inicioir al DIIbuscar
setting up and managing real-world data mining case studies in

Establishing and managing a real-world data mining case study in any domain, in particular in today's industries, is not a trivial task. With the rapid development of tools and software systems to automatically monitor, collect and warehouse large amounts of industrial data, industrial processes are going through an evolving paradigm. This change of paradigm is so fast that even management/optimization of some of the industrial processes and complex systems that were valid only 5-10 years ago may no longer be fully acceptable or sufficient for today's financial management. Consequently, the ability to identify the key elements related to modern system operation and monitoring (where best performances are the subject of study) have rapidly changed. This has a direct influence on setting up and managing a real-world data mining case study. Many issues are related to the availability of today's data, three of which are: (i) data types and their volume, (ii) data complexity and the need for integration, and (iii) the effect of internet and on-line data streams. Today's knowledge discovery from data can be classified in several ways: (i) data mining on engineered systems (e.g. complex equipment) or systems designed by nature (e.g. life sciences), (ii) explanatory or predictive data mining, (iii) data mining from static data (e.g. data warehouse) or dynamic data (e.g. data streams), (iv) user operated or automated data mining. There could still be other ways to classify data mining applications. It has been said that the superabundance of today's data and the associated information may have created a scarcity of attention. In this talk we provide several examples where we demonstrate how small or large amounts of industrial data, when understood from a real-world data mining point of view and the required data is properly integrated can result in novel knowledge discovery case studies. We also demonstrate how these case studies can lead to real world applications and even tools that could be deployed for better management of today's industrial operations. Examples given in this talk are: (i) optimization of industrial processes such as electrochemical milling and (ii) operation and management of complex equipment. These examples can be further exploited into several opportunities for today's industrial applications. We also share our experiences in developing real-world data mining case studies.