Hasmah Mansor
International Islamic University Malaysia

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search
Journal : Indonesian Journal of Electrical Engineering and Computer Science

Design of travel angle control of quanser bench-top helicopter using mamdani-based fuzzy logic controller Hasmah Mansor; Mohamad K. Azmi Mat Esa; Teddy Surya Gunawan; Zuriati Janin
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 2: February 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v17.i2.pp815-825

Abstract

This research focuses on travel angle control of a laboratory scale bench-top helicopter developed by Quanser Inc.  Bench top-helicopter is usually used by engineers and researchers to test their designed controllers before applying to the actual helicopter. Bench-top helicopter has the same behavior as the real helicopter, with 3 degree of freedom.  The bench-top helicopter is mounted on a flat surface with two rotors that depends on the voltage supplied to change the direction of the helicopter in 3 different angles. The movement of the helicopter is based on the direction of three-different angles; travel, pitch and yaw angles. The existing Linear Quadratic Regulator-Integral controller used by Quanser Inc has some limitations in terms of tracking capability and settling time; therefore this research is proposed. The objective of this research is to develop Mamdani-based Fuzzy Logic Controller for travel angle control of bench-top helicopter. Performance comparison has been done with the existing Linear Quadratic Regulator-Integral controller in both simulation and hardware. From the test results, it was found that the performance of Fuzzy Logic Controller is better than LQR-I controller especially for closed-loop simulation at desired angle of 30°. The percentage of overshoot of the Fuzzy Logic Controller has been improved from the existing controller which is 4.912% compared to 7.002% for LQR-I.
Development of Approximate Prediction Model for 3-DOF Helicopter and Benchmarking with Existing Controllers Farhat Anwar; Rounakul Islam Boby; Hasmah Mansor; Sabahat Hussain; Afsah Sharmin
Indonesian Journal of Electrical Engineering and Computer Science Vol 8, No 2: November 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v8.i2.pp502-510

Abstract

Recent trend of living is getting modernized rapidly by the involvement of automatic systems. Within the aviation industry, automatic systems had become heavily reliable by the end of the nineteen centuries. The systems usually require controllable devices with desired control algorithm known as controller. Controllers can be replaced with, almost every mechanical automation aspect where, safety is a serious issue. But it is not easy to adapt a controller with a specific model at the beginning. It is important to predict the model before a controller works on the model and the controller parameters need to be adapted to get maximum efficiency. A 3-DOF (Three Degrees of Freedom) airframe model is an advanced benchmark model of real 3-DOF helicopter. It has the same uncommon model dynamics with nonlinearities, strong duel motor cross coupling system, uncertain characteristics, disturbances dependent, unmodeled dynamics and many more. The 3-DOF airframe model is a well-known platform for controller performance benchmarking. This research paper shows the development of an approximate prediction model of a Three Degrees of Freedom helicopter model and uses the proposed approximate model to observe the performance of an existent hybrid controller. The hybrid controller is the combination of two different controllers named Quantitative Feedback Theory (QFT) controller and Adaptive controller. To achieve the research objective, the proposed mathematical model of this airframe was used to develop transfer function and simulate with the hybrid controller in MATLAB. The performance of the controller based on the proposed heliframe model of 3-DOF helicopter have also been reported added within this paper.
Neural Network Prediction for Efficient Waste Management in Malaysia Siti Hajar Yusoff; Ummi Nur Kamilah Abdullah Din; Hasmah Mansor; Nur Shahida Midi; Syasya Azra Zaini
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 2: November 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i2.pp738-747

Abstract

Maintaining current municipal solid waste management (MSWM) for the next ten years would not be efficient anymore as it has brought many environmental issues such as air pollution. This project has proposed Artificial Neural Network (ANN) based prediction algorithm that can forecast Solid Waste Generation (SWG) based on population growth factor. This study uses Malaysian population as sample size and the data for weight is acquired via authorized Malaysia statistics’ websites. All data will be normalized in the pre-processing stage before proceeding to the prediction using Visual Gene Developer. This project evaluated the performance using R2 value. Two hidden layers with ten and five nodes were used respectively. The result portrayed that there will be an increase of 29.03 percent of SWG in year 2031 compared to 2012. The limitation to this study is that the data was not based on real time as it was restricted by the government.
Design of Smart Waste Bin and Prediction Algorithm for Waste Management in Household Area Siti Hajar Yusoff; Ummi Nur Kamilah Abdullah Din; Hasmah Mansor; Nur Shahida Midi; Syasya Azra Zaini
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 2: November 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i2.pp748-758

Abstract

Maintaining current municipal solid waste management (MSWM) for the next ten years would not be efficient anymore as it has brought many environmental issues such as air pollution. This project has proposed Artificial Neural Network (ANN) based prediction algorithm that can forecast Solid Waste Generation (SWG) based on household size factor. Kulliyyah of Engineering (KOE) in International Islamic University Malaysia (IIUM) has been chosen as the sample size for household size factor. A smart waste bin has been developed that can measure the weight, detect the emptiness level of the waste bin, stores information and have direct communication between waste bin and collector crews. This study uses the information obtained from the smart waste bin for the waste weight while the sample size of KOE has been obtained through KOE’s department. All data will be normalized in the pre-processing stage before proceeding to the prediction using Visual Gene Developer. This project evaluated the performance using R2 value. Two hidden layers with five and ten nodes were used respectively. The result portrayed that the average rate of increment of waste weight is 2.05 percent from week one until week twenty. The limitation to this study is that the amount of smart waste bin should be replicated more so that all data for waste weight is directly collected from the smart waste bin.
Development of Quran Reciter Identification System Using MFCC and Neural Network Tayseer Mohammed Hasan Asda; Teddy Surya Gunawan; Mira Kartiwi; Hasmah Mansor
Indonesian Journal of Electrical Engineering and Computer Science Vol 1, No 1: January 2016
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v1.i1.pp168-175

Abstract

Currently, the Quran is recited by so many reciters with different ways and voices.  Some people like to listen to this reciter and others like to listen to other reciters. Sometimes we hear a very nice recitation of al-Quran and want to know who the reciter is. Therefore, this paper is about  the development of Quran reciter recognition and identification system based on Mel Frequency Cepstral Coefficient (MFCC) feature extraction and artificial neural network (ANN). From every speech, characteristics from the utterances will be extracted through neural network model. In this paper a database of five Quran reciters is created and used in training and testing. The feature vector will be fed into Neural Network back propagation learning algorithm for training and identification processes of different speakers. Consequently,  91.2%  of the successful match between targets and input occurred with certain number of hidden layers  which shows how efficient are Mel Frequency Cepstral Coefficient (MFCC) feature extraction  and artificial neural network (ANN) in identifying the reciter voice perfectly.
Robust Control of Bench-top Helicopter Using Quantitative Feedback Theory Ameerul Hakeem Mohd Hairon; Hasmah Mansor; Teddy Surya Gunawan; Sheroz Khan
Indonesian Journal of Electrical Engineering and Computer Science Vol 14, No 3: June 2015
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

A three degree of freedom (3-DOF) bench-top helicopter is a simplified aerial vehicle which is used to study the behaviors of the helicopter as well as testing multiple flight control approaches for their efficiency. Designing helicopter’s dynamic control is a challenging task due to the presence of high uncertainties and non-linear behavior. In this study, Quantitative Feedback Theory (QFT) is proposed to achieve robust control over the helicopter model. It utilizes frequency domain methodology which ensures plant’s stability by considering the feedback of the system and thus removing the effect of disturbances and reducing sensitivity of parameter’s variation. The proposed technique is tested against LQR-tuned PID controller to demonstrate its procedures as well as its performance. Simulation results obtained through MATLAB Simulink software shown us that QFT algorithm managed to reduce percentage of overshoot and settling time about 50% and 30% respectively over the classical PID controller. DOI: http://dx.doi.org/10.11591/telkomnika.v14i3.7899
Safety and security solution for school bus through RFID and GSM technologies Hasmah Mansor; Tun Mohamad Aqil Mohamad Fadzir; Teddy Surya Gunawan; Zuriati Janin
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 2: February 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v17.i2.pp804-814

Abstract

All children throughout the world aged 4 to 17 are going to schools every weekdays. The most common transport used by children is school bus.  In many countries accross the globe, most children uses school bus services to go to school and return back home especially to working parents.  Although safety of their children is always the main concern of all parents especially the young ones, they have to rely on the bus services due to time constraints during working hours. Sometimes parents need to call the bus driver to ensure their children has reached home or school.  This will create inconvenience to bus driver and may lead to other unwanted consequences. Realizing the root of this problem, a school bus safety and security system has been proposed. The school bus safety and security system is a solution based on Short Messaging System that notifies parents if their children have safely arrived at home or school. RFID and GSM technologies are the main technique proposed in this project. RFID is used for several purposes; to identify the children and parents’ contact number, and attendance monitoring through head count system. GSM is used as a commucation platform to inform parents’ on their children’s movement via SMS. Several tests have been conducted to analyse the overall performance of the developed hardware prototype. From the results, it can be concluded that the developed project is successfully identify the children based on their unique ID, send a text message through SMS to parents with required information; and additional feature of attendance checker. The hardware prototype was successfully tested for children’s identification, attendance and SMS notifications to parents. As a consequence, this project could increase the safety and security solution for children travelling with school bus transportation and give parents peace of mind.
Stress Recognition Using Photoplethysmogram Signal Noor Hafizah Azlin Abd Halim; Khairul Azami Sidek; Hasmah Mansor
Indonesian Journal of Electrical Engineering and Computer Science Vol 8, No 2: November 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v8.i2.pp495-501

Abstract

 This study proposed a novel method of stress recognition using photopletysmogram (PPG) signal. PPG devices are now widely used because it is convenient, low powered, cheap and also easy to handle due to its small size. A total of 5 subjects were involved in this study. The PPG signals were taken in resting condition using pulse oximetry. The subject then goes through a stressor test in order to record the physiological changes. The data were collected before and after the test was conducted and later extracted. These samples were then categorised using classification techniques to differentiate between normal and stress condition. Based on the experimentation results, the systolic peak value differences of normal and stress conditions are evident.Therefore, the outcome of this study suggest the reliability of implementing PPG signal for stress recognition.