Objetivo
The ESCA project aimed to replicate a specific area of human expertise in chromatography and chemistry by artificial intelligence systems. There were two main areas of research: the formalisation of the knowledge base in this area, and the selection of the most suitable expert system shells and tools to represent this type of knowledge base.
The first work-package was to select a suitable specific area of chromatography application to pharmaceutical analysis, where the knowledge is sufficiently established to provide a valid test of an artificial intelligence system.
The second work-package was to formalise the knowledge of this specific area by a set of logical rules and facts suitable for expression as an expert system.
It was planned to select about eight candidate shells and tool sets and to evaluate their suitability for representing this type of knowledge. The next step was make a selection of three of these candidates for the implementation task.
The application of AI to chemometrics, ie the use of mathematical techniques for setting up experiments and for analysing the results, was to be examined.
The final product was to be a comparison of the performance of these three expert systems (using different characteristics, but with identical knowledge) for real chemical analyses.
The project aimed to replicate a specific area of human expertize in chromatography and chemistry by artificial intelligence systems. There were 2 main areas of research: the formalization of the knowledge base in this area, and the selection of the most suitable expert system shells and tools to represent this type of knowledge base. The first work package was to select a suitable specific area of chromatography application to pharmaceutical analysis, where the knowledge is sufficiently established to provide a valid test of an artificial intelligence system. The second work package was to formalize the knowledge of this specific area by a set of logical rules and facts suitable for expression as an expert system. The application of artificial intelligence (AI) to chemometrics, ie, the use of mathematical techniques for setting up experiments and for analysing the results, was examined. High performance liquid chromatography (HPLC) was chosen as the area of application. Three expert system developement tools were selected from the 8 evaluated. The acquisition of knowledge from each of the application domains, which together cover the entire area of method development in HPLC, was completed. its representation in the form of several expert systems was carried out, and integration into one system (from the chemist's point of view) was achieved.
High Performance Liquid Chromatography (HPLC) was chosen as the area of application. Three expert system development tools were selected from the eight evaluated. The acquisition of knowledge from each of the application domains, which together cover the entire area of method development in HPLC, was completed. Its representation in the form of several expert systems was carried out, and integration into one system (from the chemist's point of view) was achieved.
The presentation of the results at international symposia has increased awareness of the field and heightened debate about the issues involved.
Exploitation
Chromatography is a major analytical tool in pharmaceutical research. However, its use requires the selection of a suitable chromatographic method and the optimisation of parameters for each analysis. At present these actions are dependent on the skills of an expert chromatographer.
The ESCA project aimed to alleviate this situation by developing the application of expert systems to a real-life analytical problem: method development for the analysis of novel compounds in the pharmaceutical industry.
The experience and knowledge gained through the prototypes developed and the comparison studies carried out will accelerate the introduction of expert systems in real-life industrial applications related to chemical domains.
Ámbito científico (EuroSciVoc)
CORDIS clasifica los proyectos con EuroSciVoc, una taxonomía plurilingüe de ámbitos científicos, mediante un proceso semiautomático basado en técnicas de procesamiento del lenguaje natural. Véas: El vocabulario científico europeo..
CORDIS clasifica los proyectos con EuroSciVoc, una taxonomía plurilingüe de ámbitos científicos, mediante un proceso semiautomático basado en técnicas de procesamiento del lenguaje natural. Véas: El vocabulario científico europeo..
- ciencias naturales informática y ciencias de la información inteligencia artificial sistemas expertos
Para utilizar esta función, debe iniciar sesión o registrarse
Programa(s)
Programas de financiación plurianuales que definen las prioridades de la UE en materia de investigación e innovación.
Programas de financiación plurianuales que definen las prioridades de la UE en materia de investigación e innovación.
Tema(s)
Las convocatorias de propuestas se dividen en temas. Un tema define una materia o área específica para la que los solicitantes pueden presentar propuestas. La descripción de un tema comprende su alcance específico y la repercusión prevista del proyecto financiado.
Datos no disponibles
Las convocatorias de propuestas se dividen en temas. Un tema define una materia o área específica para la que los solicitantes pueden presentar propuestas. La descripción de un tema comprende su alcance específico y la repercusión prevista del proyecto financiado.
Convocatoria de propuestas
Procedimiento para invitar a los solicitantes a presentar propuestas de proyectos con el objetivo de obtener financiación de la UE.
Datos no disponibles
Procedimiento para invitar a los solicitantes a presentar propuestas de proyectos con el objetivo de obtener financiación de la UE.
Régimen de financiación
Régimen de financiación (o «Tipo de acción») dentro de un programa con características comunes. Especifica: el alcance de lo que se financia; el porcentaje de reembolso; los criterios específicos de evaluación para optar a la financiación; y el uso de formas simplificadas de costes como los importes a tanto alzado.
Régimen de financiación (o «Tipo de acción») dentro de un programa con características comunes. Especifica: el alcance de lo que se financia; el porcentaje de reembolso; los criterios específicos de evaluación para optar a la financiación; y el uso de formas simplificadas de costes como los importes a tanto alzado.
Datos no disponibles
Coordinador
CB1 2PX CAMBRIDGE
Reino Unido
Los costes totales en que ha incurrido esta organización para participar en el proyecto, incluidos los costes directos e indirectos. Este importe es un subconjunto del presupuesto total del proyecto.