Comparison of hierarchical cluster analysis techniques for automatic classification of chemical structures

1981 ◽  
Vol 21 (4) ◽  
pp. 204-209 ◽  
Author(s):  
George W. Adamson ◽  
David Bawden
Keyword(s):  
Cluster Analysis ◽  
Hierarchical Cluster Analysis ◽  
Hierarchical Cluster ◽  
Automatic Classification ◽  
Analysis Techniques ◽  
Chemical Structures

Unsupervised and hierarchical cluster analysis and classification of SAR images

1993 ◽  
Author(s):  
Yiu-fai Wong ◽  
Kenneth J. Peters ◽  
Edward C. Poser
Keyword(s):  
Cluster Analysis ◽  
Hierarchical Cluster Analysis ◽  
Hierarchical Cluster ◽  
Sar Images

scholarly journals Classification of Red Wines Produced from Zweigelt and Rondo Grape Varieties Based on the Analysis of Phenolic Compounds by UPLC-PDA-MS/MS

Molecules ◽  
2020 ◽  
Vol 25 (6) ◽  
pp. 1342 ◽  
Author(s):  
Anna Stój ◽  
Ireneusz Kapusta ◽  
Dorota Domagała
Keyword(s):  
Cluster Analysis ◽  
Phenolic Compounds ◽  
Vitis Vinifera ◽  
Hierarchical Cluster Analysis ◽  
Hierarchical Cluster ◽  
Malolactic Fermentation ◽  
Red Wines ◽  
Grape Variety ◽  
Grape Varieties

The authentication of grape variety from which wine is produced is necessary for protecting a consumer from adulteration and false labelling. The aim of this study was to analyze phenolic compounds in red monovarietal wines produced from Zweigelt (Vitis vinifera) and Rondo (non-Vitis vinifera) varieties while using the UPLC-PDA-MS/MS method and to assess whether these wines can be classified according to grape variety that is based on chemometric analysis. Fifty-five phenolic compounds belonging to five classes—anthocyanins, flavonols, flavan-3-ols, phenolic acids, and stilbenes—were identified and quantified in Zweigelt and Rondo wines. The wines of the Zweigelt variety were characterized by lower concentrations of phenolic compounds than those of the Rondo variety. Furthermore, wines of the Zweigelt variety contained the highest concentrations of flavan-3-ols, and wines of the Rondo variety—the highest concentrations of anthocyanins. Hierarchical cluster analysis (HCA) revealed that Zweigelt wines and Rondo wines formed two separate groups. The Rondo group was divided into two subgroups, differing in type of malolactic fermentation (spontaneous or induced). Phenolic compounds analysis by means of UPLC-PDA-MS/MS combined with HCA is a useful tool for the classification of red wines that were produced from Zweigelt and Rondo grape varieties, regardless of yeast strain and type of malolactic fermentation.

scholarly journals Peripheral areas and their distinctive characteristics: The case of Hungary

2021 ◽  
Vol 29 (3) ◽  
pp. 217-230
Author(s):  
János Pénzes ◽  
Gábor Demeter
Keyword(s):  
Cluster Analysis ◽  
Hierarchical Cluster Analysis ◽  
Hierarchical Cluster ◽  
Multivariate Statistical Methods ◽  
Multivariate Statistical ◽  
Development Policies ◽  
Relevant Variables ◽  
Peripheral Areas

Abstract The delimitation and classification of peripheral settlements using multivariate statistical methods is presented in this article, with a case study of Hungary. A combination of four different methods provided the basis for the delimitation of settlements defined as peripheral. As significant overlapping was detected between the results of the different methods, peripheries – more than one-fifth of the Hungarian settlements – were identified in a common set of the results. The independence of the results from the applied methods points to the fact that peripherisation is multi-faceted, and the peripheries of Hungary are stable and well-discernible from other regions. After the identification of peripheral areas, we classified these settlements into groups based on their specific features. Multiple steps specifying the relevant variables resulted in selecting the most appropriate 10 indicators and these served as the basis for a hierarchical cluster analysis, through which 7 clusters (types of peripheries) were identified. Five of them comprised enough cases to detect the most important dimensions and specific features of the backwardness of these groups. These clusters demonstrated a spatial pattern and their socioeconomic and infrastructural features highlighted considerable disparities. These differences should be taken into consideration when development policies are applied at regional levels or below.

scholarly journals Real-time analysis and classification of bioaerosols based on optical scattering properties

2017 ◽  
Vol 66 (1) ◽  
pp. 27-40
Author(s):  
Miron Kaliszewski ◽  
Elżbieta Anna Trafny ◽  
Maksymilian Włodarski ◽  
Rafał Lewandowski ◽  
Małgorzata Stępińska ◽  
...  
Keyword(s):  
Cluster Analysis ◽  
Particle Size ◽  
Hierarchical Cluster Analysis ◽  
Hierarchical Cluster ◽  
Biological Origin ◽  
Size And Shape ◽  
Real Time Analysis ◽  
Asymmetry Data ◽  
Warfare Agents

The size and shape of biological particles are important parameters allowing discrimination between various species. We have studied several aerosols of biological origin such as pollens, bacterial spores and vegetative bacteria. All of them presented different morphology. Using optical size and shape analyser we found good correlation between light scattering properties and actual particle features determined by scanning electron and fluorescence microscopy. In this study, we demonstrated that HCA (Hierarchical Cluster Analysis) offers fast and continuous bioaerosol classification based on shape and size data matrices of aerosols. The HCA gives an unequivocal interpretation of particle size vs. asymmetry data. Therefore, it may provide high throughput and reliable screening and classification of bioaerosols using scattering characteristics. Keywords: bioaerosol classification, scattering, particle size and shape analysis, biological warfare agents’ detection, hierarchical cluster analysis (HCA)

scholarly journals Classification of primary angle closure spectrum with hierarchical cluster analysis

PLoS ONE ◽  
2018 ◽  
Vol 13 (7) ◽  
pp. e0199157 ◽  
Author(s):  
Sasan Moghimi ◽  
Ali Torkashvand ◽  
Massood Mohammadi ◽  
Mehdi Yaseri ◽  
Luke J. Saunders ◽  
...  
Keyword(s):  
Cluster Analysis ◽  
Hierarchical Cluster Analysis ◽  
Hierarchical Cluster ◽  
Angle Closure ◽  
Primary Angle Closure
Sign in / Sign up

Export Citation Format

Share Document