Abstract
Given the importance of implicit communication in human interactions, it would be valuable to have this capability in robotic systems wherein a robot can detect the motivations and emotions of the person it is working with. Recognizing affective states from physiological cues is an effective way of implementing implicit human–robot interaction. Several machine learning techniques have been successfully employed in affect-recognition to predict the affective state of an individual given a set of physiological features. However, a systematic comparison of the strengths and weaknesses of these methods has not yet been done. In this paper, we present a comparative study of four machine learning methods—K-Nearest Neighbor, Regression Tree (RT), Bayesian Network and Support Vector Machine (SVM) as applied to the domain of affect recognition using physiological signals. The results showed that SVM gave the best classification accuracy even though all the methods performed competitively. RT gave the next best classification accuracy and was the most space and time efficient.
Similar content being viewed by others
References
World Robotics (2004) Statistics, market analysis, forecasts, case studies and profitability of robot investment. Sales No. GV.E.04.0.20 or ISBN No. 92-1-101084-5
Reeves B, Nass C (1996) The media equation: how people treat computers, televisions and new media like real people and places. Cambridge University Press, New York
Cowie R, Douglas-Cowie E, Tsapatsoulis N, Votsis G, Kollias S, Fellenz W, Taylor JG (2001) Emotion recognition in human–computer interaction. IEEE Signal Process Mag 18(2):32–80
Picard R (1997) Affective computing. The MIT Press, Cambridge
Walter WG (1963) The living brain. W. W. Norton, New York
Breazeal C, Aryananda L (2002) Recognizing affective intent in robot directed speech. Auton Robots 12(1):83–104
Littlewort GC, Bartlett MS, Chenu J, Fasel I, Kanda T, Ishiguro H, Movellan JR (2004) Towards social robots: Automatic evaluation of human–robot interaction by face detection and expression classification. Adv Neural Inform Process Syst 16:1563–1570
Pantic M, Rothkrantz LJM (2003) Towards an affect-sensitive multimodal human–computer interaction. Proc IEEE 91(9):1370–1390
Conati C, Zhou X (2002) Modeling students’ emotions from cognitive appraisal in educational games. In: Proceedings of 6th international conference on intelligent tutoring systems, France
Backs RW, Lenneman JK, Wetzel JM, Green P (2003) Cardiac measures of driver workload during simulated driving with and without visual occlusion. Hum Factors 45(4):525–539
Hudlicka E, McNeese MD (2002) Assessment of user affective and belief states for inference adaptation: application to an air force pilot task. User Model User Adapt Interact 12:1–47
Hayakawa Y, Sugano S (1998) Real time simple measurement of mental strain in machine operation. ISCIE 1998 Japan–USA symposium on Flexible Automation, Otsu, Japan, pp 35–42
Dana Kulic, Croft E (2003) Estimating Intent for Human–robot Interaction. In: Proceedings of IEEE international conference on advanced robotics, pp 810–815
Tsapatsoulis N, Karpouzis K, Stamou G, Piat F, Kollias S (2000) A fuzzy system for emotion classification based on the MPEG-4 facial definition parameter set. In: Proceedings of EUSIPCO-2000, Finland
Petrushin VA (2000) Emotion recognition agents in real world. AAAI fall symposium on socially intelligent agents: human in the loop
Moriyama T, Saito H, Ozawa S (1999) Evaluation of the relation between emotional concepts and emotional parameters on speech. IEICE J J82-DII(10):1710–1720
Ark W, Dryer D, Lu D (1999) The emotion mouse human–computer interaction: ergonomics and user interfaces. In: Bullinger HJ, Ziegler J (eds) Lawrence Erlbaum Assoc, London, pp 818–823
Picard RW, Vyzas E, Healy J (2001) Toward machine emotional intelligence: analysis of affective psychological states. IEEE Trans Pattern Anal Mach Intell 23(10):1175–1191
Zhao J, Kearney G (1996) Classifying facial movement by backpropagation neural networks with fuzzy inputs. In: Proceedings of international conference on neural information processing, pp 454–457
Qi Y, Picard RW (2002) Context-sensitive Bayesian classifiers and application to mouse pressure pattern classification. In: Proceedings of international conference on pattern recognition, Canada
Cohen I, Garg A, Huang TS (2000) Emotion recognition using multilevel HMM. In: Proceedings of NIPS workshop on affective computing, Colorado
Conati C (2002) Probabilistic assessment of user’s emotions in educational games. J Appl Artif Intell, special issue on “Merging Cognition and Affect in HCI 16:555–575
Nasoz F, Alvarez K, Lisetti C, Finkelstein N (2003) Emotion recognition from physiological signals for presence technologies. Int J Cogn Technol Work Spec Issue Presence 6:1
Wilson GF, Russell CA (2003) Real-time assessment of mental workload using psychophysiological measures and artificial neural networks. Hum Factors 45(4):635–643
Takahashi K (2004) Remarks on emotion recognition from bio-potential signals. In: Proceedings of 2nd international conference on autonomous robots and agents, New Zealand
Kim KH, Bang SW, Kim SR (2004) Emotion recognition system using short-term monitoring of physiological signals. Med Biol Eng Comput 42:419–427
Bradley MM (2000) Emotion and motivation. In: Cacioppo JT, Tassinary LG, Berntson G (eds) Handbook of Psychophysiology. Cambridge University Press, New York, pp 602–642
Rani P, Sarkar N, Smith C, Kirby L (2004) Anxiety detecting robotic systems—towards implicit human–robot collaboration. Robotica 22(1):85–95
Pecchinenda A, Smith CA (1996) The affective significance of skin conductance activity during a difficult problem-solving task. Cogn Emotion 10(50):481–504
Brown RM, Hall LR, Holtzer R, Brown SL, Brown NL (1997) Gender and video game performance. Sex Roles 36(11–12):793–812
Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth & Brooks/Cole Advanced Books & Software, Pacific Grove
Kokol P, Mernik M, Završnik J, Kancler K, Malèiæ I (1994) Decision trees and automatic learning and their use in cardiology. J Med Syst 9(4):201–206
Downey S, Russell JM (1992) A decision tree approach to task independent speech recognition. In: Proceedings of inst acoustics autumn conf on speech and hearing, vol 14(6), pp 181–188
Heckerman D (1999) A tutorial on learning with Bayesian networks. In: Jordan M (ed) Learning in graphical models. MIT Press, Cambridge
Brown LE, Tsamardinos I, Aliferis CF (2004) A novel algorithm for scalable and accurate Bayesian network learning. In Proceedings of the 11th world congress on medical informatics (MEDINFO), California, September 2004
Catlett J (1991) On changing continuous attributes into ordered discrete attributes. In: Proceedings of Fifth European working session on learning. Springer, Berlin Heidelberg New York, pp 164–177
Vapnik V (1998) Statistical learning theory. Wiley, New York
Joachims T (1998) Text categorization with support vector machines: learning with many relevant features. In: Proceedings of ECML-98, 10th European conference on machine learning. DE, Heidelberg, pp 137–142
Burges C (2000) A tutorial on support vector machines for pattern recognition. In: Fayyad U (ed) Knowledge discovery and data mining. Kluwer, Norwell, pp 1–43
Hsu CW, Lin CJ (2002) A comparison of methods for multi-class support vector machines. IEEE Trans Neural Netw 13:415–425
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rani, P., Liu, C., Sarkar, N. et al. An empirical study of machine learning techniques for affect recognition in human–robot interaction. Pattern Anal Applic 9, 58–69 (2006). https://doi.org/10.1007/s10044-006-0025-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-006-0025-y