Abstract: The paper presents an on-line recognition machine
(RM) for continuous/isolated, dynamic and static gestures that arise
in Flight Deck Officer (FDO) training. RM is based on generic pattern
recognition framework. Gestures are represented as templates using
summary statistics. The proposed recognition algorithm exploits temporal
and spatial characteristics of gestures via dynamic programming
and Markovian process. The algorithm predicts corresponding index
of incremental input data in the templates in an on-line mode.
Accumulated consistency in the sequence of prediction provides a
similarity measurement (Score) between input data and the templates.
The algorithm provides an intuitive mechanism for automatic detection
of start/end frames of continuous gestures. In the present paper,
we consider isolated gestures. The performance of RM is evaluated
using four datasets - artificial (W TTest), hand motion (Yang) and
FDO (tracker, vision-based ). RM achieves comparable results which
are in agreement with other on-line and off-line algorithms such as
hidden Markov model (HMM) and dynamic time warping (DTW).
The proposed algorithm has the additional advantage of providing
timely feedback for training purposes.
Abstract: Virtual environments are a hot topic in academia and more importantly in courses offered via distance education. Today-s gaming generation view virtual worlds as strong social and interactive mediums for communicating and socializing. And while institutions of higher education are challenged with increasing enrollment while balancing budget cuts, offering effective courses via distance education become a valid option. Educators can utilize virtual worlds to offer students an enhanced learning environment which has the power to alleviate feelings of isolation through the promotion of communication, interaction, collaboration, teamwork, feedback, engagement and constructivists learning activities. This paper focuses on the use of virtual environments to facilitate interaction in distance education courses so as to produce positive learning outcomes for students. Furthermore, the instructional strategies were reviewed and discussed for use in virtual worlds to enhance learning within a social context.
Abstract: This paper presents a solution for the behavioural
animation of autonomous virtual agent navigation in virtual environments.
We focus on using Dempster-Shafer-s Theory of Evidence
in developing visual sensor for virtual agent. The role of the visual
sensor is to capture the information about the virtual environment
or identifie which part of an obstacle can be seen from the position
of the virtual agent. This information is require for vitual agent to
coordinate navigation in virtual environment. The virual agent uses
fuzzy controller as a navigation system and Fuzzy α - level for
the action selection method. The result clearly demonstrates the path
produced is reasonably smooth even though there is some sharp turn
and also still not diverted too far from the potential shortest path.
This had indicated the benefit of our method, where more reliable
and accurate paths produced during navigation task.
Abstract: This paper examines ethical and social issues which
have proved important when initiating and creating educational spaces within a virtual environment. It focuses on one project, identifying the key decisions made, the barriers to new practice
encountered and the impact these had on the project. It demonstrates
the importance of the 'backstage' ethical and social issues involved in
the creation of a virtual education community and offers conclusions,
and questions, which will inform future research and practice in this
area. These ethical issues are considered using Knobel-s framework
of front-end, in-process and back-end concerns, and include
establishing social practices for the islands, allocating access rights,
considering personal safety and supporting researchers appropriately
within this context.
Abstract: While computers are known to facilitate lower levels of learning, such as rote memorization of facts, measurable through electronically administered and graded multiple-choice questions, yes/no, and true/false answers, the imparting and measurement of higher-level cognitive skills is more vexing. These require more open-ended delivery and answers, and may be more problematic in an entirely virtual environment, notwithstanding the advances in technologies such as wikis, blogs, discussion boards, etc. As with the integration of all technology, merit is based more on the instructional design of the course than on the technology employed in, and of, itself. With this in mind, this study examined the perceptions of online students in an introductory Computer Information Systems course regarding the fostering of various higher-order thinking and team-building skills as a result of the activities, resources and technologies (ART) used in the course.
Abstract: This paper presents a solution for the behavioural animation of autonomous virtual agent navigation in virtual environments. We focus on using Dempster-Shafer-s Theory of Evidence in developing visual sensor for virtual agent. The role of the visual sensor is to capture the information about the virtual environment or identifie which part of an obstacle can be seen from the position of the virtual agent. This information is require for vitual agent to coordinate navigation in virtual environment. The virual agent uses fuzzy controller as a navigation system and Fuzzy α - level for the action selection method. The result clearly demonstrates the path produced is reasonably smooth even though there is some sharp turn and also still not diverted too far from the potential shortest path. This had indicated the benefit of our method, where more reliable and accurate paths produced during navigation task.
Abstract: The paper presents an on-line recognition machine
(RM) for continuous/isolated, dynamic and static gestures that arise
in Flight Deck Officer (FDO) training. RM is based on generic pattern
recognition framework. Gestures are represented as templates using
summary statistics. The proposed recognition algorithm exploits temporal
and spatial characteristics of gestures via dynamic programming
and Markovian process. The algorithm predicts corresponding index
of incremental input data in the templates in an on-line mode.
Accumulated consistency in the sequence of prediction provides a
similarity measurement (Score) between input data and the templates.
The algorithm provides an intuitive mechanism for automatic detection
of start/end frames of continuous gestures. In the present paper,
we consider isolated gestures. The performance of RM is evaluated
using four datasets - artificial (W TTest), hand motion (Yang) and
FDO (tracker, vision-based ). RM achieves comparable results which
are in agreement with other on-line and off-line algorithms such as
hidden Markov model (HMM) and dynamic time warping (DTW).
The proposed algorithm has the additional advantage of providing
timely feedback for training purposes.