Results 1 -
6 of
6
W.W.: A Methodology and Design Process for System Generated User Interruption based
- on Context, Preferences, and Situation Awareness. Information Reuse and Integration, IEEE International Conference
"... Abstract Over ..."
(Show Context)
Collaborative Integration of Speech and 3D Gesture for Map-based Applications, presented at
- 5th International Gesture Workshop
, 2003
"... Abstract. QuickSet [6] is a multimodal system that gives users the capability to create and control map-based collaborative interactive simulations by supporting the simultaneous input from speech and pen gestures. In this paper, we report on the augmentation of the graphical pen input enabling the ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract. QuickSet [6] is a multimodal system that gives users the capability to create and control map-based collaborative interactive simulations by supporting the simultaneous input from speech and pen gestures. In this paper, we report on the augmentation of the graphical pen input enabling the drawings to be formed by 3D hand movements. While pen and mouse can still be used for ink generation drawing can also occur with natural human pointing. To that extent, we use the hand to define a line in space, and consider its possible intersection point with a virtual paper that needs to be determined by the operator as a limited plane surface in the three dimensional space at the begin of the interaction session. The entire system can be seen as a collaborative body-centered alternative to the traditional mouse-, pen-, or keyboard-based multimodal graphical programs. Its potential applications include battlefield or crisis management, tele-medicine and other types of collaborative decision-making during which users can also be mobile. 1 Introduction & Related Work
Abstract An Exploration of Gesture-based Interaction
"... This thesis presents two related research projects exploring gesture-based interaction. The VisionWand system explores a passive wand tracked in 3D using computer vision techniques as a new input mechanism for interacting with large displays. A variety of gesture-based interaction techniques is desi ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
This thesis presents two related research projects exploring gesture-based interaction. The VisionWand system explores a passive wand tracked in 3D using computer vision techniques as a new input mechanism for interacting with large displays. A variety of gesture-based interaction techniques is designed to exploit the affordances of the wand, resulting in an effective alternative interface for large display interaction. Inspired by the observations made in the VisionWand and similar gesture-based interaction systems that different users have different habits in making gestures and performing tasks, we developed the adaptive gesture interface as a framework that exploits machine learning techniques to capture and utilize the users ’ habits on line. This framework improved the system’s performance of gesture recognition, and alleviated the user’s need for practice. We present a rigorous user experiment to demonstrate this improvement. ii Acknowledgements I wish to thank my supervisors, Allan Jepson and Ravin Balakrishnan for directing and advising me from two different areas – computer vision and human-computer interaction. My
HUAN-CHAO KEH, and
"... Abstract:- The purpose of resource management is based on the limit resource and unknown users which retrieve the resources at any time to increase the resource exploitation rate, flexibility and availability. In this study, we propose four types of strategy including Expansion (when user loads are ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract:- The purpose of resource management is based on the limit resource and unknown users which retrieve the resources at any time to increase the resource exploitation rate, flexibility and availability. In this study, we propose four types of strategy including Expansion (when user loads are large and available resources are not limiting), Constraint (when user loads are large and resources are limiting), Modulation (when user loads are small and excess resources are held), and Supervision (when user loads are small and available resources are also small). The four types of strategy are abbreviated as MSCE. The MSCE strategy of resource management delivers efficient control and management of available resources, allowing for adaptations to changes in the system environment and changes in user requirements. The Monitor agent is responsible for monitoring the resource management system, controlling the rate of resource consumption while simultaneously keeping track of user loads. By employing the Monitor agent in this fashion, the system’s resources have greater availability and their control becomes more flexible and efficient. Key-Words:- Multi-agent; MSCE; Resource Management System 1.
LIBRARIES MUTUAL DISAMBIGUATION OF RECOGNITION ERRORS IN A MULTIMODAL NAVIGATIONAL AGENT
, 2003
"... Recognition-based technology has made substantial advances in the past few years because of enhanced algorithms and faster processing speeds. However, current recognition systems are still not reliable enough to be integrated into user interface designs. A possible solution to this problem is to com ..."
Abstract
- Add to MetaCart
(Show Context)
Recognition-based technology has made substantial advances in the past few years because of enhanced algorithms and faster processing speeds. However, current recognition systems are still not reliable enough to be integrated into user interface designs. A possible solution to this problem is to combine results from existing recognition systems and mutually disambiguate the unreliable sections. In addition, the results of one recognition system can be used to prepare the other recognition system. We experimented with an approach that uses a software agent to integrate off-the-shelf speech and character recognition applications via scripting languages. We describe how a software agent called MARCO, Multimodal Agent for Route Construction, utilizes multiple recognition systems to assist users in giving directions for urban navig ation. Thesis Supervisor: Dr. Henry Lieberman
Intelligent Systems Intelligent Systems Pervasive ICT Applications Intelligent Systems
"... bt.com- com Abstract- One of the main application areas for multi-agent systems technology is enterprise mobilization, wherein the main business process actors are nomadic workers. An agent's autonomy, sociality and intelligence are highly prized features when it comes to supporting those mobil ..."
Abstract
- Add to MetaCart
(Show Context)
bt.com- com Abstract- One of the main application areas for multi-agent systems technology is enterprise mobilization, wherein the main business process actors are nomadic workers. An agent's autonomy, sociality and intelligence are highly prized features when it comes to supporting those mobile workers who are geographically isolated from the main knowledge source (i.e. the corporate hitranet) and are frequently moving from oiie location to another. Based oii experience gained from nvo field trials of applicatioiis (built using for multi-agent systems technology and ruriniiig on lighnveight haridheld devices) that support mobile business processes for telecommunications service provisioning and mairitenance, this paper proposes desirable metrics for any multi-agent systems platform iritended for enterprise mobilisation use. These metrics are then used to compare (I number of existirig multi-agent Systems platforms, and based on the results, this paper idetitijies some areas for improvemerit.
