Nowadays, an increasing number of sensors are becoming embedded in the everyday objects or in the... more Nowadays, an increasing number of sensors are becoming embedded in the everyday objects or in the environment at a low cost. Accordingly, our living environments are populated by an increasing number of artefacts, i.e., objects enhanced with sensing, computation and networking abilities. In addition, people are increasingly using mobile devices as intermediaries between themselves and the artefacts. As a result
Ubiquitous computing (UbiComp) applications operate within an extremely dynamic and heterogeneous... more Ubiquitous computing (UbiComp) applications operate within an extremely dynamic and heterogeneous environment. Thus context definition, representation, management and use become important factors that affect their operation. UbiComp applications have to dynamically adapt to changes in their environment as a result of users' or other actors' activities. To ease the development of such applications it is necessary to decouple application composition from context acquisition and representation, and at the same time provide universal models and mechanisms to manage context. This paper presents experiences with using an ontology to represent context of operation together with decision making for UbiComp applications that result from the composition of functionally independent components. These components were embedded in everyday objects, hence (a) their services were affected by their physical properties, (b) their context of operation was defined by the existence / availability...
The ability of predicting a student's performance is very important in university-level dista... more The ability of predicting a student's performance is very important in university-level distance learning environments. The scope of the research reported here is to investigate the efficiency of machine learning techniques in such an environment. To this end, a number of experiments have been conducted using five representative learning algorithms, which were trained using data sets provided by the "informatics"
Financial decision support system development usually involves a number of recognizable steps: da... more Financial decision support system development usually involves a number of recognizable steps: data preparation – cleaning, selecting, making data suitable for the predictor; prediction algorithm development and tuning – for performance on the quality of interest and evaluation – to see if indeed the system performs on unseen data. But since financial prediction is very difficult, extra insights are needed. This work is twofold aiming to provide data enhancing techniques, performance improvements, evaluation hints and pitfalls to avoid as well as to exploit them by using a prototype tool that can automate the financial decision support process.
This work proposes the integration of computer-aided instruction systems in the curricula of medi... more This work proposes the integration of computer-aided instruction systems in the curricula of medical education, and describes an intelligent tutoring system used for teaching Dermatology. The Dermatology Tutor uses a self-organized society of autonomous software agents which have different capabilities or roles. The society contains tutor, medical and information agents which participate in the tutoring process and collaborate through deliberation in order to achieve a tutoring task. The agents are built according to a BDI architecture, which implements the mental attitudes of beliefs (B), desires (D) and intentions (I). Each medical agent is a specialist in a medical field, while a tutoring agent, which implements a widely accepted dermatology teaching process, coordinates the overall operation of the system. Depending on the subject that is to be taught during any session, the tutoring agent forms teams of medical agents, which in turn use search agents to retrieve information. Although the presented multi-agent architecture is dedicated to teaching dermatology (since the tutor agent is specialized in Dermatology), it can be extended to other domains also with the incorporation of other tutor agents.
Every Intelligent Tutoring System (ITS), in order to justify the term ‘intelligent’, has to conta... more Every Intelligent Tutoring System (ITS), in order to justify the term ‘intelligent’, has to contain the specific knowledge of the taught subject as well as to embed several modules with those mechanisms that are able to handle the knowledge in an intelligent way (e.g., using rules of thumb, tricks etc.) and, in general, behave in a way that would be considered intelligent if observed by a human. Such modules are apparently necessary in ITS generators too. In this paper, the Hybrid Methodology Tutor (HMeT) is presented. HMeT is a hybrid expert system that is embedded in an ITS generator and supports the description of the structure and dynamics of the procedural knowledge, during authoring; it is also responsible for its presentation during tutoring. HMeT was designed and implemented to replace an earlier version (MeT ‐ Methodology Tutor), in order to provide for higher inferential capabilities, better user interface and more user friendliness in authoring as well as in tutoring. HMeT functions like an expert system shell for knowledge base generation, provides graphical user interfaces and prototyping facilities for fast application development and uses frames for representing the subject that will be taught and rules for inference.
Nowadays, an increasing number of sensors are becoming embedded in the everyday objects or in the... more Nowadays, an increasing number of sensors are becoming embedded in the everyday objects or in the environment at a low cost. Accordingly, our living environments are populated by an increasing number of artefacts, i.e., objects enhanced with sensing, computation and networking abilities. In addition, people are increasingly using mobile devices as intermediaries between themselves and the artefacts. As a result
Ubiquitous computing (UbiComp) applications operate within an extremely dynamic and heterogeneous... more Ubiquitous computing (UbiComp) applications operate within an extremely dynamic and heterogeneous environment. Thus context definition, representation, management and use become important factors that affect their operation. UbiComp applications have to dynamically adapt to changes in their environment as a result of users' or other actors' activities. To ease the development of such applications it is necessary to decouple application composition from context acquisition and representation, and at the same time provide universal models and mechanisms to manage context. This paper presents experiences with using an ontology to represent context of operation together with decision making for UbiComp applications that result from the composition of functionally independent components. These components were embedded in everyday objects, hence (a) their services were affected by their physical properties, (b) their context of operation was defined by the existence / availability...
The ability of predicting a student's performance is very important in university-level dista... more The ability of predicting a student's performance is very important in university-level distance learning environments. The scope of the research reported here is to investigate the efficiency of machine learning techniques in such an environment. To this end, a number of experiments have been conducted using five representative learning algorithms, which were trained using data sets provided by the "informatics"
Financial decision support system development usually involves a number of recognizable steps: da... more Financial decision support system development usually involves a number of recognizable steps: data preparation – cleaning, selecting, making data suitable for the predictor; prediction algorithm development and tuning – for performance on the quality of interest and evaluation – to see if indeed the system performs on unseen data. But since financial prediction is very difficult, extra insights are needed. This work is twofold aiming to provide data enhancing techniques, performance improvements, evaluation hints and pitfalls to avoid as well as to exploit them by using a prototype tool that can automate the financial decision support process.
This work proposes the integration of computer-aided instruction systems in the curricula of medi... more This work proposes the integration of computer-aided instruction systems in the curricula of medical education, and describes an intelligent tutoring system used for teaching Dermatology. The Dermatology Tutor uses a self-organized society of autonomous software agents which have different capabilities or roles. The society contains tutor, medical and information agents which participate in the tutoring process and collaborate through deliberation in order to achieve a tutoring task. The agents are built according to a BDI architecture, which implements the mental attitudes of beliefs (B), desires (D) and intentions (I). Each medical agent is a specialist in a medical field, while a tutoring agent, which implements a widely accepted dermatology teaching process, coordinates the overall operation of the system. Depending on the subject that is to be taught during any session, the tutoring agent forms teams of medical agents, which in turn use search agents to retrieve information. Although the presented multi-agent architecture is dedicated to teaching dermatology (since the tutor agent is specialized in Dermatology), it can be extended to other domains also with the incorporation of other tutor agents.
Every Intelligent Tutoring System (ITS), in order to justify the term ‘intelligent’, has to conta... more Every Intelligent Tutoring System (ITS), in order to justify the term ‘intelligent’, has to contain the specific knowledge of the taught subject as well as to embed several modules with those mechanisms that are able to handle the knowledge in an intelligent way (e.g., using rules of thumb, tricks etc.) and, in general, behave in a way that would be considered intelligent if observed by a human. Such modules are apparently necessary in ITS generators too. In this paper, the Hybrid Methodology Tutor (HMeT) is presented. HMeT is a hybrid expert system that is embedded in an ITS generator and supports the description of the structure and dynamics of the procedural knowledge, during authoring; it is also responsible for its presentation during tutoring. HMeT was designed and implemented to replace an earlier version (MeT ‐ Methodology Tutor), in order to provide for higher inferential capabilities, better user interface and more user friendliness in authoring as well as in tutoring. HMeT functions like an expert system shell for knowledge base generation, provides graphical user interfaces and prototyping facilities for fast application development and uses frames for representing the subject that will be taught and rules for inference.
Uploads
Papers