Rohilah Sahak
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rohilah Sahak has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
A. Zabidi
Universiti Teknologi MARA
16 shared publicationsW. Mansor
Universiti Teknologi MARA
16 shared publicationsAzlee Zabidi
Faculty of Electrical Engineering Universiti Teknologi MARA (UiTM) Shah Alam Selangor Malaysia
12 shared publicationsLee Yoot Khuan
Faculty of Electrical Engineering, University Technology Mara, 40450 Shah Alam, Selangor, MALAYSIA
11 shared publicationsWahidah Mansor
11 shared publicationsY. K. Lee
Faculty of Electrical Engineering, Universiti Teknologi Mara, 404500 Shah Alam, Selangor, Malaysia
9 shared publications
Latest Publications
- Open Access
- 1 March 2020
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 17 (3) , 1355-1361
Human gait recognition using orthogonal least square as feature selection
This study investigates the potential gait features that are related to human recognition using orthogonal least square (OLS). Firstly, video of 30 subjects walking in oblique view was recorded using Kinect. Next, all 20 skeleton joints in 3D space were extracted and further selected using OLS. Additionally, SVM with linear, polynomial and radial basis function (RBF) kernel was used to classify the selected features. As consequences, OLS was proven to be able to identify the significant features using all three kernels of SVM since all recognition accuracy attained is higher as compared to the original gait features. Results attained showed that the highest recognition accuracy was 90.67% using 48 skeleton joint points for SVM with linear as kernel, followed by 46 skeleton joint points for SVM with RBF kernel namely 88.33% and accuracy of 86.33% for 38 skeleton joint points using polynomial kernel.
- 1 March 2020
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 17 (3) , 1355-1361
Open AccessHuman gait recognition using orthogonal least square as feature selection
This study investigates the potential gait features that are related to human recognition using orthogonal least square (OLS). Firstly, video of 30 subjects walking in oblique view was recorded using Kinect. Next, all 20 skeleton joints in 3D space were extracted and further selected using OLS. Additionally, SVM with linear, polynomial and radial basis function (RBF) kernel was used to classify the selected features. As consequences, OLS was proven to be able to identify the significant features using all three kernels of SVM since all recognition accuracy attained is higher as compared to the original gait features. Results attained showed that the highest recognition accuracy was 90.67% using 48 skeleton joint points for SVM with linear as kernel, followed by 46 skeleton joint points for SVM with RBF kernel namely 88.33% and accuracy of 86.33% for 38 skeleton joint points using polynomial kernel.
- 1 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 229-234
Review on Current Methods of Gait Analysis and Recognition using Kinect
In this study the overview of human gait analysis and recognition is discussed based on method and approach by previous researches specifically using the kinect sensor. It was found that upon extraction of the twenty skeleton points using kinect sensor, most researches investigated and explored suitable method or approach in identifying significant gait features for better recognition rate. The advantages and limitation of each study by previous researchers are discussed in detail. However, there is not many findings reported on investigation of the skeleton joint coordinates in xyz-axes for full body as gait features for human gait recognition. Hence this study review and highlight the potential of coordinates of skeleton joints as gait features and thus should be further explored.
- 1 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 229-234
Review on Current Methods of Gait Analysis and Recognition using Kinect
In this study the overview of human gait analysis and recognition is discussed based on method and approach by previous researches specifically using the kinect sensor. It was found that upon extraction of the twenty skeleton points using kinect sensor, most researches investigated and explored suitable method or approach in identifying significant gait features for better recognition rate. The advantages and limitation of each study by previous researchers are discussed in detail. However, there is not many findings reported on investigation of the skeleton joint coordinates in xyz-axes for full body as gait features for human gait recognition. Hence this study review and highlight the potential of coordinates of skeleton joints as gait features and thus should be further explored.
- 9 November 2018
- Published by Springer Nature
- p. 521-528
Kinect-Based Frontal View Gait Recognition Using Support Vector Machine
- 9 November 2018
- Published by Springer Nature
- p. 521-528
Kinect-Based Frontal View Gait Recognition Using Support Vector Machine
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 238-243
Current Methods in Gait Analysis and Recognition: A Review on Model –Based Approach
In this study the overview of human gait followed by previous researches on model-based analysis in human gait recognition will be discussed. This study focuses on general techniques employed in gait recognition using video sequences of human gait that was attained from a standard video camera. Advantages and drawbacks of the employed techniques on the gait video are also identified. Additionally, detailed explanation on the stages involved in the framework of human gait recognition will be elaborated too.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 238-243
Current Methods in Gait Analysis and Recognition: A Review on Model –Based Approach
In this study the overview of human gait followed by previous researches on model-based analysis in human gait recognition will be discussed. This study focuses on general techniques employed in gait recognition using video sequences of human gait that was attained from a standard video camera. Advantages and drawbacks of the employed techniques on the gait video are also identified. Additionally, detailed explanation on the stages involved in the framework of human gait recognition will be elaborated too.
- Open Access
- 2 October 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (4.11) , 202-205
Convolutional Neural Network (CNN) based Gait Recognition System using Microsoft Kinect Skeleton Features
Biometric identification systems have recently made exponential advancements in term of complexity and accuracy in recognition for security purposes and a variety of other application. In this paper, a Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeletal joint data points is proposed for human identification. A total of 23 subjects were used for the experiments. The subjects were positioned 45 degrees (oblique view) from Kinect. A CNN based on the modified AlexNet structure was used to fit the different input data size. The results indicate that the training and testing accuracies were 100% and 69.6% respectively.
- 2 October 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (4.11) , 202-205
Open AccessConvolutional Neural Network (CNN) based Gait Recognition System using Microsoft Kinect Skeleton Features
Biometric identification systems have recently made exponential advancements in term of complexity and accuracy in recognition for security purposes and a variety of other application. In this paper, a Convolutional Neural Network (CNN) based gait recognition system using Microsoft Kinect skeletal joint data points is proposed for human identification. A total of 23 subjects were used for the experiments. The subjects were positioned 45 degrees (oblique view) from Kinect. A CNN based on the modified AlexNet structure was used to fit the different input data size. The results indicate that the training and testing accuracies were 100% and 69.6% respectively.
- 13 August 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (3.15) , 114
Support Vector Machine Performance with Optimal Parameters Identification in Recognising Asphyxiated Infant Cry
Detection of asphyxia in infant at an early stage is crucial to reduce the rate of infant morbidity. The information regarding asphyxia can be extracted from infant cry signals using support vector machine (SVM) combined with effective feature selection methods such as principal component analysis (PCA) or orthogonal least square (OLS). The performance of SVM in recognizing infant cry with asphyxia after undergone comprehensive identification of optimal parameters at the feature extraction and classification stages has not been reported. This paper describes the two stages of optimal parameter identification; at Mel-frequency Cepstral coefficient (MFCC) analysis stage, SVM with and without employing the PCA and OLS stages, and the performance of the SVM in recognizing infant cry with asphyxia resulted from all levels of optimal parameters identification. The SVM was first optimized after performing MFCC analysis to find the optimum parameters. Two types of kernels were used, the polynomial and RBF kernels. The subsequent SVM optimizations were conducted after PCA and OLS were employed. In the PCA, the significant features were selected using eigenvalue-one-criterion (EOC), cumulative percentage variance (CPV) and the Scree test (SCREE). The SVM performance was evaluated based on classification accuracy and computation time. The experimental results have shown that the optimized SVM was able to recognize the asphyxiated infant cry with an accuracy of 94.84% and computation time of 1.98s using PCA with EOC and RBF kernel.
- 13 August 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (3.15) , 114
Support Vector Machine Performance with Optimal Parameters Identification in Recognising Asphyxiated Infant Cry
Detection of asphyxia in infant at an early stage is crucial to reduce the rate of infant morbidity. The information regarding asphyxia can be extracted from infant cry signals using support vector machine (SVM) combined with effective feature selection methods such as principal component analysis (PCA) or orthogonal least square (OLS). The performance of SVM in recognizing infant cry with asphyxia after undergone comprehensive identification of optimal parameters at the feature extraction and classification stages has not been reported. This paper describes the two stages of optimal parameter identification; at Mel-frequency Cepstral coefficient (MFCC) analysis stage, SVM with and without employing the PCA and OLS stages, and the performance of the SVM in recognizing infant cry with asphyxia resulted from all levels of optimal parameters identification. The SVM was first optimized after performing MFCC analysis to find the optimum parameters. Two types of kernels were used, the polynomial and RBF kernels. The subsequent SVM optimizations were conducted after PCA and OLS were employed. In the PCA, the significant features were selected using eigenvalue-one-criterion (EOC), cumulative percentage variance (CPV) and the Scree test (SCREE). The SVM performance was evaluated based on classification accuracy and computation time. The experimental results have shown that the optimized SVM was able to recognize the asphyxiated infant cry with an accuracy of 94.84% and computation time of 1.98s using PCA with EOC and RBF kernel.
- Open Access
- 1 January 2018
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 9 (1) , 139-145
Performance of Principal Component Analysis and Orthogonal Least Square on Optimized Feature Set in Classifying Asphyxiated Infant Cry Using Support Vector Machine
An investigation into optimized support vector machine (SVM) integrated with principal component analysis (PCA) and orthogonal least square (OLS) in classifying asphyxiated infant cry was performed in this study. Three approaches were used in the classification; SVM, PCA-SVM, and OLS-SVM. Various numbers of features extracted from Mel-frequency Cepstral coefficient (MFCC) were tested to obtain the optimal parameters of SVM kernels. Once the optimal feature set is obtained, PCA and OLS selected the most significant features and the optimized SVM then classified the selected cry patterns. In PCA-SVM, eigenvalue-one-criterion (EOC), cumulative percentage variance (CPV) and the Scree test (SCREE) were used to select the most significant features. SVM with radial basis function (RBF) kernel was chosen in the classification stage. The classification accuracy and computation time were computed to evaluate the performance of each method. The best method for classifying asphyxiated infant cry is PCA-SVM with EOC since it produces the highest classification accuracy which is 94.84%. Using PCA-SVM, the classification process was performed in 1.98s only. The results also show that employing feature selection techniques could enhance the classifier performance.
- 1 January 2018
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 9 (1) , 139-145
Open AccessPerformance of Principal Component Analysis and Orthogonal Least Square on Optimized Feature Set in Classifying Asphyxiated Infant Cry Using Support Vector Machine
An investigation into optimized support vector machine (SVM) integrated with principal component analysis (PCA) and orthogonal least square (OLS) in classifying asphyxiated infant cry was performed in this study. Three approaches were used in the classification; SVM, PCA-SVM, and OLS-SVM. Various numbers of features extracted from Mel-frequency Cepstral coefficient (MFCC) were tested to obtain the optimal parameters of SVM kernels. Once the optimal feature set is obtained, PCA and OLS selected the most significant features and the optimized SVM then classified the selected cry patterns. In PCA-SVM, eigenvalue-one-criterion (EOC), cumulative percentage variance (CPV) and the Scree test (SCREE) were used to select the most significant features. SVM with radial basis function (RBF) kernel was chosen in the classification stage. The classification accuracy and computation time were computed to evaluate the performance of each method. The best method for classifying asphyxiated infant cry is PCA-SVM with EOC since it produces the highest classification accuracy which is 94.84%. Using PCA-SVM, the classification process was performed in 1.98s only. The results also show that employing feature selection techniques could enhance the classifier performance.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 388-393
Human gait recognition based on frontal view using kinect features and orthogonal least square selection
This paper discussed the recognition of human gait for both frontal and oblique view based on orthogonal least square (OLS) as feature selection and Multi-Layer perceptron (MLP) as classifier. Firstly, kinect sensor was used to acquire several frames of human gait in both oblique and frontal view. Next, feature extraction is conducted via skeleton joint point in the 3D space known as direct-gait (D-G) feature. Further, feature selection is performed in identifying the significant D-G features using OLS labeled as OLS-G features. Then, the effectiveness of the OLS-G features in recognition of human based on their gait is evaluated using neural network classifier. Result attained proven that OLS-G feature in frontal view is indeed apt for recognition of human based on their gait with recognition accuracy of 90.6%.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 388-393
Human gait recognition based on frontal view using kinect features and orthogonal least square selection
This paper discussed the recognition of human gait for both frontal and oblique view based on orthogonal least square (OLS) as feature selection and Multi-Layer perceptron (MLP) as classifier. Firstly, kinect sensor was used to acquire several frames of human gait in both oblique and frontal view. Next, feature extraction is conducted via skeleton joint point in the 3D space known as direct-gait (D-G) feature. Further, feature selection is performed in identifying the significant D-G features using OLS labeled as OLS-G features. Then, the effectiveness of the OLS-G features in recognition of human based on their gait is evaluated using neural network classifier. Result attained proven that OLS-G feature in frontal view is indeed apt for recognition of human based on their gait with recognition accuracy of 90.6%.