2019 |
Hasan, C Z C; Jailani, R; Tahir, N M 2018-October , Institute of Electrical and Electronics Engineers Inc., 2019, ISSN: 21593442, (cited By 0). Abstract | Links | BibTeX | Tags: 10 Fold Cross Validation, 3D Modeling, Autism Spectrum Disorders, Biophysics, Clinical Decision Making, Computer Aided Diagnosis, Decision Making, Discriminant Analysis, Diseases, Gait Analysis, Gait Classification, Ground Reaction Forces, Neural Networks, Parameterization Techniques, Pattern Recognition, Petroleum Reservoir Evaluation, Program Diagnostics, Support Vector Machines, Targeted Treatment, Three-Dimensional @conference{Hasan20192436, title = {ANN and SVM Classifiers in Identifying Autism Spectrum Disorder Gait Based on Three-Dimensional Ground Reaction Forces}, author = {C Z C Hasan and R Jailani and N M Tahir}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85063202256&doi=10.1109%2fTENCON.2018.8650468&partnerID=40&md5=c697d0c43ebd77d76d74cb3726872f42}, doi = {10.1109/TENCON.2018.8650468}, issn = {21593442}, year = {2019}, date = {2019-01-01}, journal = {IEEE Region 10 Annual International Conference, Proceedings/TENCON}, volume = {2018-October}, pages = {2436-2440}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, abstract = {Autism spectrum disorder (ASD) is a complex and lifelong neurodevelopmental condition that occurs in early childhood and is associated with unusual movement and gait disturbances. An automated and accurate recognition of ASD gait provides assistance in diagnosis and clinical decision-making as well as improving targeted treatment. This paper explores the use of two well-known machine learning classifiers, artificial neural network (ANN) and support vector machine (SVM) in distinguishing ASD and normal gait patterns based on prominent gait features derived from three-dimensional (3D) ground reaction forces (GRFs) data. The 3D GRFs data of 30 children with ASD and 30 typically developing children were obtained using two force plates during self-determined speed of barefoot walking. Time-series parameterization techniques were applied to the 3D GRFs waveforms to extract the significant gait features. The stepwise method of discriminant analysis (SWDA) was employed to determine the dominant GRF gait features in order to classify ASD and typically developing groups. The 10-fold cross-validation test results indicate that the ANN model with three dominant GRF input features outperformed the kernel-based SVM models with 93.3% accuracy, 96.7% sensitivity, and 90.0% specificity. The findings of this study demonstrate the reliability of using the 3D GRF input features, in combination with SWDA feature selection and ANN classification model as an appropriate method that may be beneficial for the diagnosis of ASD gait as well as for evaluation purpose of the treatment programs. © 2018 IEEE.}, note = {cited By 0}, keywords = {10 Fold Cross Validation, 3D Modeling, Autism Spectrum Disorders, Biophysics, Clinical Decision Making, Computer Aided Diagnosis, Decision Making, Discriminant Analysis, Diseases, Gait Analysis, Gait Classification, Ground Reaction Forces, Neural Networks, Parameterization Techniques, Pattern Recognition, Petroleum Reservoir Evaluation, Program Diagnostics, Support Vector Machines, Targeted Treatment, Three-Dimensional}, pubstate = {published}, tppubtype = {conference} } Autism spectrum disorder (ASD) is a complex and lifelong neurodevelopmental condition that occurs in early childhood and is associated with unusual movement and gait disturbances. An automated and accurate recognition of ASD gait provides assistance in diagnosis and clinical decision-making as well as improving targeted treatment. This paper explores the use of two well-known machine learning classifiers, artificial neural network (ANN) and support vector machine (SVM) in distinguishing ASD and normal gait patterns based on prominent gait features derived from three-dimensional (3D) ground reaction forces (GRFs) data. The 3D GRFs data of 30 children with ASD and 30 typically developing children were obtained using two force plates during self-determined speed of barefoot walking. Time-series parameterization techniques were applied to the 3D GRFs waveforms to extract the significant gait features. The stepwise method of discriminant analysis (SWDA) was employed to determine the dominant GRF gait features in order to classify ASD and typically developing groups. The 10-fold cross-validation test results indicate that the ANN model with three dominant GRF input features outperformed the kernel-based SVM models with 93.3% accuracy, 96.7% sensitivity, and 90.0% specificity. The findings of this study demonstrate the reliability of using the 3D GRF input features, in combination with SWDA feature selection and ANN classification model as an appropriate method that may be beneficial for the diagnosis of ASD gait as well as for evaluation purpose of the treatment programs. © 2018 IEEE. |
2018 |
Hasan, C Z C; Jailani, R; Tahir, N M; Desaa, H M Vertical ground reaction force gait patterns during walking in children with autism spectrum disorders Journal Article International Journal of Engineering, Transactions B: Applications, 31 (5), pp. 705-711, 2018, ISSN: 1728144X, (cited By 1). Abstract | Links | BibTeX | Tags: Autism Spectrum Disorders, Biophysics, Children with Autism, Diseases, Gait Analysis, Gait Pattern, Ground Reaction Forces, Independent Samples T-Test, Mann-Whitney U Test, Parameterization Techniques, Spectrum Analysis, Three-Dimensional, Three-Dimensional Motion Analysis @article{Hasan2018705, title = {Vertical ground reaction force gait patterns during walking in children with autism spectrum disorders}, author = {C Z C Hasan and R Jailani and N M Tahir and H M Desaa}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048945706&doi=10.5829%2fije.2018.31.05b.04&partnerID=40&md5=74e349f0b128bc46da82f21d0e484d77}, doi = {10.5829/ije.2018.31.05b.04}, issn = {1728144X}, year = {2018}, date = {2018-01-01}, journal = {International Journal of Engineering, Transactions B: Applications}, volume = {31}, number = {5}, pages = {705-711}, publisher = {Materials and Energy Research Center}, abstract = {The characteristics of vertical ground reaction force (VGRF) gait patterns in children with autism spectrum disorders (ASD) are poorly understood. The purpose of this study was to identify VGRF gait features that discriminate between children with ASD and the peer control group. The VGRF data were obtained from 30 children with ASD and 30 normal healthy children aged 4 to 12 years. A three-dimensional motion analysis system with eight cameras and two force plates were used to collect VGRF data while subjects performed self-selected speed of barefoot walking. Parameterization techniques were applied to VGRF waveforms to extract the VGRF gait features. Mean significant differences between the two groups were tested using independent samples t-test and Mann-Whitney U test. Significant group differences were found for four VGRF gait features. Results indicated that children with ASD exhibited a significant reduction of the second peak of VGRF, earlier relative time to the occurrence of the second peak of VGRF, lower push-off rate, and higher peak ratio of the two VGRF peaks during normal speed of walking. These prominent differences showed that children with ASD had difficulties in supporting their body weight during terminal stance phase and these conditions affect the gait instability. The findings of this study develop further understanding of VGRF gait patterns that significantly differentiate between children with ASD and the peer control groups. © 2018 Materials and Energy Research Center. All Rights Reserved.}, note = {cited By 1}, keywords = {Autism Spectrum Disorders, Biophysics, Children with Autism, Diseases, Gait Analysis, Gait Pattern, Ground Reaction Forces, Independent Samples T-Test, Mann-Whitney U Test, Parameterization Techniques, Spectrum Analysis, Three-Dimensional, Three-Dimensional Motion Analysis}, pubstate = {published}, tppubtype = {article} } The characteristics of vertical ground reaction force (VGRF) gait patterns in children with autism spectrum disorders (ASD) are poorly understood. The purpose of this study was to identify VGRF gait features that discriminate between children with ASD and the peer control group. The VGRF data were obtained from 30 children with ASD and 30 normal healthy children aged 4 to 12 years. A three-dimensional motion analysis system with eight cameras and two force plates were used to collect VGRF data while subjects performed self-selected speed of barefoot walking. Parameterization techniques were applied to VGRF waveforms to extract the VGRF gait features. Mean significant differences between the two groups were tested using independent samples t-test and Mann-Whitney U test. Significant group differences were found for four VGRF gait features. Results indicated that children with ASD exhibited a significant reduction of the second peak of VGRF, earlier relative time to the occurrence of the second peak of VGRF, lower push-off rate, and higher peak ratio of the two VGRF peaks during normal speed of walking. These prominent differences showed that children with ASD had difficulties in supporting their body weight during terminal stance phase and these conditions affect the gait instability. The findings of this study develop further understanding of VGRF gait patterns that significantly differentiate between children with ASD and the peer control groups. © 2018 Materials and Energy Research Center. All Rights Reserved. |
Testingadminnaacuitm2020-05-28T06:49:14+00:00
2019 |
2018-October , Institute of Electrical and Electronics Engineers Inc., 2019, ISSN: 21593442, (cited By 0). |
2018 |
Vertical ground reaction force gait patterns during walking in children with autism spectrum disorders Journal Article International Journal of Engineering, Transactions B: Applications, 31 (5), pp. 705-711, 2018, ISSN: 1728144X, (cited By 1). |