Periodic Table’s\nProperties Using Unsupervised\nChemometric Methods: Undergraduate Analytical Chemistry Laboratory\nExercise

An application of unsupervised chemometrics methods using\nperiodic\ntable properties for an analytical chemistry laboratory exercise is\npresented. Chemometric techniques such as hierarchical clustering\nanalysis (HCA), k-means, and principal component analysis (PCA) were\napplied to a multivariate data set of chemical properties of the elements\n(atomic radius, electronegativity, ionization energy, electronic affinity,\nthermal conductivity, density, entropy, and specific heat). The exercise\nwas carried out by undergraduate students attending a chemometric\nanalysis class during the fifth semester of their third year at our\neducational institution. The theory of HCA, k-means, and PCA is discussed,\nand multivariate analysis procedures (data set construction, preprocessing,\ndendrogram, k-means clustering, scores, and loadings) were carried\nout using the well-liked programming language R, a widely used programming\nlanguage designed for data analysis and statistics, within the user-friendly\nRStudio integrated development environment. The unsupervised algorithms\nwere able to find “natural” clustering from the periodic\ntable using the data structure without any prior knowledge of the\nclass assignment of the samples. This analytical chemistry laboratory\nexercise with chemometric techniques can also be used in a wide range\nof laboratory activities such as water analysis, food analysis, drug\nanalysis, and physical chemistry.