Recognition of emotions using ICEEMD-based characterization of multimodal physiological signals. Ordonez-Bolanos, O., A., Gomez-Lara, J., F., Becerra, M., A., Peluffo-Ordonez, D., H., Duque-Mejia, C., M., Medrano-David, D., & Mejia-Arboleda, C. In 2019 IEEE 10th Latin American Symposium on Circuits & Systems (LASCAS), pages 113-116, 2, 2019. IEEE.
Recognition of emotions using ICEEMD-based characterization of multimodal physiological signals [link]Website  doi  abstract   bibtex   
Physiological-signal-Analysis-based approaches are typically used for automatic emotion identification. Given the complex nature of signals-related emotions, their right identification often results in a non-Trivial and exhaustive process-especially because such signals suffer from high dependence upon multiple external variables. Some emotional criteria of interest are arousal, valence, and dominance. Several research works have addressed this issue, mainly through creating prediction systems, notwithstanding, due to aspects such as accuracy, in-context interpretation and computational cost, it is still considered a great-of-interest, open research eld. This paper is aimed at verifying the usefulness of the so-called improved complete empirical mode decomposition (ICEEMD) as a physiological-signal-characterization building block within an emotion-predicting system. To this purpose, some physiological signals along with patients' metadata from the DEAP database are considered. The experiments are set-up as follows: Signals are pre-processed by amplitude adjusting and simple filtering. Then, a feature set is built using HC, and multiple statistic measures from information given by the three considered decompositions, namely: ICEEMD, discrete wavelet transform (DWT),and Maximal overlap DWT. Subsequently, Relief F selection algorithm was applied for reducing the dimensionality of the feature space. Finally, classifiers (LDC and K-NN cascade architectures) are used to assess the class-separability given by the feature set. The different decomposition techniques were compared, and the relevant signals and measures were established. Experimental results evidence the suitability of ICEEMD decomposition for physiological-signal-driven emotions analysis.
@inproceedings{
 title = {Recognition of emotions using ICEEMD-based characterization of multimodal physiological signals},
 type = {inproceedings},
 year = {2019},
 pages = {113-116},
 websites = {https://ieeexplore.ieee.org/document/8667585/},
 month = {2},
 publisher = {IEEE},
 id = {4400fe53-d983-3bea-a5f0-8d4c35f5eea9},
 created = {2022-02-02T07:25:45.442Z},
 file_attached = {false},
 profile_id = {aba9653c-d139-3f95-aad8-969c487ed2f3},
 group_id = {55483c42-1c6e-3138-8b55-8d557318ba00},
 last_modified = {2022-02-02T07:25:45.442Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Ordonez-Bolanos2019},
 private_publication = {false},
 abstract = {Physiological-signal-Analysis-based approaches are typically used for automatic emotion identification. Given the complex nature of signals-related emotions, their right identification often results in a non-Trivial and exhaustive process-especially because such signals suffer from high dependence upon multiple external variables. Some emotional criteria of interest are arousal, valence, and dominance. Several research works have addressed this issue, mainly through creating prediction systems, notwithstanding, due to aspects such as accuracy, in-context interpretation and computational cost, it is still considered a great-of-interest, open research eld. This paper is aimed at verifying the usefulness of the so-called improved complete empirical mode decomposition (ICEEMD) as a physiological-signal-characterization building block within an emotion-predicting system. To this purpose, some physiological signals along with patients' metadata from the DEAP database are considered. The experiments are set-up as follows: Signals are pre-processed by amplitude adjusting and simple filtering. Then, a feature set is built using HC, and multiple statistic measures from information given by the three considered decompositions, namely: ICEEMD, discrete wavelet transform (DWT),and Maximal overlap DWT. Subsequently, Relief F selection algorithm was applied for reducing the dimensionality of the feature space. Finally, classifiers (LDC and K-NN cascade architectures) are used to assess the class-separability given by the feature set. The different decomposition techniques were compared, and the relevant signals and measures were established. Experimental results evidence the suitability of ICEEMD decomposition for physiological-signal-driven emotions analysis.},
 bibtype = {inproceedings},
 author = {Ordonez-Bolanos, O. A. and Gomez-Lara, J. F. and Becerra, M. A. and Peluffo-Ordonez, D. H. and Duque-Mejia, C. M. and Medrano-David, D. and Mejia-Arboleda, C.},
 doi = {10.1109/LASCAS.2019.8667585},
 booktitle = {2019 IEEE 10th Latin American Symposium on Circuits & Systems (LASCAS)}
}

Downloads: 0