Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/457228
Full metadata record
DC FieldValueLanguage
dc.coverage.spatialAberrant behavior prediction and severity analysis for autistic child through deep transfer learning to avoid adverse drug effect
dc.date.accessioned2023-02-08T07:14:50Z-
dc.date.available2023-02-08T07:14:50Z-
dc.identifier.urihttp://hdl.handle.net/10603/457228-
dc.description.abstractAutism Spectrum Disorder, in child is identified through various newlineparameters such as social skills, repetitive behaviors, speech and non-verbal newlinecommunication. Among the above parameters repetitive behavior plays a vital newlinerole for physician to prescribe to identify the severity of Autism Spectrum newlineDisorder (ASD). The repetitive behavior, and more aggressiveness in the newlineautistic child is the symptom for growth of the disorder. To control the newlinerepetitive behavior, the physician prescribe drug, and dosage level is based on newlineAberrant Behavior Checklist (ABC) value. ABC is measured only for few newlineseconds by the physician at clinic. However, ABC need to be measured after newlinecontinuous monitoring of autistic child in different social environment such as newlineclass room, playground, and corridor, which is not possible for the physician. newlineMoreover, continuous monitoring helps the physician to prescribe exact newlinedosage of drug, and can avoid adverse drug effect. The above problem solve newlinethrough IP webcam app based continuous monitoring of autistic child, and newlinerepetitive behavior measured through proposed algorithms such as (i) Support newlineVector Machines (SVM), (ii) Deep Convolutional Neural Networks (deep newlineCNN), and (iii) Deep Transfer Learning (DTL). The proposed method, newlinereplaces the empirical method of ABC measurement. In this thesis, the newlineproposed method recognizes behavior and changes in autistic child through newlineactivity detection and repetitive behaviours, due to overdosage of drugs. newlineIn proposed method, continuous monitoring of the autistic child is newlinedone through IP web camera. The child image from the recorded video is newlinetaken for the behaviour analysis of the child. The videos are recorded from newlinedifferent locations such as school playground, canteen, lobby and classroom. newlineThe images from video of different locations help to understand the social newlinebehaviour of an autistic child and identify the repetitive behaviours in child. newline
dc.format.extentxviii,171p.
dc.languageEnglish
dc.relationp.160-170
dc.rightsuniversity
dc.titleAberrant behavior prediction and severity analysis for autistic child through deep transfer learning to avoid adverse drug effect
dc.title.alternative
dc.creator.researcherPrabha B
dc.subject.keywordDeep Transfer Learning
dc.subject.keywordAdverse Drug Effect
dc.subject.keywordAutism Spectrum Disorder
dc.description.note
dc.contributor.guidePriya M
dc.publisher.placeChennai
dc.publisher.universityAnna University
dc.publisher.institutionFaculty of Information and Communication Engineering
dc.date.registered
dc.date.completed2022
dc.date.awarded2022
dc.format.dimensions21cm
dc.format.accompanyingmaterialNone
dc.source.universityUniversity
dc.type.degreePh.D.
Appears in Departments:Faculty of Information and Communication Engineering

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File23.84 kBAdobe PDFView/Open
02_prelim pages.pdf945.27 kBAdobe PDFView/Open
03_content.pdf8.35 kBAdobe PDFView/Open
04_abstract.pdf8.24 kBAdobe PDFView/Open
05_chapter 1.pdf35.47 kBAdobe PDFView/Open
06_chapter 2.pdf104.84 kBAdobe PDFView/Open
07_chapter 3.pdf136.86 kBAdobe PDFView/Open
08_chapter 4.pdf577.46 kBAdobe PDFView/Open
09_chapter 5.pdf592.98 kBAdobe PDFView/Open
10_chapter 6.pdf449.28 kBAdobe PDFView/Open
11_annexures.pdf659.79 kBAdobe PDFView/Open
80_recommendation.pdf68.85 kBAdobe PDFView/Open


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: