Authors:
Liliana A. S. Medina
and
Ana L. N. Fred
Affiliation:
Instituto Superior Técnico, Portugal
Keyword(s):
Genetic algorithm, Unsupervised learning, Temporal data, Electrocardiogram, Stress detection.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Data Manipulation
;
Data Mining
;
Databases and Information Systems Integration
;
Enterprise Information Systems
;
Evolutionary Computing
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Symbolic Systems
Abstract:
Electrocardiography signals are typically analyzed for medical diagnosis of pathologies and are relatively unexplored as physiological behavioral manifestations. In this work we propose to analyze these signals with the intent of assessing the existence of significant changes of their features related to stress occurring in the performance of a computer-based cognitive task.
Given the exploratory nature of this analysis, usage of unsupervised learning techniques is naturally adequate for our purposes. We propose a work methodology based on unsupervised automatic methods, namely clustering algorithms and clustering ensemble methods, as well as on evolutionary algorithms.
The implemented automatic methods are the result of the adaptation of existing clustering techniques, including evolutionary computation, with the goal of detecting patterns by analysis of data with continuous temporal evolution. We propose a genetic algorithm for the specific task of assessing the continuous evolut
ion and the separability of the stress states.
The obtained results show the existence of differentiated states in the data sets that represent the ECG signals, thus confirming the adequacy and validity of the proposed methodology in the context of the exploration of these electrophysiological signals for emotional states detection.
(More)