Ion Smeureanu

Intelligent agents and risk based model for supply chain management

Abstract This paper presents a software agent based frameworks architecture for boosting performance in supply chain management applications. The framework is based on agent interaction and semantic web service composition. The purpose of such a platform is to develop flexible business applications for SCM transactions modeling, in collaborative and distributed economic systems. The interaction between agents is limited by a cybernetic model that takes into account several constraints one of the main being bankruptcy risk potential of the peer partner company.

Content Adaptation in Mobile Multimedia System for M-Learning

The goal of the paper is to present an architecture designed for mobile multimedia content adaptation, applied to the newest solutions for instruction and learning, generically named mobile learning or m-learning. The field of research is situated at the intersection of mobile tools and e-learning and the research has as a goal to provide the opportunity to access computer resources from any location and to adapt the multimedia content to the specific features of mobile devices, communication environment, userspsila preferences and userspsila knowledge. The systems developed based on the architecture proposed in this paper will be able to provide powerful facilities for searching and support for instruction effectiveness, for performances evaluation, are time and location independent. The technical solutions proposed follow to use the potential of mobile devices to become important tools in education field.

Modelling Domestic Lighting Energy Consumption in Romania by Integrating Consumers Behavior

Abstract Sustainable energy consumption is a research area of a large interest in last years. New energy-efficient lighting technologies exist, which can significantly reduce household electricity consumption, but their adoption has been slow. A considerable number of international studies show that sustainable development scenarios will be realistic if they involve the human behavior. The paper provides a solution to integrate consumer behavior with techno-economic energy issues, inside a complex energy model. This approach aims to reduce the error, from the demand side of the energy model. Consumer behavior in energy consumption is described by using specific attributes of energy technologies, namely virtual technologies. The GAMS/TIMES/VEDA energy modelling software tool has been used to integrate the techno-economic energy specific data and consumer behavior, in order to achieve the research purposes. A sociological survey about Romanians’ behavior in energy consumption has been conducted and its results have been integrated in the energy based model, in form of virtual technologies. This approach, known as “Social MARKAL”, allows the analyst to evaluate the possible contribution of information campaigns in changing lighting consumers’ behavior and effect of technology switch. The model is developed for the period 2010-2026, and is implemented by using GAMS/TIMES/VEDA software platform. The results presented this paper focuses on the household lighting technologies.

Fractal web service composition framework

By using semantic web service composition, individual web services can be combined to create complex, but easily reconfigurable systems. Such systems can play a vital role in todays changing economic conditions, as they allow business to quickly adapt to market changes. Taking into consideration that manual web service composition is both time-consuming and error prone, the proposed framework uses a semi-automatic approach. The composition is done in a fractal manner as existing web service chains can easily be incorporated in new web service chains.

A MPEG-21 Based Architecture for Data Visualization in Multimedia Web Applications

The development of an open architecture for multimedia data integration and visualization in template based distributed applications is a challenge for the scientific researches. Because of characteristics of multimedia data, their management and querying techniques are unlike than those of traditional data. We can increase the potential use of multimedia data across various applications by storing and managing data using multimedia databases. A standard solution to define the architecture of multimedia systems assures the integration of multimedia web application with the other applications.The goal of the paper is to propose an architecture based on MPEG-21 (moving picture experts group) standard for various multimedia data types integration, managing and visualization into web applications.

Learning Style in Ontology-Based E-Learning System

This paper presents a modality to use learning styles as the main parameter in determining individual differences in an ontology-based personalised e-learning system. The learning style is one of the ways to identify the student’s preferences which, along with other criteria, such as: student’s level of knowledge, learning style, and level of education, skills, requirements and feedback, lead to the adaptive system’s choice of personalised learning materials. This work is meant to emphasize how a personalised e-learning system for the managers of a hospital in Romania, presented in previous research, uses the learning styles in modelling the student’s profile. For this aim ontological components implemented with Protege environment are used. This approach leads to automate the e-learning environment and to develop the student’s own knowledge, the personalised learning, the educational content adapted to the learning styles, respectively to the student’s profile.

Customer segmentation in private banking sector using machine learning techniques

Machine learning techniques have proven good performance in classification matters of all kinds: medical diagnosis, character recognition, credit default and fraud prediction, and also foreign exchange market prognosis. Customer segmentation in private banking sector is an important step for profitable business development, enabling financial institutions to address their products and services to homogeneous classes of customers. This paper approaches two of the most popular machine learning techniques, Neural Networks and Support Vector Machines, and describes how each of these perform in a segmentation process.

Optimizing Residential Energy Consumption in Romania

This paper proposes a modelling approach based on TIMES/VEDA systems, designed to optimize energy system model and connected aspects, like economic development and consumer behaviour, in order to decrease energy consumption in households. The economic and technological factors have been used to set-up the energy model. A case study of Romania’s residential energy consumption model is included.

Semantics-driven multimedia data access

The multim edia data are more present in the actual informatics systems. Because of characteristics of multimedia data, their management and querying techniques are unlike than those of traditional data. We can increase the potential use of multimedia data across various applications by assuring semantics-driven access to multimedia data. In this paper we propose a solution, based on MPEG-21 standard, to describe the multimedia content and to integrate it with the semantic web.