Siong-Hoe Lau

An Investigation of User Perceptions and Attitudes towards Learning Objects.

This study empirically evaluates the technology acceptance model drawn from Information Systems (IS) literature to investigate how user beliefs and attitudes influence learning-object use among higher education learners by evaluating the relationships between perceived usefulness, perceived ease of use, attitude, behavioural intentions and actual use. In the study, 601 potential learning-object users were presented with an introductory demonstration of learning objects for a Digital Systems course. Following the demonstration and practice, data on user beliefs, attitudes and intention to use learning objects were gathered, while data on actual use of learning objects was collected at the end of the semester. Subjects with prior experience using the learning objects were eliminated from further analysis, resulting in a final sample of 481 users. structural equation modelling was employed to test the hypothesised study model. The analysis showed that both the user beliefs and attitudes have significant positive relationships with behavioural intention and that behavioural intention accurately predicted the actual use of learning objects. The results extend the validity of the TAM into a learning object context and clearly pointed out that it can be used to predict users’ future behaviour.

Real-time facial expression recognitions: A review

With the unambiguous statement on the importance of facial configuration for the judgments of human emotion, facial expression recognition has been the utmost research in affective computing in the recent years. The motive is to empower computer so that it could be adaptive to extracting and classifying various user emotions into the “universal facial expressions” or its subsets. This paper reviews a number of methodological approaches relative to real-time facial expression recognitions systems and proposes further research areas that require more attention towards the successful implementation of a more efficient channel for machine - emotion interaction.

Automatic multiple faces tracking and detection using improved edge detector algorithm

The automatic face tracking and detection has been one of the fastest developing areas due to its wide range of application, security and surveillance application in particular. It has been one of the most interest subjects, which suppose but yet to be wholly explored in various research areas due to various distinctive factors: varying ethnic groups, sizes, orientations, poses, occlusions and lighting conditions. The focus of this paper is to propose an improve algorithm to speed up the face tracking and detection process with the simple and efficient proposed novel edge detector to reject the non-face-likes regions, hence reduce the false detection rate in an automatic face tracking and detection in still images with multiple faces for facial expression system. The correct rates of 95.9% on the Haar face detection and proposed novel edge detector, which is higher 6.1% than the primitive integration of Haar and canny edge detector.

Examining the behavior changes in belief and attitude among smart phone users for mobile learning

Prior empirical studies have articulated that IT adoption and usage were determined by user beliefs and attitudes toward IT. We adopted Technology Acceptance Model’s constructs to conduct a case study across two stages; Introduction and hand-on to examine the changes in users’ beliefs and behavioral intention to use smart phone for learning. This paper reports on a study of 60 potential users on smart phones. The results show that the hand-on session was effective in improving users’ beliefs and intentions to use smart phones for learning.

Performance of invariant feature descriptors with adaptive prediction in occlusion handling

Object tracking in computer vision plays an important role for automating the process of video surveillance and robot navigation. The trajectories of every moving object are analyzed to further interpret the events in a scene. Occlusion problem is always the main challenge that interrupts the tracking trajectory and reduces the tracking performance. Thus, this paper aims to investigate an improved performance of invariant feature descriptors in occlusion handling by using adaptive prediction from Kalman filter. The invariant feature descriptors that are extracted from a tracked object are robust against transformation and partial occlusion. These descriptors are combined with Kalman filter prediction to resolve full occlusion in object tracking. Unlike conventional Kalman filter prediction, the error covariance parameters are auto-tuned based on the changing conditions of the feature descriptors in a tracked object. Experiments are conducted to show the response of invariant feature descriptors during partial and full occlusion. The response rate is contributed as the benchmark for parameters tuning in Kalman filter prediction.

The Effectiveness of Learning Objects as Alternative Pedagogical Tool in Laboratory Engineering Education

This study aims to analyse the effectiveness of learning objects as alternative pedagogical tool in laboratory engineering education. 160 undergraduate students who enrolled in a Digital Systems course were randomly assigned to either a control group or an experimental group. This study utilised pre-test, post-test, postponed-test, and questionnaires as the basis of data collection to measure the effectiveness of learning objects. Before the experiment began, both groups were given pre-test. During the experiment, the students in the control group took a regular course without learning objects while the students in the experiment group took a regular course with learning objects. After 7 weeks of the experiment period, all students were given the post-test followed by distribution of questionnaires to the experiment group. Four weeks after the post-test, both groups were given postponed-tests. The results show that the post-test and postponed-test mean scores of the experiment group students are better than control group students. Further analysis with the three sub-groups (low-achiever, medium-achiever and high-achiever) reveals that the experimental group performed better especially the low-achiever and medium-achiever sub-groups benefited more in increase and retention of knowledge and concept compared to the same sub-groups in the control group.