Ioan Dumitrache

Medicine expert system dynamic Bayesian Network and ontology based

The paper proposes an application framework to be used for medicine assisted diagnosis based on ontology and Bayesian Network (DBNO). There are two goals: (1) to separate the domain knowledge from the probabilistic information and (2) to create an intuitive user interface. The framework architecture has three layers: knowledge, uncertainty model and user interface. The contributions of the domain experts are decoupled, the ontology builder will create the domain concepts and relationships focusing on the domain knowledge only. The uncertainty model is Bayesian Network and the probabilities of the variables states are stored in a profile repository. The diagnostician will use the user interface feeded with the domain ontology and one uncertainty profile. The application was tested on a sample medicine model for the diagnose of heart disease.

Robot Localization Implemented with Enzymatic Numerical P Systems

Membrane computing is an interdisciplinary research field focused on new computational models, also known as P systems, inspired by the compartmental model of the cell and the membrane transport mechanisms. Numerical P systems are a type of P systems introduced by Gh. Păun in 2006 for possible applications in economics. Recently, an extension of numerical P systems, enzymatic numerical P systems, has been defined in the context of robot control. This paper presents a new approach to modeling and implementing autonomous mobile robot behaviors and proposes a new odometry module implemented with enzymatic numerical P systems for robot localization. The advantages of modeling robot behaviors with enzymatic membrane controllers and the experimental results obtained on real and simulated robots are also discussed.

On the power of enzymatic numerical P systems

We study the computing power of a class of numerical P systems introduced in the framework of autonomous robot control, namely enzymatic numerical P systems. Three ways of using the evolution programs are investigated: sequential, all-parallel and one-parallel (with the same variable used in all programs or in only one, respectively); moreover, both deterministic and non-deterministic systems are considered. The Turing universality of some of the obtained classes of numerical P systems is proved (for polynomials with the smallest possible degree, one, also introducing a new proof technique in this area, namely starting the universality proof from the characterization of computable sets of numbers by means of register machines). The power of many other classes remains to be investigated.

Expert system for medicine diagnosis using software agents

In order to simplify the information exchange within the medical diagnosis process, a collaborative software agents framework is presented.The human body systems (e.g. respiratory, cardiovascular) are embedded into distinct software agents.The automated information exchange between different medicine specialists from different areas of expertise.The framework has three key components: knowledge management, uncertainty reasoning and software agents. In order to simplify the information exchange within the medical diagnosis process, a collaborative software agents framework is presented. The human body systems (e.g. respiratory, cardiovascular) are embedded into distinct software agents. The holistic perspective is given by the all connected agents exchanging information. The purpose of the framework is to allow the automated information exchange between different medicine specialists. The key factor of the exchange is sharing concepts between the areas of expertise. Each human body system expert will act over his concepts (evidences, causes, effects), however the information from other systems will be assimilated as well. The framework has three key components: knowledge management, uncertainty reasoning and software agents. The ontology is chosen to address the management of human body systems knowledge. The Bayesian Network is the graphical model for probabilistic knowledge representation and reasoning about partial beliefs under uncertainty. The software agents, as collaboration framework, are in charge of the belief propagation between system instances.

Supervisory control and data acquisition for virtual enterprise

The new manufacturing paradigms, such as agile manufacture and lean production, are leading industrial countries towards the new generation of concurrent enterprises involving virtual enterprise architecture and concurrent engineering extended methodology. Continuing adaptation to the market can only be achieved efficiently if the planning and control processes are both optimized horizontally (Automatic Control Systems) and vertically (Management Control Systems). The desired improvement in performance and the realization of global enterprise objectives require a tight integration of the units of the enterprise. The close monitoring of the operational performance of various plants, manufacturing shop-floors/cells/machines, as well as their associated instrumentation and control is of increasing strategic importance. Failures can lead to increased costs and reduced product quality, consistency and production, and to plant shutdowns and increased environmental impact. There is a real need for advanced monitoring technologies to be applied, and their potential demonstrated, on complex industrial plants. The planning and scheduling of manufacturing systems integrated into virtual enterprise architectures requires the implementation of new General Master Production Planning and Scheduling techniques and Supervisory Control and Data Acquisition (SCADA) functions. This paper discusses some key issues on the SCADA-oriented open system for virtual enterprise architecture.

Intelligent agent-based control systems in manufacturing

The paper presents a real-time supervisory control architecture for large-scale manufacturing systems. The architecture is based on autonomous intelligent agents at the shop-floor level, organized in dynamical, reconfigurable structures depending on the manufacturing systems state and goals. The supervisory level is introduced in order to evaluate and improve the performances of the control architecture. Functioning of the whole architecture is event-driven and based on rules that the supervisor should be capable of completing. The formal support for performance evaluation and control policies synthesis is DES.

Universality of Enzymatic Numerical P systems

This paper provides the proof that Enzymatic Numerical P systems with deterministic, but parallel, execution model are universal, even when the production functions used are polynomials of degree 1. This extends previous known results and provides the optimal case in terms of polynomial degree.

The Intelligent Manufacturing Paradigm in Knowledge Society

The today society has to face great challenges due, ironically, to its own development capacity and speed, that resulted in phenomena like globalization and competition, in a more and more rapidly changing environment. The development of Information & Communication Technologies (ICT), which was intent to solve usual problems, became actually a driver for the increased complexity of socioeconomical advance. In this context, especially in manufacturing, the role of human resources was, for the last century, ambiguous, with balances between the trends that relied mostly on technology and those that trusted human superiority. Actually, it is the role of knowledge management, as a relatively new discipline, to find a way by which humans and technology could optimally collaborate, towards the benefits and satisfaction of whole society. This work intends to propose some functioning principles for knowledge management architectures, where human and software agents could coexist and share knowledge, in order to solve new problems. The authors have taken into account researches in the fields of manufacturing system, as well as from the area of knowledge management, control systems, organizational research and complexity analysis, in order to develop a model for the imbricate development of manufacturing and knowledge. The first part presents the evolution of manufacturing paradigm, underlining the parallel development of ICT and knowledge management. The second one focuses on the paradigm of Intelligent Manufacturing and presents some of the developed control approaches based on complexity theory and multi-agent systems. The following part presents some developments in the field of the knowledge management and the last ones introduce the authors view on the subject. Finally, some future trends towards a knowledge society where humans and software agents will symbiotically work through their mutual progress and satisfaction are suggested. 4

From Mass Production to Intelligent Cyber-Enterprise

The paper proposes a new paradigm for the enterprise of the future, with respect to the requirements and the constraints it will be forced to face in order to progress and evolve. It is a paradigm which will take into account not only the complex relations between enterprise components - human, material and informational, but also the integration enterprise-society will all its aspects. There are presented some of the main trends in the control and management of manufacturing systems, in order to enlighten the evolution of the concepts towards that of Cyber-Physical Systems, which is the core of the proposed paradigm. A generic model of the next generation of Manufacturing Systems will be introduced, based on the paradigm of Intelligent Cyber-Enterprise.

Knowledge Management Based Supply Chain in Learning Organization

Abstract The rapid increasing global systems complexity within the Knowledge Based Economy, the driver for the new coming Knowledge Society, provides “great challenges” to be undertaken within the innovative thinking in diversity. The authors goal within the present paper is to conceptualize the skills formation using a Knowledge Society paradigm approach to ensure efficient synchronization between the Adaptive Virtual Organization and Knowledge Management concepts by identifying a set of common activities performed with the aim of assisting the Adaptive Virtual Organization in meeting the going demand for knowledge of todays global economy. Therefore the need for implementing a Learning Organization concept as to offer the needed support within the Enterprise Information System Supply Chain Management becomes a great necessity.