UniMAP RIS :: Browsing UniMAP Conference and Proceedings by Issue Date

Publication

The study of dynamically active washing process of a washing machine

(Universiti Malaysia Perlis (UniMAP), 2008-03-08)

Heap, Yee Nean

;

Ryspek, Usubamatov

;

Mohd Zaki Ab Muin

In area of washing machines and clothes washing technology industry, there are many features of clothes washing machines. All these available machines have two main washing technology configurations which can be presented by top loading and front loading. These washing technology involve a washing drum which filled with washing liquid contain detergent and the submerged dirty clothes are cleaned with rotary motion of an actuator or rotating drum. In the washing process, clothes mixed up with detergent solution and the rotary washing action given by actuator or rotating drum help to dissolve grease and carry away dirt into washing liquid. The rotary actuator with ribs rotate clothes with washing liquid added into vertical dram during washing process. These known washing machines are deficient relatively. It is because the passive washing process takes place efficiently only after some period of time. Proposed a new washing technology where it introduces active process in washing action. This washing technology will produce better outcome result in term of improved quality of washing process.

Publication

Power flow tracing via modified proportional tree method

(Universiti Malaysia Perlis (UniMAP), 2008-03-08)

Mohd Herwan Sulaiman

;

Mohd Wazir Mustafa

;

Omar Aliman

Tracing the flow of electricity becomes an important issue under deregulation system. It is more complicated compared to other fields due to norlinear nature of power flow and specific properties of electricity. Since the complexity of electricty transmission system, it is not straight forward to map out the contribution of particular generator to a particular line or loud. Thus there are several algorithms proposed to trace the power flow and loss through literatures. This paper will discuss the power flow and loss allocation using Modified Proportional Tree M-Lhod (MPTM). The method is based on Proportional Tree Method (PTM) and proportion sharing principle. After power flow solution is obtained, the test system is modeled like a tree, where the power flow tracing is started from a particular generator to a particular line or load through the routes that connected between them. It is also possible to appoint the losses at each transmission line to which generators. 4-bus and IEEE 14-bus test systems were used to illustrate the effectiveness of the method. Comparison with other method is also given.

Publication

An analysis on power quality measurement and monitoring techniques for nonlinear load

(Universiti Malaysia Perlis (UniMAP), 2008-03-15)

Shahrul Ashikin Azmi

;

Mohd Rafi Adzman

;

Mohd Fayzul Mohammed

;

Siti Rafidah Abdul Rahim

;

Zainuddin Mat Isa

;

Ismail Daut

Electric power quality is an aspect of power engineering that has been with us since the inception of power systems. The measurement of the quality of the electric power in a network is therefore becoming an urging need especially in a deregulated electricity market. In the paper, the types of power quality variation are described and the method of characterizing each type with measurements are presented. By using the advances of power quality monitoring equipment and tools, analysis on power quality measurement result are described. The increased amount af data being collected requires more advanced analysis tools. power quality monitoring has advanced from strictly problem solving to ongoing monitoring of system performance.

Publication

A study on voltage sag in industry system with adjustable speed drive

(Universiti Malaysia Perlis (UniMAP), 2008-03-15)

Syahrul Ashikin Azmi

;

Mohd Fayzul Mohammed

;

Siti Rafidah Abdul Rahim

;

Mohd Rafi Adzman

;

Zainuddin Mat Isa

;

Ismail Daut

The awareness of electric power quality has increased over the past decade as electronic equipment has become more susceptible to power disturbances. The most distruptive power disturbances is voltage sags. Voltage sags produce an important effect on the behavior of adjustable speed drives (ASD's). Tripping of ASD is one of the greatest voltage sag problem, causing motor to stop with the resulting loss of time and production, or damaged equipment may cause significant economical loses. This paper is focused on the effect of voltage sags on adjustable speed drive (ASD) which commonly used in industry system. Voltage sags are normally used described by magnitude variation and unbalanced (asymmetry). These factors are important to determine the behavior of ac motor drive during sags. A VSI (Voltage Source Inverter) driving a three-phase induction motor is analyzed through digital simulation. Simulation on sag depth and three types of voltage sags which are based on voltage sag classification, with an emphasis on the changes dc bridge voltage, rms inverter voltage and motor speed were done. Thus, voltages and speed measurement are obtained. Simulation result clearly show that the different types of sags and sag depth would cause dc-link voltage variation and finally result in motor speed changes.

Publication

A study on communication method between two humans during cooperative task

(Universiti Malaysia Perlis (UniMAP), 2009-09-11)

Shahriman Abu Bakar

;

Ryojun, Ikeura

;

Ahmad Faizal Salleh

;

Takemi, Yuno

At present the majority of autonomous robots are mostly used in factories where speed and accuracy are given highest priority. In our research, we are focusing in the area where the robot that cooperate with human to lift or carry a human subject. In this area the robots are required to interact with human and move in such a fashion where it will move with human-like motion so that the human subject that is being move will not feel intimidated. In order to design robot that have smooth human like motion capability during human robot interaction in cooperative task, we need to understand how human-human understand each other, how and what kind of information are exchange between them that enable human-human to be able to accomplish to move object with smooth qualities. Based on this, we need to design a system that is available to be used not only by robotic experts but by general population so that anybody can use this system for their care giving purpose. In this paper we conduct a study of how human-human utilize their sense in moviug and stopping an object and we analyzed the smoothness of the motion by analyzing the hand jerk characteristic during the said task.

Publication

Modified energy based time-frequency features for classifying human emotions using EEG

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

M. Murugappan

;

R.Nagarajan

;

Sazali Yaacob

In this paper we summarize the emotion recognition from the electroencephalogram (EEG) signals. The combination of surface Laplacian filtering, time-frequency analysis (Wavelet Transform) and linear classifiers are used to detect the discrete emotions (happy, surprise, fear, disgust, and neutral) of human through EEG signals. EEG signals are collected from 20 subjects through 62 active electrodes, which are placed over the entire scalp based on International 10-10 system. All the signals are collected without much discomfort to the subjects, and can reflect the influence of emotion on the autonomic nervous system. An audio-visual (video clips) induction based protocol has been designed for evoking the discrete emotions. The raw EEG signals are preprocessed through Surface Laplacian filtering method and decomposed into five different EEG frequency bands using Wavelet Transform (WT). In our work, we used “db4” wavelet function for extracting the statistical features for classifying the emotions. A new statistical features based on frequency band energy and it’s modified from are discussed for achieving the maximum classification rate. The validation of statistical features is performed using 5 fold cross validation. In this work, KNN outperforms LDA by offering a maximum average classification rate of 78.4783 % on 62 channels and 73.6087% on 24 channels respectively. Finally we present the average classification accuracy and individual classification accuracy of two different classifiers for justifying the performance of our emotion recognition system.

Publication

Development and application of an enhanced ART-Based neural network

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Keem Siah Yap

;

Chee Peng Lim

;

Eric W.M Lee

;

Junita Mohamed Saleh

The Generalized Adaptive Resonance Theory (GART) neural network is developed based on an integration of Gaussian ARTMAP and the Generalized Regression Neural Network. As in our previous work [13], GART is capable of online learning and is effective in tackling both classification and regression tasks. In this paper, we further propose an Ordered–Enhanced GART (EGART) network with pruning and rule extraction capabilities. The new network, known as O–EGART–PR, is equipped with an ordering algorithm that determines the sequences of training samples, a Laplacian function, a new vigilance function, a new match-tracking mechanism, and a rule extraction procedure. The applicability of O–EGART–PR to pattern classification and rule extraction problems is evaluated with a problem in fire dynamics, i.e., to predict the occurrences of flashover in a compartment fire. The outcomes demonstrate that O–EGART–PR outperforms other networks and produces meaningful rules from data samples.

Publication

Wireless cameras network for intelligent traffic surveillance system

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Zainab Nazar Khalil Wafi

;

R Badlishah Ahmad

;

Paulraj M P

Wireless Networks (WNs) have attracted wide interests in both academic and industrial communities due to their diversity of applications. In this paper a Wireless Camera Network (WCN) which utilizes advanced embedded system & wireless network (WNs) protocol for networks used to improve motorways safety from abnormal situations. The system consist of numbers of embedded smart cameras connected via wi-fi and are deployed along a motorway and connected via wireless network (wi-fi) to be an eye for operators. The system will capture and interpret images (which may cause danger to motorway users) and an alarm system will be triggered to inform motorway operators for immediate actions. Various algorithms for image processing and object recognition will be implemented for image interpretations. At the same time, images from network smart cameras will be sent for storage to a server for record purposes.

Publication

Motorbike engine faults diagnosing system using entropy and functional link neural network in wavelet domain

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Paulraj M P

;

Sazali Yaacob

;

Mohd Zubir Md Zin

The sound of working vehicle provides an important clue for engine faults diagnosis. Endless efforts have been put into the research of fault diagnosis based on sound. It offers concrete economic benefits, which can lead to high system reliability and save maintenance cost. A number of diagnostic systems for vehicle repair have been developing in recent years. Artificial Neural Network is a very demanding application and popularly implemented in many industries including condition monitoring via fault diagnosis. This paper presents a feature extraction algorithm using total entropy of 5 level decomposition of wavelet transform. The engine noise signal is decomposed into 5 levels (A5, D5, A4, D4, A3, D3, A2, D2, A1, D1) using Daubechies “db4” wavelet family. From the decomposed signals, the entropy is applied for each levels and the feature are extracted and used to develop a functional link neural network.

Publication

A study of infrastructure for real-time location system

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Hazry Desa

;

Mohd Sofian Mohammad Rosbi

;

Mohd Zahiruddin Md. Zain

This paper proposed the infrastructure for real-time location system (RTLS). RTLS determine and track the location of assets and person using active tags which contain a battery and can transmit signals autonomously to a reader. Two or more readers can estimate the tag’s range from each reader and determine its location. The data will be send to the data location engine before displayed in the geographical interface server(GIS) which includes mapping software and its application with remote sensing.

Publication

Speaker verification based on speech signal

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Shariffah Fauziah Jap

;

Ali Chekima

;

Mazlina Mamat

;

Wan Mahani Abdullah

This paper presents the initial effort to perform speaker verification by utilizing the speech signal characteristics found in individual’s voice to recognize its speaker. A total of six speakers from different backgrounds were selected as sample and each of them is required to pronounces numbers zero to nine for 5 times. The recorded speech signal then undergoes a series of speech processing, which contains Pre-emphasis, Framing, Windowing and Endpoint Detection. To obtain the features of each speech signal, the Linear Prediction Coefficients (LPC) technique is used. The collection of LPC coefficients then were feed to the Multilayer Perceptron Neural Network trained by Back Propagation algorithm, which acts as a pattern matching algorithm. The results show that the speech signal has the potential to be used to verify its speaker in high accuracy.

Publication

DES enabled fingerprint system

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Gobinath Subramaniam

;

Kalyani Subramanian

;

Senthil Raja Balakrishnan

;

Baskaran Kaliaperumal

Biometrics systems function to identify individuals by matching a specific personal characteristic, the biometrics identifier, with one previously recorded. Biometric identification considers individual physiological characteristics and/or typical behavioural patterns of a person to validate their authenticity. Fingerprints are used to generate the key; this key value is used in the Data Encryption Standard (DES) algorithm. Initially the finger print image is converted into a pixel matrix. After the matrix conversion the matrix is applied into the one way hash function. The hash code value is a 64 bit string value. This hash code value is passed into the DES algorithm as key for the encoding and decoding process. This 64-bit key value is converted as a 56 bit key value by the DES algorithm computational operations. The system also performs an authentication checking process in the decryption process to verify the correctness of the key value. Fingerprint Selection contains receiving finger print data and conversion of finger print values into matrix tasks. This accepts the finger print data as an image file. Key Generation generates the key for the security system. Using the selected finger print image data generates the key value. Encryption performs the document encoding task. The user can select any file for the encryption process. Decryption process is performed to retrieve the original document from the encoded document. Biometrics offers new perspectives in high-security applications while supporting natural, user-friendly and fast authentication.

Publication

An innovative approach for energy conservation in induction motor

(Universiti Malaysia Perlis, 2009-10-11)

V. Chandrasekaran

;

T. Manigandan

Three phase Induction motors are mainly employed in Textile mills, Agriculture and almost in all the machine tools. About 65% to 70 % of electrical energy generated is being utilized by three phase induction motors because of their robust construction and easy operation. Hence, a small improvement in the design of induction motor for energy conservation and increased efficiency is cost effective. Conventional induction motor consists of a three phase distributed winding in the stator and short circuited squirrel cage rotor. Generally, to have standard dimensions, induction motors are designed for standard output ratings. To have factor of safety, the ratings of the motor are generally chosen on higher side. Due to said reasons over rated motors are normally used. To improve the efficiency of the motor operation and to have sufficient energy conservation, a novel design and operation of Double Winding Induction Motor (DWIM) is suggested in this paper. This motor consists of two windings on the same stator core and conventional squirrel cage rotor. Out of two stator windings, one winding is used to meet the mechanical load. A three phase EMF is developed in other winding, works as an induction alternator. Both mechanical and electrical loading can be controlled by a PIC Microcontroller for its maximum efficiency and power balancing modes of operation.

Publication

Early diagnosis of Ischemia stroke using neural network

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Anita Thakur

;

Surekha Bhanot

;

S. N. Mishra

Technological and computing evolution promoted new opportunities to improve the quality of life, in particular, the quality of early detection of acute disease. Many intelligent systems have been developed with the purpose of enhancing health-care and providing better health care facilities at reduced cost. Artificial Intelligent techniques are indeed worth exploring and integrating in the medical system for diagnosis, prediction and prescription. The aim of this paper is to determine a noninvasive method that the general population can easily use to detect whether a patient has cerebral ischemia stroke. The problem addressed in this paper is prediction of possibility of cerebral ischemia and it is estimated from symptoms and risk factors given by the patients. Exactly early prognosis of cerebral ischemia stroke has practical importance in medicine. A feed forward neural network with back propagation was used for decision of cerebral ischemia stroke prediction. Developed Neural network model with appropriate training provides an accuracy of 99.99%.

Publication

Offense/defense decision-making controller for a billiard robot

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Jr-Syu Yang

;

Chan-Yun Yang

;

Chia-Hsiao Liu

The objective of this research is to develop a defense/offense decision-making controller for a billiard robot by using Fuzzy and Extension theory. The main purpose is to make the billiard robot possess the imitation ability of how human beings do the defense/offense decision-making in a block ball game. The offense cushion shot means to pocket the object ball. After hitting the table rail, the defense strategy is developed by four conditions which are the distance between the cue ball and the object ball, distance between the object ball and the corresponding pocket, the angles between the cue ball, the object ball and the corresponding pocket, and the information of the block ball. In addition to the four parameters, it must be considered whether the cue ball or the object ball contacts the rail of the table after the cue ball strikes the object ball. Finally, the billiard robot will execute the hitting command to let the cue ball strike the object ball and make an offense or defense shot in the experiments.

Publication

An efficient variant signature scheme on ECDSA

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

M. Prabu

;

R. Shanmugalakshmi

This paper describes a new variant level of Signature Scheme on ECDSA. In support of this scheme, a study of on a number of schemes was done. The number of scheme includes Lamport, Schnorr, DSA etc., In this study three schemes, DSA, ECDSA and Variant ECDSA are taken for a comparative study. From that comparison, the paper tries to develop a new scheme on ECDSA. Finally, It was found out that, Variant signature on ECDSA is better than other schemes. We give a brief preamble to the Signature Algorithm in chapter 1 and then give the Concepts of the Elliptic Curve version of DSA. Finally a Variant of ECDSA will be given in chapter 9.

Publication

Development of Man-Machine Interface using Matlab: an adaptive network-based fuzzy inference system modeling for laser machining

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

Sivarao

;

Rizal, M.S.

;

Tajul, A.

;

Taufik

Development of GUI on MATLAB environment is rarely carried out by researchers especially for controlling complex and non-linear machining processes. Hence, it becomes more complicated and time consuming for one to explore artificial intelligent tools to model a process using MATLAB due to unfamiliarity and phobia of programming. In this paper, how GUI is developed and integrated to model laser machining process using Adaptive Network-based Fuzzy Inference System (ANFIS) together with GUI’s ability in generating the model output is presented. Laser cutting machine is widely known for having the most number of controllable parameters among the advanced machine tools and it becomes more difficult for the process to be engineered into desired responses such as surface roughness and kerf width to achieve precision machining conditions. Knowing both laser processing and ANFIS programming are difficult and being fear of modelers, a novel GUI is developed and used as an interface to model laser processing using ANFIS with various setting capabilities where, numeric and graphical output can be printed. On the other hand, the GUI can also be used to predict the responses to conduct comparative analysis. To validate the accuracy of the ANFIS modeling, the error is calculated through Root Mean Square Error (RMSE) and Average Percentage Error. The RMSE values are compared with various type of trained variables and settings on ANFIS platform, so that the best ANFIS model can be finalized before prediction. The developed GUI can be used in industry of laser machining for an operator to optimize the best machine setting before the machine is operated. Thus, the industry could reduce the production cost and down time by off-hand setting as compared to the traditional way of trial and error method.

Publication

Multi-criteria fuzzy regression model for evaluating oil palm grading

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

A. Nureize

;

J. Watada

Measurement of quality is an important task in the evaluation of agricultural products. A higher quality of raw input material produces a higher quantity and quality of end products. Therefore, in the palm oil production, the quality inspection process of fruits needs to be conducted properly to ensure that high-quality fruit bunches are selected. Additionally, human subjective judgments during the evaluation make the fruit grading inexact. Thus, the objectives of this paper is to build a fuzzy multi-criteria evaluation model that characterises the criteria of oil palm fruits to decide the fuzzy weights of these criteria based on a fuzzy regression model. A numerical example is included to illustrate the computational process of the proposed model.

Publication

Sports video analysis for player strength and weakness psychiatry in the context of object-relational data bases

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

UmaMaheswari

;

M. Rajaram

;

S. N. Sivanandam

The advent of video coverage of sports has provided an impetus to develop models for tactics analysis for providing training assistance by summarizing the play tactics from video streams. Though there are plenty of sports data and statistics available, there has been no real effort to scientifically extract value from such data. The rapid growth in size of the match database far exceeds the human abilities to analyze such data, thus creating an opportunity for using data mining on this database. The aim of this work is to mine sports video annotation data to extract knowledge about match play sequences and applying that knowledge for classification of players for developing player specific training taxonomy. The major objective of this paper is to analyze individual player’s performances and to devise a classification technique so as to classify them into appropriate groups using the frequently played patterns and other performance indices like strike rate, six-runs and fourruns. This classification helps the coaches to know the current form of the player and to understand their strengths and weaknesses. With this information, a coach can assess the effectiveness of certain coaching decisions and formulate game strategy for subsequent games. To achieve the objective of this work, video stream of cricket matches were observed manually and ball shot descriptions were taken as annotation and stored into an object-relational data model. Frequently occurring patterns were identified, then further evaluation was carried out on those patterns to group them into different clusters based ontheir influence in producing success and failure. Classification mechanism is applied to analyze each and every individual player’s strengths and weaknesses to fix them into a respective class of training taxonomy.

Publication

Colour image enhancement using bright and dark stretching techniques for tissue based Tuberculosis Bacilli detection

(Universiti Malaysia Perlis (UniMAP), 2009-10-11)

M. Kushairi Osman

;

Mohd Yusoff Mashor

;

Hasnan Jaafar

Tuberculosis is a serious disease caused by infection with the germ Mycobacterium tuberculosis. Sputum sample analysis is a common method for TB bacilli detection. In some cases, tissue from the suspected system is also obtained using bronchoscope or fine needle aspiration for diagnosis. The Ziehl- Neelsen stain or acid-fast stain is a special stain used to identify the TB bacilli. The preparation of Ziehl-Neelsen slides require several procedures and the slide should be analysed under microscope. There are some factors that may degrade the image quality such as exposure and staining problems. Therefore, image enhancements are necessary to produce fine images in term of contrast and intensity. This paper proposes two methods for colour image enhancement; bright stretching and dark stretching algorithms. Both methods are well known to produce good image enhancement for gray scale images. However, the current study has adapted these methods to be used for colour images. Although the adapted image processing technique is quite simple, the results indicate that these methods may have some potential to be used for improving the quality of Ziehl-Neelsen slide images. The results show that both techniques were successfully improved the image contrast and enhance the image quality.

UniMAP Conference and Proceedings

Permanent URI for this collection

Browse

Browse

Browsing UniMAP Conference and Proceedings by Issue Date

Results Per Page

Sort Options