Algorithms for hierarchical clustering: an overview, <scp>II</scp>

Murtagh, Fionn; Contreras, Pedro

doi:10.1002/widm.1219

Cited by 211 publications

(81 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we propose a new scheme which nds correlations between charge transfer numbers from any given fragmentation, and suggests how these fragments could be combined to form a smaller set of fragments for further consideration. This new scheme consists of three steps: (i) compute the full correlation matrix between all fragments, (ii) perform a hierarchical clustering [121,122] based on the correlation matrix, and (iii) cut the cluster hierarchy at a desired level to learn which fragments could be merged.…”

Section: Correlations Between Charge Transfer Numbersmentioning

confidence: 99%

Quantitative wave function analysis for excited states of transition metal complexes

Mai

Dorn

Fumanal

et al. 2018

Coordination Chemistry Reviews

134

163

View full text Add to dashboard Cite

The character of an electronically excited state is one of the most important descriptors employed to discuss the photophysics and photochemistry of transition metal complexes. In transition metal complexes, the interaction between the metal and the di erent ligands gives rise to a rich variety of excited states, including metal-centered, intra-ligand, metal-to-ligand charge transfer, ligand-to-metal charge transfer, and ligand-to-ligand charge transfer states. Most often, these excited states are identi ed by considering the most important wave function excitation coe cients and inspecting visually the involved orbitals. This procedure is tedious, subjective, and imprecise. Instead, automatic and quantitative techniques for excited-state characterization are desirable. In this contribution we review the concept of charge transfer numbers-as implemented in the TheoDORE package-and show its wide applicability to characterize the excited states of transition metal complexes. Charge transfer numbers are a formal way to analyze an excited state in terms of electron transitions between groups of atoms based only on the well-de ned transition density matrix. Its advantages are many: it can be fully automatized for many excited states, is objective and reproducible, and provides quantitative data useful for the discussion of trends or patterns. We also introduce a formalism for spin-orbit-mixed states and a method for statistical analysis of charge transfer numbers. The potential of this technique is demonstrated for a number of prototypical transition metal complexes containing Ir, Ru, and Re. Topics discussed include orbital delocalization between metal and carbonyl ligands, nonradiative decay through metal-centered states, e ect of spin-orbit couplings on state character, and comparison among results obtained from di erent electronic structure methods.

show abstract

Section: Correlations Between Charge Transfer Numbersmentioning

confidence: 99%

Quantitative wave function analysis for excited states of transition metal complexes

Mai

Dorn

Fumanal

et al. 2018

Coordination Chemistry Reviews

134

163

View full text Add to dashboard Cite

show abstract

“…Agglomerative hierarchical clustering methods have been continually evolving since their origins back in the 1950s, and historically they have been deployed in very diverse application domains, such as geosciences, biosciences, ecology, chemistry, text mining and information retrieval, among others [19]. Nowadays, with the advent of the big data revolution, hierarchical clustering methods have had to address the new challenges brought by more recent application domains that require the hierarchical clustering of thousands of observations [20].…”

Section: Discussionmentioning

confidence: 99%

Versatile Linkage: a Family of Space-Conserving Strategies for Agglomerative Hierarchical Clustering

Fernández

Gómez

2019

J Classif

View full text Add to dashboard Cite

Agglomerative hierarchical clustering can be implemented with several strategies that differ in the way elements of a collection are grouped together to build a hierarchy of clusters. Here we introduce versatile linkage, a new infinite system of agglomerative hierarchical clustering strategies based on generalized means, which go from single linkage to complete linkage, passing through arithmetic average linkage and other clustering methods yet unexplored such as geometric linkage and harmonic linkage.We compare the different clustering strategies in terms of cophenetic correlation, mean absolute error, and also tree balance and space distortion, two new measures proposed to describe hierarchical trees. Unlike the β-flexible clustering system, we show that the versatile linkage family is space-conserving.

show abstract

“…(2) Hierarchical-based algorithms [12,13] construct a cluster tree based on data objects and then seek optimal clustering results by iteratively splitting or aggregating. Hierarchical-based algorithms are simple and efficient, but their executive processes are easily affected, and the terminating condition is difficult to determine.…”

Section: Data Object Clustering Methodsmentioning

confidence: 99%

Automatic Determination of Clustering Centers for “Clustering by Fast Search and Find of Density Peaks”

Min

Huang

Sheng

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Dividing abstract object sets into multiple groups, called clustering, is essential for effective data mining. Clustering can find innate but unknown real-world knowledge that is inaccessible by any other means. Rodriguez and Laio have published a paper about a density-based fast clustering algorithm in Science called CFSFDP. CFSFDP is a highly efficient algorithm that clusters objects by using fast searching of density peaks. But with CFSFDP, the essential second step of finding clustering centers must be done manually. Furthermore, when the amount of data objects increases or a decision graph is complicated, determining clustering centers manually is difficult and time consuming, and clustering accuracy reduces sharply. To solve this problem, this paper proposes an improved clustering algorithm, ACDPC, that is based on data detection, which can automatically determinate clustering centers without manual intervention. First, the algorithm calculates the comprehensive metrics and sorts them based on the CFSFDP method. Second, the distance between the sorted objects is used to judge whether they are the correct clustering centers. Finally, the remaining objects are grouped into clusters. This algorithm can efficiently and automatically determine clustering centers without calculating additional variables. We verified ACDPC using three standard datasets and compared it with other clustering algorithms. The experimental results show that ACDPC is more efficient and robust than alternative methods.

show abstract

Algorithms for hierarchical clustering: an overview, II

Cited by 211 publications

References 70 publications

Quantitative wave function analysis for excited states of transition metal complexes

Quantitative wave function analysis for excited states of transition metal complexes

Versatile Linkage: a Family of Space-Conserving Strategies for Agglomerative Hierarchical Clustering

Automatic Determination of Clustering Centers for “Clustering by Fast Search and Find of Density Peaks”

Contact Info

Product

Resources

About