Norhashimah Mohd Saad

Power quality analysis using spectrogram and gabor transformation

This paper discusses the implementation of time-frequency analysis techniques to analyze power quality disturbances. The approached methods are spectrogram and Gabor transform algorithms. Signal parameters such as time marginal and frequency marginal are extracted from the time-frequency distributions. The parameters are analyzed in terms of correctness measurement of root mean square (RMS), total harmonic distortion (THD), total waveform distortion (TWD) and total interharmonic distortion (TnHD) values. Power quality events that are analyzed are swell, sag, interruption, harmonic, interharmonic, transient, notching and normal voltage. The results show that Gabor transform provides better performance in terms of correctness of parameters measurement, window length, frequency resolution and memory size.

Detection of Heart Blocks in ECG Signals by Spectrum and Time-Frequency Analysis

The electrocardiogram (ECG) is a non-invasive test that records the electrical activity of the heart and is important in the investigation of cardiac abnormalities. Each portion of the ECG waveform carries various types of information for the cardiologists analyzing patients heart condition. ECG interpretation at the present time remains dependent manually in time domain. It is difficult for the cardiologists to make a correct diagnosis of cardiac disorder. A computerized interpretation of ECG is needed in order to make the diagnosis more efficient. This paper discusses the use of digital signal processing approach for the detection of heart blocks in ECG signals. Signal analysis techniques such as the periodogram power spectrum and spectrogram time-frequency analysis are employed to analyze ECG variations. Seven subjects are identified: normal, first degree heart block, second degree heart block type I, second degree heart block type II, Third degree heart block, right bundle branch block and left bundle branch block. Analysis results revealed that normal ECG subject is able to maintain higher peak frequency range (8 Hz), while heart block subjects revealed a significant low peak frequency range (< 4 Hz). The results revealed that the periodogram power spectrum can be used to differentiate between normal and heart block subjects, while the spectogram time-frequency analysis is used to give better characterization of ECG parameters. These analyses can be used to construct ECG monitoring and analyzing system for heart blocks detection.

Automated segmentation of brain lesion based on diffusion-weighted MRI using a split and merge approach

This paper presents a segmentation of brain lesion from diffusion-weighted magnetic resonance images (DW-MRI or DWI) using a split and merge approach. The lesions are hyperintense lesion from tumour, acute infarction, haemorrhage and abscess, and hypointense lesion from chronic infarction and haemorrhage. Pre-processing is applied to the DWI for intensity normalization, background removal and intensity enhancement. Then, the split and merge algorithm is designed to segment the lesion. Histogram thresholding technique is used at each split level to detect pixels with either hyperintense or hypointense. Several statistical features are discussed and evaluated to select the best feature as homogeneity criteria. The analysis shows that mean and number of lesion pixels are the best homogeneity criteria. Hyperintense and hypointense lesions are segmented automatically by merging the regions that are homogenous according to the criteria.

Brain lesion segmentation of Diffusion-weighted MRI using gray level co-occurrence matrix

This paper presents an automated segmentation of brain lesion from Diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on region and boundary information in gray level co-occurrence matrix (GLCM). The lesions are hyperintense lesion from tumour, acute infarction, haemorrhage and abscess, and hypointense lesion from chronic infarction and haemorrhage. Pre-processing is applied to the DWI for intensity normalization, background removal and intensity enhancement. Then, GLCM is computed to segment the lesions. Different peaks from the GLCM cross-section indicate the present of normal brain region, cerebral spinal fluid (CSF), hyperintense or hypointense lesions. Minimum and maximum threshold values are computed from the GLCM cross-section. Region and boundary information from the GLCM are introduced as the statistical features for segmentation of hyperintense and hypointense lesions. The proposed method provides very good segmentation results even in a small brain lesion.

Segmentation of brain lesions in diffusion-weighted MRI using thresholding technique

This paper presents brain lesion segmentation of diffusion-weighted magnetic resonance images (DW-MRI or DWI) based on thresholding technique. The lesions are solid tumour, acute infarction, haemorrhage, and abscess. Preprocessing is applied to the DWI for normalization, background removal and enhancement. Two different techniques which are Gamma-law transformation and contrast stretching are applied for the enhancement. For the image segmentation process, the DWI is divided by 8×8 regions. Then image histogram is calculated at each region to find the maximum number of pixels for each intensity level. The optimal threshold is determined by comparing normal and lesion regions. By using Gamma-law transformation, 0.48 is found as the optimal thresholding value whereas 0.28 for the contrast stretching. The proposed technique has been validated by using area overlap (AO), false positive rate (FPR), and false negative rate (FNR). Thresholding with gamma-law transformation algorithm provides better segmentation results with AO, FPR, FNR (0.68, 0.14, 0.18) compared to contrast stretching (0.62, 0.15, 0.23).

Integration of Fuzzy C-Means with Correlation Template and Active Contour for Brain Lesion Segmentation in Diffusion-Weighted MRI

This study proposed automatic detection and segmentation of brain lesion in diffusion-weighted magnetic resonance images (DWI) based on Fuzzy C-Means (FCM). Due to noises and intensity inhomogeneity, FCM technique fails in producing accurate results. Active contour and correlation template are integrated to overcome this problem. The brain lesions are acute stroke and solid tumor foe hyperintense lesions, and necrosis and chronic stroke for hypointense lesions. The proposed analysis framework has been validated by using Jaccard (AO), Dice, false negative rate (FNR) and false positive rate (FPR). FCM with correlation template provides more accurate results compared with FCM with active contour. The results are 0.547, 0.258, 0.192 and 0.687 for Jaccard, FPR, FNR and Dice indices. This method also can segment the lesions precisely.

A Detail Study of Wavelet Families for EMG Pattern Recognition

Zigbee technology has been developed for short range wireless sensor networks and it follows IEEE 802.15.4 standard. For such sensors, several considerations should be taken including; low data rate and less design complexity in order to achieve efficient performance considering to the transceiver systems. This research focuses on implementing a digital transceiver system for Zigbee sensor based on IEEE 802.15.4 . The system is implemented using offset quadrature phase shift keying (OQPSK) modulation technique with half sine pulse-shaping method. Direct conversion scheme has been used in the design of Zigbee receiver in order to fulfill the requirements mentioned above. System performance is analyzed considering to BER when it encountered adaptive white Gaussian noise (AWGN), besides showing the effect of using direct sequence spread spectrum (DSSS) technique.The inverted pendulum is an under-actuated and nonlinear system, which is also unstable. It is a single-input double-output system, where only one output is directly actuated. This paper investigates a single intelligent control system using an adaptive neuro-fuzzy inference system (ANFIS) to stabilize the inverted pendulum system while tracking the desired position. The non-linear inverted pendulum system was modelled and built using MATLAB Simulink. An adaptive neuro-fuzzy logic controller was implemented and its performance was compared with a Sugeno-fuzzy inference system in both simulation and real experiment. The ANFIS controller could reach its desired new destination in 1.5 s and could stabilize the entire system in 2.2 s in the simulation, while in the experiment it took 1.7 s to reach stability. Results from the simulation and experiment showed that ANFIS had better performance compared to the Sugeno-fuzzy controller as it provided faster and smoother response and much less steady-state error.Association Rule mining plays an important role in the discovery of knowledge and information. Association Rule mining discovers huge number of rules for any dataset for different support and confidence values, among this many of them are redundant, especially in the case of multi-level datasets. Mining non-redundant Association Rules in multi-level dataset is a big concern in field of Data mining. In this paper, we present a definition for redundancy and a concise representation called Reliable Exact basis for representing non-redundant Association Rules from multi-level datasets. The given non-redundant Association Rules are loss less representation for any datasets.This paper presents a novel technique for numeral reading in Indian language speech synthesis systems using the rule-based Concatenative speech synthesis technique. The model uses a set of rules to determine the context of the numeral pronunciation and is being integrated with the waveform concatenation technique to produce speech out of the input text in Indian languages. To analyze the performance of the proposed technique, a set of numerals are considered in different context and a comparison of the proposed technique with an existing numeral reading method is also presented to show the effectiveness of the proposed technique in producing intelligible speech out of the entered text.This paper presents a data processing system based on an architecture comprised of multiple stacked layers of computational processes that transforms Raw Binary Pollution Data com- ing directly from Two EUMETSAT Metop satellites to our servers, into ready to interpret and visualise continuous data stream in near real time using techniques varying from task automation, data preprocessing and data analysis to machine learning using feed forward ar- tificial neural networks. The proposed system handles the acquisition, cleaning, processing, normalizing, and predicting of Pollution Data in our area of interest of Morocco.Advanced Communication Systems are wideband systems to support multiple applications such as audio, video and data so and so forth. These systems require high spectral efficiency and data rates. In addition, they should provide multipath fading and inter-symbol interference (ISI) free transmission. Multiple input multiple output orthogonal frequency division multiplexing (MIMO OFDM) meets these requirements Hence, MIMO-OFDM is the most preferable technique for long term evaluation advanced (LTE-A). The primary objective of this paper is to control bit error rate (BER) by proper channel coding, pilot carriers, adaptive filter channel estimation schemes and space time coding (STC). A combination of any of these schemes results in better BER performance over individual schemes. System performance is analyzed for various digital modulation schemes. In this paper,adaptive filter channel estimated MIMO OFDM system is proposed by integrating channel coding, adaptivefilter channel estimation, digital modulation and space time coding. From the simulation results, channel estimated 2×2 MIMO OFDM system shows superior performance over individual schemes.Electricity markets are different from other markets as electricity generation cannot be easily stored in large amounts and in order to avoid blackouts, the generation of electricity must be balanced with customer demand for it on a second-by-second basis. Customers tend to rely on electricity for day-to-day living and cannot replace it easily so when electricity prices increase, customer demand generally does not reduce significantly in the short-term. As electricity generation and customer demand must be matched perfectly second-by-second, and because generation cannot be stored to a large extent, cost bids from generators must be balanced with demand estimates in advance of real-time. This paper outlines a a forecasting algorithm built on artificial neural networks in order to predict short-term (72 hours ahead) wholesale prices on the Irish Single Electricity Market so that market participants can make more informed trading decisions. Research studies have demonstrated that an adaptive or self-adaptive approach to forecasting would appear more suited to the task of predicting energy demands in territory such as Ireland. Implementing an in-house self-adaptive model should yield good results in the dynamic uncertain Irish energy market. We have identified the features that such a model demands and outline it here.Received May 2, 2018 Revised Jul 9, 2018 Accepted Aug 2, 2018 Zigbee technology has been developed for short range wireless sensor networks and it follows IEEE 802.15.4 standard. For such sensors, several considerations should be taken including; low data rate and less design complexity in order to achieve efficient performance considering to the transceiver systems. This research focuses on implementing a digital transceiver system for Zigbee sensor based on IEEE 802.15.4. The system is implemented using offset quadrature phase shift keying (OQPSK) modulation technique with half sine pulse-shaping method. Direct conversion scheme has been used in the design of Zigbee receiver in order to fulfill the requirements mentioned above. System performance is analyzed considering to BER when it encountered adaptive white Gaussian noise (AWGN), besides showing the effect of using direct sequence spread spectrum (DSSS) technique. Keyword:This paper presents the use of Simelectronics Program for modeling and control of a two degrees-of freedom coupled mass-spring-damper mechanical system.The aims of this paper are to establish a mathematical model that represents the dynamic behaviour of a coupled mass-spring damper system and effectively control the mass position using both Simulink and Simelectronics.The mathematical model is derived based on the augmented Lagrange equation and to simulate the dynamic accurately a PD controller is implemented to compensate for the oscillation sustained by the system as a result of the complex conjugate pair poles near to the imaginary axis.The input force has been subjected to an obstacle to mimic actual challenges and to validate the mathematical model a Simulink and Simelectronics models were developed, consequently, the results of the models were compared. According to the result analysis, the controller tracked the position errors and stabilized the positions to zero within a settling time of 6.5sec and significantly reduced the overshoot by 99.5% and 99. 7% in Simulink and Simelectronics respectively. Furthermore, it is found that Simelectronics model proved to be capable having advantages of simplicity, less time-intense and requires no mathematical model over the Simulink approach.

Harmonic Load Diagnostic Techniques and Methodologies: A Review

Received Nov 21, 2017 Revised Jan 29, 2018 Accepted Feb 17, 2018 For continuous target following under complex scene, an objective following calculation in light of multi-shading joint likelihood investigation model was introduced. The calculation embraced shading histogram to speak to the actual factual trademark with Camshaft standard and completed exploratory research in such angles as multichannel joint shading highlights measurements, projection delineate weighted preparing, the following window size and position ascertaining, calculation handling component of course. It utilised red, green, blue, tint, luminance channel shading as the objective watched attributes, and planned the computation technique given the likelihood measurement to recognise any shading focus from the compound scene. It likewise settled the counting method for following window size and position which adjusted the multi-shading model. Utilizing weighting projection outline strategy, the foundation obstruction around the objective potential territory was dispensed with. Finally, more reasonable joining judgment and the calculation cycle tenets were advanced. After the test accreditation, the ongoing execution and recognition proportion introduce a decent outcome.

Automated Real-Time Vision Quality Inspection Monitoring System

Received Mar 3, 2018 Revised Apr 11, 2018 Accepted Apr 21, 2018 Paintball has gained a huge popularity in Malaysia with growing number of tournaments organized nationwide. Currently, Ideal Pro Event, one of the paintball organizer found difficulties to pair a suitable opponent to against one another in a tournament. This is largely due to the manual matchmaking method that only randomly matches one team with another. Consequently, it is crucial to ensure a balanced tournament bracket where eventual winners and losers not facing one another in the very first round. This study proposes an intelligent matchmaking using Particle Swarm Optimization (PSO) and tournament management system for paintball organizers. PSO is a swarm intelligence algorithm that optimizes problems by gradually improving its current solutions, therefore countenancing the tournament bracket to be continually improved until the best is produced. Indirectly, through the development of the system, it is consider as an intelligence business idea since it able to save time and enhance the company productivity. This algorithm has been tested using 3 size of population; 100, 1000 and 10,000. As a result, the speed of convergence is consistent and has not been affected through big population.N. N. S. Abdul Rahman, N.M. Saad, A. R. Abdullah, M. R. M. Hassan, M. S. S. M. Basir, N. S. M. Noor 1,2,4,6Faculty of Electronic and Computer Engineering, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia 2,3Center for Robotics and Industrial Automation, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia 3,5Faculty of Electrical Engineering, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, MalaysiaLight rail transit (LRT), or fast tram is urban public transport using rolling stock similar to a tramway, but operating at a higher capacity, and often on an exclusive right-of-way. Indonesia as one of developing countries has been developed the LRT in two cities of Indonesia, Palembang and Jakarta. There are opinions toward the development of LRT, negative and positive opinions. To reveal the level of LRT development acceptance, this research uses machine learning approach to analyze the data which is gathered through social media. By conducting this paper, the data is modeled and classified in order to analyze the social sentiment towards the LRT development.Mohamad, S., Nasir, F.M., Sunar, M.S., Isa, K., Hanifa, R.M., Shah, S.M., Ribuan, M.N., Ahmad, A. 1,4,6,7,8Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Johor, Malaysia 1,2,3UTM-IRDA Digital Media Centre, Media and Game Innovation Centre of Excellence, Universiti Teknologi Malaysia, Johor, Malaysia 1,2,3Faculty of Computing, Universiti Teknologi Malaysia, Johor, Malaysia 5Centre for Diploma Studies, Universiti Tun Hussein Onn Malaysia, Johor, Malaysia 6Research Centre for Applied Electromagnetics, Universiti Tun Hussein Onn Malaysia, Johor, MalaysiaReceived Jan 31, 2018 Revised Apr 21, 2018 Accepted Apr 30, 2018 Bluetooth is an emerging mobile ad-hoc network that accredits wireless communication to connect various short range devices. A single hop network called piconet is the basic communication topology of bluetooth which allows only eight active devices for communication among them seven are active slaves controlled by one master. Multiple piconets are interconnected through a common node, known as Relay, to form a massive network called as Scatternet. It is obvious that the performance of Scatternet scheduling is highly dependent and directly proportionate with the performance of the Relay node. In contrary, by reducing the number of Relays, it may lead to poor performance, since every Relay has to perform and support several piconet connections. The primary focus of this study is to observe the performance metrics that affects the inter-piconet scheduling since the Relay node’s role is like switch between multiple piconets. In this paper, we address and analyze the performance issues to be taken into consideration for efficient data flow in Scatternet based on Relay node.

Automated Computer Vision System Based on Color Concentration and Level for Product Quality Inspection

Recently, the use of automated product quality inspection in industries is rapidly increasing. Quality is commonly related with product to satisfy the customer’s desire and it is important to maintain it before sending to customers. This study presents a technique for product inspection using a computer vision approach. Soft drink beverages have been used as product that to be tested for quality inspection. The database is created to inspect the product based on color concentration and water level quality inspection. The system used Otsu’ method for segmentation, histogram from combined red, green, blue (RGB) color model for features extraction, and quadratic distance classifier to classify the product based on color concentration. For water level, the coordinate of image is set to measure the range of water level. Internet Protocol (IP) camera is used while validate the performance of the system. The result shows that the proposed technique is 98% accurate using 246 samples.