Citation

Hasnul, Muhammad Anas and Ab Aziz, Nor Azlina and Abd. Aziz, Azlan (2021) ECG Based Emotion Recognition System Using Fusion of Feature Extractions, Feature Selection, And Classifiers. In: 2nd FET PG Engineering Colloquium Proceedings 2021, 1-15 Dec. 2021, Online Conference. (Unpublished)

Text 04 Anas.pdf Restricted to Repository staff only Download (20kB)

Abstract

The study started with pre-processing two open-sourced and one inhouse dataset. The raw ECG data is filtered and combined for augmentation. Next, HR and HRV features are extracted from the augmented signals. Then, the pipline is segmented into before and after data augmentation. Finally, the classification is done using five machine learning algorithms where the best algorithm is selected for the feature optimization process. Sequential forward selection (SFS) is applied for optimization where the feature sequence is recorded and analysed. The results are observed, and the performance are compared.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Emotion Recognition System, Electrocardiogram, Data Augmentation, Heart Rate, Heart Rate Variability, Engineering design—Data processing
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA174 Engineering design
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	25 Jan 2022 08:05
Last Modified:	25 Jan 2022 08:05
URII:	http://shdl.mmu.edu.my/id/eprint/9875

Downloads

Edit (login required)