Detection of Orienting Response to Novel Sounds in Healthy Elderly Subjects: A Machine Learning Approach Using EEG Features

Emine Elif Tülay

Article Details

Detection of Orienting Response to Novel Sounds in Healthy Elderly Subjects: A Machine Learning Approach Using EEG Features

Authors:

Emine Elif Tülay

Publisher:

Istanbul University

Main Topics:

Yazılım Mühendisliği (Diğer)

Journal:

Acta Infologica Vol.7 Issue 1, pp.71-80

Document Type:

Article

Publication Date:

2/2024

Document Language:

English

Document ID (Org No.):

2001309396

pISSN:

2602-3563

Keywords:

Abstract:

 Unexpected events in the environment elicit the orienting response that protects humans from dangerous situations and there is great importance in identifying these events, especially in aging. The aims of the current study are attempting to find which classification model exhibits the best performance by means of event-related spectral perturbation ERSP features based on EEG and to understand which frequency bands, and time windows, contribute most to the classification of external stimuli. The data of 20 healthy elderly participants were included in the study and the 3-Stimulation auditory oddball paradigm was applied to participants. Different classifiers including Support Vector Machine SVM with Linear and Polynomial kernels, Linear Discriminant Analysis LDA, and Naive Bayes were fed by ERSP features obtained from varying frequency bands and time domains. The classification process was fulfilled using custom-written scripts via the FieldTrip Toolbox version no: 20220104 integrated with the MVPA-light toolbox running under Matlab R2018b. The best performance was obtained by linear SVM which was fed by theta response 4  8 HZ in the early time window 0.1  0.5 s with 90 accuracy in the case of standard stimuli distinguished from novel stimuli. Delta responses also exhibit distinctive characteristics for standard and novel stimuli by running LDA 87 accuracy and polynomial SVM 86 accuracy. These findings show that the delta and theta responses have contributed to detecting standard and novel sounds with remarkable performances of SVM and LDA.

 Unexpected events in the environment elicit the orienting response that protects humans from dangerous situations and there is great importance in identifying these events, especially in aging. The aims of the current study are attempting to find which classification model exhibits the best performance by means of event-related spectral perturbation ERSP features based on EEG and to understand which frequency bands, and time windows, contribute most to the classification of external stimuli. The data of 20 healthy elderly participants were included in the study and the 3-Stimulation auditory oddball paradigm was applied to participants. Different classifiers including Support Vector Machine SVM with Linear and Polynomial kernels, Linear Discriminant Analysis LDA, and Naive Bayes were fed by ERSP features obtained from varying frequency bands and time domains. The classification process was fulfilled using custom-written scripts via the FieldTrip Toolbox version no: 20220104 integrated with the MVPA-light toolbox running under Matlab R2018b. The best performance was obtained by linear SVM which was fed by theta response 4  8 HZ in the early time window 0.1  0.5 s with 90 accuracy in the case of standard stimuli distinguished from novel stimuli. Delta responses also exhibit distinctive characteristics for standard and novel stimuli by running LDA 87 accuracy and polynomial SVM 86 accuracy. These findings show that the delta and theta responses have contributed to detecting standard and novel sounds with remarkable performances of SVM and LDA.

 Unexpected events in the environment elicit the orienting response that protects humans from dangerous situations and there is great importance in identifying these events, especially in aging. The aims of the current study are attempting to find which classification model exhibits the best performance by means of event-related spectral perturbation ERSP features based on EEG and to understand which frequency bands, and time windows, contribute most to the classification of external stimuli. The data of 20 healthy elderly participants were included in the study and the 3-Stimulation auditory oddball paradigm was applied to participants. Different classifiers including Support Vector Machine SVM with Linear and Polynomial kernels, Linear Discriminant Analysis LDA, and Naive Bayes were fed by ERSP features obtained from varying frequency bands and time domains. The classification process was fulfilled using custom-written scripts via the FieldTrip Toolbox version no: 20220104 integrated with the MVPA-light toolbox running under Matlab R2018b. The best performance was obtained by linear SVM which was fed by theta response 4  8 HZ in the early time window 0.1  0.5 s with 90 accuracy in the case of standard stimuli distinguished from novel stimuli. Delta responses also exhibit distinctive characteristics for standard and novel stimuli by running LDA 87 accuracy and polynomial SVM 86 accuracy. These findings show that the delta and theta responses have contributed to detecting standard and novel sounds with remarkable performances of SVM and LDA.

 Çevrede meydana gelen beklenmedik olaylar, insanı tehlikeli durumlardan koruyan yönlendirici tepkiyi ortaya çıkarır ve bu olayların tespit edilmesi özellikle yaşlanma sürecinde büyük önem taşır. Mevcut çalışmanın amacı, EEGye dayalı olaya ilişkin spektral pertürbasyon ERSP özellikleri aracılığıyla hangi sınıflandırma modelinin en iyi performansı gösterdiğini bulmaya çalışmak ve hangi frekans bantlarının ve zaman pencerelerinin dış uyaranın sınıflandırılması için en çok katkıda bulunduğunu anlamaktır. 20 sağlıklı yaşlı katılımcının verileri çalışmaya dahil edilmiştir ve katılımcılara 3-Stimülasyon işitsel oddball paradigması uygulanmıştır. Lineer ve Polinom çekirdek fonksiyonlu Destek Vektör Makinesi DVM, Lineer Diskriminant Analizi LDA ve Naive Bayes gibi farklı sınıflandırıcılar, değişen frekans bantlarından ve zaman alanlarından elde edilen ERSP öznitelikleri ile beslenmiştir. Sınıflandırma işlemi, Matlab R2018b altında çalışan MVPA-light araç kutusu ile entegre FieldTrip Toolbox sürüm no: 20220104 aracılığıyla özel yazılmış komutlar kullanılarak gerçekleştirilmiştir. En iyi performans erken zaman penceresinde 0.1  0.5 s teta yanıtı 4  8 HZ ile beslenen lineer DVM tarafından standart uyaranların yeni uyaranlardan ayırt edilmesi durumunda 90 doğrulukla elde edilmiştir. Delta yanıtları ayrıca LDA 87 doğruluk ve polinom DVM 86 doğruluk çalıştırarak standart ve yeni uyaranlar için ayırt edici özellikler sergilemektedir. Bu bulgular, delta ve teta yanıtlarının, DVM ve LDAnın dikkate değer performanslarıyla standart ve yeni seslerin algılanmasına katkıda bulunduğunu göstermektedir.

Article Details

Detection of Orienting Response to Novel Sounds in Healthy Elderly Subjects: A Machine Learning Approach Using EEG Features

Authors:

Emine Elif Tülay

Publisher:

Istanbul University

Main Topics:

Yazılım Mühendisliği (Diğer)

Journal:

Acta Infologica Vol.7 Issue 1, pp.71-80

Document Type:

Article

Publication Date:

2/2024

Document Language:

English

Document ID (Org No.):

2001309396

pISSN:

2602-3563

Delta

Theta

Auditory Stimuli

Machine LearningDelta

Teta

İşitsel Uyaran

Makine Öğrenmesi

Issues

Article Details

Authors: Emine Elif Tülay

Publisher: Istanbul University

Main Topics: Yazılım Mühendisliği (Diğer)

Journal: Acta Infologica Vol.7 Issue 1, pp.71-80

Document Type: Article

Publication Date: 2/2024

Document Language: English

Document ID (Org No.): 2001309396

pISSN: 2602-3563

Issues

Authors:

Emine Elif Tülay

Publisher:

Istanbul University

Main Topics:

Yazılım Mühendisliği (Diğer)

Journal:

Acta Infologica Vol.7 Issue 1, pp.71-80

Document Type:

Article

Publication Date:

2/2024

Document Language:

English

Document ID (Org No.):

2001309396

pISSN:

2602-3563