Nasrul Humaimi Mahmood
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nasrul Humaimi Mahmood has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Rubita Sudirman
Universiti Teknologi Malaysia
4 shared publications - Ahlam Al-Dhamari
Department of Electronic and Computer Engineering, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Malaysia
2 shared publications - Ching Yee Yong
University College of Technology Sarawak, 96000, Sibu, Sarawak, Malaysia
2 shared publications Kim Mey Chew
Universiti Teknologi Malaysia
2 shared publicationsAhmad Hazwan AB Rahim
Fac. of Electr. Eng., Univ. Teknol. Malaysia, Skudai, Malaysia
1 shared publicationF. Taha
Cordless Charger Research Group|Faculty of Electrical Engineering
1 shared publication
Latest Publications
- 27 January 2021
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in Turkish Journal of Electrical Engineering and Computer Sciences
- Vol. 29 (1) , 152-168
Abnormal behavior detection using sparse representations through sequential generalization of k-means
- 27 January 2021
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in Turkish Journal of Electrical Engineering and Computer Sciences
- Vol. 29 (1) , 152-168
Abnormal behavior detection using sparse representations through sequential generalization of k-means
- Open Access
- 24 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 61085-61095
Transfer Deep Learning Along With Binary Support Vector Machine for Abnormal Behavior Detection
Today, machine learning and deep learning have paved the way for vital and critical applications such as abnormal detection. Despite the modernity of transfer learning, it has proved to be one of the crucial inventions in the field of deep learning because of its promising results. For the purpose of this study, transfer learning is utilized to extract human motion features from RGB video frames to improve detection accuracy. A convolutional neural network (CNN) based on Visual Geometry Group network 19 (VGGNet-19) pre-trained model is used to extract descriptive features. Next, the feature vector is passed into Binary Support Vector Machine classifier (BSVM) to construct a binary-SVM model. The performance of the proposed framework is evaluated by three parameters: accuracy, area under the curve, and equal error rate. Experiments performed on two different datasets comprising highly different context abnormalities accomplished an accuracy of 97.44% and an area under the curve (AUC) of 0.9795 for University of Minnesota (UMN) dataset and accomplished an accuracy of 86.69% and an AUC of 0.7987 for University of California, San Diego Pedistrain1 (UCSD-PED1) dataset. Moreover, the performance of the pre-trained network VGGNet-19 with handcrafted feature descriptors and with other CNN pre-trained networks, respectively, has been investigated in this study for abnormal behavior detection. The results demonstrated that VGGNet-19 has better performance than histogram of oriented gradients, background subtraction, and optical flow. In addition, the VGGNet-19 shows higher detection accuracy than other pre-trained networks: GoogleNet, ResNet50, AlexNet, and VGGNet-16.
- 24 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 61085-61095
Open AccessTransfer Deep Learning Along With Binary Support Vector Machine for Abnormal Behavior Detection
Today, machine learning and deep learning have paved the way for vital and critical applications such as abnormal detection. Despite the modernity of transfer learning, it has proved to be one of the crucial inventions in the field of deep learning because of its promising results. For the purpose of this study, transfer learning is utilized to extract human motion features from RGB video frames to improve detection accuracy. A convolutional neural network (CNN) based on Visual Geometry Group network 19 (VGGNet-19) pre-trained model is used to extract descriptive features. Next, the feature vector is passed into Binary Support Vector Machine classifier (BSVM) to construct a binary-SVM model. The performance of the proposed framework is evaluated by three parameters: accuracy, area under the curve, and equal error rate. Experiments performed on two different datasets comprising highly different context abnormalities accomplished an accuracy of 97.44% and an area under the curve (AUC) of 0.9795 for University of Minnesota (UMN) dataset and accomplished an accuracy of 86.69% and an AUC of 0.7987 for University of California, San Diego Pedistrain1 (UCSD-PED1) dataset. Moreover, the performance of the pre-trained network VGGNet-19 with handcrafted feature descriptors and with other CNN pre-trained networks, respectively, has been investigated in this study for abnormal behavior detection. The results demonstrated that VGGNet-19 has better performance than histogram of oriented gradients, background subtraction, and optical flow. In addition, the VGGNet-19 shows higher detection accuracy than other pre-trained networks: GoogleNet, ResNet50, AlexNet, and VGGNet-16.
- 1 September 2013
- Published by Elsevier in Materials Research Bulletin
- Vol. 48 (9) , 3172-3177
Characterization and antibacterial properties of stable silver substituted hydroxyapatite nanoparticles synthesized through surfactant assisted microwave process
- 1 September 2013
- Published by Elsevier in Materials Research Bulletin
- Vol. 48 (9) , 3172-3177
Characterization and antibacterial properties of stable silver substituted hydroxyapatite nanoparticles synthesized through surfactant assisted microwave process
- 25 January 2013
- Published by Trans Tech Publications, Ltd. in Applied Mechanics and Materials
- Vol. 284-287, 3126-3130
Human Hand Movement Analysis Using Principle Component Analysis Classifier
This study investigates and acts as a trial clinical outcome for human motion and behavior analysis in order to investigate human arm movement during jogging and walking. It was developed to analyze and access the quality of human motion that can be used in hospitals, clinics and human motion researches. It aims to establish how widespread the movement and motion of arm will bring to effect of human in life. An experiment was set up in a laboratory environment with conjunction of analyzing human motion and its behavior. The instruments demonstrate adequate internal consistency of optimum scatter plot in gyroscope and accelerometer for pattern classification. PCA used in this study was successfully differentiate and classify
- 25 January 2013
- Published by Trans Tech Publications, Ltd. in Applied Mechanics and Materials
- Vol. 284-287, 3126-3130
Human Hand Movement Analysis Using Principle Component Analysis Classifier
This study investigates and acts as a trial clinical outcome for human motion and behavior analysis in order to investigate human arm movement during jogging and walking. It was developed to analyze and access the quality of human motion that can be used in hospitals, clinics and human motion researches. It aims to establish how widespread the movement and motion of arm will bring to effect of human in life. An experiment was set up in a laboratory environment with conjunction of analyzing human motion and its behavior. The instruments demonstrate adequate internal consistency of optimum scatter plot in gyroscope and accelerometer for pattern classification. PCA used in this study was successfully differentiate and classify
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 943-946
Time-Frequency Domain and Spectrogram Distribution for Human Motion and Movement Behaviour Analysis
This study investigates and acts as a trial clinical outcome for human motion and behaviour analysis in consensus of health related quality of life in Malaysia. It was developed to analyse and access the quality of human motion that can be used in hospitals, clinics and human motion researches. It aims to establish how widespread the quality of life effects of human motion. Reliability and validity are needed that can help facilitate subject outcomes. An experiment was set up in a laboratory environment with conjunction of analysing human motion and its behaviour. The instruments demonstrate adequate internal consistency of optimum window length (n) in sampling human motion signals from gyroscope (n=16), accelerometer (n=16) and compass (n=8) signals. A simple system for time-domain signal to frequency-domain signal conversion and spectrogram was developed to demonstrate the results.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 943-946
Time-Frequency Domain and Spectrogram Distribution for Human Motion and Movement Behaviour Analysis
This study investigates and acts as a trial clinical outcome for human motion and behaviour analysis in consensus of health related quality of life in Malaysia. It was developed to analyse and access the quality of human motion that can be used in hospitals, clinics and human motion researches. It aims to establish how widespread the quality of life effects of human motion. Reliability and validity are needed that can help facilitate subject outcomes. An experiment was set up in a laboratory environment with conjunction of analysing human motion and its behaviour. The instruments demonstrate adequate internal consistency of optimum window length (n) in sampling human motion signals from gyroscope (n=16), accelerometer (n=16) and compass (n=8) signals. A simple system for time-domain signal to frequency-domain signal conversion and spectrogram was developed to demonstrate the results.
- 6 July 2005
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 207-211
Cableless battery charger using induction technique for electric vehicles
Electromagnetic induction is the production of an electromotive force in a conductor as a result of a changing magnetic field about the conductor. The induced emfalways such that it opposes the change that gives rise to it, according to Lenz's law. In our work, we are considering in controlling the magnetic flux distribution through an air-gap during the energy transfer from the source to load. This research has put a core situation in investigating the possible ways of charging the batteries via mutual induction as in transformers. This enables the charging process to he cableless. It involves two coils transferring energy from one to the other through air in the most cffrcient way. Our work is presented in this paper. Simulation and hardware implementation has been carried out successfully. We have measured the magnetic flux density for ac input voltage of 100 Volt with different frequency values. The optimum frequency in our design is 25 Hz. We found that it is possible to control the magnetic flux distribution during energy transmission by optimizing the frequency and shielding the flux path.
- 6 July 2005
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 207-211
Cableless battery charger using induction technique for electric vehicles
Electromagnetic induction is the production of an electromotive force in a conductor as a result of a changing magnetic field about the conductor. The induced emfalways such that it opposes the change that gives rise to it, according to Lenz's law. In our work, we are considering in controlling the magnetic flux distribution through an air-gap during the energy transfer from the source to load. This research has put a core situation in investigating the possible ways of charging the batteries via mutual induction as in transformers. This enables the charging process to he cableless. It involves two coils transferring energy from one to the other through air in the most cffrcient way. Our work is presented in this paper. Simulation and hardware implementation has been carried out successfully. We have measured the magnetic flux density for ac input voltage of 100 Volt with different frequency values. The optimum frequency in our design is 25 Hz. We found that it is possible to control the magnetic flux distribution during energy transmission by optimizing the frequency and shielding the flux path.