Combined Cluster Analysis and Principal Component Analysis to Reduce Data Complexity for Exhaust Air Purification

Abstract

Anthropogenic and demographic processes cause worldwide air problems, giving rise to focus on exhaust air purification to counteract these effects. Due to the large number of substances found in exhaust air and the various operational parameters needed, a huge amount of often high dimensional data has to be analyzed. The ultimate goal is to finally reduce data complexity in terms of information reflecting the substances´ characteristics.The Cluster Analysis (CA) of data from 30 exhaust air compounds with 11 indices representing both structural characteristics and physicochemical data resulted in 7 clusters. The Principal Component Analysis (PCA) led to the identification of 6 Principal Components (PCs) and therefore to a dimensional reduction compared to the originally used 11 indices. After re-gathering the total information of the original data-set upon the 6 PCs only, a re-clustering showed that we were able to restore the same cluster structure as in the original CA based on the 11 indices. This process is a first proof of principle in successful re-clustering after dimensional data reduction by our proposed combined CA-PCA method and hence a step towards a possible development of an adsorption method to selectively remove malodorous/toxic components from the exhaust air.

Malaria determining risk factors at the household level in two rural villages of mainland Equatorial Guinea

“…The variables used to estimate the socioeconomic status (SES) were based on the house characteristics, namely type of floor, walls, window protection, the presence of eaves, the energy source for cooking, toilet facilities, electricity, owning a bed net, and the number of people living in the house [ 19 – 22 ]. In order to establish the socioeconomic status of a household, a 2-step cluster analysis was the procedure used instead of a categorical Principal Component Analysis [ 23 , 24 ], thus allowing for the inclusion of categorical and quantitative variables and the automatic selection of the number of clusters in the data.…”

Characterization of Botanical Parts of <i>Erythrina crista-galli</i> Using Pyrolysis-Gas Chromatography/Mass Spectrometry and Multivariate Analysis

“…PCA minimizes the data dimension by creating the so-called principal components (PCs), which are linear combinations of the variables in the data set to summarize the data [30]. Fig.…”

“…In terms of specific characteristics, each group or cluster is homogeneous and should be distinct from others. The closeness of two objects is expressed by similarity or dissimilarity, which can be computed by mathematical methods, and eventually displayed in a dendrogram based on the features of individual objects [30]. HCPC is a clustering approach that allows to combine principal component method, hierarchical clustering, and partitioning clustering method to identify clusters within a data set.…”

An examination of motives underlying active sport tourist behavior: a market segmentation approach

“…Before analyzing the psychometric properties of the survey instrument, Principal Component Analysis (PCA) was conducted using promax rotation on the 13 sport-related factors and five tourism-related factors in order to converge the two scales into one unified Sport Tourism Motivation Scale (STMS). The purpose of PCA is to extract the most important information from the data set through dimensional reduction, thereby producing a simplified structure of the observation and variables (Ebeling, Vargas, & Hubo, 2013). The same procedure was employed on the Information Source Acquisition items to obtain a reduced factor structure from its original 18-item scale.…”