Publicado

2018-04-01

Characterization of postures to analyze people’s emotions using Kinect technology

Caracterización de posturas para el análisis de emociones de personas, por medio de la tecnología Kinect

Palabras clave:

analysis of emotions, recognition of postures, free software, Kinect, KNN (en)
análisis de emociones, reconocimiento de posturas, software libre, Kinect, KNN (es)

Autores/as

This article synthesizes the research undertaken into the use of classification techniques that characterize people's positions, the objective being to identify emotions (astonishment, anger, happiness and sadness). We used a three-phase exploratory research methodology, which resulted in technological appropriation and a model that classified people’s emotions (in standing position) using the Kinect Skeletal Tracking algorithm, which is a free software. We proposed a feature vector for pattern recognition using classification techniques such as SVM, KNN, and Bayesian Networks for 17,882 pieces of data that were obtained in a 14-person training sample. As a result, we found that that the KNN algorithm has a maximum effectiveness of 89.0466%, which surpasses the other selected algorithms.
El presente artículo sintetiza la investigación realizada en el uso de técnicas de clasificación para un proceso de caracterización de posturas de personas que tiene como objetivo la identificación de emociones (Asombro, Enfado, Felicidad y Tristeza). En este proyecto de investigación fue necesario utilizar una metodología de investigación exploratoria en tres fases donde el resultado es una apropiación tecnológica y un modelo de clasificación de emociones en personas en posición de pie, usando el algoritmo de Skeletal Tracking de Kinect basado en software libre. Se propuso un vector de características para el reconocimiento de patrones usando técnicas de clasificación como SVM, KNN y Redes Bayesianas en 17.882 datos obtenidos en una muestra de entrenamiento de 14 personas. Como resultado se evidenció que el algoritmo KNN tiene una efectividad máxima del 89.0466% superando a los demás algoritmos seleccionados.

Citas

Mann, S., Intelligent image processing. IEEE, John Wiley & Sons, Inc., 2002. DOI: /10.1002/0471221635

Valli, A., Natural interaction white paper, 2007.

Rivera-Mateos, M., El turismo experiencial como forma de turismo responsable e intercultural, en: García-Rodríguez, L., Roldán-Tapía, A.R., Eds., Relac. Intercult. en la Divers., 2013, pp. 199-217.

Smith, W.L., Experiential tourism around the world and at home: definitions and standards, Int. J. Serv. Stand., 2(1), 1 P, 2006. DOI: 10.1504/IJSS.2006.008156

Dale, R., Moisl, H. and Somers, H.L., Handbook of natural language processing, Marcel Dekker, 2000.

Cambria, E. and Hussain, A., Sentic album: content-, concept-, and context-based online personal photo management system, Cognit. Comput., 4(4), pp. 477-496, 2012. DOI: 10.1007/s12559-012-9145-4ch

Simon-Kemp, W.A.S., Digital in 2016, 2016.

Cambria, E., Livingstone, A. and Hussain, A. The Hourglass of Emotions. In: Esposito, A., Esposito, A.M., Vinciarelli, A., Hoffmann, R. and, Müller, V.C., (eds.), Cognitive Behavioural Systems. Lecture Notes in Computer Science, vol 7403. Springer, Berlin, Heidelberg. 2012. DOI: 10.1007/978-3-642-34584-5_11

Minsky, M., The emotion machine: commonsense thinking, artificial intelligence, and the future of the human mind, 2007.

Vesterinen, E., Affective computing. Pattern Analysis and Applications, 1(1), pp. 71-73, 1998.

Siegman, A.W. and Feldstein, S., Nonverbal behavior and communication. L. Erlbaum, 1987.

Pons, C., Comunicación no verbal. Barcelona: Editorial Kairós, 2015.

Kaur, A. and Gupta, V., A survey on sentiment analysis and opinion mining techniques, J. Emerg. Technol. Web Intell., 5(4), pp. 367-371, 2013. DOI: 10.4304/jetwi.5.4.367-3

Gamon, M., Aue, A., Corston-Oliver, S. and Ringger, E., Pulse: mining customer opinions from free text, Springer, Berlin, Heidelberg, 2005, pp. 121-132. DOI: 10.1007/11552253_12

Poria, S., Cambria, E., Hussain, A. and Bin Huang, G., Towards an intelligent framework for multimodal affective data analysis, Neural Networks, 63, pp. 104-116, 2015. DOI: 10.1016/j.neunet.2014.10.005

Kapoor, A., Burleson, W. and R Picard, W., Automatic prediction of frustration, Int. J. Hum. Comput. Stud., 65(8), pp. 724-736, 2007. DOI: 10.1016/J.IJHCS.2007.02.003

Lisetti, C.L., Pattern Analysis & Applic, 1, J. Wiley, 1998, 71 P. DOI: 10.1007/BF01238028

Yan, J., Zheng, W., Xu, Q., Lu, G., Li, H. and Wang, B., Sparse Kernel reduced-rank regression for bimodal emotion recognition from facial expression and speech, IEEE Trans. Multimed., 18(7), pp. 1319-1329, 2016. DOI: 10.1109/TMM.2016.2557721

Poria, S., Cambria, E., Howard, N., Bin Huang, G. and Hussain, A., Fusing audio, visual and textual clues for sentiment analysis from multimodal content, Neurocomputing, 174, pp. 50-59, 2016. DOI: 10.1016/j.neucom.2015.01.095

Benhumea, H.S., Interfaz de lenguaje natural usando Kinect. Unidad Zacatenco, 2012.

Zeev-Zalevsky, J.G., Shpunt, A. and Maizels, A., Method and system for object reconstruction [online]. [date of reference: Sept. 04th of 2016]. Available at: https://patents.google.com/patent/US20170004623

Grafsgaard, J.F., Fulton, R.M., Boyer, K.E., Wiebe, E.N. and Lester, J.C., Multimodal analysis of the implicit affective channel in computer-mediated textual communication, Proc. 14th ACM Int. Conf. Multimodal Interact., pp. 145-152, 2012. DOI: 10.1145/2388676.2388708

Patwardhan, A.S. and Knapp, G.M., Multimodal affect analysis for product feedback assessment, 2013, pp. 178-187.

Choubik, Y. and Mahmoudi, A., Machine learning for real time poses classification using kinect skeleton data, in: 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV), 2016, pp. 307-311. DOI: 10.1109/CGiV.2016.66

Shum, H.P. H., Ho, E.S.L., Jiang, Y. and Takagi, S., Real-time posture reconstruction for Microsoft Kinect, IEEE Trans. Cybern., 43(5), pp. 1357-1369, 2013. DOI: 10.1109/TCYB.2013.2275945

Davis, R.B., Ounpuu, S., Tyburski, D. and Gage, J.R., A gait analysis data collection and reduction technique, Hum. Mov. Sci., 10(5), pp. 575-587, 1991. DOI: 10.1016/0167-9457(91)90046-Z