Showing papers in "Journal of Telecommunication, Electronic and Computer Engineering in 2016"

The Application of Google Classroom as a Tool for Teaching and Learning

Abstract: Learning activities in the computer lab is one of the challenging in higher education. Subject that is most practical activities such as Data Mining are by nature illustrative or demonstrative in the computer lab that emphasize the acquisition of observational skills; and allow students to see the concept dealt in action and relate theory more closely to reality. However, the students’ reaction to practical work is often negative as a result they are not effective in laboratory work and this may reflect a student perception that there is lack of clear purpose for the lab hands on task. The main objective of this study is to explore the effectiveness of Google Classroom’s active learning activities for data mining subject under the Decision Sciences program. A set of questionnaire has been distributed to a sample of 100 students who enrolled data mining subject were used in this study. The analysis of the data was carried out using Technology Acceptance Model (TAM) to examine the relationship between the identified factors and the effectiveness of the learning activities. The results prove that majority of the students satisfy with the Google Classroom’s tool that were introduced in the class where all ratios are above averages. In particular, comparative performance is good in the areas of ease of access, perceived usefulness, communication and interaction, instruction delivery and students’ satisfaction towards the Google Classroom’s learning activities.

Smart City Indicators: A Systematic Literature Review

Abstract: Smart city is currently a trend for major cities in the world and also most cities in Indonesia. The city as center of human civilization cannot be separated from problems related to excess capacities and matters of convenience. The more and more people are moving from the rural to urban areas has increasingly pose new problems in the city. The city needs to change in order to sustain in the future. There are needs of a strong indicators as the support for a city, in terms of the physical environment, social, people, infrastructure, education and ICT infrastructure. In this paper we discuss on a systematic literature review of studies related to smart city. Systematic literature review has three stages, introduction stage, demographic analysis stage and analysis of the results. The final results reveal important indicators in smart city based on the conclusions of previous studies.

Heart disease prediction system using k-Nearest neighbor algorithm with simplified patient's health parameters

Abstract: Heart disease is the primary cause of death nowadays. Treatments of heart disease patients have been advanced, for example with machine-to-machine (M2M) technology to enable remote patient monitoring. To use M2M to take care remote heart disease patient, his/her medical condition should be measured periodically at home. Thus, it is difficult to perform complex tests which need physicians to help. Meanwhile, heart disease can be predicted by analysing some of patient's health parameters. With help of data mining techniques, heart disease prediction can be improved. There are some algorithms that have been used for this purpose like Naive Bayes, Decision Tree, and k-Nearest Neighbor (KNN). This study aims to use data mining techniques in heart disease prediction, with simplifying parameters to be used, so they can be used in M2M remote patient monitoring purpose. KNN is used with parameter weighting method to improve accuracy. Only 8 parameters are used (out of 13 parameters recommended), since they are simple and instant parameters that can be measured at home. The result shows that the accuracy of these 8 parameters using KNN algorithm are good enough, comparing to 13 parameters with KNN, or even other algorithms like Naive Bayes and Decision Tree.

Classification of Landsat 8 Satellite Data Using NDVI Tresholds

Abstract: This study aims to classify Landsat 8 satellite data using NDVI thresholds. Initially, visible and near infrared bands of Landsat 8 satellite were used to derive Normalized Different Vegetation Index (NDVI) image. Vegetation, non-vegetation and water areas were then analyzed where thresholds for separating them are carefully determined with the aid of ground truth information of the study area. Density slicing was performed in order to separate the image into different land covers. Eventually, color mapping and class labeling were done to complete the classification process. The accuracy of the classified image is then assessed using a confusion matrix where overall classification accuracy and Kappa coefficient are computed. The result shows that NDVI-based classification is able to classify the Landsat 8 satellite data with a high accuracy.

The Evolution of Non-invasive Blood Glucose Monitoring System for Personal Application

Abstract: Glucose monitoring technology has been used by diabetic patients to monitor their blood glucose level for the past three decades. This technology is very useful for managing diet among diabetic patients. This paper reviews the fundamental technique of blood glucose detection method and the development of blood glucose monitoring systems that have been developed ever since. The most common and widely used technique is an invasive technique that requires users to prick their finger to draw the blood. However, recently a lot of new technologies have been developed for non-invasive technique to monitor blood glucose monitoring and studies in this area are growing rapidly. Among all, the optical and transdermal approach are the two most potential sensing modalities for non-invasive glucose monitoring that show a very good prospect.

Illumination and Contrast Correction Strategy using Bilateral Filtering and Binarization Comparison

Abstract: Illumination normalization and contrast variation on images are one of the most challenging tasks in the image processing field. Normally, the degrade contrast images are caused by pose, occlusion, illumination, and luminosity. In this paper, a new contrast and luminosity correction technique is developed based on bilateral filtering and superimpose techniques. Background pixels was used in order to estimate the normalized background using their local mean and standard deviation. An experiment has been conducted on few badly illuminated images and document images which involve illumination and contrast problem. The results were evaluated based on Signal Noise Ratio (SNR) and Misclassification Error (ME). The performance of the proposed method based on SNR and ME was very encouraging. The results also show that the proposed method is more effective in normalizing the illumination and contrast compared to other illumination techniques such as homomorphic filtering, high pass filter and double mean filtering (DMV).

A Review of Social-Aware Navigation Frameworks for Service Robot in Dynamic Human Environments

Abstract: The emergence of service robot into human daily life in the past years has opened up various challenges including human-robot interaction, joint-goal achievement and machine learning. Social-aware navigation also gains vast research attention in enhancing the social capabilities of service robots. Human motions are stochastic and social conventions are very complex. Sophisticated approaches are needed for a robot to abide to these social rules and perform obstacle avoidance. To maintain the level of social comfort and achieve a given task, the robot navigation is now no longer a search for a shortest collision-free path, but a multi-objective problem that requires a unified social-aware navigation framework. A careful selection of navigation components including global planner, local planner, the prediction model and a suitable robot platform is also required to offer an effective navigation amidst the dynamic human environment. Hence, this review paper aims to offer insights for service robot implementation by highlighting four varieties of navigation frameworks, various navigation components and different robot platforms.

A Review: Substrate Integrated Waveguide Antennas and Arrays

Abstract: This study aims to provide an overview and deployment of Substrate-Integrated Waveguide (SIW) based antenna and arrays, with different configurations, feeding mechanisms, and performances. Their performance improvement methods, including bandwidth enhancement, size reduction, and gain improvement are also discussed based on available literature. SIW technology, which acts as a bridge between planar and non-planar technology, is a very favorable candidate for the development of components operating at microwave and millimeter wave band. Due to this, SIW antennas and array take the advantages of both classical metallic waveguide, which includes high gain, high power capacity, low cross polarization, and high selectivity, and that of planar antennas which comprises low profile, light weight, low fabrication cost, conformability to planar or bent surfaces, and easy integration with planar circuits.

Eye Tracking Application on Emotion Analysis for Marketing Strategy

Abstract: This paper present on understanding the human behavior with eye tracking studies related to consumer cognition in marketing product. The study of human behavior using eye tracking is a growing multidisciplinary field that links electronics, psychology and cognitive science to study the human behavior on problem solving and decision making. In this paper, we particularly investigate the human behavior in consumer cognition. We conducted experiments to track the human eyes by using the Tobii TX300 eye tracker. The eye–mind relationship can help to use eye motions activity measurements expressing to some degree about human behavior. The result shows that the visual attention of human is very much related to the cognition of the products.

Background Correction using Average Filtering and Gradient Based Thresholding

Abstract: Segmentation process on the image with illumination and contrast variation problem is a very challenging task. This problem can reduce the effectiveness of segmentation result. Therefore, the implementation of the proposed method based on the background correction is able to improve the image quality and automatically increases the segmentation. The proposed method used in this study is based on mean filtering and Otsu thresholding techniques to enhance the non-uniform image for better segmentation. The proposed method used the mean value of the image to normalize the background image. Then, the resulting image from the previous step underwent the segmentation process using Gradient Based Adaptive thresholding. Finally, a comparison in term of misclassification error (ME) was calculated and compared with the six other methods. For the ‘rectangles’ image, our method with gradient achieved 0.050478 and it is better compared to the other six methods. However, the ME value of the ‘text’ image produced by our method is 0.058722, slightly higher than the Niblack’s method, Chen’s method and gradient based method. Therefore, it still acceptable in comparison to those methods by Yanowitz and Bruckstein’s (YB) method, Blayvas’s method, and Chan’s method. The proposed method is better method to enhance and improved the image quality. The main impact of this study is to eliminate the illumination and normalize the contrast variation. In conclusions, the implementation of the proposed method produces an effective and efficient results for background correction and increases the segmentation result.

A Systematic Review on Usability Evaluation Methods for M-Commerce Apps

Abstract: There are several literatures pertaining to the usability of mobile commerce (m-commerce) applications, however, these literatures do not sufficiently address issues about usability methods or adequately provide knowledge concerning usability methods used in most of the empirical usability evaluation for applications in m-commerce. Hence, this paper attempts to review available literatures with the aim of capturing the usability techniques commonly or frequently used in the domain of usability evaluation for applications in m-commerce. To achieve the stated research goal, the study applied systematic literature review methodology. Sixty seven (67) papers in the area of usability evaluation for m-commerce apps were downloaded. Out of these papers, twenty one (21) most relevant studies were selected for review in order to extract the appropriate information needed for the analysis. The results from the review reveal that heuristic evaluation, formal test and think-aloud methods are the most commonly utilized methods in m-commerce application usability evaluation compared to the cognitive walkthrough and informal test methods. In addition, most of the studies applied control experiment (33.30% of the total reviewed studies); other studies that applied case study in usability evaluation make up 14.28%. However, most of the studies reviewed, lacked comprehensive framework to demonstrate the applicability of other usability methods in m-commerce domain such as survey and field study. The results from this paper provide additional knowledge for usability practitioners, designers, developers, and the research community to know the current usability methods applied in m-commerce application evaluation.

Load Frequency Control for Hydropower Plants using PID Controller

Abstract: Many development republics began to get rid of conventional energy and towards to use renewable energy like hydropower system, solar cells and wind turbines as soon as possible. Load Frequency Control (LFC) problem is coming to be the main topics for mentioning schemes due to not corresponding between main power system inputs such as change load demand and change in speed turbine settings. This paper illustrates a selftuning control of hydropower system that suggested and confirmed under Automatic Generation Control (AGC) in power scheme. The suggested power system involves one single area. The suggested self-tuning control system is employed in performing the automatic generation control for load frequency control request and compared it with conventional control structure. The power system dynamic modeling has regularly built in several essential parameters which have a significant influence According to frequency limitation. The main problem with all controllers is an exaggerated reaction to minor errors, producing the system to oscillate. The output response results for hydropower system obviously proved the benefit of using maximum load demand by tuning PID controller. Whereas, tuning PID controller has got properly more rapid output response and minimal overshoot.

Review of Multilevel Inverter Topologies and Its Applications

Abstract: Nowadays, multilevel inverter technologies have attracted attention as a convenient solution in many industrial applications. There are a few interesting features of using this configuration, where less component count, less switching losses, and improved output voltage/current waveform. The most significant criteria in multilevel inverter is the minimization of harmonic components in the inverter output voltage/current. The evolution of multilevel inverter technologies and the commercial products based on a multilevel inverter topology has shown tremendous developments due to the many advantages. In this paper, a review of the classical multilevel inverters and the recently introduced topologies are presented. They are trending as the most preferable power electronics device that have been widely used in the applications like motor-drive applications up to MegaWatt (MW) power levels, renewable energy (solar/wind power inverters) and reactive power compensation (i.e. STATCOM). This paper provides a general comparisons for various type of multilevel inverters and their suitable applications with useful references.

ARIMA with Regression Model in Modelling Electricity Load Demand

Abstract: Electricity is among the most crucial needs for every people in this world. It is defined by the set of physical phenomena related with the flow of electrical charge. The importance of electricity itself leads to the increasing electricity load demand in the world including Malaysia. The purpose of the current study is to evaluate the performance of combined ARIMA with Regression model in forecasting electricity load demand in Johor Bahru. Box-Jenkins Autoregressive Integrated Moving Average (ARIMA) and Regression models will be used as benchmark models since the model has been proven in many forecasting context. Using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) as a forecasting accuracy criteria, the study concludes that the combined method is more appropriate model.

Exostructure Services for Infrastructure Resources Optimization

Abstract: The emerging challenges for Malaysia medium sized enterprises to remain competitive is testing and stressing the extent of the capacity and even the capability of IT infrastructure, especially regarding on its resource utilization for cost effective sustainability during this time of economic uncertainty. They are stuck in between the larger enterprises that enjoy economies of scales and the much smaller enterprises with insufficient baseline to motivate contribution. This research evaluated two theories from Harvard University: Commodity of IT infrastructure and Disruptive Technology for its suitability and ascertain its adaptability to a localized environment. Primary data collection via mass survey is conducted for exploratory analysis. The findings show significant imbalance IT infrastructure investment decision and the reasons behind, supported by the statistical evidences collected. The paper then seeks to establish a new cost effective virtualization framework for them to plan ahead. As infrastructure investment requires a longer period to yield positive contribution, early implementation will prepare them for the next bull run

Automatic Infant Cry Pattern Classification for a Multiclass Problem

Abstract: Crying is the only way of communication for infants to express their physical and emotional needs. Automatic infant cry analysis that provides fast and non-invasive process is suitable to assess the physical and emotional states of infants. The cry analysis provides an opportunity to understand infants’ needs. It is also beneficial in clinical environment for identifying specific pathologies through infant cry. This paper presents an automatic infant cry classification system for a multiclass problem. The cry classification system consists of three stages: (1) feature extraction, (2) feature selection, and (3) pattern classification. We extracted spectral features, such as Mel Frequency Cepstral Coefficients (MFCC) and Linear Prediction Cepstral Coefficients (LPCC) to represent the acoustic characteristics of the cry signals. In addition, the combination of spectral and dynamic features was also investigated. Due to the high dimensionality of data resulting from the feature extraction stage, we selected relevant features to perform feature selection to reduce the data dimensionality. In this stage, five different feature selection techniques were experimented. In the pattern classification stage, two Artificial Neural Network (ANN) architectures: Multilayer Perceptron (MLP) and Radial Basis Function Network (RBFN) were used for classifying the cry signals into five categories: asphyxia, pain, hunger, deaf, and normal. Experimental results show that the best classification accuracy of 93.43% (Kappa value of 0.91) was obtained from MFCC + ∆MFCC + ∆∆MFCC feature set, when using CFS selection technique and RBFN.

Mobile video streaming applications: a systematic review of test metrics in usability evaluation

Abstract: In evaluating the usability of mobile video streaming applications, the performance of the applications comes into focus. This is because the performance of mobile streaming applications affects their usability. From this study, video streaming and video quality are identified as the two most evaluated elements in the usability test of mobile video streaming applications. These elements are affected by several related factors that are peculiar to the mobile platforms and domains. These in turn affect the usability of the applications. In mobile platforms, bandwidth is low and network connections are unstable; this is coupled with the limitations caused by the smallness of the screen sizes of the mobile devices. Furthermore, startup delays, jitter, latency and rebuffering are the determining factors for the performance of mobile video streaming. On the other hand, video quality is determined by frame rate, bit rate, and resolution. These factors present themselves due to the mobile context of mobile streaming applications. They combine to influence the performance of the applications as well as their usability. Therefore, in considering the usability of these set of applications, these factors (metrics) are important as they determine the performance of the applications and by and large also affect the usability of the applications. Other factors identified in the study that affect the usability of mobile streaming applications include: functionality, social context and user interface and appearance. On the whole, this paper presents the results of a systematic review of test metrics in the usability evaluation of mobile video streaming applications. The systematic review approach used include: defining the search strategy, selection of primary studies, the extraction of data, and the implementation of a synthesis strategy. Using this methodology, 238 studies were found; however, only 51 relevant studies were eventually selected for the review. The study reveals that time taken for video streaming and the video quality were the two most popular metrics used in the usability test and evaluation of mobile video streaming applications. Besides, most of the studies concentrated on the usability of mobile TV as users switch from traditional TV to mobile TV.

Measuring the Accuracy of Crowd Counting using Wi-Fi Probe-Request-Frame Counting Technique

Abstract: Wi-Fi in smartphones are designed to periodically transmit probe-request-frame to determine when a known access point is within range and by capitalizing this Wi-Fi behavior, crowd counting and analysis have been done by continuous monitoring and counting these Wi-Fi frames. The proliferation of Wi-Fi enabled mobile devices and the ever-increasing number of mobile devices in use, suggests opportunities for developing lowcost crowd counting and analysis solution. This work attempt to measure how well do monitoring and counting these Wi-Fi frames correlate with the actual number of people presence in a crowd. In this paper, we also compare the pros and cons of various crowd counting technologies, describe the system that we used for counting Wi-Fi frames and compare its accuracy against manual crowd counting technique in an event involving the public continuously for 8 hours. The results are promising, the correlation between manual counting and Wi-Fi frames counting is 0.89322. In addition to that, the Wi-Fi frames counting technique can even reveal the retention rate of the crowd.

Implementing ARCS Model to Design a Motivating Multimedia E-Book for Polytechnic ESL Classroom

Abstract: This paper describes the design of multimedia E-book (mE-book) based on the Keller’s ARCS Model of Motivational Design (1987). This paper also presented the implementation of mE-book as a motivating learning aid to promote ESL language learning in Polytechnic classrooms. Sixty (60) Polytechnic students experienced mE-book in their language classroom and their perceived motivation towards this learning material is measured using the Instructional Materials Motivation Survey (IMMS). This study is an attempt to adduce a scope for implementing multimedia in language learning in a motivating way for adult learners.

Max-Average: An Extended Max-Min Scheduling Algorithm for Grid Computing Environtment

Abstract: Sharing numerous computational and communication power from connected heterogeneous systems over the world are the two key points of Grid computing. Grid computing can also be referred as a computing platform for users to utilise the remote heterogeneous resources for solving their large scale jobs that require a huge amount of processing power or a huge data storage. Sharing these resources that way effectively requires a very good scheduling strategy, which is the focus of this research. This paper presents a new proposed grid based scheduling algorithm called Max-Average, inspired from Max-Min algorithm. In order to produce good quality solutions, the proposed algorithm is designed in two phases; firstly it uses an initial task queue like the traditional Max -Min for estimating task completion time for each of resources, and in the second phase choose the fitting resource for scheduling according to requirements. The results from our simulation showed that our proposed algorithm is performing better in producing good quality solutions, particularly in executing tasks fast and in balancing the load (resource utilisation) among the resources more effectively when compared to standard Minimum Execution Time (MET), Minimum Completion Time (MCT), Min-Min, and Max-Min heuristic approaches

Unsupervised Contrast Correction for Underwater Image Quality Enhancement through Integrated-Intensity Stretched-Rayleigh Histograms

Abstract: The attenuation of light that travels through the water medium results the underwater image to suffer from several problems. Low contrast and color performance are the problems that resulting the image to loss important information. In addition, the objects in the image are hardly differentiated from the background. Consequences from these problems, this paper extend the methods of enhancing the quality of underwater image with the aim of improving the image contrast and increase the color performance. The proposed method consists of two stages. At first stage, contrast correction technique is applied to the image. The image is multiplied with a gain factor. The image histogram is divided into two regions at the mid-point and stretched towards the higher and lower intensity values. The composition of these two different intensities images produces contrast-enhanced image. At the second stage, the image is applied with color correction, where the image is converted into Hue-Saturation-Value (HSV) color model. Dividing and stretching of S and V components increase the image color. By considering the contrast and color performance of the output image, the proposed method outperforms the state-of-the-art methods

Localization of Multiple Harmonic Sources for Inverter Loads Utilizing Periodogram

Abstract: This paper introduces a new technique to localize the multiple harmonic sources that caused by power inverter loads in power distribution system utilizing periodogram technique with single-point measurement approach at the point of common coupling (PCC). The periodogram technique is used to analyzed and distinguish multiple harmonic sources location in power system whether at downstream, upstream or both stream by their impedances characteristics. The proposed localization of multiple harmonic sources method is based on the correlational relationship between fundamental impedance (Z1) and harmonic impedance (Zh) in order to identify the suspected buses. The adequacy of the proposed methodology is tested and verified on distribution system for several different cases.

Current Challenges of Requirement Change Management

Abstract: Nowadays, responding to requirements change in software industry is essential for survival in the competitive market to achieve business objectives. However, it is clearly evident that changing requirements have many problems which causes software failure. This was a great motivation to analyse literature for identifying current challenges of Requirements Change Management (RCM); which in return can improve our ability to make better decisions and resolve changing requirements problems. Major challenges of RCM have been elucidated as reusability, change anticipation, change activity measurement, connectivity with software artifacts and change management automation. Identifying RCM challenges will help to draw a road map for researchers and practioners to find optimal solutions.

Lexical Based Sentiment Analysis - Verb, Adverb & Negation

Abstract: Sentiment analysis is a method to determine whether the feedback given by the user is positive or negative. The comments posted by users consists noisy text which includes abbreviations, misspelling and short forms. Sentiment analysis becomes challenging when dealing with noisy data. The objective of this paper is to introduce a lexical based method in classifying sentiment of Facebook comments in Malay language. Two types of lexical based techniques namely Term Counting and Term Counting Average are implemented in order to classify the sentiment of Facebook comments. Several parts of speech tags are being taken into account. Pre-processing process is involved in dealing noisy texts in data. Term Counting works better for adjectives and adverbs while Term Counting Average performs better for verbs and negation words.

A Review Study on Flexible Link Manipulators

Abstract: This paper presents a review on various studies of flexible link manipulators which cover mathematical modeling and control of single link, two link and multi-link manipulators. This review has shown that the effectiveness of some controls such as Model Predictive Control (MPC) scheme alone and combined with Piezoelectric actuators (PZT), combination of robust nonlinear and fuzzy compensator, employing piezoelectric actuators by taking into account their position along the link, linear quadratic regulator (LQR), and fuzzy logic controllers. Based on the reviews, these control approaches are better than other control schemes to control the flexible link manipulators and vibrations suppression.

Classification of Human Fall from Activities of Daily Life using Joint Measurements

Abstract: Falls are a major health concern to most of communities with aging population. There are different approaches used in developing fall detection system such as some sort of wearable, non-wearable ambient sensor and vision based systems. This paper proposes a fall detection system using Kinect for Windows to generate depth stream which is used to classify human fall from other activities of daily life. From the experimental results our system was able to achieve an average accuracy of 94.43% with a sensitivity of 94.44% and specificity of 68.18%. The results also showed that brutally sitting on floor has a higher acceleration, which is very close to the acceleration shown by fall. Even then the system was able to achieve a high accuracy in determining brutal movements with the use of joint positions, this is an indication that further improvements to the algorithm can make the system more robust.

Optimization of Sliding Mode Control using Particle Swarm Algorithm for an Electro-hydraulic Actuator System

Abstract: The dynamic parts of electro-hydraulic actuator (EHA) system are widely applied in the industrial field for the process that exposed to the motion control. In order to achieve accurate motion produced by these dynamic parts, an appropriate controller will be needed. However, the EHA system is well known to be nonlinear in nature. A great challenge is carried out in the EHA system modelling and the controller development due to its nonlinear characteristic and system complexity. An appropriate controller with proper controller parameters will be needed in order to maintain or enhance the performance of the utilized controller. This paper presents the optimization on the variables of sliding mode control (SMC) by using Particle Swarm Optimization (PSO) algorithm. The control scheme is established from the derived dynamic equation which stability is proven through Lyapunov theorem. From the obtained simulation results, it can be clearly inferred that the SMC controller variables tuning through PSO algorithm performed better compared with the conventional proportionalintegral-derivative (PID) controller.

Development and Evaluation of i-Brochure: A Mobile Augmented Reality Application

Abstract: Brochure is a typical promotional tool that has been used by most higher learning institutions to disseminate information to their prospective international students. However, some drawbacks of brochure include; information consisting of only text and images, non-interactive and if updated, the brochure will be obsolete. With the advent of mobile technology, Mobile Augmented Reality has been introduced to facilitate human in their daily lives. This paper discusses the development and evaluation of a Mobile Augmented Reality interactive brochure application. The aim of this application is to provide interactive information beyond that of a typical brochure in promoting higher learning institutions amongst the international students. By using the Mobile Augmented Reality application, the students will be able to access information in the form of virtual contents which cannot be acquired from a typical paper brochure. The results of user evaluation towards the use of the application indicated that they agreed with all the measurements which include Usefulness, Ease of use, Functionality and effectiveness, Outcome/future use and Satisfaction.

Mobile Phone Augmented Reality Postcard

Abstract: The purpose for this project is to introduce and empower the technology of Mobile Phone Augmented Reality (AR) into the usage of everyday souvenirs for the tourism industry. AR technology these days have advanced into a mainstream technology that can easily be executed with modern day smartphones be it on the Android or iOS platform. The idea is to construct a 3D model of a historical monument which allows the tourist to obtain information and a 360 degree view of the monument itself. Therefore, this project is believed to be able to bring up the idea of using AR technology and its application on a souvenir. The type of souvenir that will be focused on would be the postcard as it is still one of the main purchased items by tourists while travelling. A pilot study based on 50 respondents around Melaka tourist hotspots will be conducted after the completion of this project to determine that by implementing AR into souvenirs, tourists are able to gain information interactively

The Removal of Specular Reflection in Noisy Iris Image

Abstract: Iris recognition is a biometric system that uses human iris features to determine and verify the identity of human. Other biometric systems are fingerprint, face, ear, voice, gait, blood vessels and many more. A complete iris recognition system includes: iris acquisition, iris segmentation, feature extraction and matching. The main factor to obtain high segmentation and recognition accuracy is the quality of iris pattern. The quality of iris pattern can be affected because of specular reflection. Specular reflection happens during iris acquisition and it can reduce the features of iris pattern. This work is significant since the improved iris pattern can enhance the performance of iris localization, iris segmentation and feature extraction in the iris recognition system. In this paper, the iris image enhancement methods are proposed to remove the specular reflection. UBIRIS v1 and CASIA v4 databases are used for testing. Based on the results, the proposed methods managed to remove the specular reflection without affecting the iris image quality. The proposed methods also obtained fast execution time and low memory