J
James C. Bezdek
Researcher at University of Melbourne
Publications - 401
Citations - 57266
James C. Bezdek is an academic researcher from University of Melbourne. The author has contributed to research in topics: Cluster analysis & Fuzzy logic. The author has an hindex of 86, co-authored 400 publications receiving 53852 citations. Previous affiliations of James C. Bezdek include University of Florida & Becton Dickinson.
Papers
More filters
Journal ArticleDOI
Cluster tendency assessment in neuronal spike data.
TL;DR: The results show that t-Distributed Stochastic Neighbor Embedding (t-SNE) provides representations of the data that yield more accurate visualization of potential cluster structure to inform the clustering stage, and it is shown that noise associated with recording extracellular neuronal potentials can disrupt computational clustering schemes, highlighting the benefit of probabilistic clustering models.
Journal ArticleDOI
Evaluating Evolving Structure in Streaming Data With Modified Dunn's Indices
TL;DR: This paper presents online versions of two modified generalized Dunn's indices that can be used for the dynamic evaluation of an evolving (cluster) structure in streaming data and compares the only comparable approach to the incremental Xie-Beni and Davies-Boudin indices.
Book ChapterDOI
Smart sampling: a novel unsupervised boosting approach for outlier detection
TL;DR: This paper proposes a novel boosting algorithm for outlier detection called BSS, where it sequentially improves the accuracy of each ensemble detector in an unsupervised manner and discusses the effectiveness of the approach in terms of bias-variance trade-off.
Proceedings ArticleDOI
Cluster validity for kernel fuzzy clustering
TL;DR: Existing cluster validity indices that can be directly applied to partitions obtained by kernel fuzzy clustering algorithms are described and four propositions that allow other existing clusters validity indices to be adapted to kernel fuzzy partitions are presented.
Proceedings ArticleDOI
Comparison of scalable fuzzy clustering methods
TL;DR: Four scalable variants of FCM are compared to the base algorithm and it is shown that the scalable algorithms are consistent with regard to speedup, but less consistent when quality is considered.