Abstract
Autism Spectrum Disorder (ASD) is a developmental disorder characterized by difficulties in social interaction, communication, and restricted or repetitive patterns of thought and behaviour. Diagnosing ASD is important since it is a life long condition and early diagnosis of ASD has a great deal of importance in terms of controlling the disease. This research work focuses on the analysis of the features that are vital in diagnosing the symptoms of ASD in an individual and to help in the early identification of ASD. The autism dataset for this research work is taken from the UCI repository. The proposed method, SVMAttributeEval, assigns feature weight to the features and the features are ranked based on their importance. The recursive Feature Elimination method is applied and the performance of the classification algorithms LibSVM, IBk, and Naïve Bayes for the reduced feature subsets selected by the wrapper method is measured. The empirical results show an improvement in the accuracy of the classifiers on the removal of the least significant features with feature reduction of 60% achieved against the original feature set. The performance of the classification algorithms has significantly improved for the reduced feature subset of ASD. The LibSVM classification algorithm achieves 93.26% accuracy, IBk (92.3%), and Naïve Bayes (91.34%) for the selected feature subset as compared to the values achieved for the whole feature set.
Similar content being viewed by others
References
Geschwind D, Sowinski J, Lord C, Iversen P, Shestack J, Jones P et al (2001) The autism genetic resource exchange: a resource for the study of autism and related neuropsychiatric conditions. Am J Hum Genet 69:463–466
Wiggins L, Reynolds A, Rice C, Moody E, Bernal P, Blaskey L, Rosenberg S, Lee L, Levy S (2014) Using standardized diagnostic instruments to classify children with autism in the study to explore early development. J Autism Dev Disord 45(5):1271–1280
Sabeena S, Sarojini B (2015) Optimal feature subset selection using ant colony optimization. Indian J Sci Technol 8:1
Katiyar P, Senthil Kumarn U, Balakrishanan S (2013) Detection and discrimination of DDoSattacks from flash crowd using entropy variations. Int J Eng Technol 5(4):3514–3519
Mythili MS, Mohamed Shavanas AR (2013) A study on autism spectrum disorders using classification techniques. Int J Soft Comput Eng 2(4):1
Fernell E, Eriksson MA, Gillberg C (2013) Early diagnosis of autism and impact on prognosis: a narrative review. PubMed 5:33–43
Barbaro J (2013) Early identification of Autism Spectrum Disorders: Why it‟s important”
Fulton AM, Trembath JMPD (2017) Gender comparisons in children with ASD entering early intervention. Res Dev Disabil 68:27–34
Howsman DP, Uwe K, Melnyk S, Jill James S, Hakhn J (2017) Classification and adaptive behavior prediction of children with autism spectrum disorder based upon multivariate data analysis of markers of oxidative stress and DNA methylation. PLoS Comput Biol 13(3):e1005385. https://doi.org/10.1371/journal.pcbi.1005385
Ho BPV, Stephenson J, Carter M (2018) Cognitive-behavioral approaches for chidren with autism spectrum disorder: a trend analysis. Res Autism Spectr Disord 45:27–41
Wiggins LD, Levy SE, Daniels J et al (2015) Autism spectrum disorder symptoms among children enrolled in the study to explore early development (SEED). J Autism Dev Disord 45:3183–3194. https://doi.org/10.1007/s10803-015-2476-8
Thabtah Fadi, Kamalov Firuz, Rajab Khairan (2018) A new computational intelligence approach to detect autistic features for autism screening. Int J Med Inf 117:112–124
Heinsfeld AS, Franco AR, Craddock RC, Buchweitz A, Meneguzzi F (2018) Identification of autism spectrum disorder using deep learning and the ABIDE dataset. NeuroImage Clin 17:16–23
Klopper F, Testa R, Pantelis C, Skafidas E (2017) A cluster analysis exploration of autism spectrum disorder subgroups in children without intellectual disability. Res Autism Spectr Disord 36:66–78
Horner RH, Carr EG et al (2017) Problem behavior intervention for young children with autism: a research synthesis. J Autism Dev Disord 32(5):1
Centers for Disease Control and Prevention (2014) Prevalence of autism spectrum disorders among children 8 years—autism and developmental disabilities monitoring network, 11 sites, United States, 2010. MMWR Surveillance Summaries 63(SS02):1–21
Walker CK, Krakowiak P, Baker A, Hansen R, Ozonoff S, Hertz-Picciotto I (2014) Preecalmpsia, placental insufficiency, and autism spectrum disorder or developmental delay. JAMA Pediatrics. Advance on-line publication
Johnson CP (2004) Early clinical characteristics of children with autism. In: Gupta VB (ed) Autistic spectrum disorders in children. Marcel Dekker Inc., New York, pp 85–123
Baratloo A, Hosseini M, Negida A, El Ashal G (2015) Part 1: simple Definition and Calculation of Accuracy, Sensitivity and Specificity. Emerg (Tehran) 3(2):48–49
Hart JE, More C (2012) Strategies for addressing the disproportionate representation of diverse students with autism spectrum disorder article in intervention in school and clinic. https://doi.org/10.1177/1053451212454168
Alzubi R, Ramzan N, Alzoubi H (2017) Hybrid feature selection method for autism spectrum disorder SNPs. In: IEEE Conference on computational intelligence in bioinformatics and computational biology
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Mohan, P., Paramasivam, I. Feature reduction using SVM-RFE technique to detect autism spectrum disorder. Evol. Intel. 14, 989–997 (2021). https://doi.org/10.1007/s12065-020-00498-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12065-020-00498-2