Understanding Parent-Infant Behaviors Using Non-negative Matrix Factorization
There are considerable differences among infants in the quality of interaction with their parents. These differences depend especially on the infants development which affects the parent behaviors. In our study we are interested on 3 groups of infants: typical development infants (TD), autistic infants (AD) and mental retardation infants (MR). In order to identify the groups of signs/behaviors that differentiate the development of the three groups of children we investigated a clustering method NMF (non-negative matrix factorization), an algorithm based on decomposition by parts that can reduce the dimension of interaction signs to a few number of interaction behaviors groups. Coupled with a statistical data representation tf-idf, usually used for document clustering and adapted to our work, NMF provides an efficient method for identification of distinct interaction groups. Forty-two infants and their parents were observed in this study. Parent-infant interactions were videotaped by one of the parents at home during the first two years age of child.
KeywordsParent-infant interaction Clustering tf-idf NMF Autism
Unable to display preview. Download preview PDF.
- 4.Muratori, F., Apicella, F., Muratori, P., Maestro, S.: Intersubjective disruptions and caregiver-infant interaction in early autistic disorder. Research in Autism Spectrum Disorders, Corrected Proof (in Press 2010)Google Scholar
- 5.Muratori, F., Maestro, S.: Autism as a downstream effect of primary difficulties in intersubjectivity interacting with abnormal development of brain connectivity. Dialogical Science 2(1), 93–118 (2007)Google Scholar
- 8.Lee, D., Seung, H.: Algorithms for non-negative matrix factorization. In: NIPS, pp. 556–562 (2000)Google Scholar
- 9.Xu, W., X., Liu, Gong, Y.: Document clustering based on non-negative matrix factorization. In: SIGIR, pp. 267–273 (2003)Google Scholar
- 10.Ding, C., he, X., Simon, H.: On the equivalence of nonnegative matrix factorization and spectral clustering. In: Fifth SIAM International Conference on Data Mining, pp. 606–610. SIAM, Philadelphia (2005)Google Scholar
- 11.Strang, G.: Introduction to Linear Algebra. Wellesley-Cambridge Press (2003)Google Scholar
- 15.Vinciarelli, A., Pantic, M., Bourlard, H., Pentland, A.: Social signal processing: state-of-the-art and future perspectives of an emerging domain. In: ACM Multimedia, pp. 1061–1070 (2008)Google Scholar