ABSTRACT
Severe behavior problems of children with developmental disabilities often require intervention by specialists. These specialists rely on direct observation of the behavior, usually in a controlled clinical environment. In this paper, we present a technique for using on-body accelerometers to assist in automated classification of problem behavior during such direct observation. Using simulated data of episodes of severe behavior acted out by trained specialists, we demonstrate how machine learning techniques can be used to segment relevant behavioral episodes from a continuous sensor stream and to classify them into distinct categories of severe behavior (aggression, disruption, and self-injury). We further validate our approach by demonstrating it produces no false positives when applied to a publicly accessible dataset of activities of daily living. Finally, we show promising classification results when our sensing and analysis system is applied to data from a real assessment session conducted with a child exhibiting problem behaviors.
- T. M. Achenbach and L. A. Rescorla. Manual for the ASEBA Preschool Forms & Profiles. Burlington, VT: University of Vermont, Research Center for Children, Youth, & Families., 2000.Google Scholar
- F. Albinali, M. S. Goodwin, and S. S. Intille. Recognizing stereotypical motor movements in the laboratory and classroom: a case study with children on the autism spectrum. Proc. Int. Conf. Ubiquitous Computing, 2009. Google ScholarDigital Library
- M. Aman, N. Singh, A. Stewart, and C. Field. Psychometric characteristics of the aberrant behavior checklist. American J. of Mental Deficiency, 89:492--502, 1985.Google Scholar
- Diagnostic and statistical manual of mental disorders. Number 4. American Psychiatric Association, 1994.Google Scholar
- L. Atallah, B. Lo, R. King, and G. Yang. Sensor Positioning for Activity Recognition Using Wearable Accelerometers. Trans. on Biomedical Circuits and Systems, 5(4):320--329, 2011.Google ScholarCross Ref
- www.axivity.com. last visited: June 12th, 2012.Google Scholar
- R. O. Duda, P. E. Hart, and D. G. Stork. Pattern classification. Wiley-Interscience, 2nd edition, 2001. Google ScholarDigital Library
- A. Eisenhower, B. Baker, and J. Blacher. Preschool children with intellectual disability; syndrome specificity, behaviour problems, and maternal well-being. J. of Intellectual Disability Research, 49:657--671, 2005.Google ScholarCross Ref
- G. A. Fink. Markov Models for Pattern Recognition -- From Theory to Applications. Springer, 2008. Google ScholarDigital Library
- S. L. Foster and J. D. Cone. Design and use of direct observation. In A. R. Ciminero, K. Calhoun, and H. E. Adams, editors, Handbook of behavioral assessment, pages 253--354. Wiley, New York, 1986.Google Scholar
- M. S. Goodwin, S. S. Intille, F. Albinali, and W. F. Velicer. Automated Detection of Stereotypical Motor Movements. J. of Autism and Developmental Disorders, 41(6):770--782, 2010.Google ScholarCross Ref
- F. M. Gresham, T. Watson, and C. Skinner. Functional Behavioral Assessment: Principles, procedures and future directions. School of Psychology Review, 30:156--172, 2001.Google ScholarCross Ref
- G. P. Hanley, B. A. Iwata, and B. E. McCord. Functional analysis of problem behavior: A review. J. of Applied Behavior Analysis, 36(2):147--185, 2003.Google ScholarCross Ref
- S. Hartley, D. Sikora, and R. McCoy. Prevalence and risk factors of maladaptive behaviour in young children with autistic disorder. J. of Intellectual Disability Research, 52(10):819--829, 2008.Google ScholarCross Ref
- S. Herring, L. Gray, J. Taffe, G. Tonge, D. Sweeney, and S. Einfield. Behaviour and emotional problems in toddlers with pervasive developmental disorders and developmental delay: association with parental mental health and family functioning. J. of Intellectual Disability Research, 50:874--882, 2006.Google ScholarCross Ref
- R. Horner, E. Carr, P. Strain, A. Todd, and H. Reed. Problem behavior interventions for young children with autism: A research synthesis. J. of Autism and Developmental Disorders, 32(5):423--446, 2002.Google ScholarCross Ref
- P. Howlin, S. Goode, J. Hutton, and M. Rutter. Adult outcome for children with autism. J. of Child Psychology and Psychiatry, (45):212--229, 2004.Google ScholarCross Ref
- B. A. Iwata and A. S. Worsdell. Implications of Functional Analysis Methodology for the Design of Intervention Programs. Exceptionality, 13(1):25--34, 2005.Google ScholarCross Ref
- L. Lecavalier, S. Leone, and J. Wiltz. The impact of behaviour problems on caregiver stress in young people with autism spectrum disorders. J. of Intellectual Disability Research, (50):172--183, 2006.Google ScholarCross Ref
- W. Machalicek, M. O'Reilly, N. Beretvas, J. Sigafoos, and G. Lancioni. A review of interventions to reduce challenging behavior in school settings for students with autism spectrum disorders. Research in Autism Spectrum Disorders, 1(3):229--246, 2007.Google ScholarCross Ref
- J. Matson and S. Lovullo. A review of behavioral treatments for self-injurious behaviors of persons with autism spectrum disorders. Behavior Modification, 32(1):61--76, 2008.Google ScholarCross Ref
- C.-H. Min and A. H. Tewfik. Automatic characterization and detection of behavioral patterns using linear predictive coding of accelerometer sensor data. In Proc. Int. Conf. Engineering in Medicine and Biology, 2010.Google Scholar
- C.-H. Min and A. H. Tewfik. Novel pattern detection in children with Autism Spectrum Disorder using Iterative Subspace Identification. In Proc. Int. Conf. on Acoustics, Speech, and Signal Processing, 2010.Google ScholarCross Ref
- M. R. Patel, J. E. Carr, C. Kim, A. Robles, and D. Eastridge. Functional analysis of aberrant behavior maintained by automatic reinforcement: Assessments of specific sensory reinforcers. Research in Developmental Disabilities, 21(5):393--407, 2000.Google ScholarCross Ref
- T. Plötz, N. Hammerla, and P. Olivier. Feature Learning for Activity Recognition in Ubiquitous Computing. In Proc. Int. Joint Conf. on Art. Intelligence, 2011. Google ScholarDigital Library
- D. Roggen et al. Collecting complex activity data sets in highly rich networked sensor environments. In Proc. Int. Conf. Networked Sensing Systems, 2010.Google Scholar
- J. Rojahn, J. Matson, D. Lott, A. Esbensen, and Y. Smalls. The behavior problems inventory: An instrument for the assessment of self-injury, stereotyped behavior, and aggression/destruction in individuals with developmental disabilities. J. of Autism and Developmental Disorders, 31(6):577--588, 2001.Google ScholarCross Ref
- B. Schölkopf and A. Smola. Learning with kernels: Support vector machines, regularization, optimization, and beyond., 2002.Google ScholarDigital Library
- R. Smith and B. Iwata. Antecedent influences on behavior disorders. J. of Applied Behavior Analysis, 30:343--375, 1997.Google ScholarCross Ref
- T. Westeyn, K. Vadas, T. Starner, and G. Abowd. Recognizing Mimicked Autistic Self-Stimulatory Behaviors Using HMMs. Proc. Int. Symp. Wearable Computing, 2005. Google ScholarDigital Library
- International statistical classification of diseases and related health problems (icd-10). World Health Organization, 1992.Google Scholar
Index Terms
- Automatic assessment of problem behavior in individuals with developmental disabilities
Recommendations
Comparative parenting stress measures between segmental and community-based rehabilitation services in parents of children and adolescents with intellectual and developmental disabilities (IDD): A cross-sectional survey
BACKGROUND:There is a dearth of information on the effects of different types (Segmental rehabilitation service (SRS) vs Community-based rehabilitation service (CRS)) on the parenting stress and family quality of life in ...
Using Technology-Based Augmentative and Alternative Communication to Develop Adaptive Behavior in a Child with Autism Spectrum Disorders – An Intervention Program
Universal Access in Human-Computer InteractionAbstractIndividuals with autism face lots of difficulties in developing their communication skills, which affect their socialization while also increase their challenged behavior. Consequently, many individuals with autism are candidates for Augmentative ...
Evaluating an iPad Game to Address Overselectivity in Preliterate AAC Users with Minimal Verbal Behavior
ASSETS '17: Proceedings of the 19th International ACM SIGACCESS Conference on Computers and AccessibilityOverselectivity is a learning challenge that is largely unaddressed in the assistive technology community. Screening and intervention, done by specialists, is time-intensive and requires substantial training. Little to no treatments are available to the ...
Comments