Missing Data Analysis in Emotion Recognition for Smart Applications

Missing data is a widespread fundamental problem that cannot be ignored. It distorts the data, sometimes even to the point where it is impossible to analyze data at all. In emotion recognition, it is discovered that one of the best approaches to identify human emotions is by analyzing EEG (electroencephalography) results combined with peripheral signals. In this article EEG data is used to test which missing data techniques are more efficient and reliable in emotion recognition. During the research, created software is used for testing all the methods. The article concludes with techniques useful for missing data analysis, and applicable in emotion recognition applications.

[1]  J. Russell.  A circumplex model of affect. , 1980 .

[2]  Johannes Wagner,et al.  Exploring Fusion Methods for Multimodal Emotion Recognition with Missing Data , 2011, IEEE Transactions on Affective Computing.

[3]  N. Draper,et al.  Applied Regression Analysis , 1966 .

[4]  Teresa A. Myers.  Goodbye, Listwise Deletion: Presenting Hot Deck Imputation as an Easy and Effective Tool for Handling Missing Data , 2011 .

[5]  A. Acock.  Working With Missing Values , 2005 .

[6]  T. Chartrand,et al.  Using Nonconscious Behavioral Mimicry to Create Affiliation and Rapport , 2003, Psychological science.

[7]  Roderick J A Little,et al.  A Review of Hot Deck Imputation for Survey Non‐response , 2010, International statistical review = Revue internationale de statistique.

[8]  Shangfei Wang,et al.  Emotion recognition through integrating EEG and peripheral signals , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Roderick J. A. Little.  Regression with Missing X's: A Review , 1992 .

[10]  D. Fox,et al.  Towards Personal Service Robots for the Elderly , 1999 .

[11]  Sidney K. D'Mello,et al.  A Review and Meta-Analysis of Multimodal Affect Detection Systems , 2015, ACM Comput. Surv..

[12]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[13]  D. Bennett.  How can I deal with missing data in my study? , 2001, Australian and New Zealand journal of public health.

[14]  J. Graham,et al.  Missing data analysis: making it work in the real world. , 2009, Annual review of psychology.

[15]  Malcolm Munro,et al.  The effects of teaching primary school children the Islamic prayer in a virtual environment , 2015, 2015 Science and Information Conference (SAI).

[16]  Nicu Sebe,et al.  Learning Bayesian network classifiers for facial expression recognition both labeled and unlabeled data , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[17]  Pekka Abrahamsson,et al.  Understanding the affect of developers: theoretical background and guidelines for psychoempirical software engineering , 2015, SSE@SIGSOFT FSE.