Towards Understanding Clustering Problems and Algorithms: An Instance Space Analysis

نویسندگان

چکیده

Various criteria and algorithms can be used for clustering, leading to very distinct outcomes potential biases towards datasets with certain structures. More generally, the selection of most effective algorithm applied a given dataset, based on its characteristics, is problem that has been largely studied in field meta-learning. Recent advances form new methodology known as Instance Space Analysis provide an opportunity extend such meta-analyses gain greater visual insights relationship between datasets’ characteristics performance different algorithms. The aim this study perform first time clustering problems As result, we are able analyze impact choice test instances employed, strengths weaknesses some popular algorithms,

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Memory and Space: Towards an Understanding of the Cognitive Map.

UNLABELLED More than 50 years of research have led to the general agreement that the hippocampus contributes to memory, but there has been a major schism among theories of hippocampal function over this time. Some researchers argue that the hippocampus plays a broad role in episodic and declarative memory, whereas others argue for a specific role in the creation of spatial cognitive maps and na...

متن کامل

A New Approach in Strategy Formulation using Clustering Algorithm: An Instance in a Service Company

The ever severe dynamic competitive environment has led to increasing complexity of strategic decision making in giant organizations. Strategy formulation is one of basic processes in achieving long range goals. Since, in ordinary methods considering all factors and their significance in accomplishing individual goals are almost impossible. Here, a new approach based on clustering method is pro...

متن کامل

Cross-Instance Tuning of Unsupervised Document Clustering Algorithms

In unsupervised learning, where no training takes place, one simply hopes that the unsupervised learner will work well on any unlabeled test collection. However, when the variability in the data is large, such hope may be unrealistic; a tuning of the unsupervised algorithm may then be necessary in order to perform well on new test collections. In this paper, we show how to perform such a tuning...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Algorithms

سال: 2021

ISSN: ['1999-4893']

DOI: https://doi.org/10.3390/a14030095