Research Article

Effectiveness of Partition and Graph Theoretic Clustering Algorithms for Multiple Source Partial Discharge Pattern Classification Using Probabilistic Neural Network and Its Adaptive Version: A Critique Based on Experimental Studies

Table 7

Comparison of classification capability of OPNN and APNN with versions of -means clustering algorithms.

Serial number Input feature vectorClassification capability
PNN versions (without clustering) OPNN
(with standard -means clustering)
APNN
(with the Forgy -means clustering)
OPNN APNNOPNNAPNNOPNNAPNN
Iter. (%)Iter. (%)Iter. (%)Iter. (%)

Φ- - (30°)93.6%93%100081100083200080500081
Φ- - (10°)94%93.3%100084100084200081500082
Φ- - (30°)89%91%500080100081500080500081
Φ- - (10°)91%92%500081100082500081500081
Measure of types of mean (30°)9494500084100085500082500082
Measure of types of mean (10°)9495500085100086500083500083