Browse Proceedings

Pharmaceutical drug design is a long and expensive process. Early selection of promising molecules can dramatically improve this process, but this selection is often similar to searching for a needle in a haystack. In most cases, all that a chemist ...

A rule-based expert system, CTSHIV (Customized Treatment Strategies for HIV) that recommends an individualized treatment strategy for HIV patients is described. Since the HIV virus mutates rapidly, a patient can develop a resistance to particular ...

The objective of the project is to create a neural network that generalizes a doctor's knowledge and predicts the planning target volume in radiotherapy from the 3-dimensional image of a detected tumor. The idea and the first results of predicting the ...

Until now a lot of research has been done on software reuse; the reuse in database environment, however, didn't seem to have received enough attention. From this point of view the goal of the MetaBase project is to show that it is possible to apply ...

Technology is constantly changing. If we want to build a good clinical information system we have to know that within two or three years many applications will be overrun by new methods. Reasons for this can be legislation, new medical standards, new ...

The organisation of information is critical in a society of the future, especially concerning health care. The introduction of a new standard called "Virtual Medical Worlds" provides the potential to organize existing medical information and provide the ...

We present the interval-valued inference structures developed earlier in and the framework in which the comparative studies were made in a medical domain, particularly in the identification of body systems. Performance metrics developed in were used for ...

Decision support systems (DSS) have become increasingly important in medical applications, particularly when important decision must be made effectively and reliably. The best way to design a successful DSS is through the participative design, ...

SPECT is valuable for the evaluation of hepatic function and CT can offer better anatomical images for liver and its adjacent structures. Image registration from the two modalities, CT and SPECT, acquires both structural and functional information, and ...

The paper describes experiments using a new concept in mechatronic robot surgery: that of a robot with a force control handle moved by the surgeon. The surgeon back-drives the robot under servo-assistance, whilst feeling the force from a rotating cutter ...

The paper describes an experimental master-slave system that demonstrates new techniques for controlling a flexible actuator with force feedback to the user in way suitable for palpation. The method has adopted novel sensor and actuator elements that ...

Closed surgical techniques used in the internal fixation of fractures (osteosynthesis) have increased the reliance upon fluoroscopic (X-ray) image guidance, as well as increased the complexity of fracture fixation techniques. Concerns over X-ray ...

We are developing automated-detection and analysis schemes of mammographic masses. The purpose of this study is to improve our previous schemes on the mass detection and analysis. In our detection scheme, pectoralis muscles area is firstly extracted. ...

The purpose of this study is to apply a genetic-algorithm (GA) template-matching method to detect lung nodules in chest helical x-ray CT (computed tomography) images. We combined GA and template matching to search the positions of nodules and to ...

We have developed a computerized scheme to detect nodular shadows in chest radiography by a genetic algorithm (GA) and artificial neural networks (ANN). The scheme is based on a conventional image recognition method of template matching. The GA ...

Robots are finding increasing use in surgery as a means of releasing the surgeon from hazard and fatigue and also in enhancing the safety and comfort of the patient. This is particularly true of Minimal Access Surgery (MAS), which includes thoraoscopy (...

This paper reports on the successful application of novel learning, classification and feature extraction techniques to the stapedotomy surgical procedure. The goal was the on-line estimation of the stapes bone thickness from force and torque data ...

In this paper a computational architecture to model human emotions is described and developed. In previous work of brain modeling there has been significant effort to model the brain's analytical and learning capabilities. However, modeling feelings has ...

We describe an approach to developing an adaptive virtual environment user interface to enable the user to perform a wide variety of tasks while immersed in the virtual environment. Currently, virtual environment operation places an unmanageable ...

Based on human model simulation, an estimation method for basic human error probability (HEP) parameters is presented, for probability safety assessment/human reliability assessment (PSA/HRA) in nuclear power plant NPP. A framework of HEP parameters ...

Knowledge discovery in databases (KDD) offers a methodology for developing tools to extract meaningful knowledge from large volumes of data. We propose a generalized KDD model for supervised training. A main step in this process, data mining, involves ...

In order to be useful, a learning algorithm must be able to generalize well when faced with inputs not previously presented to the system. A bias is necessary for any generalization, and as shown by several researchers in recent years, no bias can lead ...

It is argued that the world representation by symbolic metaphysics and knowledge representation by symbolic logic are two different strategies in AI. Fundamental knowledge of elements and causes of reality, being ontologically and logically prior to ...

The control information along a decision route that leads to the creation of a design solution is often referred to as design plan. Knowledge-based design systems frequently use precompiled design plans to control and schedule design activities. It is, ...

Intelligent task performing machines need to be able to benefit from experience and continue to improve its own task performance capabilities progressively. Towards that end, a machine capable of learning needs to be able to abstract bodies of complex ...

In this paper, we introduce a dynamic backpropagation algorithm for continuous-time dynamic neural fuzzy systems, as a generalization of the standard backpropagation algorithm for feed-forward neural network systems. The proposed algorithm is applied to ...