List of Publications
There are numbers of autism related research can be found in Malaysia that generally focus on the ASD, learning disorder, communication aids, therapy and many more. The list of publications is provided below:
- Click this to search using keyword determined by the user.
- It will lead to a new web page with a text search box.
- Type your keyword in the search box
- Click on Keyword to search for any publication. Bigger words indicate the most used tags and smaller words indicate the least used.
- Click on dropdown buttons to choose any years, types of publications or authors of your choice.
- Click on underlined words in the publication detail to view more information.
2018 |
Hariharan, M; Sindhu, R; Vijean, V; Yazid, H; Nadarajaw, T; Yaacob, S; Polat, K Improved binary dragonfly optimization algorithm and wavelet packet based non-linear features for infant cry classification Journal Article Computer Methods and Programs in Biomedicine, 155 , pp. 39-51, 2018, ISSN: 01692607, (cited By 21). Abstract | Links | BibTeX | Tags: Accidents, Algorithms, Article, Artificial Neural Network, Asphyxia, Binary Dragonfly Optimization Aalgorithm, Classification (of information), Classification Algorithm, Classifier, Coding, Computer-Assisted, Constants and Coefficients, Crying, Database Systems, Databases, Deafness, Diagnosis, Energy, Entropy, Extraction, Extreme Learning Machine, Factual, Factual Database, Feature Extraction, Feature Selection Methods, Fuzzy System, Hearing Impairment, Human, Hunger, Infant, Infant Cry, Infant Cry Classifications, Jaundice, Kernel Method, Learning, Linear Predictive Coding, Machine Learning, Mathematical Transformations, Mel Frequency Cepstral Coefficient, Mel Frequency Cepstral Coefficients, Multi-Class Classification, Neural Networks, Nonlinear Dynamics, Nonlinear System, Optimization, Pain, Pathophysiology, Prematurity, Reproducibility, Reproducibility of Results, Signal Processing, Speech Recognition, Wavelet Analysis, Wavelet Packet, Wavelet Packet Transforms @article{Hariharan201839, title = {Improved binary dragonfly optimization algorithm and wavelet packet based non-linear features for infant cry classification}, author = {M Hariharan and R Sindhu and V Vijean and H Yazid and T Nadarajaw and S Yaacob and K Polat}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85036611215&doi=10.1016%2fj.cmpb.2017.11.021&partnerID=40&md5=1f3b17817b00f07cadad6eb61c0f4bf9}, doi = {10.1016/j.cmpb.2017.11.021}, issn = {01692607}, year = {2018}, date = {2018-01-01}, journal = {Computer Methods and Programs in Biomedicine}, volume = {155}, pages = {39-51}, publisher = {Elsevier Ireland Ltd}, abstract = {Background and objective Infant cry signal carries several levels of information about the reason for crying (hunger, pain, sleepiness and discomfort) or the pathological status (asphyxia, deaf, jaundice, premature condition and autism, etc.) of an infant and therefore suited for early diagnosis. In this work, combination of wavelet packet based features and Improved Binary Dragonfly Optimization based feature selection method was proposed to classify the different types of infant cry signals. Methods Cry signals from 2 different databases were utilized. First database contains 507 cry samples of normal (N), 340 cry samples of asphyxia (A), 879 cry samples of deaf (D), 350 cry samples of hungry (H) and 192 cry samples of pain (P). Second database contains 513 cry samples of jaundice (J), 531 samples of premature (Prem) and 45 samples of normal (N). Wavelet packet transform based energy and non-linear entropies (496 features), Linear Predictive Coding (LPC) based cepstral features (56 features), Mel-frequency Cepstral Coefficients (MFCCs) were extracted (16 features). The combined feature set consists of 568 features. To overcome the curse of dimensionality issue, improved binary dragonfly optimization algorithm (IBDFO) was proposed to select the most salient attributes or features. Finally, Extreme Learning Machine (ELM) kernel classifier was used to classify the different types of infant cry signals using all the features and highly informative features as well. Results Several experiments of two-class and multi-class classification of cry signals were conducted. In binary or two-class experiments, maximum accuracy of 90.18% for H Vs P, 100% for A Vs N, 100% for D Vs N and 97.61% J Vs Prem was achieved using the features selected (only 204 features out of 568) by IBDFO. For the classification of multiple cry signals (multi-class problem), the selected features could differentiate between three classes (N, A & D) with the accuracy of 100% and seven classes with the accuracy of 97.62%. Conclusion The experimental results indicated that the proposed combination of feature extraction and selection method offers suitable classification accuracy and may be employed to detect the subtle changes in the cry signals. © 2017 Elsevier B.V.}, note = {cited By 21}, keywords = {Accidents, Algorithms, Article, Artificial Neural Network, Asphyxia, Binary Dragonfly Optimization Aalgorithm, Classification (of information), Classification Algorithm, Classifier, Coding, Computer-Assisted, Constants and Coefficients, Crying, Database Systems, Databases, Deafness, Diagnosis, Energy, Entropy, Extraction, Extreme Learning Machine, Factual, Factual Database, Feature Extraction, Feature Selection Methods, Fuzzy System, Hearing Impairment, Human, Hunger, Infant, Infant Cry, Infant Cry Classifications, Jaundice, Kernel Method, Learning, Linear Predictive Coding, Machine Learning, Mathematical Transformations, Mel Frequency Cepstral Coefficient, Mel Frequency Cepstral Coefficients, Multi-Class Classification, Neural Networks, Nonlinear Dynamics, Nonlinear System, Optimization, Pain, Pathophysiology, Prematurity, Reproducibility, Reproducibility of Results, Signal Processing, Speech Recognition, Wavelet Analysis, Wavelet Packet, Wavelet Packet Transforms}, pubstate = {published}, tppubtype = {article} } Background and objective Infant cry signal carries several levels of information about the reason for crying (hunger, pain, sleepiness and discomfort) or the pathological status (asphyxia, deaf, jaundice, premature condition and autism, etc.) of an infant and therefore suited for early diagnosis. In this work, combination of wavelet packet based features and Improved Binary Dragonfly Optimization based feature selection method was proposed to classify the different types of infant cry signals. Methods Cry signals from 2 different databases were utilized. First database contains 507 cry samples of normal (N), 340 cry samples of asphyxia (A), 879 cry samples of deaf (D), 350 cry samples of hungry (H) and 192 cry samples of pain (P). Second database contains 513 cry samples of jaundice (J), 531 samples of premature (Prem) and 45 samples of normal (N). Wavelet packet transform based energy and non-linear entropies (496 features), Linear Predictive Coding (LPC) based cepstral features (56 features), Mel-frequency Cepstral Coefficients (MFCCs) were extracted (16 features). The combined feature set consists of 568 features. To overcome the curse of dimensionality issue, improved binary dragonfly optimization algorithm (IBDFO) was proposed to select the most salient attributes or features. Finally, Extreme Learning Machine (ELM) kernel classifier was used to classify the different types of infant cry signals using all the features and highly informative features as well. Results Several experiments of two-class and multi-class classification of cry signals were conducted. In binary or two-class experiments, maximum accuracy of 90.18% for H Vs P, 100% for A Vs N, 100% for D Vs N and 97.61% J Vs Prem was achieved using the features selected (only 204 features out of 568) by IBDFO. For the classification of multiple cry signals (multi-class problem), the selected features could differentiate between three classes (N, A & D) with the accuracy of 100% and seven classes with the accuracy of 97.62%. Conclusion The experimental results indicated that the proposed combination of feature extraction and selection method offers suitable classification accuracy and may be employed to detect the subtle changes in the cry signals. © 2017 Elsevier B.V. |
2017 |
Ilias, S; Tahir, N M; Jailani, R Institute of Electrical and Electronics Engineers Inc., 2017, ISBN: 9781509009251, (cited By 0). Abstract | Links | BibTeX | Tags: Classification (of information), Discriminant Analysis, Diseases, Extraction, Feature Extraction, Gait Analysis, Gait Classification, Image Retrieval, Industrial Electronics, Kernel Function, Kinematic Parameters, Kinematics, Learning, Linear Discriminant Analysis, Machine Learning Approaches, Motion Analysis System, Polynomial Functions, Principal Component Analysis, Support Vector Machines, SVM Classifiers @conference{Ilias2017275, title = {Feature extraction of autism gait data using principal component analysis and linear discriminant analysis}, author = {S Ilias and N M Tahir and R Jailani}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85034081031&doi=10.1109%2fIEACON.2016.8067391&partnerID=40&md5=7deaef6538413df7bfaf7cf723001d72}, doi = {10.1109/IEACON.2016.8067391}, isbn = {9781509009251}, year = {2017}, date = {2017-01-01}, journal = {IEACon 2016 - 2016 IEEE Industrial Electronics and Applications Conference}, pages = {275-279}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, abstract = {In this research, the application of machine learning approach specifically support vector machine along with principal component analysis and linear discriminant analysis as feature extractions are evaluated and validated in discriminating gait features between normal subjects and autism children. Gait features of 32 normal and 12 autism children were recorded and analyzed using VICON motion analysis system and a force platform during normal walking. Here, twenty one gait features describing the three types of gait characteristics namely basic, kinetic and kinematic in these children are extracted. Further, with these gait features as input during classification, the ability of SVM as classifier are investigated using three different kernel functions specifically linear, polynomial, and radial basis. Results showed that LDA as feature extraction is the highest accuracy with kinematic parameters as gait features along with polynomial function as kernel for the SVM classifier. This finding proven that LDA is suitable as feature extraction and SVM is indeed apt as gait classifier in classifying the gait pattern autism and normal children. © 2016 IEEE.}, note = {cited By 0}, keywords = {Classification (of information), Discriminant Analysis, Diseases, Extraction, Feature Extraction, Gait Analysis, Gait Classification, Image Retrieval, Industrial Electronics, Kernel Function, Kinematic Parameters, Kinematics, Learning, Linear Discriminant Analysis, Machine Learning Approaches, Motion Analysis System, Polynomial Functions, Principal Component Analysis, Support Vector Machines, SVM Classifiers}, pubstate = {published}, tppubtype = {conference} } In this research, the application of machine learning approach specifically support vector machine along with principal component analysis and linear discriminant analysis as feature extractions are evaluated and validated in discriminating gait features between normal subjects and autism children. Gait features of 32 normal and 12 autism children were recorded and analyzed using VICON motion analysis system and a force platform during normal walking. Here, twenty one gait features describing the three types of gait characteristics namely basic, kinetic and kinematic in these children are extracted. Further, with these gait features as input during classification, the ability of SVM as classifier are investigated using three different kernel functions specifically linear, polynomial, and radial basis. Results showed that LDA as feature extraction is the highest accuracy with kinematic parameters as gait features along with polynomial function as kernel for the SVM classifier. This finding proven that LDA is suitable as feature extraction and SVM is indeed apt as gait classifier in classifying the gait pattern autism and normal children. © 2016 IEEE. |
Ilias, S; Tahir, N M; Jailani, R; Hasan, C Z C Linear Discriminant Analysis in Classifying Walking Gait of Autistic Children Conference Institute of Electrical and Electronics Engineers Inc., 2017, ISBN: 9781538614099, (cited By 0). Abstract | Links | BibTeX | Tags: Autism, Autistic Children, Children with Autism, Discriminant Analysis, Diseases, Extraction, Feature Extraction, Gait Analysis, Gait Classification, Kinematics, Linear Discriminant Analysis, Motion Analysis System, Neural Networks, Principal Component Analysis, Three-Dimensional @conference{Ilias201767, title = {Linear Discriminant Analysis in Classifying Walking Gait of Autistic Children}, author = {S Ilias and N M Tahir and R Jailani and C Z C Hasan}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048377850&doi=10.1109%2fEMS.2017.22&partnerID=40&md5=06de53be2b4f3976ddcc420067ab6e44}, doi = {10.1109/EMS.2017.22}, isbn = {9781538614099}, year = {2017}, date = {2017-01-01}, journal = {Proceedings - UKSim-AMSS 11th European Modelling Symposium on Computer Modelling and Simulation, EMS 2017}, pages = {67-72}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, abstract = {The aim of this research is to investigate the effectiveness between Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) along with neural network (NN) in classifying the gait of autistic children as compared to control group. Twelve autistic children and thirty two normal children participated in this study. Firstly the walking gait of these two groups are acquired using VICON Motion Analysis System to extract the three dimensional (3D) gait features that comprised of 21 gait features namely five features from basic temporal spatial, five features represented the kinetic parameters and twelve features from kinematic. Further, PCA and LDA are utilized as feature extraction in determining the significant features among these gait features. With NN as classifier, results showed that LDA as feature extraction outperform PCA for classification of autism versus normal children namely kinematic gait patterns attained 98.44% accuracy followed by basic temporal spatial gait features with accuracy of 87.5%. © 2017 IEEE.}, note = {cited By 0}, keywords = {Autism, Autistic Children, Children with Autism, Discriminant Analysis, Diseases, Extraction, Feature Extraction, Gait Analysis, Gait Classification, Kinematics, Linear Discriminant Analysis, Motion Analysis System, Neural Networks, Principal Component Analysis, Three-Dimensional}, pubstate = {published}, tppubtype = {conference} } The aim of this research is to investigate the effectiveness between Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) along with neural network (NN) in classifying the gait of autistic children as compared to control group. Twelve autistic children and thirty two normal children participated in this study. Firstly the walking gait of these two groups are acquired using VICON Motion Analysis System to extract the three dimensional (3D) gait features that comprised of 21 gait features namely five features from basic temporal spatial, five features represented the kinetic parameters and twelve features from kinematic. Further, PCA and LDA are utilized as feature extraction in determining the significant features among these gait features. With NN as classifier, results showed that LDA as feature extraction outperform PCA for classification of autism versus normal children namely kinematic gait patterns attained 98.44% accuracy followed by basic temporal spatial gait features with accuracy of 87.5%. © 2017 IEEE. |