A Wrapper Feature Selection Algorithm: An Emotional Assessment Using Physiological Recordings from Wearable Sensors
| Autor: | Roberto Gil-Pita, Inma Mohino-Herranz, Fernando Seoane, Joaquín García-Gómez, Manuel Rosa-Zurera |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Boosting (machine learning)
Computer science media_common.quotation_subject 0206 medical engineering Emotions Wearable computer Feature selection 02 engineering and technology Biosensing Techniques Overfitting lcsh:Chemical technology Biochemistry Article Analytical Chemistry Electrocardiography Wearable Electronic Devices feature selection 0202 electrical engineering electronic engineering information engineering Humans lcsh:TP1-1185 emotional assessment Electrical and Electronic Engineering Instrumentation Wearable technology media_common Monitoring Physiologic business.industry Models Theoretical 020601 biomedical engineering Atomic and Molecular Physics and Optics Sadness Autonomic nervous system physiological signal 020201 artificial intelligence & image processing business Algorithm Classifier (UML) Algorithms |
| Zdroj: | Sensors Volume 20 Issue 1 Sensors, Vol 20, Iss 1, p 309 (2020) Sensors (Basel, Switzerland) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s20010309 |
| Popis: | Assessing emotional state is an emerging application field boosting research activities on the topic of analysis of non-invasive biosignals to find effective markers to accurately determine the emotional state in real-time. Nowadays using wearable sensors, electrocardiogram and thoracic impedance measurements can be recorded, facilitating analyzing cardiac and respiratory functions directly and autonomic nervous system function indirectly. Such analysis allows distinguishing between different emotional states: neutral, sadness, and disgust. This work was specifically focused on the proposal of a k-fold approach for selecting features while training the classifier that reduces the loss of generalization. The performance of the proposed algorithm used as the selection criterion was compared to the commonly used standard error function. The proposed k-fold approach outperforms the conventional method with 4% hit success rate improvement, reaching an accuracy near to 78%. Moreover, the proposed selection criterion method allows the classifier to produce the best performance using a lower number of features at lower computational cost. A reduced number of features reduces the risk of overfitting while a lower computational cost contributes to implementing real-time systems using wearable electronics. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |