Universiti Teknikal Malaysia Melaka: UTeM Open Journal System
Not a member yet
2735 research outputs found
Sort by
Illumination-Invariant Image Matching Based on Simulated Kalman Filter (SKF) Algorithm
No full textIn this paper, a novel image template matching approach to tackle illumination-invariant problem has been proposed. The traditional algorithm to solve image matching problem takes a lot of memory and computational time. Therefore, the image matching problem is assigned to optimization problem and can be solved precisely. Although there are some methods presented recently for image matching illumination-invariant, all of them have limitations in term of dealing with the pixels complexity and many unknown parameters in a certain algorithm. The search of the image template has been performed exhaustively by using Simulated Kalman Filter (SKF) algorithm. The experiment is conducted using an image taken from the database and the contrast image is changed to get the illumination effect. Experimental results show the comparison between SKF and Particle Swarm Optimization (PSO) to get the performance of the correct matching. The percentage of the matching result for the image within six conditions are 24%, 16%, 16%, 12%, 28% and 4% accordingly, which are higher than the PSO algorithm, which obtained 0% correct matching for all conditions
Analysis of Colour Constancy Algorithms for Improving Segmentation of Malaria Images
No full textMalaria is a very serious disease that caused by the transmitted of parasites through the bites of infected Anopheles mosquito. Malaria death cases can be reduced and prevented through early diagnosis and prompt treatment. Currently, microscopy-based diagnosis remains the most widely used approach for malaria diagnosis. The appearance of the infected red blood cells (RBCs) and their morphological features are very important for recognising the presence of malaria parasites. However, it is difficult to identify the presence of malaria parasites as well as observing its morphological characteristics due to the non-standard preparation of the blood slides; producing colour varieties in different slides. Thus, this study aims to apply colour constancy algorithms for standardisation of blood images in order to enhance segmentation of malaria parasites. In this paper, four different colour constancy algorithms namely Gray-World, white patch, modified white patch and progressive algorithms have been analysed to identify colour constancy algorithm that can give the significant segmentation performance. The experimental results show that segmentation on Gray-World images has successfully segmented 100 malaria images with average segmentation accuracy, sensitivity and specificity of 99.60%, 91.26% and 99.85%, respectively
Computing a Perceptual Map Using a Stereo-Vision Mobile Robot
No full textA new computational model of how humans integrate successive “local environments” obtained as views at limiting points in the environment to create a perceptual map has been proposed and validated using a laser-ranging mobile robot. Compared with the SLAM (Simultaneous Localization and Mapping)-based approach, the proposed process is less computationally demanding and provides an interesting account of how humans compute their cognitive maps. Since vision plays an important role in how humans compute their maps, we extend the previous work by implementing the model using a vision-based mobile robot. Specifically, our model takes a prerecorded series of stereo-vision images of a large indoor environment at USM and produces a perceptual map. The results show that the model is not dependent on the use of a laser-ranging device and this is significant if the model is intended as a cognitive model of spatial cognition
A Simplified Method to Synthesize UWB Compact Bandpass Filter with Dual Notch Bands
No full textThis paper presents a simplified method to synthesize a new and compact UWB bandpass filter with good selectivity, wide bandwidth and two notched frequencies at 5.2GHz and 7.8GHz. UWB bandpass is created by cascading highpass and lowpass filters. The proposed work uses network synthesis techniques to design highpass and lowpass filters with Chebyshev transfer function using insertion loss method. The optimized low pass and high pass circuits are implemented with the help of hairpin line and interdigital structure (IDS), respectively. The open ended stub and spurline are loaded on the outermost fingers of IDS to create notches at 5.2GHz and 7.8GHZ frequencies, respectively. The size of the filter is highly miniaturized and compact in shape when compared with the other existing structures. The insertion loss in the pass band of the filter is smaller than 0.4dB and stop band is wide. Filter is fabricated on FR4 with dielectric constant 4.4 and thickness of 1.6mm
A Study of Electrical Resistance Tomography on Inhomogeneous System
No full textThis study is conducted to investigate inhomogeneous in Electrical Resistance Tomography system using COMSOL Multiphysics finite element software. An inhomogeneous system is represented with the concrete-steel medium. Three type of cases which are varies the dimension of steel, varies a number of steel phantom in concrete, and different location of steel in concrete are the subject in this study. Each case uses results from adjacent and opposite current driven method for comparison. As a result, extension in steel dimension could benefit the ERT system to obtain a good measurement. Also, as a number of steel placed in concrete medium increases, the potential difference will drop when compared with homogenous. It is demonstrated that as a phantom is placed close to the source or measuring electrode area, it could show changes in potential difference reading. In conjunction with that, that area indirectly becomes more sensitive and feedback
Development and Comparison between Charge Pump Circuit and LTC 3108 Circuit for Thermal Energy Harvester
No full textPower conditioning circuit is a very important role for any energy harvester. Therefore, choosing a suitable power conditioning circuit is an important process also. In this paper, two power conditioning circuits which are Charge pump circuit and LTC 3108 circuit are designed and compared. At the same time, the TEG is used as input energy for the circuits. From the input of TEG which is 1.18V, Charge pump need 6 minutes to boost the circuit to 4.06V. However, the LTC 3108 circuit only need 10 seconds to boost up the voltage to 4.92V. Then, decade resistance box is connected to the circuits. Regarding the power output, the power output of both circuits is about the same. However, the matching load of the LTC 3108 circuit is 20kΩ but the matching load for the Charge pump is 50Ω only
EFFECT OF DEGUSSA P25 CONTENT ON THE DEPOSITION OF TiO2 COATING ON CERAMIC SUBSTRATE
No full textTiO2 coatings were deposited on unglazed ceramic tiles to study the property of its antimicrobial activity. Here, the effect of TiO2 nanoparticles content (Degussa P25) on the TiO2 coatings’ characteristics was investigated. TiO2 sol containing 25, 50, and 100 g/L Degussa P25 were deposited few times on ceramic tiles via sol-gel dip coating method and heat treated at 500°C. The coatings were analyzed using SEM and the phases were characterized using GAXRD. The results show that Degussa P25 content significantly influences the TiO2 coatings morphology and thickness. Increasing the Degussa P25 content led to a thicker and denser coating with different Degussa P25 content yielded different thickness at specific dipping time. 50 g/L of Degussa P25 was discovered as the maximum amount to be used for achieving good adherence coating on the ceramic tiles. Five dipping of TiO2 sol containing 50 g/L Degussa P25 was found appropriate to generate coating of continuous layer with average thickness of ~29 µm. The Degussa P25 content, however, shows insignificant effect on coating crystallinity
Joining of Thin Plates Using Various Arc Welding Heat Sources – A Review
No full textAdvancements and improvements in welding processes are mostly to expand profitability without losing the nature of the weldment. In order to protect the quality and the cost, using light material has become an interest among industries. One of the purpose of the developments in thin plate welding technology is to minimize the cost and the weight. The main objective of the current study to investigates the current status of thin plates joining using arc welding as the heat sources for common method variance in research and assists researchers in taking appropriate actions. Welding distortion resulted from residual stress and it can cause problems in terms of dimensional tolerance and manufacturing integrity in the assembled structure. In this paper, methods for thin plate welding process were reviewed and it was evident that numerical modeling and experimental has been employed on evaluation of welding parameters and its effect to the weld performance and characteristic. This paper also aims at outlining the recent findings from similar and dissimilar material, laser welding, TIG and MIG welding in regards to the thin plate welding. The most significant findings emerged from this study is that output responses related to heat source, deformation of welded joint, thermal and physical properties. Some recommendations and future research methods are also proposed
Facial Emotion Recognition Based on Empirical Mode Decomposition and Discrete Wavelet Transform Analysis
Get PDFThis paper presents a new framework of using empirical mode decomposition (EMD) and discrete wavelet transform (DWT) with an application for facial emotion recognition. EMD is a multi-resolution technique used to decompose any complicated signal into a small set of intrinsic mode functions (IMFs) based on sifting process. In this framework, the EMD was applied on facial images to extract the informative features by decomposing the image into a set of IMFs and residue. The selected IMFs was then subjected to DWT in which it decomposes the instantaneous frequency of the IMFs into four sub band. The approximate coefficients (cA1) at first level decomposition are extracted and used as significant features to recognize the facial emotion. Since there are a large number of coefficients, hence the principal component analysis (PCA) is applied to the extracted features. The k-nearest neighbor classifier is adopted as a classifier to classify seven facial emotions (anger, disgust, fear, happiness, neutral, sadness and surprise). To evaluate the effectiveness of the proposed method, the JAFFE database has been employed. Based on the results obtained, the proposed method demonstrates the recognition rate of 80.28%, thus it is converging
N170 Wave Amplitude Analysis on Driving Performance on Highway Road
Get PDFAttention in the physiological definition is taking possession of the mind in one of several simultaneously events of thoughts which implies withdrawing some things to deal effectively with other. In driving particularly, attention is essential to keep track of the driver’s vigilance to avoid the road accident. In this paper, analysis of the driver’s attention is done through their driving performance from both of Electroencephalographic (EEG) amplitude and accident score. During the driving experiment, two stimulations will be given to the subjects which are silent environment (in certain dB) and listening to the live streaming radio. The results show that when listening to the radio, the driving performance is improved and the score of the accident is reduced as well. This figure gave a concrete justification that driver’s attention able to maintain or even increase when the stimulation is triggered