2020 |
Liang, S; Loo, C K; Sabri, Md A Q Autism Spectrum Disorder Classification in Videos: A Hybrid of Temporal Coherency Deep Networks and Self-organizing Dual Memory Approach Journal Article Lecture Notes in Electrical Engineering, 621 , pp. 421-430, 2020, ISSN: 18761100, (cited By 0). Abstract | Links | BibTeX | Tags: Artificial Intelligence, Autism Spectrum Disorders, Autistic Children, Catastrophic Forgetting, Children with Autism, Diagnosis, Diseases, E-learning, Hybrid Approach, Learning, Neural Networks, Primary Objective, Scalable Systems, Temporal Coherency, Unsupervised Online Learning @article{Liang2020421, title = {Autism Spectrum Disorder Classification in Videos: A Hybrid of Temporal Coherency Deep Networks and Self-organizing Dual Memory Approach}, author = {S Liang and C K Loo and A Q Md Sabri}, editor = {Kim H -Y Kim K.J.}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85077496650&doi=10.1007%2f978-981-15-1465-4_42&partnerID=40&md5=8d885d212faf9e5a9d686c58a2e4eecd}, doi = {10.1007/978-981-15-1465-4_42}, issn = {18761100}, year = {2020}, date = {2020-01-01}, journal = {Lecture Notes in Electrical Engineering}, volume = {621}, pages = {421-430}, publisher = {Springer}, abstract = {Autism is at the moment, a common disorder. Prevalence of Autism Spectrum Disorder (ASD) is reported to be 1 in every 88 individuals. Early diagnosis of ASD has a significant impact to the livelihood of autistic children and their parents, or their caregivers. In this paper, we have developed an unsupervised online learning model for ASD classification. The proposed approach is a hybrid approach, consisting, the temporal coherency deep networks approach, and, the self-organizing dual memory approach. The primary objective of the research is, to have a scalable system that can achieve online learning, and, is able to avoid the catastrophic forgetting phenomena in neural networks. We have evaluated our approach using an ASD specific dataset, and obtained promising results that are well inclined in supporting the overall objective of the research. © Springer Nature Singapore Pte Ltd 2020.}, note = {cited By 0}, keywords = {Artificial Intelligence, Autism Spectrum Disorders, Autistic Children, Catastrophic Forgetting, Children with Autism, Diagnosis, Diseases, E-learning, Hybrid Approach, Learning, Neural Networks, Primary Objective, Scalable Systems, Temporal Coherency, Unsupervised Online Learning}, pubstate = {published}, tppubtype = {article} } Autism is at the moment, a common disorder. Prevalence of Autism Spectrum Disorder (ASD) is reported to be 1 in every 88 individuals. Early diagnosis of ASD has a significant impact to the livelihood of autistic children and their parents, or their caregivers. In this paper, we have developed an unsupervised online learning model for ASD classification. The proposed approach is a hybrid approach, consisting, the temporal coherency deep networks approach, and, the self-organizing dual memory approach. The primary objective of the research is, to have a scalable system that can achieve online learning, and, is able to avoid the catastrophic forgetting phenomena in neural networks. We have evaluated our approach using an ASD specific dataset, and obtained promising results that are well inclined in supporting the overall objective of the research. © Springer Nature Singapore Pte Ltd 2020. |
2018 |
Khowaja, K; Al-Thani, D; Salim, S S 2018-October , Dechema e.V., 2018, ISSN: 20490992, (cited By 1). Abstract | Links | BibTeX | Tags: Artificial Intelligence, Autism Spectrum Disorders, Children with Autism, Comparison of Performance, Diseases, Game Prototypes, Games, Instruction Methods, Maintenance, Prototype, Research, Serious Games, Vocabulary Learning @conference{Khowaja2018288, title = {Vocabulary learning of children with autism spectrum disorder (Asd): From the development to an evaluation of serious game prototype}, author = {K Khowaja and D Al-Thani and S S Salim}, editor = {Ciussi M.}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85058940806&partnerID=40&md5=02b800c8fa997482a73efac067b59fc9}, issn = {20490992}, year = {2018}, date = {2018-01-01}, journal = {Proceedings of the European Conference on Games-based Learning}, volume = {2018-October}, pages = {288-298}, publisher = {Dechema e.V.}, abstract = {The review of the literature has shown that despite the effectiveness of serious games in the learning of various skills of children with autism spectrum disorder (ASD), they have been underutilised for the learning of vocabulary among children with ASD. This paper presents the development and evaluation of a serious game prototype for the vocabulary learning of children with ASD. The serious game design framework, especially for children with ASD, was used as a basis to support from the design to the development of the prototype. This framework includes components from the ASD perspective and components used in the existing serious game design frameworks for typical children perspective and the game design in general. To elicit requirements on the ASD components (autism behaviours, instruction method, strategies, and modalities) of the framework, a detailed survey study was conducted with the teachers working at the schools or centres for children with ASD. The results of this study contributed to the development of a prototype. The single-subject research design (SSRD) was used as a research design for the evaluation of prototype and analyse its impact on the improvement of autism behaviours targeted in the prototype over the period of time. The evaluation of prototype was carried out in terms of the number of correct responses given, number of attempts made to identify the correct answer and time taken to identify the correct option. The comparison of performance from the baseline to intervention and maintenance using serious game prototype show that learning of vocabulary items among children with ASD improved after using the prototype and they retained items at the end of weeks 1 and 2 following the withdrawal of intervention. The number of attempts made reduced from the baseline to intervention and then remained the same during maintenance. The time taken to identify the correct answer marginally increased from the baseline to the intervention but reduced during the maintenance in comparison to the baseline. © 2018, Dechema e.V. All rights reserved.}, note = {cited By 1}, keywords = {Artificial Intelligence, Autism Spectrum Disorders, Children with Autism, Comparison of Performance, Diseases, Game Prototypes, Games, Instruction Methods, Maintenance, Prototype, Research, Serious Games, Vocabulary Learning}, pubstate = {published}, tppubtype = {conference} } The review of the literature has shown that despite the effectiveness of serious games in the learning of various skills of children with autism spectrum disorder (ASD), they have been underutilised for the learning of vocabulary among children with ASD. This paper presents the development and evaluation of a serious game prototype for the vocabulary learning of children with ASD. The serious game design framework, especially for children with ASD, was used as a basis to support from the design to the development of the prototype. This framework includes components from the ASD perspective and components used in the existing serious game design frameworks for typical children perspective and the game design in general. To elicit requirements on the ASD components (autism behaviours, instruction method, strategies, and modalities) of the framework, a detailed survey study was conducted with the teachers working at the schools or centres for children with ASD. The results of this study contributed to the development of a prototype. The single-subject research design (SSRD) was used as a research design for the evaluation of prototype and analyse its impact on the improvement of autism behaviours targeted in the prototype over the period of time. The evaluation of prototype was carried out in terms of the number of correct responses given, number of attempts made to identify the correct answer and time taken to identify the correct option. The comparison of performance from the baseline to intervention and maintenance using serious game prototype show that learning of vocabulary items among children with ASD improved after using the prototype and they retained items at the end of weeks 1 and 2 following the withdrawal of intervention. The number of attempts made reduced from the baseline to intervention and then remained the same during maintenance. The time taken to identify the correct answer marginally increased from the baseline to the intervention but reduced during the maintenance in comparison to the baseline. © 2018, Dechema e.V. All rights reserved. |
Testingadminnaacuitm2020-05-28T06:49:14+00:00
2020 |
Autism Spectrum Disorder Classification in Videos: A Hybrid of Temporal Coherency Deep Networks and Self-organizing Dual Memory Approach Journal Article Lecture Notes in Electrical Engineering, 621 , pp. 421-430, 2020, ISSN: 18761100, (cited By 0). |
2018 |
2018-October , Dechema e.V., 2018, ISSN: 20490992, (cited By 1). |