scholarly journals EXTENSIONS TO THE K-AMH ALGORITHM FOR NUMERICAL CLUSTERING

2018 ◽  
Vol 17 (4) ◽  
Author(s):  
Ali Seman ◽  
Azizian Mohd Sapawi
Keyword(s):  
Numerical Clustering

scholarly journals Analysis of the Effect of Conditions of Preparation of Nitrogen-Doped Activated Carbons Derived from Lotus Leaves by Activation with Sodium Amide on the Formation of Their Porous Structure

Materials ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 1540
Author(s):  
Mirosław Kwiatkowski ◽  
Xin Hu
Keyword(s):  
Porous Structure ◽  
Activated Carbons ◽  
Structure Parameters ◽  
Mass Ratio ◽  
Nitrogen Doped ◽  
Adsorption Analysis ◽  
Lotus Leaves ◽  
The Impact ◽  
Sodium Amide ◽  
Numerical Clustering

This paper presents results of the analysis of the impact of activation temperature and mass ratio of activator to carbonized precursor R on the porous structure of nitrogen-doped activated carbons derived from lotus leaves by carbonization and chemical activation with sodium amide NaNH2. The analyses were carried out via the new numerical clustering-based adsorption analysis (LBET) method applied to nitrogen adsorption isotherms at −195.8 °C. On the basis of the results obtained it was shown that the amount of activator, as compared to activation temperatures, has a significantly greater influence on the formation of the porous structure of activated carbons. As shown in the study, the optimum values of the porous structure parameters are obtained for a mass ratio of R = 2. At a mass ratio of R = 3, a significant decrease in the values of the porous structure parameters was observed, indicating uncontrolled wall firing between adjacent micropores. The conducted analyses confirmed the validity of the new numerical clustering-based adsorption analysis (LBET) method, as it turned out that nitrogen-doped activated carbons prepared from lotus leaves are characterized by a high share of micropores and a significant degree of surface heterogeneity in most of the samples studied, which may, to some extent, undermine the reliability of the results obtained using classical methods of structure analysis that assume only a homogeneous pore structure.

Relationships within the genus Myoxocephalus (Pisces: Cottidae) based on morphological and biochemical data using numerical and conventional methods of analyses

1972 ◽  
Vol 50 (5) ◽  
pp. 671-682 ◽  
Author(s):  
Garry I. McT. Cowan
Keyword(s):  
Analytical Techniques ◽  
Morphological Data ◽  
Biochemical Data ◽  
Numerical Treatment ◽  
Malic Dehydrogenase ◽  
Systematic Relationships ◽  
Conventional Methods ◽  
Numerical Clustering

Systematic relationships within the cottid genus Myoxocephalus are derived, based on morphological and biochemical (muscle myogen, lactic and malic dehydrogenase electropherograms) characteristics. The effects of numerical and conventional taxonomic analyses on the relationships derived from both sources of data are investigated.Comparison of numerical clustering of morphological and biochemical data indicates that the relationships are not comparable. However if the data are combined, the relationships obtained are similar to those based solely on morphological information.Conventional analyses of 45 morphological and 35 biochemical characters yielded similar patterns of relationship. The biochemical ones are, however, notably more conservative and simplified. The two treatments of morphological data and the numerical treatment of combined morphological and biochemical data indicate very similar relationships. However the numerical treatment of biochemical data resulted in completely different affinities.It is nevertheless possible to conclude that where evidence is available from a wide variety of systems within the organism, the two analytical techniques yield similar results. Also the inclusion of a limited amount of biochemical data should not be expected to result in greatly improved or altered systematic conclusions.

scholarly journals EXTENSIONS TO THE K-AMH ALGORITHM FOR NUMERICAL CLUSTERING

2018 ◽  
Author(s):  
Ali Seman ◽  
Azizian Mohd Sapawi
Keyword(s):  
Real World ◽  
Confidence Level ◽  
Categorical Data ◽  
Euclidean Distance ◽  
P Value ◽  
Accuracy Score ◽  
Original Algorithm ◽  
Real World Datasets ◽  
The Cost ◽  
Numerical Clustering

The k-AMH algorithm has been proven efficient in clustering categorical datasets. It can also be used to cluster numerical values with minimum modification to the original algorithm. In this paper, we present two algorithms that extend the k-AMH algorithm to the clustering of numerical values. The original k-AMH algorithm for categorical values uses a simple matching dissimilarity measure, but for numerical values it uses Euclidean distance. The first extension to the k-AMH algorithm, denoted k-AMH Numeric I, enables it to cluster numerical values in a fashion similar to k-AMH for categorical data. The second extension, k-AMH Numeric II, adopts the cost function of the fuzzy k-Means algorithm together with Euclidean distance, and has demonstrated performance similar to that of k-AMH Numeric I. The clustering performance of the two algorithms was evaluated on six real-world datasets against a benchmark algorithm, the fuzzy k-Means algorithm. The results obtained indicate that the two algorithms are as efficient as the fuzzy k-Means algorithm when clustering numerical values. Further, on an ANOVA test, k-AMH Numeric I obtained the highest accuracy score of 0.69 for the six datasets combined with p-value less than 0.01, indicating a 95% confidence level. The experimental results prove that the k-AMH Numeric I and k-AMH Numeric II algorithms can be effectively used for numerical clustering. The significance of this study lies in that the k-AMH numeric algorithms have been demonstrated as potential solutions for clustering numerical objects.  

Conformational analysis from crystallographic data using conceptual clustering

1996 ◽  
Vol 52 (3) ◽  
pp. 535-549 ◽  
Author(s):  
D. Conklin ◽  
S. Fortier ◽  
J. I. Glasgow ◽  
F. H. Allen
Keyword(s):  
Conformational Analysis ◽  
A Priori ◽  
Knowledge Bases ◽  
Conceptual Clustering ◽  
Clustering Methods ◽  
Molecular Conformations ◽  
Crystallographic Databases ◽  
New Concepts ◽  
Molecular Databases ◽  
Numerical Clustering

The rapid growth of crystallographic databases has created a demand for novel and efficient techniques for the analysis of molecular conformations, in order to derive new concepts and rules and to generate useful classifications of the available data. This paper presents a conceptual clustering approach, termed IMEM (image memory), which discovers the conformational diversity present in a dataset of crystal structures. In contrast to numerical clustering methods, IMEM views a molecular structure as comprising qualitative relationships among its parts, i.e. the structure is viewed as a molecular scene. In addition, IMEM does not require the user to have any a priori knowledge of an expected number of conformational classes within a given dataset. The IMEM approach is applied to several datasets derived from the Cambridge Structural Database and, in all cases, chemically correct and sensible conformational classifications were discovered. This is confirmed by a rigorous comparison of IMEM results with published conformational data obtained by energy-minimization and numerical clustering methods. Conformational analysis tools have an important part to play in the conversion of raw molecular databases to knowledge bases.

Sign in / Sign up

Export Citation Format

Share Document