A Pilot Exploratory Study to Form Subgroups Using Cluster Analysis of Family Needs Survey Scores for Providing Tailored Support to Parents Caring for a Population-Based Sample of 5-Year-Old Children with Developmental Concerns

In a population-based developmental screening program, healthcare providers face a practical problem with respect to the formation of groups to efficiently address the needs of the parents whose children are screened positive. This small-scale pilot study explored the usefulness of cluster analysis to form type-specific support groups based on the Family Needs Survey (FNS) scores. All parents (N = 68), who accompanied their 5-year-old children to appointments for formal assessment and diagnostic interviews in the second phase of screening, completed the FNS as part of a developmental questionnaire package. The FNS scores of a full dataset (N = 55) without missing values were subjected to hierarchical and K-means cluster analyses. As the final solution, hierarchical clustering with a three-cluster solution was selected over K-means clustering because the hierarchical clustering solution produced three clusters that were similar in size and meaningful in each profile pattern: Cluster 1—high need for information and professional support (N = 20); cluster 2—moderate need for information support (N = 16); cluster 3—high need for information and moderate need for other support (N = 19). The range of cluster sizes was appropriate for managing and providing tailored services and support for each group. Thus, this pilot study demonstrated the utility of cluster analysis to classify parents into support groups, according to their needs.

Hierarchical clustering for multiple nominal data streams with evolving behaviour

Over the decade, a number of attempts have been made towards data stream clustering, but most of the works fall under clustering by example approach. There are a number of applications where clustering by variable approach is required which involves clustering of multiple data streams as opposed to clustering data examples in a data stream. Furthermore, a few works have been presented for clustering multiple data streams and these are applicable to numeric data streams only. Hence, this research gap has motivated current research work. In the present work, a hierarchical clustering technique has been proposed to cluster multiple data streams where data are nominal. To address the concept changes in the data streams splitting and merging of the clusters in the hierarchical structure are performed. The decision to split or merge is based on the entropy measure, representing the cluster’s degree of disparity. The performance of the proposed technique has been analysed and compared to Agglomerative Nesting clustering technique on synthetic as well as a real-world dataset in terms of Dunn Index, Modified Hubert $$\varGamma $$ Γ statistic, Cophenetic Correlation Coefficient, and Purity. The proposed technique outperforms Agglomerative Nesting clustering technique for concept evolving data streams. Furthermore, the effect of concept evolution on clustering structure and average entropy has been visualised for detailed analysis and understanding.

Comparative Study of Abiotic Stress Factors on GC-MS-Detected Phytoconstituents of Aloe greatheadii var: davyana Using Heat Map and Hierarchical Clustering Dendrogram

Aloe greatheadii var. davyana or spotted aloe is indigenous to South Africa and widely distributed in the northern provinces. The plant has a vast ethnopharmacological application which is mostly attributed to its phytochemical content. The aim of the study was to examine the effect of abiotic stress factors on the plant’s phytochemical content. The phytochemical content of A. greatheadii hexane extracts from four different provinces (Limpopo, Mpumalanga, Gauteng, and North West), harvested from the wild at varied altitudes, rainfall patterns, and soil types, was examined using gas chromatography-mass spectra (GC-MS). The phytochemical content of hexane extracts from the four South African provinces was analysed using heat map analysis and hierarchical clustering dendrogram. The phytochemical content of A. greatheadii hexane extracts was composed of fatty acids, alkanes, benzene, carboxylic acids, ketones, phytosterols, and vitamins. Eicosane, henicosane, and [(2S)-2-[(2R)-4-hexadecanoyloxy-3-hydroxy-5-oxo-2H-furan-2-yl]-2-hydroxyethyl] hexadecanoate were the only compounds detected in all samples from the four provinces. The concentration levels of 2-(((2-ethylhexyl)oxy)carbonyl) benzoic acid, beta-sitosterol, tritetracontane, and ethyl 13-methyltetradecanoate were closely related and expressed a low clustering distance amongst the samples. Variations in soil pH, soil type, and rainfall patterns were detected and differed in the four provinces. The different abiotic stress factors affected the biochemical pathways for the different compounds, with conditions in Gauteng being less favourable for many of the compounds detected. Abiotic stress factors have shown to influence phytochemical biochemical pathways and quantity. Aloe greatheadii plants can be selected based on location seemingly due to the variations that persist in their phytochemical content.

Performance Comparison with Hierarchical and Partitional Clustering Methods

In data mining, one of the commonly-used techniques is the clustering. Clustering can be done by the different algorithms such as hierarchical, partitioning, grid, density and graph based algorithms. In this study first of all the concept of data mining explained, then giving information the aims of using data mining and the areas of using and then clustering and clustering algorithms that used in data mining are explained theoretically. Ultimately within the scope of this study, "Mall Customers" data set that taken from Kaggle database, based partitioned clustering and hierarchical clustering algorithms aimed at the separation of clusters according to their costumers features. In the clusters obtained by the partitional clustering algorithms, the similarity within the cluster is maximum and the similarity between the clusters is minimum. The hierarchical clustering algorithms is based on the gathering of similar features or vice versa. The partitional clustering algorithms used; k-means and PAM, hierarchical clustering algorithms used; AGNES and DIANA are algorithms. In this study, R statistical programming language was used in the application of algorithms. At the end of the study, the data set was run with clustering algorithms and the obtained analysis results were interpreted.