A new estimator of intrinsic dimension based on the multipoint Morisita index
作者：
Highlights：
• A new estimator of intrinsic dimension is suggested.
• Comparisons with commonly used estimators of intrinsic dimension are conducted.
• The suggested estimator turns out to be robust to sample size and noise.
• The suggested estimator is able to handle large datasets.
• The suggested estimator is computationally efficient.
摘要
Highlights•A new estimator of intrinsic dimension is suggested.•Comparisons with commonly used estimators of intrinsic dimension are conducted.•The suggested estimator turns out to be robust to sample size and noise.•The suggested estimator is able to handle large datasets.•The suggested estimator is computationally efficient.
论文关键词：Intrinsic dimension,Multipoint Morisita index,Fractal dimension,Multifractality,Dimensionality reduction
论文评审过程：Received 8 August 2014, Revised 20 May 2015, Accepted 20 June 2015, Available online 2 July 2015, Version of Record 19 August 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.06.010
