Utilization of Stockwell Transform and Random Forest Algorithm for Efficient Detection and Classification of Power Quality Disturbances

Table 9

Confusion matrix of random forest.

True PQDs	Predicted PQDs by random forest
	C1	C2	C3	C4	C5	C6	C7	C8	C9	C10	C11	C12	C13	C14	C15	C16	C17
C1	353
C2		339
C3			375
C4				330
C5					328							7
C6						352
C7							386
C8								361
C9					1				363		11	3
C10										323
C11									8		339
C12					7							311					10
C13													360
C14														372
C15					5						2				339
C16																355
C17											1						356
Overall accuracy = 99.01%