English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Diatoms are ideal bio-indicators of water ecosystem health and can be classified into one of the trophic state indexes (TSI) according to the nutrient level. Thus, the diatoms can be used to indicate the relationship between the organisms and the environmental parameters. In order to find the correct diatom- indicator connection, we can use a certain classification algorithm directly from measure data. This process of diatom classification can be significantly improved using information technology, especially data mining tools. In this direction, this paper work present several classification models with the novel method called aggregation trees based on evenly sigmoid shaped membership function (MF). Earlier, numerous statistical approaches have been used for this purpose, which provide very useful data inside information, but they are limited to interpretation. Further improvement is made by using decision trees, which increases interpretability, but remains not resistant to over fitting and robustness on data change. The proposed method in this paper synthesizes these advantages, in terms of interpretability, resistance of over-fitting and high classification accuracy compared with classical classification algorithms. This is confirmed by the experimental evaluation. Based on these evaluation results, one model for each TSI is presented and discussed. From ecological point of view, the described method improves the water quality and sustaining bio diversity understandings of this ecosystem. The method added new ecological knowledge about the ecological indicators for certain diatoms, which have been recently discovered

Classifying diatoms into trophic state index classes with novel classification algorithm