Scribd
Upload
18 views

Recording of Physiological Signal For Emotion Recognition System Development

The document presents a proposal for developing an emotion recognition system using physiological signals recorded from subjects. It describes collecting electroencephalogram (EEG), electrocardiogram (ECG), and phonocardiogram (PCG) signals using various equipment. The signals will undergo preprocessing, decomposition, feature extraction and classification to recognize emotions. Applications include healthcare, education and intelligent systems. Related work from the lab and other researchers exploring emotion recognition from physiological signals is also cited.

Uploaded by

Aditya Nalwaya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
18 views

Recording of Physiological Signal For Emotion Recognition System Development

The document presents a proposal for developing an emotion recognition system using physiological signals recorded from subjects. It describes collecting electroencephalogram (EEG), electrocardiogram (ECG), and phonocardiogram (PCG) signals using various equipment. The signals will undergo preprocessing, decomposition, feature extraction and classification to recognize emotions. Applications include healthcare, education and intelligent systems. Related work from the lab and other researchers exploring emotion recognition from physiological signals is also cited.

Uploaded by

Aditya Nalwaya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 18

Recording of Physiological

Signal for Emotion Recognition


system development
Presentation
to
Institute Human Ethics Committee

Principal Investigator Research Personnel


Dr. Ram Bilas Pachori (Professor) Mr. Aditya Nalwaya (PhD Scholar)
Discipline of Electrical Engineering,
Indian Institute of Technology Indore,
Indore
Content
• Introduction
• Flow diagram
• Experimental setup
• Application
• Conclusion
• Related work
• References

Thursday, February 3, 2022 2


Introduction
• Emotions influence human behavior, understanding, decision making to help them survive
and excel.
• Emotion recognition can be done in many ways, such as by analyzing facial expressions,
behavior, verbal expressions, written expressions, physiological signals, self-reporting or by
asking questions to the subject.
• Out of given ways except for physiological signals all other can be controlled by human and
thus could mislead in recognition of any emotion.
• Human nervous system control internal bodily function and directs our body’s external
response.
• It receives external information through sensory organs, transmits the received information
to brain via spinal cord, processes it in the brain and generate appropriate responses.
• Thus, the physiological signals are generated in response to the external stimuli.

Thursday, February 3, 2022 3


Flow Diagram for Emotion Recognition

Thursday, February 3, 2022 4


Emotion Elicitation

Thursday, February 3, 2022 https://nobaproject.com/modules/affective-neuroscience 5


Physiological
Signal
• Electroencephalogram(EEG)
• Electrocardiogram (ECG)
• Phonocardiogram (PCG)

https://i1.wp.com/biomedikal.in/wp-content/uploads/2011/05/sps.jpg

Thursday, February 3, 2022 6


Signal pre-processing Original Signal

• Preprocessing stage makes the signal suitable for further


processing. Preprocessing includes operations such as artifact
removal, noise filtering, and resampling the signal.
• The EEG recording contains the information of heart beats, eye-
blinking, body movements etc. (known as artifacts)
• Since we do not require such information in our data, in pre- Denoised Signal

processing stage we remove the artifacts from the recorded data.

Thursday, February 3, 2022 7


Advanced signal processing techniques
• EEG signals are non-stationary in nature.
• The advanced signal processing techniques help us to
decomposed these EEG signals into suitable components.
• The techniques such as empirical mode decomposition
(EMD) [1], flexible wavelet transform (FAWT) [2] are
recently used in literature for decomposition of non-
stationary signals.

[1] Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., & Liu, H. H. (1998). The empirical mode decomposition
and the Hilbert spectrum for nonlinear and non-stationary time series analysis. In Proceedings of the Royal Society of London A:
mathematical, physical and engineering sciences (Vol. 454, No. 1971, pp. 903-995). The Royal Society.
[2] Bayram, I. (2013). An analytic wavelet transform with a flexible time-frequency covering. IEEE Transactions on Signal
Processing, 61(5), 1131-1142.
Thursday, February 3, 2022 8
Feature extraction process
• This process extract EEG signal characteristic.
• The features will be computed from the components
like as entropy [3], correntropy [4], etc.
• These features help in classifying the EEG signals
corresponding to different emotions.

[3] Sharma, R., Pachori, R. B., & Acharya, U. R. (2015). Application of entropy measures on intrinsic mode functions for the
automated identification of focal electroencephalogram signals. Entropy, 17(2), 669-691.
[4] Liu, W., Pokharel, P. P., & Príncipe, J. C. (2007). Correntropy: Properties and applications in non-Gaussian signal processing.
IEEE Transactions on Signal Processing, 55(11), 5286-5298.

Thursday, February 3, 2022 9


Classification
• Once the features are extracted using suitable
classifier data is classified into different emotion
classes.
• There are several classifier available in the literature
for the classification purpose namely, least square
support vector machine (LS-SVM) [5], random forest
[6] etc.
• Thus, after classifying the data we can identify the
emotion that was felt by the subject during the
recording of data.

[5] Suykens, J. A., & Vandewalle, J. (1999). Least squares support vector machine classifiers. Neural processing letters, 9(3), 293-300.
[6] Liaw, A., & Wiener, M. (2002). Classification and regression by Random Forest. R news, 2(3), 18-22.

Thursday, February 3, 2022 10


Experimental setup for EEG signal recoding
• EEG electrode cap
• BIOPAC (MP150) data acquisition system
• Electro-gel for conductivity.
• Disposable glove
• E6 disposable sponge disks

Thursday, February 3, 2022 11


Experimental setup for ECG signal recoding
• ADInstruments
• PowerLab data acquisition device
• Bio Amps (8-channel)

Thursday, February 3, 2022 12


Experimental setup for PCG signal recoding

Thursday, February 3, 2022 13


Application
Emotion recognition has a vast area of application such as :
• Health care,
• Brain computer interaction (BCI),
• Education,
• Video game,
• Smart entertainment system,
• smart room,
• intelligent car etc.

Thursday, February 3, 2022 14


Conclusion
• Emotion recognition is very active research area and thus it has lot
more to explore.
• As on date there is no publically available database for PCG signal for
emotion recognition.
• Multi-model framework such as EEG+PCG+ECG is yet to be explored.
• Many new advance signal processing techniques are still unexplored
in this area.
• Thus, for answering all the above questions we need to create our on
database.

Thursday, February 3, 2022 15


Related work (from Lab.)
• V. Gupta, M. D. Chopda and R. B. Pachori, "Cross-Subject Emotion Recognition
Using Flexible Analytic Wavelet Transform From EEG Signals," in IEEE Sensors
Journal, vol. 19, no. 6, pp. 2266-2274, 15 March 15, 2019.
• Sharma, Rahul, Ram Bilas Pachori, and Pradip Sircar. "Automated emotion
recognition based on higher order statistics and deep learning
algorithm." Biomedical Signal Processing and Control 58 (2020).
• A. Bhattacharyya, R. K. Tripathy, L. Garg and R. B. Pachori, "A Novel Multivariate-
Multiscale Approach for Computing EEG Spectral and Temporal Complexity for
Human Emotion Recognition," in IEEE Sensors Journal, vol. 21, no. 3, pp. 3579-
3591, 1 Feb. 1, 2021.

Thursday, February 3, 2022 16


Related work (around the world)
• Ahmet Mert, Aydin Akan,Emotion recognition based on time–frequency
distribution of EEG signals using multivariate synchrosqueezing transform,Digital
Signal Processing,Volume 81,2018,Pages 106-115,ISSN 1051-2004,
• Veena, S. T., and M. N. Sumaiya. "Human emotion classification using eeg
signals by multivariate synchrosqueezing transform." Human Behaviour
Analysis Using Intelligent Systems. Springer, Cham, 2020. 179-204.
• Abdulhamit Subasi, Turker Tuncer, Sengul Dogan, Dahiru Tanko, Unal Sakoglu,EEG-
based emotion recognition using tunable Q wavelet transform and rotation forest
ensemble classifier,Biomedical Signal Processing and Control,Volume
68,2021,102648,ISSN 1746-8094.

Thursday, February 3, 2022 17


Reference
• Wei-Long Zheng, and Bao-Liang Lu, Investigating Critical Frequency Bands and Channels for
EEG-based Emotion Recognition with Deep Neural Networks, accepted by IEEE Transactions on
Autonomous Mental Development (IEEE TAMD) 7(3): 162-175, 2015.
• "DEAP: A Database for Emotion Analysis using Physiological Signals (PDF)", S. Koelstra, C. Muehl, M.
Soleymani, J.-S. Lee, A. Yazdani, T. Ebrahimi, T. Pun, A. Nijholt, I. Patras, EEE Transactions on Affective
Computing, vol. 3, no. 1, pp. 18-31, 2012
• Soleymani, Mohammad, et al. "A multimodal database for affect recognition and implicit
tagging." IEEE transactions on affective computing 3.1 (2011): 42-55.
• Subramanian, Ramanathan, et al. "ASCERTAIN: Emotion and personality recognition using
commercial sensors." IEEE Transactions on Affective Computing 9.2 (2016): 147-160.
• Correa, Juan Abdon Miranda, et al. "Amigos: A dataset for affect, personality and mood research
on individuals and groups." IEEE Transactions on Affective Computing (2018).
• Katsigiannis, Stamos, and Naeem Ramzan. "DREAMER: A database for emotion recognition
through EEG and ECG signals from wireless low-cost off-the-shelf devices." IEEE journal of
biomedical and health informatics 22.1 (2017): 98-107.

Thursday, February 3, 2022 18

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy