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

Table 1

Summary of detection and classification of PQDs.

Sl. no	Authors	Year	Number of classes	Number of features	Feature extraction technique	Classification technique
1	Khoa and Van Dai [18]	2020	9	5	Stockwell transform (ST)	Decision tree (DT)
2	Samanta et al. [19]	2020	9	12	Stockwell transform	Wild goat optimization extreme learning machine (WGOELM)
3	Chakravorti and Dash [20]	2017	15	36	Extreme learning machine (ELM)	Reduced kernel ELM (RKELM)
4	Thirumala et al. [21]	2019	16	6	Extended wavelet transform (EWT)	Support vector machine (SVM)
5	U. Singh and S. N. Singh [22]	2017	15	9	Fractional Fourier transform	Decision tree
6	Mahela and Shaik [23]	2017	10	14	Stockwell transform (ST)	Fuzzy clustering method
7	Li et al. [24]	2016	9	9	Double resolution S-transform	Directed acyclic graph-SVM
8	Sahani and Dash [25]	2018	16	4	Hilbert–Huang transform	Weighted bidirectional-ELM
9	Manikandan et al. [26]	2015	7	5	Sparse signal decomposition	Hybrid dictionary
10	Saini and Beniwal [27]	2018	12	7	Fast Fourier transform	Extreme learning machine
11	Hole and Naik [28]	2020	6	10	Discrete wavelet transform	Naive Bayes
13	Markovska et al. [29]	2020	21	9	Discrete wavelet transform	Random forest
14	Saxena et al. [30]	2022	5	5	Principal component analysis	Support vector machine