Surgical planning as a treatment for vascular diseases re- quires fast blood ow simulations that are eÆcient in handling changing geometry. It is, for example, necessary to try diþerent paths of a planned by...
详细信息
Multilayer perceptions (MLP) or feed forward neural networks (FFNN) are generally used to represent many-to-one (m-o) mappings or functions from ℜn to codomain ℜm. Input units distribute real values to hidden layer un...
详细信息
ISBN:
(纸本)0889863474
Multilayer perceptions (MLP) or feed forward neural networks (FFNN) are generally used to represent many-to-one (m-o) mappings or functions from ℜn to codomain ℜm. Input units distribute real values to hidden layer units and individual output units produce values in ℜ Thus MLP's represent or simulate the mappings of functions where the range consists of vectors. However it is also useful to represent mappings where the range consists of elements that are sets or collections (bags) of vectors of real values. Representing mappings from vectors to sets of real numbers or vectors of real numbers has a useful application that is of interest since a one-to-many (o-m) mapping from ℜn to codomain ℜ m is equivalent to a m-o mapping from ℜn to codomain P(ℜm) where P(ℜm) is the power set of ℜ m. The paper describes a modified training algorithm that successfully stores a one-to-many mapping on a feed-forward network requiring a relatively small number of training epochs.
Reducing packet loss and increasing overall efficiency in multiple source queuing systems is one of the most important issues in the design of traffic control algorithms. On the other hand, the other important issue i...
详细信息
Reducing packet loss and increasing overall efficiency in multiple source queuing systems is one of the most important issues in the design of traffic control algorithms. On the other hand, the other important issue in such systems is to provide every individual source with the ability to take advantage of a fair portion of the shared available resources such as buffer space or server bandwidth. In this paper a novel technique for reducing packet loss in a class of queuing systems with self-similar traffic patterns is introduced. The technique takes advantage of the modeling power of neural networks to offer a dynamic buffer management scheme capable of efficiently addressing the trade off between packet loss and fairness issues.
Computational Grids are emerging as a new infrastructure for Internet-based parallel and distributed computing. They enable the sharing, exchange, discovery, and aggregation of resources distributed across multiple ad...
详细信息
Computational Grids are emerging as a new infrastructure for Internet-based parallel and distributed computing. They enable the sharing, exchange, discovery, and aggregation of resources distributed across multiple administrative domains, organizations and enterprises. To accomplish this, Grids need infrastructure that supports various services: security, uniform access, resource management, scheduling, application composition, computational economy, and accounting. Although several initiatives are engaged in the development of Grid technologies, Grid accounting issues are yet to be addressed. To overcome this limitation, we propose a new infrastructure called GridBank that provides services for accounting. The support of computational economy and accounting services can lead to a self-regulated accountability in Grid computing. This paper presents requirements of Grid accounting and different economic models within which it can operate and proposes a Grid Accounting Services Architecture to meet them. The paper highlights implementation issues with a detailed discussion on the format for various records/databases that the GridBank needs to maintain. It also presents protocols for interaction between the GridBank and various components within Grid computing environments.
Haptic technology has great potentials in many applications. This paper introduces our work on delivery haptic information via the Web. A multimodal tool has been developed to allow blind people to create virtual grap...
详细信息
Haptic technology has great potentials in many applications. This paper introduces our work on delivery haptic information via the Web. A multimodal tool has been developed to allow blind people to create virtual graphs independently. Multimodal interactions in the process of graph creation and exploration are provided by using a low-cost haptic device, the Logitech WingMan Force Feedback Mouse, and Web audio. The Web-based tool also provides blind people with the convenience of receiving information at home. In this paper, we present the development of the tool and evaluation results. Discussions on the issues related to the design of similar Web-based haptic applications are also given.
This paper introduces the development of a multimodal data visualisation system and its evaluations. This system is designed to improve blind and visually impaired people’s access to graphs and tables. Force feedback...
This paper introduces the development of a multimodal data visualisation system and its evaluations. This system is designed to improve blind and visually impaired people’s access to graphs and tables. Force feedback, synthesized speech and non-speech audio are utilised to present graphical data to blind people. Through the combination of haptic and audio representations, users can explore virtual graphs rendered by a computer. Various types of graphs and tables have been implemented, and a three-stage evaluation has been conducted. The experimental results have proven the usability of the system and the benefits of the multimodal approach. The paper presents the details of the development and experimental findings, as well as the changes of role of haptics in the evaluation.
In this paper, a cooperative sweeping strategy with deadlock avoidance of complete coverage path planning for multiple cleaning robots in a changing and unstructured environment is proposed, using biologically inspire...
详细信息
In this paper, a cooperative sweeping strategy with deadlock avoidance of complete coverage path planning for multiple cleaning robots in a changing and unstructured environment is proposed, using biologically inspired neural networks. Cleaning tasks require a special kind of trajectory being able to cover every unoccupied area in specified cleaning environments, which is an essential issue for cleaning robots and many other robotic applications. Multiple robots can improve the work capacity, share the cleaning tasks, and reduce the time to complete sweeping tasks. In the proposed model, the dynamics of each neuron in the topologically organized neural network is characterized by a shunting neural equation. Each cleaning robot treats the other robots as moving obstacles. The robot path is autonomously generated from the dynamic activity landscape of the neural network, the previous robot location and the other robot locations. The proposed model algorithm is computationally efficient. The feasibility is validated by simulation studies on three cases of two cooperating cleaning robots. The multiple cleaning robots sweeping will not be trapped in deadlock situations.
This paper presents an information system for Chinese Information Extraction from Financial news (CHIEF). The ultimate target of the system is to extract information concerning the occurrence time and places of the fi...
详细信息
This paper presents an information system for Chinese Information Extraction from Financial news (CHIEF). The ultimate target of the system is to extract information concerning the occurrence time and places of the financial activities in the different companies from a local Hong Kong newspaper, namely (Tao Kung Pao). To facilitate event extraction purpose, two groups of templates were defined, i.e. the company related and company restructuring templates. They are used to select the desired information for each type of financial activities, such as (bankruptcy) or (merge). Each specific event is then represented using a frame-based knowledge structure. Two types of slots are embedded in each frame: they are the activity- and time-related slots. Based on these slots, multiple activities are interconnected according to their entity relations, temporal relations or the deduced relations. Effectively, CHIEF is a question-answering system designed for handling the company related queries, event based queries, temporal queries and complex queries in a finance domain.
Research attempting to merge human and mechanical systems through a nervous system is one of the most dynamic fields in interface technology. Recently, artificial cochlear and retinal nerves were connected via a nervo...
详细信息
Research attempting to merge human and mechanical systems through a nervous system is one of the most dynamic fields in interface technology. Recently, artificial cochlear and retinal nerves were connected via a nervous system. However, there has been no report concerning the replacement of human tactile sensation by artificial sensors connected to the tactile sensory nerve system. The present study reports the development of a system which enables the touch strength applied to a robot hand to be sensed and applied to the hand of a human operator via the microstimulation method. The operator controls the grasping action of a robot hand equipped with tactile sensors at a remote location via a network. The contact information between an object and the robot hand is transmitted via the network, and the tactile sensory nerve of the operator is stimulated by a microelectrode. The force applied to the robot hand can be sensed as an applied force to the hand of the human operator. Applications of the proposed system include the presentation of tactile perception in remote manipulation. In addition, the proposed system is an effective method for transmitting sensation from artificial limbs. The present paper describes the experimental system and results.
暂无评论