Inhaltszusammenfassung

The present situation in biological and medical sciences is characterized by the availability of massive amounts of experimental data. This has two main reasons, which are both related to the developments in computer hard- and software. First it is possible to generate massive amounts of data with the help of modern automated laboratory techniques. And second it becomes cheaper and easier to store and retrieve this data. In most cases these databases are used to retrieve experimental data in ...The present situation in biological and medical sciences is characterized by the availability of massive amounts of experimental data. This has two main reasons, which are both related to the developments in computer hard- and software. First it is possible to generate massive amounts of data with the help of modern automated laboratory techniques. And second it becomes cheaper and easier to store and retrieve this data. In most cases these databases are used to retrieve experimental data in a convenient way and to circumvent the consultation of the original literature. But these databases also provide the empirical evidence, which may be the basis for the discovery of new scientific theories. The derivation of theories from experimental data is traditionally a process depending on the experience, skill and intuition of the individual researcher. But even the best expert works under limitations: Humans cannot handle large amount of data, have troubles detecting complex relationships, cannot keep working for a long time and tend to make errors in an unpredictable way. Therefore many efforts have been made to use computational methods in this process. In Artificial Intelligence research Data Mining techniques were developed for the identification of useful and understandable patterns in databases. This review will focus on the application of Knowledge Discovery in Databases (KDD), Data Mining (DM) and Machine Learning (ML) in toxicology. The emphasis will be on methods that are capable of providing new insights and theories.» weiterlesen» einklappen

Autoren

Klassifikation

DFG Fachgebiet:
4.43 - Informatik

DDC Sachgruppe:
Informatik