Topic: Data Analysis (R language)

//////////////////////////////////////////////

Q. Consider the following dataset which consists of five devices, and each device is explained by three features, i.e. Feature X, Feature Y, and Feature Z. Assuming that k-means clustering analysis will be developed based on this dataset and the two clusters are identified with the respective centroids as follows: centroid for cluster 1, M1 = {1.0, 1.0, 1.0}, centroid for cluster 2, M2 = {15.0, 15.0. 15.0}.

1.Using the Euclidean distance formula, compute the distance between D1 and M1.

(9.0 / 9.7 / 16.5 / 17.0)

2. Using the Euclidean distance formula, compute the distance between D1 and M2.

(9.0 / 9.7 / 16.5 / 17.0)

3. Based on the answers for Questions A1 and A2, D1 should be placed in cluster 2.

(T / F )

4. In building a k-means clustering model, the process of identifying the suitable value of k is referred to as identifying the elbow of the Within Sum of Squares (WSS) curve.

(T / F )

Device Feature X Feature Y Feature Z D1 8.7 6.9 1.5 D2 6.4 12.4 4.6 D3 10.4 9.9 9.3 D4 7.4 2.5 2.2 D5 10.8 11.2 3.6