DOI QR코드

DOI QR Code

Application of Support Vector Regression for Improving the Performance of the Emotion Prediction Model

감정예측모형의 성과개선을 위한 Support Vector Regression 응용

  • Received : 2012.09.10
  • Accepted : 2012.09.15
  • Published : 2012.09.30

Abstract

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

오늘날 정보사회에서는 정보에 대한 가치를 인식하고, 이를 위한 정보의 활용과 수집이 중요해지고 있다. 얼굴 표정은 그림 하나가 수천개의 단어를 표현할 수 있듯이 수천 개의 정보를 지니고 있다. 이에 주목하여 최근 얼굴 표정을 통해 사람의 감정을 판단하여 지능형 서비스를 제공하기 위한 시도가 MIT Media Lab을 필두로 활발하게 이루어지고 있다. 전통적으로 기존 연구에서는 인공신경망, 중회귀분석 등의 기법을 통해 사람의 감정을 판단하는 연구가 이루어져 왔다. 하지만 중회귀모형은 예측 정확도가 떨어지고, 인공신경망은 성능은 뛰어나지만 기법 자체가 지닌 과적합화 문제로 인해 한계를 지닌다. 본 연구는 사람들의 자극에 대한 반응으로서 나타나는 얼굴 표정을 통해 감정을 추론해내는 지능형 모형을 개발하는 것을 목표로 한다. 기존 얼굴 표정을 통한 지능형 감정판단모형을 개선하기 위하여, Support Vector Regression(이하 SVR) 기법을 적용하는 새로운 모형을 제시한다. SVR은 기존 Support Vector Machine이 가진 뛰어난 예측 능력을 바탕으로, 회귀문제 영역을 해결하기 위해 확장된 것이다. 본 연구의 제안 모형의 목적은 사람의 얼굴 표정으로부터 쾌/불쾌 수준 그리고 몰입도를 판단할 수 있도록 설계되는 것이다. 모형 구축을 위해 사람들에게 적절한 자극영상을 제공했을 때 나타나는 얼굴 반응들을 수집했고, 이를 기반으로 얼굴 특징점을 도출 및 보정하였다. 이후 전처리 과정을 통해 통계적 유의변수를 추출 후 학습용과 검증용 데이터로 구분하여 SVR 모형을 통해 학습시키고, 평가되도록 하였다. 다수의 일반인들을 대상으로 수집된 실제 데이터셋을 기반으로 제안모형을 적용해 본 결과, 매우 우수한 예측 정확도를 보임을 확인할 수 있었다. 아울러, 중회귀분석이나 인공신경망 기법과 비교했을 때에도 본 연구에서 제안한 SVR 모형이 쾌/불쾌 수준 및 몰입도 모두에서 더 우수한 예측성과를 보임을 확인할 수 있었다. 이는 얼굴 표정에 기반한 감정판단모형으로서 SVR이 상당히 효과적인 수단이 될 수 있다는 점을 알 수 있었다.

Keywords

Acknowledgement

Supported by : 한국콘텐츠 진흥원

References

  1. Ahn, H. and H. Y. Lee, "A Combination Model of Multiple Artificial Intelligence Techniques Based on Genetic Algorithms for Investment Decision Support Aid : An Application to KOSPI", The e-Business Studies, Vol.10, No.1(2009), 215-236. https://doi.org/10.15719/geba.10.1.200903.215
  2. Ahn, H., K. J. Kim, and I. G. Han, "Purchase Prediction Model using the Support Vector Machine", Journal of Intelligence and Information Systems, Vol.11, No.3(2005), 69-81.
  3. Alvarado, N., "Arousal and Valence in the Direct Scaling of Emotional Response to Film Clips", Motivation and Emotion, Vol.21(1997), 323-348. https://doi.org/10.1023/A:1024484306654
  4. Andrews, M. A. W., "Why do we use facial expressions to convey emotions?", SCIENTIFIC American Mind, November/December(2010), 70.
  5. Berry, M. J. A. and G. Linoff, Data Mining Techniques : For Marketing Sales and Customer Support, Wiley Computer Publishing, 1997.
  6. Chang, C. C. and C. J. Lin, "LIBSVM : a library for support vector machines", ACM Transactions on Intelligent Systems and Technology, Vol.2, No.3(2011), 27:1-27:27. Software available at http://www.csie.ntu.edu.tw/- cjlin/libsvm (Downloaded 12 September, 2012).
  7. Cho, K. R. and J. K. Seok, "Mechanical Parameter Identification of Servo Systems using Robust Support Vector Regression", The Transactions of Korean Institute of Power Electronics, Vol.10, No.5(2005), 468-480.
  8. Drucker, H., C. J. C. Burges, L. Kaufman, A. Smola, and V. Vapnik, "Support vector regression machines", In M. Mozer et al. (Eds), Advances in Neural Information Processing Systems, Vol.9(1997), 155-161.
  9. Ekman, P., "Universals and Cultural Differences in Facial Expressions of Emotion", In J. Cole (Ed.), Nebraska Symposium on Motivation, Vol.19(1972), 207-282.
  10. Ekman, P. and Frisen, W. V., Facial Action Coding System : A Technique for the Measurement of Facial Movement, Consulting Psychologists Press, 1978.
  11. Go, H. J., D. J. Lee, and M. G. Chun, "An Emotion Recognition Method using Facial Expression and Speech Signal", Journal of the Korea Information Science Society : Software and Applications, Vol.31, No.6(2004), 799-807.
  12. Han, S. J., K. C. Kwak., H. J. Go., S. S Kim, and M. G. Geun, "Facial Expression Recognition using ICA-Factorial Representation Method", Proceedings of the Korean Institute of Intelligent Systems Conference, Vol.13, No.3(2003), 371-376.
  13. Hearst, M. A., Dumais, S. T., Osman, E., Platt, J., and Schӧlkopf, B., "Support vector machines", IEEE Intelligent Systems, Vol.13, No.4(1998), 18-28. https://doi.org/10.1109/5254.708428
  14. Henn, S., "How Did That Ad Make You Feel? Ask A computer", NPR, February 3, 2012, http: //www.npr.org/2012/02/03/146343563/how-d id-that-ad-make-you-feel-ask-a-computer (Accessed 12 September, 2012).
  15. Hong, T. H. and E. M. Kim, "The Prediction of Purchase Amount of Customers Using Support Vector Regression with Separated Learning Method", Journal of Intelligence and Information Systems, Vol.16, No.4(2010), 213-225.
  16. Hong, T. H. and T. S. Shin, "Using Estimated Probability from Support Vector Machines for Credit Rating in IT Industry", Proceedings of the Korea Intelligent Information System Society Conference, (2005), 509-515.
  17. Joachims, T., "Text categorization with support vector machines", Proceedings of the European Conference on Machine Learning, (1998), 137-142.
  18. Joo, J. T., K. J. Park., G. E. Ko., H. C. Yang, and K. B. Shim, "Emotion Recognition and Expression using Facial Expression", Proceedings of the Korean Institute of Intelligent Systems Conference, Vol.17, No.1(2007), 295- 298.
  19. Jung, M. K. and J. K. Kim, "The Intelligent Determination Model of Audience Emotion for Implementing Personalized Exhibition", Journal of Intelligence and Information Systems, Vol.18, No.1(2012), 39-57.
  20. Kim, S. W. and H. C. Ahn, "Development of an Intelligent Trading System Using Support Vector Machines and Genetic Algorithms", Journal of Intelligence and Information Systems, Vol.16, No.1(2010), 71-92.
  21. Kim, Y. J. and S. B. Cho, "A Context-Aware Recommender System for Ringtones in a Mobile Phone using an Emotion Model", Proceedings of Korea Computer Congress, Vol.36, No.1(2009), 162-165.
  22. Kim, Y. I., E. K. Shin, and T. H. Hong, "Comparison of Stock Price Index Prediction Performance Using Neural Networks and Support Vector Machine", The Journal of Internet Electronic Commerce Research, Vol.4, No.3(2004), 221- 243. https://doi.org/10.1023/B:ELEC.0000027981.81945.2a
  23. Kwon, O. R. and J. C. Chun, "HCI : 3D Facial Animation with Head Motion Estimation and Facial Expression Cloning", The KIPS Transactions : Part B, Vol.14, No.4(2007), 311-320.
  24. Lane, R. and L. Nadel, Cognitive Neuroscience of Emotion, Oxford Univ Press, 2000.
  25. Lee, C. H. and R. S. Moon, "Detection of Face-element for Facial Analysis", Journal of The Institute of Electronics Egineers of Korea, Vol.41, No.2(2004), 131-136.
  26. Lee, S. Y. and I. B. Lee, "Pattern Classifier utilizing Fuzzy Theory and SVM", Proceedings of The 4th Regular Conference on Korean Securities Association, (2002), 787-809.
  27. Lee, S. H., J. H. Bang, and S. R. Lee, "User Emotion Extraction Engine($E^{3}$) based on Fuzzy Inference and Bayesian Networks in Smart Phone Environment", Proceedings of Korea Computer Congress, Vol.38, No.1(2011), 100-103.
  28. Lewis, P. A., H. D. Critchley, P. Rotshtein, and R. J. Dolan, "Neural Correlates of Processing Valence and Arousal in Affective Words", Cerebral Cortex, Vol.17, No.3(2007), 742- 748.
  29. Lu, C. J., T, S. Lee, and C. C. Chiu, "Financial time series forecasting using independent component analysis and support vector regression", Decision Support Systems, Vol.47, No.2(2009), 115-125. https://doi.org/10.1016/j.dss.2009.02.001
  30. Nicolaou, M., H. Gunes, and M. Pantic, "Continuous Prediction of Spontaneous Affect from Multiple Cues and Modalities in Valence- Arousal Space", IEEE Transactions on Affective Computing, Vol.2, No.2(2011), 92- 105. https://doi.org/10.1109/T-AFFC.2011.9
  31. Oliveira, A. M., M. P. Teixeira, I. B. Fonseca, and M. Oliveira, "Joint Model-Parameter Validation of Self-Estimates of Valence and Arousal : Probing a Differential-Weighting Model of Affective Intensity", Proceedings of the 22nd Annual Meeting of the International Society for Psychophysics, (2006), 245-250.
  32. Osuna, E., R. Freund, and F. Girosi, "Training support vector machines : an application to face detection", Proceedings of Computer Vision and Pattern Recognition, (1997), 130-136.
  33. Park, C. K., "Estimating Software Development Cost using Support Vector Regression", Korean Management Science Review, Vol.23, No.2 (2006), 75-91.
  34. Park, J. M., K. J. Kim, and I. G. Han, "Bankruptcy Prediction using Support Vector Machines", Asia Pacific Journal of Information Systems, Vol.15, No.2(2005), 51-63.
  35. Park, M. H., H. D. Ko, and H. R. Byun, "Analysis and Synthesis of Facial Expression using Base Faces", Journal of the Korea Information Science Society : Software and Applications, Vol.27, No.8(2000), 827-833.
  36. Russell, J. A., "Pancultural aspects of the human conceptual organization of emotions", Journal of Personality and Social Psychology, Vol.45, (1983), 1281-1288. https://doi.org/10.1037/0022-3514.45.6.1281
  37. Schuessler, J., The Social-Cue Reader, The New York Times, December 10, 2006, http://www. nytimes.com/2006/12/10/magazine/10sec tion3b.t-2.html.
  38. Shin, D. I., "A Trend in the technology of emotion recognition", Weekly Tech Trends Report, No.1283(2007), 1-9.
  39. Shim, J. H., "A Differential Pricing Model for Industrial Land based on Locational Characteristics", Journal of the Korean Society of Civil Engineers, Vol.31, No.2D(2011), 303-314.
  40. Son, T. S., J. U. Seo., J. T. Seo., J. S. Mun, and H. M. Choe, "A Study on the Covert Channel Detection in the TCP/IP Header based on the Support Vector Machine", Journal of The Korea Institute of Information Security and Cryptology, Vol.14, No.1(2004), 35-45.
  41. Tay, F. E. H. and Lijuan, C., "Application of support vector machines in financial time series forecasting", Omega : The International Journal of Management Science, Vol.29, No.4(2001), 309-317. https://doi.org/10.1016/S0305-0483(01)00026-3
  42. TV Daily, "Intel acquires Olaworks...The first case to companies in Korea", April, 17, 2012, http://tvdaily.mk.co.kr/read.php3?aid=133462 3356306623016(Accessed 12 September, 2012).
  43. Vapnik, V., Statistical Learning Theory, New York, NY : Wiley, 1998.

Cited by

  1. GA-optimized Support Vector Regression for an Improved Emotional State Estimation Model vol.8, pp.6, 2012, https://doi.org/10.3837/tiis.2014.06.014