Effect Analysis of Data Imbalance for Emotion Recognition Based on Deep Learning


KIPS Transactions on Computer and Communication Systems, Vol. 12, No. 8, pp. 235-242, Aug. 2023
10.3745/KTCCS.2023.12.8.235,   PDF Download:  
Keywords: Biased Data, XAI, LIME, Emotional Recognition, CNN
Abstract

In recent years, as online counseling for infants and adolescents has increased, CNN-based deep learning models are widely used as assistance tools for emotion recognition. However, since most emotion recognition models are trained on mainly adult data, there are performance restrictions to apply the model to infants and adolescents. In this paper, in order to analyze the performance constraints, the characteristics of facial expressions for emotional recognition of infants and adolescents compared to adults are analyzed through LIME method, one of the XAI techniques. In addition, the experiments are performed on the male and female groups to analyze the characteristics of gender-specific facial expressions. As a result, we describe age-specific and gender-specific experimental results based on the data distribution of the pre-training dataset of CNN models and highlight the importance of balanced learning data.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
H. Noh and Y. Lim, "Effect Analysis of Data Imbalance for Emotion Recognition Based on Deep Learning," KIPS Transactions on Computer and Communication Systems, vol. 12, no. 8, pp. 235-242, 2023. DOI: 10.3745/KTCCS.2023.12.8.235.

[ACM Style]
Hajin Noh and Yujin Lim. 2023. Effect Analysis of Data Imbalance for Emotion Recognition Based on Deep Learning. KIPS Transactions on Computer and Communication Systems, 12, 8, (2023), 235-242. DOI: 10.3745/KTCCS.2023.12.8.235.