Abstract: Clustering models are required in many ecological studies and analysis. Clustering and/or classification of sites based on wet deposit loads, of waters based on their quality, of climate regions and habitats are few examples. Design a good clustering model in ecology should take into account several aspects: data analysis, choice of variable to be use in the clustering analysis, choice of classification techniques and evaluation of the classification results by an ecological point of view. Clustering and classification techniques are strongly dependent on the type of data. Techniques having good results for some types of data may have poor results for other ones.
Our main aim is to realize a model for river’s sectors clustering based on biotope characteristics. The model is able to automatic provide the optimum number of classes, their components and the biotope attributes hierarchy. The influence of data standardization on the biotope attributes hierarchy was also analyzed. Our case study was the Vişeu River watershed, a second order tributary of Danube River, localized in the north part of the Romanian territory.

Brief Biography of the Speaker:
Dana Simian received the diploma. in engineering from the University of Sibiu, Romania, the diploma. in Mathematics from the University Babes-Bolyai of Cluj-Napoca, Romania and the Ph.D. from Babes-Bolyai University of Cluj- Napoca, Romania. She graduated many courses in Computer Science. She has a great experience in algorithms and numerical methods for modelling and optimization, and in machine learning. She published 16 books, more than 60 articles and participated in the editorial board of more than 22 scientific publications (proceedings of international conferences).
She organized 8 special sessions within international conferences, 2 international workshops and an international conference on topics related to algorithms and computational techniques in modeling, approximation and optimization. She is member of many international scientific committees. She is reviewer of many scientific publications.