Affective computing
Fast training of support vector machines using sequential minimal optimization
Advances in kernel methods
Toward Machine Emotional Intelligence: Analysis of Affective Physiological State
IEEE Transactions on Pattern Analysis and Machine Intelligence - Graph Algorithms and Computer Vision
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Classification of EEG for Affect Recognition: An Adaptive Approach
AI '09 Proceedings of the 22nd Australasian Joint Conference on Advances in Artificial Intelligence
Classification of EEG for Affect Recognition: An Adaptive Approach
AI '09 Proceedings of the 22nd Australasian Joint Conference on Advances in Artificial Intelligence
The impact of system feedback on learners' affective and physiological states
ITS'10 Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part I
| Hi-index | 0.00 |
Reliable classification of an individual's affective state through processing of physiological response requires the use of appropriate machine learning techniques, and the analysis of how experimental factors influence the data recorded. While many studies have been conducted in this field, the effect of many of these factors is yet to be properly investigated and understood. This study investigates the relative effects of number of subjects, number of recording sessions, sampling rate and a variety of different classification approaches. Results of this study demonstrate accurate classification is possible in isolated sessions and that variation between sessions and subjects has a significant effect on classifier success. The effect of sampling rate is also shown to impact on classifier success. The results also indicate that affective space is likely to be continuous and that developing an understanding of the dimensions of this space may offer a reliable way of comparing results between subjects and studies.