Automatic Knowledge Acquisition from Complex Processes for the Development of Knowledge-Based Systems

R-Roda, Ignasi; Comas, Joaquím; Poch, Manel; Sànchez–Marrè, Miquel; Cortés, Ulises

doi:10.1021/ie000528c

Cited by 13 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once a set of decision trees was generated to diagnose and resolve operational problems in an activated sludge system, a second phase was begun to build a complete EDSS. Among the modules, a case‐based reasoning system and a mechanistic model were developed. The same methodology as that used by Poch et al was followed, and the resulting tool was implemented in a full‐scale facility (Granollers, NE Spain) that treated 35 000 m 3 d −1 .…”

Section: Analysis Of the Developed Edssmentioning

confidence: 99%

Crossing the Death Valley to Transfer Environmental Decision Support Systems to the Water Market

et al. 2017

Self Cite

View full text Add to dashboard Cite

sensors, and the overwhelming evidence of environmental strain and global economic issues caused by the extensive pressure on resources exerted by the demands of growing populations indicate that environmental systems composed of multiple interacting agents or variables that cause emergent behavior require complex manage ment strategies. In addition, improving environment-friendly practices related to the use and/or reuse of natural resources to minimize detrimental effects on the natural environment has become a prominent issue. Therefore, increasingly advanced and sophisticated management tools capable of integrating heuristic knowledge and quantitative and qualitative information are required.The initial concept of a decision support system (DSS) emerged in the business, economics, and management sciences. A DSS is an intelligent information system that reduces the time in which decisions are made within a domain and improves the consistency and quality of these decisions. [1] DSSs use a combination of models, analytical techniques, and information retrieval to help develop and evaluate appropriate alternatives; [2,3] and such systems focus on strategic decisions and not operational ones. More specifically, a DSS should contribute to the reduction of the uncertainty faced by managers when they need to take decisions regarding future options. [4] Similar definitions can be found in ref. [5,6] Environmental decision support systems (EDSSs) are a class of DSS that demonstrates all of the capabilities of a DSS on an environmental field scale. [5,7,8] EDSSs have been increasingly applied in more intense and efficient ways, and an increased number of systems have been developed. A metric of their increasing implementation is that more than 3300 references have been cited on this topic in specialized journals over the last ten years (search on SCOPUS on February 2016).The quality and quantity of available water resources is decreasing because of the intensive use of surface and groundwater by cities, industry and agriculture, and the associated impacts of the point pollution and diffuse discharge of the generated wastewater. [9] The optimal and integrated management of water resources is a paradigmatic example of circumstances in which an EDSS can play an important role by integrating data from different origins and with different quality with infrastructures managed by several public and private actors under different legal frameworks with a final goal of preserving Environmental decision support systems (EDSSs) are attractive tools to cope with the complexity of environmental global challenges. Several thoughtful reviews have analyzed EDSSs to identify the key challenges and best practices for their development. One of the major criticisms is that a wide and generalized use of deployed EDSSs has not been observed. The paper briefly describes and compares four case studies of EDSSs applied to the water domain, where the key aspects involved in the initial conception and the use and transfer evolution that determine...

show abstract

Section: Analysis Of the Developed Edssmentioning

confidence: 99%

Crossing the Death Valley to Transfer Environmental Decision Support Systems to the Water Market

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

Decision Support Systems for Integrated Water Resources Management Under Water Scarcity

Comas

Poch

2009

The Handbook of Environmental Chemistry

Self Cite

View full text Add to dashboard Cite

Environmental decision support systems (EDSS) can be defined as intelligent information systems that are able to integrate numerical models (linear or nonlinear) with artificial intelligence (AI) techniques, together with geographical information and environmental ontologies. EDSS emulate the expert's reasoning processes in decision making, integrating geographical information and environmental ontologies, reducing the time in which decisions are made, as well as improving the consistency and quality of those decisions. EDSS can be useful to cope with the complexity and multidisciplinary nature of Integrated Water Resource Management (IWRM). Besides, the Drought Management Plan Report written by the Water Scarcity and Droughts Expert Network (November 2007) states the "Development of decision support systems for the best exploitation of all information available, including drought forecasts, in order to optimize drought management and mitigation measures" as one of the main needs for advances in drought research. The necessity to confront complexity when dealing with IWRM is first stated in the paper. Then an EDSS as a promising tool to cope with this complexity is introduced, putting special emphasis in a proposal for EDSS development. Next the paper reviews the more relevant decision support systems (DSS) published for IWRM under water scarcity. Classical DSS to model environmental systems as well as those DSS including knowledge-based or AI techniques (i.e., EDSS) are reviewed. Open questions related to the EDSS development and application include improvement of data and knowledge acquisition and knowledge implementation methods, better integration of numerical models and AI techniques (both in simulation and real applications), evaluation of EDSS (lack of benchmarks), protocols to facilitate sharing and reuse of knowledge, involvement of end-users, and probably others.

show abstract

Computational Intelligence Techniques for Supervision and Diagnosis of Biological Wastewater Treatment Systems

Dias

Ferreira

2009

Computational Intelligence Techniques for Bioprocess Modelling, Supervision and Control

View full text Add to dashboard Cite

Automatic Knowledge Acquisition from Complex Processes for the Development of Knowledge-Based Systems

Cited by 13 publications

References 24 publications

Crossing the Death Valley to Transfer Environmental Decision Support Systems to the Water Market

Crossing the Death Valley to Transfer Environmental Decision Support Systems to the Water Market

Decision Support Systems for Integrated Water Resources Management Under Water Scarcity

Computational Intelligence Techniques for Supervision and Diagnosis of Biological Wastewater Treatment Systems

Contact Info

Product

Resources

About