Fuzzy model for detection and estimation of the degree of autism spectrum disorder
Early detection of autism spectrum disorder (ASD) is of great significance for early intervention. Besides, knowing the degree of severity in ASD and how it changes with the intervention is imperative for the treatment process. This study proposes Takagi- Sugeno-Kang (TSK) fuzzy modeling approach th...
| Main Authors: | , , |
|---|---|
| Format: | Proceeding Paper |
| Language: | English |
| Published: |
2012
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/29062/1/Fuzzy_model_for_detection_and_estimation_of_the_degree_of_autism_spectrum_disorder.pdf |
| _version_ | 1825647158828728320 |
|---|---|
| author | Shams, Wafaa Khazaal Abdul Rahman, Abdul Wahab A. Qidwai, Uvais |
| author_facet | Shams, Wafaa Khazaal Abdul Rahman, Abdul Wahab A. Qidwai, Uvais |
| author_sort | Shams, Wafaa Khazaal |
| collection | IIUM |
| description | Early detection of autism spectrum disorder (ASD) is of great significance for early intervention. Besides, knowing the degree of severity in ASD and how it changes with the intervention is imperative for the treatment process. This study proposes Takagi- Sugeno-Kang (TSK) fuzzy modeling approach that is based on subtractive clustering to classify autism spectrum disorder and to estimate the degree of prognosis. The study has been carried out using Electroencephalography (EEG) signal on two groups of control and ASD children age-matched between seven to nine years old. EEG signals are quantized to temporal-time domain using Short Time Frequency Transformation (STFT). Spectrum energy is extracted as features for alpha band. The proposed system is modeled to estimate the degree in which subject is autistic, normal or uncertain. The results show accuracy in range (70-97) % when using fuzzy model .Also this system is modeled to generate crisp decision; the results show accuracy in the range (80-100) %. The proposed model can be adapted to help psychiatrist for diagnosis and intervention process. |
| first_indexed | 2024-03-05T23:13:28Z |
| format | Proceeding Paper |
| id | oai:generic.eprints.org:29062 |
| institution | International Islamic University Malaysia |
| language | English |
| last_indexed | 2024-03-05T23:13:28Z |
| publishDate | 2012 |
| record_format | dspace |
| spelling | oai:generic.eprints.org:290622020-12-16T16:52:32Z http://irep.iium.edu.my/29062/ Fuzzy model for detection and estimation of the degree of autism spectrum disorder Shams, Wafaa Khazaal Abdul Rahman, Abdul Wahab A. Qidwai, Uvais QA75 Electronic computers. Computer science Early detection of autism spectrum disorder (ASD) is of great significance for early intervention. Besides, knowing the degree of severity in ASD and how it changes with the intervention is imperative for the treatment process. This study proposes Takagi- Sugeno-Kang (TSK) fuzzy modeling approach that is based on subtractive clustering to classify autism spectrum disorder and to estimate the degree of prognosis. The study has been carried out using Electroencephalography (EEG) signal on two groups of control and ASD children age-matched between seven to nine years old. EEG signals are quantized to temporal-time domain using Short Time Frequency Transformation (STFT). Spectrum energy is extracted as features for alpha band. The proposed system is modeled to estimate the degree in which subject is autistic, normal or uncertain. The results show accuracy in range (70-97) % when using fuzzy model .Also this system is modeled to generate crisp decision; the results show accuracy in the range (80-100) %. The proposed model can be adapted to help psychiatrist for diagnosis and intervention process. 2012 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/29062/1/Fuzzy_model_for_detection_and_estimation_of_the_degree_of_autism_spectrum_disorder.pdf Shams, Wafaa Khazaal and Abdul Rahman, Abdul Wahab and A. Qidwai, Uvais (2012) Fuzzy model for detection and estimation of the degree of autism spectrum disorder. In: Proceedings of the 19th International Conference on Neural Information Processing (ICONIP 2012), November 12-15, 2012, Doha, Qatar. http://link.springer.com/chapter/10.1007%2F978-3-642-34478-7_46 |
| spellingShingle | QA75 Electronic computers. Computer science Shams, Wafaa Khazaal Abdul Rahman, Abdul Wahab A. Qidwai, Uvais Fuzzy model for detection and estimation of the degree of autism spectrum disorder |
| title | Fuzzy model for detection and estimation of the degree of autism spectrum disorder |
| title_full | Fuzzy model for detection and estimation of the degree of autism spectrum disorder |
| title_fullStr | Fuzzy model for detection and estimation of the degree of autism spectrum disorder |
| title_full_unstemmed | Fuzzy model for detection and estimation of the degree of autism spectrum disorder |
| title_short | Fuzzy model for detection and estimation of the degree of autism spectrum disorder |
| title_sort | fuzzy model for detection and estimation of the degree of autism spectrum disorder |
| topic | QA75 Electronic computers. Computer science |
| url | http://irep.iium.edu.my/29062/1/Fuzzy_model_for_detection_and_estimation_of_the_degree_of_autism_spectrum_disorder.pdf |
| work_keys_str_mv | AT shamswafaakhazaal fuzzymodelfordetectionandestimationofthedegreeofautismspectrumdisorder AT abdulrahmanabdulwahab fuzzymodelfordetectionandestimationofthedegreeofautismspectrumdisorder AT aqidwaiuvais fuzzymodelfordetectionandestimationofthedegreeofautismspectrumdisorder |