A Neural Network Based Approach to Social Touch Classification

Touch is an important interaction modality in social interaction, for instance touch can communicate emotions and can intensify emotions communicated by other modalities. In this paper we explore the use of Neural Networks for the classification of touch. The exploration and assessment of Neural Networks (NNs) is based on the Corpus of Social Touch established by Jung et al. This corpus was split in a train set (65%) and test set (35%), the train set was used to find the optimal parameters for the NN and for training the final model. Also different feature sets were investigated; the basic feature set included in the corpus, energy-histogram and dynamical features. Using all features led to the best performance of 64% on the test set, using a NN consisting of one hidden layer with 46 neurones. The confusion matrix showed the expected high confusion between pat-tap and grab-squeeze. A leave-one-subject-out approach lead to a performance of 54%, which is comparable with the results of Jung et al.

[1]  Mari Velonaki,et al.  Interpretation of Social Touch on an Artificial Arm Covered with an EIT-based Sensitive Skin , 2014, Int. J. Soc. Robotics.

[2]  Hatice Gunes,et al.  Automatic, Dimensional and Continuous Emotion Recognition , 2010, Int. J. Synth. Emot..

[3]  Illah R. Nourbakhsh,et al.  A survey of socially interactive robots , 2003, Robotics Auton. Syst..

[4]  Cynthia Breazeal,et al.  Affective Touch for Robotic Companions , 2005, ACII.

[5]  Dirk Heylen,et al.  Touching the Void -- Introducing CoST: Corpus of Social Touch , 2014, ICMI.

[6]  Rafael A. Calvo,et al.  Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications , 2010, IEEE Transactions on Affective Computing.

[7]  Karon E. MacLean,et al.  Gesture Recognition in the Haptic Creature , 2010, EuroHaptics.

[8]  Matthew J. Hertenstein,et al.  The Communicative Functions of Touch in Humans, Nonhuman Primates, and Rats: A Review and Synthesis of the Empirical Research , 2006, Genetic, social, and general psychology monographs.

[9]  Yuichi Itoh,et al.  Emoballoon: A balloon-shaped interface recognizing social touch interactions , 2013, 2013 IEEE Virtual Reality (VR).

[10]  Roger K. Moore,et al.  Hidden Markov model decomposition of speech and noise , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[11]  Ba Tu Truong,et al.  Automatic genre identification for content-based video categorization , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[12]  M. Pawlewski,et al.  Motion-based classification of cartoons , 2001, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01EX489).

[13]  Mari Velonaki,et al.  Interpretation of the modality of touch on an artificial arm covered with an EIT-based sensitive skin , 2012, Int. J. Robotics Res..

[14]  David S. Doermann,et al.  Sports video classification using HMMS , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[15]  Kazuhiko Shinozawa,et al.  Recognizing human touching behaviors using a haptic interface for a pet-robot , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[16]  C. Spence,et al.  The science of interpersonal touch: An overview , 2010, Neuroscience & Biobehavioral Reviews.

[17]  Diane J. Cook,et al.  Automatic Video Classification: A Survey of the Literature , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).