About
100
Publications
3,187
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
352
Citations
Additional affiliations
May 2012 - December 2016
November 1994 - December 2016
January 1994 - January 1999
Publications
Publications (100)
This carefully edited and reviewed volume addresses the increasingly popular demand for seeking more clarity in the data that we are immersed in. It offers excellent examples of the intelligent ubiquitous computation, as well as recent advances in systems engineering and informatics. The content represents state-of-the-art foundations for researche...
In this paper we present feature selection in biological data by combining unsupervised learning with supervised cross validation. Unsupervised clustering methods are used to perform a clustering of object-data for a chosen subset of input features and given number of clusters. The resulting object clusters are compared with the predefined original...
In this chapter we present a novel method for scoring function specification and feature selection by combining unsupervised learning with supervised cross validation. Various clustering algorithms such as one dimensional Kohonen SOM, k-means, fuzzy c-means and hierarchical clustering procedures are used to perform a clustering of object-data for a...
In this chapter we present results of empirical research work done on the data based identification of estimation models for tumor markers and cancer diagnoses: Based on patients’ data records including standard blood parameters, tumor markers, and information about the diagnosis of tumors we have trained mathematical models that represent virtual...
This book offers an excellent presentation of intelligent engineering and informatics foundations for researchers in this field as well as many examples with industrial application. It contains extended versions of selected papers presented at the inaugural ACASE 2012 Conference dedicated to the Applications of Systems Engineering. This conference...
In this paper we present a novel method for scoring function specification and feature selection by combining unsupervised learning with supervised cross validation. Unsupervised clustering methods (k-means, one dimensional Kohonen SOM, fuzzy c-means) are used to perform a clustering of object-data for a chosen subset of input features and given nu...
In this paper we describe the identification of variable interaction networks in a medical data set. The main goal is to generate mathematical models for standard blood parameters as well as tumor markers using other available parameters in this data set. For each variable we identify those variables that are most relevant for modeling it; relevanc...
In this article, we describe the use of tumour marker estimation models in the prediction of tumour diagnoses. In previous works, we have identified classification models for tumour markers that can be used for estimating tumour marker values on the basis of standard blood parameters. These virtual tumour markers are now used in combination with st...
Background / Purpose:
As measuring tumor markers is often expensive, we have applied several data based approaches for identifying mathematical models for estimating selected tumor markers on the basis of routinely available blood values; estimators for the tumor markers AFP, CA-125, CA15-3, CEA, CYFRA, and PSA have been identified.
Main conclus...
In this paper we report on the use of evolutionary algorithms for optimizing the identification of classification models for selected tumor markers. Our goal is to identify mathematical models that can be used for classifying tumor marker values as normal or as elevated; evolutionary algorithms are used for optimizing the parameters for learning cl...
In this paper we present results of empirical research work done on the data based identification of estimation models for cancer diagnoses: Based on patients' data records including standard blood parameters, tumor markers, and information about the diagnosis of tumors we have trained mathematical models for estimating cancer diagnoses. Several da...
The paper presents the analysis of two different approaches for a system to support cancer diagnosis. The first one uses only tumor marker data containig missing values to predict cancer occurrence and the second one also includes standard blood parameters. Both systems are based on several heterogeneous artificial neural networks for estimating mi...
The paper presents a heterogeneous neural network based system that can be used for estimation of missing tumor marker values in patient data and in a second step for calculating the possibility of a cancerous disease. For estimation of missing values we use different approaches: neural network based estimation of a specific marker depending on exi...
In this paper we describe the use of evolutionary algorithms for the selection of relevant features in the context of tumor marker modeling. Our aim is to identify mathematical models for classifying tumor marker values AFP and CA 15-3 using available patient parameters; data provided by the General Hospital Linz are used. The use of evolutionary a...
Tumor markers are substances that are found in blood, urine, or body tissues and that are used as indicators for tumors; elevated tumor marker values can indicate the presence of cancer, but there can also be other causes. We have used a medical database compiled at the blood laboratory of the General Hospital Linz, Austria: Several blood values of...
In this paper a system for the prediction of tumor marker values based on standard blood is presented. Several neural networks are used to learn from blood examination measurements and predict tumor markers in case these values are missing. In a post processing step the predicted values are evaluated in a fuzzy logic like style against different hy...
The paper presents methods that allow an intelligent multiagent system to coordinate and negotiate their actions in order to achieve a common goal.
Workflows are used nowadays in different areas of application. Emergency services are one of these areas where explicitly
defined workflows help to increase traceability, control, efficiency, and quality of rescue missions. In this paper, we introduce
a generic workflow model for describing fire fighting operations in different scenarios. Based on...
The design of intelligent and sensor-based autonomous agents learning by themselves to perform complex real-world tasks is
a still-open challenge for artificial and computational intelligence. In this paper a concept of a framework for conflict
resolution in an autonomous robotic agent system is presented. The structure of an intelligent robotic ag...
This paper presents a concept for a Decision Support System for Therapy Planning based on the Q-Learning method. It focuses the consideration on a multilevel approach for constructing a data driven evidence based system for classification of different drug dosages and their effectiveness for clinical trials. We consider time - ordered sequences of...
Proceedings - 2009 1st International Workshop on Near Field Communication, NFC 2009. Hagenberg, Austria, 24 Feb. 2009, vii
This paper presents an approach for a Q-learning based decision support system for therapy planning. It focuses the consideration on a multilevel approach for constructing a data driven evidence based model for classification of different drug dosages and their effectiveness for clinical trials. We consider time-ordered sequences of patient data (c...
In heterogeneous system design, partitioning of the functional specifications into hardware (HW) and software (SW) components is an important procedure. Often, an HW platform is chosen, and the SW is mapped onto the existing partial solution, or the actual partitioning is performed in an ad hoc manner. The partitioning approach presented is novel i...
The paper presents a method that allows an intelligent multiagent system to coordinate and negotiate their actions in order
to achieve a common goal. Each individual agent consists of several autonomous components that allow the agent to perceive
and react to its environment, to plan and execute an action, and to negotiate with other agents in an i...
In this paper, we presented an application of neural network-based models in the intelligent agent domain. The use of neural networks has the advantage that the model can adapt itself to changing environment conditions by simple retraining steps. This is illustrated by two functions needed for the lifelong learning-based modeling of an intelligent...
The data-driven decision support tool built around the SAS technology has been developed to support the evaluation and monitoring of the quality of educational process. The tool forms an integrated framework that can be used for managing of teaching and learning processes and for performing comparative studies in the participating institutions. The...
This paper discusses similarities of computer support in three areas: development of software, supporting the flow of work/documents in an office and the production of goods in a flexible work cell. All three areas obey the same underlying principle, i.e. defining a process and then interpreting the process by an enactment (interpretation) mechanis...
With the development of new computing paradigms, such as neural networks and genetic algorithms, new tools have become available in computer-aided systems theory. These tools can be used to tackle problems that are considered hard in traditional systems theory, like the modeling and identification of nonlinear dynamical systems.
We present a genera...
This paper presents an approach for a multilevel knowledge base system for evidence-based medicine. A sequence of events called patient trial is extracted from computer patient records. These events describe one flow of therapy for a concrete disease. Each event is represented by state and time. We introduce a measure between states, which is used...
This paper presents a system-theoretical approach for an intelligent multiagent system which is used to control and coordinate
a society of robotic agents acting independently in a partially known environment. We focus our presentation on only one aspect
of the coordination of the robotic agent group, namely on the conflict management. We present s...
Intelligent agents are a new paradigm for developing complex
system applications. Agent systems are based on autonomous
software-hardware components (technical agents) that cooperate within an
environment to perform some task. An agent can be viewed as a
self-contained, concurrently executing thread of control that
encapsulates some states and comm...
The paper presents a methodology and methods that allows a robotic
system comprised of intelligent robotic agents to coordinate and
negotiate their actions in order to achieve common goals. Each
individual robotic agent consists of several autonomous components of
its control system that allow the agent to perceive and react to its
environment, to...
Within the last years the paradigm of intelligent software agents became an emerging topic in computer science research and
development. Intelligent software agents are computational systems that populate complex dynamic environment, act and react
there in an autonomous way in order realize a specific task based on a set of goals given to them. In...
Many multimedia applications will be designed to run on
heterogeneous computing environments or will be interconnected to offer
multimedia services. However multimedia incorporation proves
insufficient for training and education system implementation. Its a
main issue that students or training participants not only conduct and
record but also have...
A framework for the design of a model-based control system for flexible manufacturing is presented in this paper. The system consists of three basic layers: the Task Planning, the Task-Level Programming, and the Simulation layer. Task planning is based on the description of operations and their precedence relation. The resulting fundamental plan de...
We present the concept of an intelligent robotic agent that
displays both learning-based and reactive capabilities. The
learning-based components of the agent enable it to build up action
strategies over its lifetime in a real world environment. Due to its
complexity and dynamically changing nature, it is impossible to gather
full knowledge about t...
In this paper we present a method and a tool for modelling a teletraining session in heterogenous, distributed open environments. We propose a mathematical notion for the training process. Therefore we divide a whole training session into presentation units, define some relations on these units and develop a controller for running the session. Unit...
The paper presents the system Telesession Designer and Transmitter for computer supported creation of interactive multimedia telepresentations of training session and the event based control system for telepresentation execution in an open and distributed environment. We propose a way of unifying these different objects into one standardized format...
The paper presents the system "Telesession Designer and Transmitter" for computer supported creation of interactive multimedia tele presentations of training session and the event based control system for tele presentation execution in an open and distributed environment. We propose a way of unifying these different objects into one standardized fo...
Neural network approaches to calculating robot kinematics have been studied intensely in the past. Most of them were concerned with learning robot kinematics by feedforward networks with sigmoidal units, and offered only approximate solutions to the kinematics problem. In this paper, we present a method that circumvents this limitation by using a p...
This paper gives the concept of an autonomous robotic agent that is capable of showing both machine learning and reactive behavior. The first methodology is used to collect information about the environment and to plan robot actions based on this information while the robot is performing tasks. Processing and storing information obtained during sev...
This paper presents the concept of an autonomous robotic agent
combining reactive and machine learning-based algorithms. The focus is
on the machine learning-based part that we implement by neural networks.
A method for reducing the environment state space to a smaller
conceptual world space is given. We then show how the concept of
“lifelong learn...
An application of neural network-based techniques to model and
control a robot arm equipped with revolute joints is presented. The use
of symbolic means for neural models synthesis is shown. The steps of the
calibration process and the way of using the calibrated model in a
typical computed torque controller are described. The performance of the
co...
In this work, we present our view of an intelligent robotic
manipulator that can work autonomously in a dynamically changing
environment. The increased intelligence is needed to enable the
manipulator to react to changing environments without contacting a
supervising coordinator. This approach requires increased computational
capabilities on the pa...
The purpose of a flexible manufacturing system (FMS) is to perform
a series of well defined operations on a family of similar pads. The
operations (e.g. milling or drilling) are realized by machines which are
serviced by robots. A cell controller coordinates the flow of parts
through the cell. Monitoring, i.e., to watch the system behavior during
i...
This paper describes a realized concept for designing and automatic programming of flexible workcells based on intelligent tools. A design tool, a task planning tool, a process planning tool and different simulation tools are integrated in the Intelligent Control of Autonomous Robotic System (ICARS). In this system design, programming, execution an...
The modeling of nonlinear dynamical systems is one of the emergent
application areas of artificial neural networks. In this paper, we
present a general methodology based on neural networks and genetic
algorithms that can be applied to modeling of nonlinear dynamical
systems. We describe a general methodology for modeling nonlinear
systems with know...
The flexible and economic production of goods requires a new level
of automation. Workcells integrating manufacturing stations and robots,
form the basis of a flexible manufacturing process. The manufacturing
process to be performed in such a cell also needs definition. A
prerequisite is an adequate process definition environment which uses
compute...
The design techniques discussed here are concerned with computer
integrated, cellular manufacturing systems. Such systems consist of
automated robotic cells. Planning and control within a cell is carried
out in off- and on-line modes by a hierarchical controller. A
workstation and its control modules are called computer assisted
workcell (CAW). An...
A comprehensive framework for design of an intelligent cell-controller requires integration of several layers of support methods and tools. We have proposed an architecture that facilitates an automatic generation of different plans of sequencing operations, synthesis of action plan for robots servicing the devices, synthesis of the workcell's simu...
A new method of optimal cost trajectory planning based on a graph searching algorithm is presented. Various heuristic functions which play the key role in the construction of effective algorithms for solving such problems are proposed. Some numerical examples are given based on the kinematic and dynamic models of a IRb-6 ASEA robot. This method roo...
First Page of the Article
This paper presents a framework for the design of a hierarchical Simulator of a robotized sequential technological process. The framework employs concepts of discrerte event simulation modelling. The Simulator consists of two layers: the Simulator of a robot and technological process, and the interpreter and planner of robot tasks. A format specifi...
A framework is proposed for support of design, task planning, and
simulation of automated manufacturing systems. The framework establishes
a hierarchy of method banks essential for improving the efficiency and
cost effectiveness of manufacturing processes. The methods should
support automatic generation of sequencing rules, design and
configuration...
A comprehensive framework for generating a robot's program for an automated production system will require an integration of several layers of system theory-based support methods and tools. Each layer of the robot's program synthesis system requires different CAST tools. The tools for each level are:Level 1
:graph search methods
Level 2
:Petri net...
A framework is being developed for simulation-based design of flexible manufacturing systems. The framework integrates generation of assembly plans, design and configuration of the manufacturing facility and equipment, synthesis of task-oriented robot programs, and simulation of a manufacturing system. Each layer is briefly summarized, and a simula...
A description is given of a system of robot action and motion
planning, called task planner, that would transform task-level
specification into manipulator-level specification. The output of the
task planner would be a robot motion program to achieve the desired fine
state of task when executed in the specified initial state. The program
is compose...
A mathematical model is presented of kinematics of a redundant
planar manipulator that is able to determine the next configuration on
the basis of the preceding one and the required shift of the
end-effector. The new configuration is synthesized by the following
scheme: synthesis of a hypothetical configuration, verification of its
technical realiz...
The paper present a model of the kinematics of a rotary, redundant manipulator, in the form of a Finite State Machine, this is in fact, an example of AI production systems. This model is able to supply us with succesive configurations, calculated immediately in Cartesian space and allowing at the same time to considerably simplify the computations...
In the paper we present system-theoretic descriptions of the robot's kinematics models, in a discrete and discretized workspace. For those descriptions, the problem of planning collision-free trajectories of motion is stated and represented as a classical problem of optimizing the behaviour of dynamical system.
The notion of decomposable finite sequential system in the category of semigroups is introduced. The paper deals with the reducibility, controllability and p-definiteness properties. It is shown that many statements concerning the linear systems preserve their validity for the systems considered in this paper. For example it is proved that, under c...
The paper deals with the synthesis problem for tree automata. A sequential synthesis algorithm is presented based on the hypothesis formulation-verification-modification scheme.
The problem of decomposition of a dynamical system is of great interest in system theory. It is known that decomposition methods enable one to find many various structural realizations of a given dynamical system. Such a situation makes it impossible to perform efficient structural identification. So the main task of this paper is to establish some...
The problem of decomposition of dynamical system is of great interest in system theory. The paper considers various decomposition methods for systems called finite homomorphic sequential systems. We determine conditions under which a decomposition into certain connections of group systems is possible. We also determine properties of connections com...
A special class of eventistic systems is considered in the paper. Problems of their modeling, decomposition and synthesis are presented. Theorems concerning direct and indirect computer simulation of decomposed eventistic systems have been given.
Some ideas by M. D. Mesarovic concerning a state-space representation for general time systems (and for general dynamical systems) are developed. The state space construction is presented. It uses the aggregation of state objects by the Cartesian product operation. The state space obtained in such a way is compared with the state space constructed...
It is assumed that an eventistic system and a goals space are given as independent entities. An interconnection between them is expressed by the relation of realization of conditions. For every goal from the set of goals a filter representing conditions of the goal achievement is defined. A goal-oriented eventistic system has a set of trajectories...
Therapy modeling and planning are important components for optimal and cost-effective patient care. Therapeutic response of the individual patient not only relies on the selection of effective drugs but is also heavily influenced by appropriate drug dosage. A variety of intelligent techniques have been initiated to support physicians in deciding an...
A multiagent robotic system consists of a group of autono-mous agents on the first -lower -level of its hierarchy, and the contract and conflict management agents on the second -upper -level of the hierarchy. The contract man-agement agent considers task distribution when a new job enters the system. It has to direct autonomous agents by specifying...