Universiti Teknikal Malaysia Melaka: UTeM Open Journal System
Not a member yet
2735 research outputs found
Sort by
Adaptive Ontology based on Cross Phrase Identification in e-Government
Get PDFCurrently, the implementation of interoperability in e-Government services becomes very crucial. It is the connection of different systems and different schema of applications managed by different administrations. The system is very important in supporting e-Government for achieving good services. Therefore, it has to ensure good quality of services. Discrepancies in data and system structure have caused problems to interlink between systems. In this paper, we propose a method for cross-phrase identification of semantic relation based on word similarity measurement and morposemantic relations for e-Government services. It will solve the interoperability of e-Government services using heterogeneity data to make adaptive ontology
Selection of Spectrogram’s Best Window Size in EMG Signal during Core Lifting Task
Get PDFElectromyography (EMG) is one of the most commonly used tools to study human muscle condition. Past researchers have introduced various techniques from time distribution (TD), frequency distribution (FD) and timefrequency distribution (TFD) to extract information from this EMG signal. However, due to the complex characteristics of the EMG signal itself, TFD such as spectrogram has been widely used as it can provide both temporal and spectral information. However, since spectrogram has a fix window size, there exists a dilemma of resolution, where the too narrow window will result in a poor frequency resolution, and a too wide window will cause poor time resolution. Thus, this study aims to select the best window size to be used with spectrogram to monitor human muscle electrical activity during core lifting task. Four electrodes were placed over different types of muscles, which are the right and left biceps branchii (BB), and right and left erector spinae (ES). In this study, six window sizes (64, 128, 256, 512, 1024, and 2048) were used. The test has been done using two evaluating criteria, namely frequency resolution (Fr) and time resolution (Tr). The result shows that both window size of 512 and 1024 are acceptable, but the best window for this application is window size 512
Triangle Geometry Method Based Dominant Distribution Foreground for Digit Recognition
Get PDFDigit recognition has been studied for four decades ago. Many approaches and techniques such as Hidden Markov Model, Neural Network, back-propagation and k-nearest neighbor have been applied to recognize the digit images. Recently, the triangle geometry method has been applied to extract features from triangle properties such as ratio, angle and gradient. However, a problem in determining points of a triangle was triggered due to the points’ position in straight line. Thus, a method of extracting triangle features using triangle geometry based on the dominant of distribution foreground for digit recognition has been proposed. The dominant of distribution foreground is referred to the digit of ‘0’ which is represented as a foreground image during the binarization process. The process to determine the triangle points are based on the dominant of distribution foreground. The classifiers of Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) are used to measure the classification accuracies for four types of digit datasets which are HODA, IFCHDB, MNIST, and BANGLA. The comparison results classification of accuracies demonstrated the effectiveness of our proposed method
Identification of Software Quality Characteristics on Academic Application In Higher Education Institution (HEI)
Get PDFThe purpose of an academic application in higher education is to ease the user in managing their daily activities using the system. Among the largest users category in higher education institutions are academicians. The system is a critical system because it is the backbone of the institution where important tasks are performed using the system. Some of the examples of academic applications are course management system, program structure management, e-course teaching evaluation, and eLearning. Different universities may have their own academic applications. In software engineering, quality of the system is a vital element to ensure the system is accepted by the user. Various software models are available representing the good quality model. This research describes the processes in identifying the quality factors for academic application based on the importance of the quality factors from the user's perspectives
Bandwidth Control Algorithm on YouTube Video Traffic in Broadband Network
Get PDFThis paper presents an analysis of YouTube video traffic and fitted to best distribution traffic model to control bandwidth usage in a broadband network. The study scope comprised of collections of inbound YouTube video traffic for 7 days with the time-interval of each day is 3 hours. The broadband network is supported at 10Gbps line speed to Wide Area Network (WAN). The objective of this research is to characterize YouTube video traffic on broadband network, to fit the original traffic to best traffic model and bandwidth control algorithm called Policing and Shaping is developed based on time based threshold for 0.5Gbps at night and 1.0Gbps in day time. Performance shows the bandwidth controlled as bandwidth save, reduced traffic burst and processing time. Results present benefits of the developed algorithms where enhancement in processing time is 25.25% and the bandwidth is saved about 7.1668Mbps with Policing algorithms. Shaping algorithm process presents performance of processing time is increased up to 55.26% and the bandwidth is saved for about 25.548Mbps. Results also present best Cumulative Distribution Functions (CDF) traffic model using Maximum Likelihood Estimator (MLE) technique four best traffic models is identified which are Extreme Value, Weibull, Normal and Rician traffic model. Among the four, Weibull shown as the best fitted model that presents value of MLE=-1178.4 with the Scale α=9.49411e+08 and Shape β=2.81324 for 2 parameters traffic modeling. Research benefits in the development of design algorithm for Network Quality of Services (QoS) especially for bandwidth control and performance
EEG-Based Emotion Assessment using Detrended Flunctuation Analysis (DFA)
Get PDFStroke patients suffer from emotional and behavioral changes. The emotion assessment of stroke patients is helpful to carry out appropriate treatment. Emotion assessment through Electroencephalogram (EEG) is reliable and can be applied to stroke patients. Fractal analysis using Detrended Fluctuation Analysis (DFA) is applied to detect the temporal correlation and the simplicity of EEG signals. Emotion contained-EEG signals of two groups of stroke patients, with left brain damage (LBD) and right brain damage (RBD), and a group of normal control (NC) were assessed using DFA in alpha, beta and gamma frequency bands. The EEG signals of the three groups show different degrees of temporal anti-correlation. Moreover, alpha and beta bands which exhibit larger brain oscillation have better performance in emotion classification than gamma band. The overall performance of DFA has achieved 92.00% classification accuracy in LBD, and 91.75% in RBD. Thus, DFA is useful in emotion assessment of stroke patients
Morphological Segmentation of Retinal Blood Vessels and Consequent Tortuosity Extraction
Get PDFInvestigation of a retinal blood vessel system is frequently discussed issue in the field of the clinical ophthalmology due to it serves as reliable indicator of retinal damage. The analysis deals with two coherent tasks regarding retinal blood vessels system. Firstly, the algorithm based on the morphological operations is proposed to be able to perform precise extraction and localization of individual blood vessels for further processing. On the base of this segmentation procedure, e obtain a segmentation model differentiating the retinal blood vessels from retinal background. The second step deals with the major output of the analysis it is tortuosity extraction as it is parameter describing curvature of blood vessels. The tortuosity allows for a description of each vessel element by level of a curvature. It is significantly beneficial for clinical practice, because on the base of blood vessel curvature, physiological or damaged retinal system can be recognized
Combining Likes-Retweet Analysis and Naive Bayes Classifier within Twitter for Sentiment Analysis
Get PDFSentiment analysis is a research study that aims to extract subjectivity of opinions. Due to massive growth number of user generated content in social media, Twitter is one of the most popular microblogging application which user is freely to discuss and share opinions about specific topic or entity. Twitter have several features that potentially can be used to improve sentiment analysis such as like and retweet. Like and retweet are mechanism in Twitter to propagate or share and to show appreciation of other user posting. This paper proposes a combination of textual and non-textual features to improve performance of sentiment prediction. In this research we apply Naïve Bayes for textual classification and Fisher Score to determine non-textual (like and retweet) features. By combining two kinds of features, our experimental find the optimal value of α and β. The evaluation performance using F1-measure gives 0.838 of accuracy with α and β are 0.6 and 0.4 respectively
Design and Development of Google Glass-Based Campus Navigation System
Get PDFThis paper investigates the feasibility of a Google Glass-based campus navigation system for both indoor and outdoor areas. The Indoor Positioning System (IPS) of the proposed system utilizes the magnetic positioning technology of IndoorAtlas Maps™ API which depends on structure's magnetic field fluctuations or geomagnetic fingerprints. The outdoor navigation mechanism simply consists of a map displayed within the Google Glass app with an augmented routing path leading to the set destination, while the indoor navigation interface displays a blue dot indicator of the current position on top of the augmented map with minimum spanning tree route. Furthermore, a data logging feature is incorporated for logging the movements of the user through the use of QR coded checkpoints for outdoor location monitoring and indoorto-outdoor navigation transitions. The proposed system was tested in De La Salle University (DLSU) - Manila Campus, where 30 participants (15 DLSU and 15 Non-DLSU) were invited to utilize the proposed system navigating from an entry point to a set destination. The proposed Google Glass-based navigation system was found to have an average error of 1.77 meters (indoor) and around 77% of the users who utilized the application responded with a positive feedback. However, Google glass’ limited battery life and high cost are among the barriers to adaptation. These results could provide empirical evidence supporting the feasibility of Google glass-based navigation deployment in other public areas, e.g. malls, government buildings, hospitals, etc
PERSEPSI PENERIMA SKIM BANTUAN TERHADAP PERANAN AGENSI KEBAJIKAN DI MALAYSIA (PERCEPTION OF AID SCHEME RECIPIENTS TOWARDS THE ROLES OF WELFARE AGENCY IN MALAYSIA)
Get PDFTujuan utama kajian ini ialah untuk mengenal pasti persepsi penerima bantuan terhadap skim bantuan sebuah agensi kebajikan di Malaysia. Seramai 157 responden yang terdiri daripada penerima bantuan telah dipilih secara persampelan mudah. Pengumpulan data menggunakan soal selidik berstruktur. Hasil kajian menunjukkan golongan wanita lebih ramai menerima bantuan berbanding lelaki. Sebahagian besar penerima terdiri daripada etnik Melayu, diikuti India dan Cina, berpendapatan di bawah RM500 sebulan dan majoritinya menerima bantuan di bawah skim Bantuan Am. Kajian juga mendapati terdapat perkaitan yang signifikan di antara persepsi penerima bantuan ke atas perkhidmatan pelanggan dengan agensi bantuan. Dapatan ini menunjukkan persepsi perkhidmatan pelanggan yang lebih baik memberi impak ke atas skim bantuan berkenaan. Dapatan juga menunjukkan wujud hubungan yang signifikan di antara faktor demografi dengan perubahan sosial dan jati diri dan pendapatan keluarga. Kata Kunci: persepsi, perkhidmatan pelanggan, sikap, sosial, jati diri ABSTRACTThe main purpose of this study is to identify the beneficiaries' perception of the aid scheme of a welfare agency in Malaysia. A total of 157 respondents of the beneficiaries were chosen by convenience sampling. Data were collected using a structured questionnaire. The findings show that more women are receiving the aid compared to the men. Most of the recipients are the Malays, followed by the Indian and Chinese, earning below than RM500 a month and they are receiving in under the General Aid scheme. The study also found that there was a significant correlation between the perceptions of beneficiaries and the customer service of the welfare agencies. This finding demonstrates that better customer service perceptions will give impact to the aid scheme. Last but not least, the findings highlight a significant relationship between demographic factors with the social change as well as self-esteem and family income.Keywords: perception, customer service, attitude, social, identit