical Circuits and Systems Conference (BioCAS)

View full text Add to dashboard Cite

show abstract

“…Rasheed et al [23] conducted a thorough review of the existing literature, highlighting why early identification of ES is necessary and how DL and ML algorithms are employed for ES prediction. Raut et al [24] discussed various ML classification techniques for ES detection. After experimenting with various classification techniques, they determined that Random Forest (RF) was the best classifier.…”

Section: A Existing Review Workmentioning

confidence: 99%

“…[19] partially described feature extraction methods in their work. [17], [18], [20], [22], [21], [23], and [24] completely dicussed different ML classifiers. Various DL classifiers are partially described by [17].…”

Section: A Existing Review Workmentioning

confidence: 99%

AI-Based Epileptic Seizure Detection and Prediction in Internet of Healthcare Things: A Systematic Review

et al. 2023

View full text Add to dashboard Cite

Epilepsy is a neurological condition affecting around 50 million individuals worldwide, reported by the World Health Organization. This is identified as a hypersensitive disease by clinical associations. The unique characteristics of Electroencephalography have proven to be stable and universal; therefore, researchers have a lot of credibilities. So, it is the most used test for Epileptic Seizure detection and prediction. This study examines the contributions that have so far been made utilizing Electroencephalography technology to detect, predict, and monitor Epileptic Seizures. We have reviewed around 56 research articles, and those papers are selected from different academic databases. The studies explored various approaches, including Machine Learning, Deep Learning, and the Internet of Things framework. A comprehensive discussion of different classification algorithms is analyzed, and their performances are explored. Furthermore, various open issues of the stated approach are discussed, and potential future works are addressed.

show abstract