Dayang Rohaya Awang Rambli

Preliminary Evaluation on User Acceptance of the Augmented Reality Use for Education

Augmented reality is a technology that enables user to interact with 3D virtual object and real world in real time application. The use of Augmented Reality (AR) in education shows a potential to enhance traditional learning method. The purpose of this study is to observe the familiarity of AR application especially its implementation in learning environment, and to determine the usefulness of AR application in education. The study was conducted during Malaysia Technology Expo 2009 in small scale participants consists of students, teachers, and industrial people. The result showed that most of the participants never been experienced with AR application before, but the idea to implement AR for education are well accepted with a very positive feedback. Based on the findings, some issues and user expectation for further development of AR application in learning environment are being discussed.

Forecasting method selection using ANOVA and Duncan multiple range tests on time series dataset

Selection of a suitable forecasting technique is of prime importance in order to obtain a better prediction result. This paper demonstrated the use of two statistical approaches namely, Analysis of Variance (ANOVA) and Duncan multiple range tests for determining the performance of different forecasting methods. Three forecasting methods were chosen and compared: regression, decomposition, and ARIMA. Data from monthly incidence of Salmonellosis in US from 1993 to 2006 was collected and used for technical analysis. ANOVA was initially used to identify significant difference between the actual data and three forecasting methods. Based on the results from ANOVA, selection of appropriate method was conducted using Duncan multiple range tests. The results showed that both regression and ARIMA could be used in the Salmonellosis data. On the contrary, decomposition method yielded the least performance and is not suitable for being applied on the available dataset.

A comparative study of univariate forecasting methods for predicting tuberculosis incidence on human

The negative impact of zoonosis has stimulated study into a prediction system that able to estimate the future number of zoonosis, especially in human being. Zoonosis refers to any infectious disease that is able to be transmitted from animals to humans. This empirical paper compares three univariate methods for zoonosis forecasting up to one year. Regression analysis, decomposition, and Holt-Winters were selected as the simple and quick techniques for this purpose. The methods were compared using a time series of monthly number for tuberculosis incidence in human. Different error measures were used to determine the best model among them. It was found that the Holt-Winters method produced better prediction than the rest of the methods with MAPE was 6.301 and Theil U value was 0.037.

Haptic Exploratory Interactions in Foot Reflexology Practice from the Practitioners' Perspectives

Haptic exploration helps in the assessment of an objects property that includes its shapes and surface material. The interaction has been widely applied in various domains ranging from textile industry to medical field. Despite its importance, the identified haptic exploratory procedures by renowned authors might not be completely applicable in other domains. This paper presents a study that examines the haptic exploratory procedures in foot reflexology domain since the practices promote relaxation and stress relief. The study explored 2 traditional foot reflexology sessions, results were compared with the existing haptic exploratory procedures. The findings indicate new haptic exploratory procedures that are of important benefit to haptic exploration and enhanced the existing haptic exploratory procedure.

Forecasting of salmonellosis incidence in human using Artificial Neural Network (ANN)

Salmonellosis is one of the most common seasonal zoonosis. As from the definition, zoonosis refers to the transmission of infectious diseases from animal to human. This paper presents the prediction of Salmonellosis incidence using Artificial Neural Network (ANN) on the basis of monthly data. A series of Salmonellosis incidence in US from 1993 to 2006, published by Centers for Disease Control and Prevention (CDC), was collected for technical analysis. Multi Layer Perceptron (MLP) has been chosen for the ANN design. The model consists of three layers: input layer, hidden layer, and output layer. Number of nodes in hidden layer was varied in order to find the most accurate forecasting result. The comparisons of models were justified by using Mean Absolute Percentage Error (MAPE). Furthermore, MAPE and Theils U were used to measure the result accuracy. The least MAPE derived from the best model was 10.761 and Theils U value was 0.209. It implied that the model was highly accurate and a close fit. It was also indicated the capability of final model to closely represent and made prediction based on the tuberculosis historical dataset.

Current limitations and opportunities in mobile augmented reality applications

Mobile AR has evolved from the bulkiness of head-mounted device and backpack device to smart device (smartphone, tablet etc.). To date, the current implementation has made what AR is today. However, the advancement of AR technology has met with limitation and challenges on its own, which resulted in not able to reach mass-market. This paper in turn presents current limitations and challenges that need to overcome. We have done a review based on past research papers on limitation in technical (hardware, algorithms and interaction technique) and non-technical (social acceptance, privacy and usefulness) aspects of developing and implementing mobile augmented reality applications. We also presented some future opportunities in mobile AR applications.

Human pose tracking in low-dimensional subspace using manifold learning by charting

Tracking full articulated human body motion is a very challenging task due to the high dimensionality of human skeleton model, self-occlusion and large variety of body poses. In this work, we explore a novel Low-dimensional Manifold Learning (LDML) approach to overcome high dimensional search space of human model. Low-dimensional demonstration not only delivers a compact tractable search space, but it is efficient to capture general human pose variations. The key contribution of this work is an algorithm of Quantum-behaved Particle Swarm Optimization (QPSO) for pose optimization in latent space of human motion. Firstly, we learn the human motion model in low-dimensional latent space using nonlinear dimension reduction technique charting based on hierarchical strategy. Increased dependence provision is carried out using hierarchy strategic measures in charting, which improves accuracy in higher flexibility and adaptation. Then we applied QPSO algorithm to estimate the human poses in low-dimensional latent space. Preliminary experimental tracking results show that our approach is able to give good accuracy as compared to conventional state-of-the-arts methods.

Particle swarm optimization based articulated human pose tracking using enhanced silhouette extraction

In this paper, we address the problem of three dimensional human pose tracking and estimation using Particle Swarm Optimization (PSO) with an improved silhouette extraction mechanism. In this work, the tracking problem is formulated as a nonlinear function optimization problem so the main objective is to optimize the fitness function between the 3D human model and the image observations. In order to improve the tracking performance, new shadow detection, removal and a level-set mechanism are applied during silhouette extraction. Both the silhouette and edge likelihood are used in the fitness function. Experiments using HumanEva-II dataset demonstrate that the proposed approach performance is considerably better than baseline algorithm which uses the Annealed Particle Filter (APF).

The Initial Design of Learning Outcomes in the Sport Training Application

Teaching and learning activities should be designed and developed based on a pedagogical approach. These activities occur within a particular context and are designed to achieve intended learning outcomes through a series of tools and resources. This paper shows an initial design of learning outcomes that will be specifically designed for reusability to support automation and computer-assisted discovery for sport training application.

A study of stochastic algorithms for 3D articulated human body tracking

The 3D vision based research has gained great attention in recent time because of its increasing applications in numerous domains including smart security surveillance, sports, and computer games and so on. This paper presents a study of various stochastic algorithms to identify their utilization in an efficient manner for effective 3D human articulated body tracking. First part of this paper enlightens the stochastic filtering algorithms including particle filter and its variants annealing particle filter. The second part focused on evolutionary optimization algorithms based effective tracking. Currently these two types of algorithms are most extensively used for tracking due to their ability to solve highly nonlinear problems and their consideration uncertainties in the pose estimation. In order to evaluate the performances of these algorithms both qualitatively and quantitatively, we investigate the implementation of the various stochastic algorithm including, particle filter, annealing particle filter, particle swarm optimization and quantum-behaved particle swarm optimization.