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

.


Introduction
In the last few years, power quality (PQ) problems have come up because smart grid technology and irregular loads have been added to power systems.Tese problems are caused by nonlinear loads such as electronic converters and variable-speed drives, which cause voltage drops, harmonics, interruptions, and other problems.Generations residing in diferent places have added to the problem.To deal with these problems successfully, disruptions need to be found and put into the right classifcations.Researchers have used signal processing and machine learning to look at PQ data and extract features that can be used to classify it [1,2].Accurately detecting and classifying power quality problems is important for keeping power systems reliable, fguring out what causes them to be unreliable, and coming up with ways to fx them.Also, it helps build more advanced tracking and control systems that can adapt to changes in the grid.As power systems change and incorporate new control technology and green energy sources, it will become more important to deal with power quality issues.Modern power systems need to keep researching PQ analysis methods in order to work well and last for a long time [3].
Te precise detection and classifcation of power quality disturbances (PQDs) are essential for maintaining a reliable power supply, protecting electronic equipment, and enhancing power system performance.By identifying and classifying these disturbances, suitable measures can be taken to mitigate their negative efects.Understanding the causes and sources of PQDs enables targeted solutions to minimise their occurrence and improve power system resilience [4].Tis is especially important in modern power systems that integrate sensitive electronic equipment and renewable energy.A continued focus should be placed on the development of advanced techniques for detecting, classifying, and mitigating PQDs to ensure a high-quality power supply and efcient operation of the power system.Correctly categorizing the signals of PQDs, especially complex signals, becomes extremely difcult in tough and noisy conditions.Many researchers have studied how to best categorize PQDs during the past few decades.Feature extraction and classifcation are the two key components of these strategies.Te frst stage is to use signal processing methods to glean useful information from the PQ noise [5].Tis step is crucial because it helps distinguish between diferent kinds of disruptions, which is necessary for later classifcation.For the successful implementation of classifcation, improved recognition at the feature extraction stage is crucial [6].
Power quality disturbances encompass various issues such as sag, swell, interruptions, voltage fuctuations, harmonics, notching, and transients.Accurately detecting and classifying PQDs in power systems is crucial for identifying their causes and implementing appropriate solutions.Tis research aimed to address this challenge by leveraging advanced machine learning techniques to efectively identify and classify PQDs based on their specifc characteristics.Te detection and classifcation of PQDs are particularly challenging due to the complex and overlapping nature of the signals involved.Successful identifcation and classifcation of PQDs require both robust feature extraction techniques and efcient classifers.By developing suitable methods for feature extraction and implementing efective classifcation algorithms, this research contributes to the feld of power quality analysis and facilitates the identifcation and mitigation of PQDs [7].Once PQD signals are generated, signal processing techniques are employed to extract relevant features from signals belonging to diferent classes.Tese extracted features are utilized to train a machine learning classifer, enabling the identifcation of various PQDs.Subsequently, the features of the test signal data are fed into the trained classifer, allowing the classifcation of each PQD using machine learning methods [8].
1.1.Literature Review.A robust detection technique is required to identify power quality issues across a wide frequency range, spanning from high-frequency sharp changes up to 1 kHz to low frequencies of 50 Hz.Tis technique should possess the ability to extract features and classify power quality events with robustness while maintaining low space and time complexity in its implementation.However, signal processing techniques face limitations due to Heisenberg's uncertainty principle, which hinders the simultaneous enhancement of time and frequency resolution.Te Fourier transform (FT) ofers excellent frequency resolution but lacks time resolution, rendering it inadequate for realtime power signal analysis.Te short-time Fourier transform (STFT) divides nonstationary signals into windows, yet it sufers from improper window size selection.Wavelet transform (WT) overcomes some limitations but exhibits higher technical complexity and performance degradation in noisy environments.To address these challenges, the Stransform (ST) combines the advantages of WT and STFT, enabling robust noise resistance and accurate detection of both low-and high-frequency events.ST constructs a feature matrix utilizing frequency-dependent resolution, which can be efectively employed for the classifcation of power quality events using machine learning classifers [9].
As mentioned earlier, power quality interruptions have a negative impact on system efciency.Te literature suggests various smart approaches for automatic recognition of PQDs [10].Tese approaches typically involve two main steps: (i) signal analysis and feature extraction and (ii) PQD classifcation.Signal analysis techniques such as Fourier transform (FT) [11], short-time Fourier transform (STFT) [12,13], wavelet transform (WT) [14,15], and S-transform (ST) [16] have been successfully employed to analyse signals in the time and frequency domains.Tese methods extract relevant features for further analysis.Considering the limitations of signal processing-based fault event approaches, this study proposes a PQD identifcation method utilizing the S-transform.Te selection of appropriate features remains difcult, necessitating developments in statistical evaluation and machine learning techniques [17].Following the feature engineering (FE) phase, the feature selection (FS) procedure is used to select a reduced number of the best features that have a strong relationship with the output classes.Because of how features work and how they relate to each other, FS is seen as an extra step that comes before classifcation.It requires putting together a feature vector with the most important features based on how they relate to the output classes.
Trough the use of the Hilbert-Huang transform (HHT) and the weighted bidirectional-extreme learning machine (WBELM), Sahani and Dash presented a real-time method for detecting and classifying PQDs.Online power quality monitoring systems benefted greatly from their method, which beats competing classifers [25].Using sparse signal decomposition (SSD) on an overcomplete hybrid dictionary (HD) matrix, Manikandan et al. suggested a new method for detecting and classifying PQDs.Te method is well suited for PQ monitoring networks as it captures morphological details and extracts PQ features for categorization [26].Another approach [27] utilizes a quick time-time transform and a residual-extreme learning machine to detect and classify power quality issues in wind-grid integrated systems.Tis method optimizes computational speed and demonstrates accuracy even in the presence of noisy signals.Te remaining sections of this work are organized as follows: Section 2 presents the details of the PQDs considered in this study, providing a comprehensive understanding of their characteristics.Section 3 describes the principle of S-transform (ST) feature extraction and outlines the approach for classifying PQDs using the extracted features.In Section 4, the results are presented and a comparative performance analysis is conducted to evaluate the efectiveness of the proposed method.Section 5 concludes the work by discussing the signifcant fndings obtained from the study and highlighting potential future directions for further research and development in the feld of PQD detection and classifcation.

Power Quality Disturbances
Tere are a total of 17 distinct types of PQD signals taken into account in this investigation.All PQDs for which synthetic equation data are available are included in Table 2.

Proposed Methodology
Power quality disturbance signals are known for their nonstationary nature, as their spectral characteristics change over time.Te ability to accurately describe and classify the type of PQD present in a given nonstationary signal relies on the extraction of suitable features.In the proposed methodology, the detection of PQDs within nonstationary signals is accomplished through the utilization of the S-transform.Subsequently, classifcation of the detected disturbances is performed using a random forest (RF) classifer.Te Stransform is a powerful tool that captures the timefrequency information of signals and overcomes the limitations of fxed-width windows and complex window function selection encountered by other methods.By applying the ST to the nonstationary PQ signals, important features that characterize the diferent types of disturbances can be extracted.Tese features provide valuable insights into the underlying characteristics of the PQDs and serve as discriminative factors for subsequent classifcation.To classify the detected disturbances, a random forest classifer Te RF classifer excels at handling complex and high-dimensional datasets, making it well suited for the classifcation of PQDs.By combining the ST for detection and the RF classifer for classifcation, the proposed framework ofers a comprehensive approach for PQD analysis.It enables the identifcation and characterization of diferent types of PQDs in nonstationary signals, providing valuable insights for further analysis and mitigation strategies in power systems.

Teory of Stockwell Transform.
In 1996, Stockwell came up with the Stockwell transform (ST) method, which lets signs that change over time be looked at in more than one way.Unlike other methods, ST's output does not change when the input data are noisy [14].Because of this, ST is the best way to get local phase information and a resolution in the time-frequency domain that changes with frequency.ST uses a set relative bandwidth for multiresolution analysis to flter signals.Continuous wavelet transform (CWT) uses a mother wavelet that stays the same, while ST uses a mother wavelet that changes to fgure out the local phase.
Te CWT for a signal x (t) is defned by the following equation: where τ is the wavelet position and d is the scale parameter.Te S-transform of x (t) is a CWT multiplied by the phase factor.
In the ST, the mother wavelet (window function) is picked based on the frequency content of the signal instead of scale d, which is how it is done in the CWT.Tis is stated to be where σ(f) � 1/a + b|f| represents Gaussian window width.From equations ( 2) and (3) for a � 0, the ST can be rewritten as where, 0.9 where, 0.8 ≤ β ≤ 0.8,0.5T≤ (t 2 − t 1 ) ≤ 3T, 8 ms ≤ τ30 ms and 300 Hz ≤ f n ≤ 900 Hz Harmonics + oscillatory transients (C13) sin(ωt) Journal of Electrical and Computer Engineering Using the Fourier transform, we can mathematically defne the s-transform as Te discrete form of the S-transform can be obtained by combining the fast Fourier transform (FFT) with the convolution theorem.
Discrete S-transform: Setting T as the sample interval results in the discrete PQ signal x(KT) rather than the continuous x(t).Te discrete Fourier transform (DFT) of the sampled signals, for K � 0 to N − 1, is shown in the following equation: where n � 1, 2, . ... .., N − 1.By using DFT and the IDFT, the ST of a discrete-time series x[n] for τ � jT and f � n/NT can be written as where Te amplitude of the S-transform can be expressed as equation ( 8) and the phase as equation ( 9 Many trees are grown by repeating this technique.Each tree in the forest makes a guess during the prediction phase, and the ultimate prediction is reached by averaging all of the trees' predictions, sometimes through some sort of voting procedure [33].Assume there are X input data points with X � x 1 , x 2 , x 3 , . . . . . .x m being an m-dimensional vector.Tis information is sent to a group of C trees, whose names are denoted by T 1 (X), T 2 (X), T 3 (X), . . . . . ..T C (X). Te group of trees then predicts that the output will be a value Y.
After all the trees have made their predictions, an average is calculated to be used as the fnal forecast.
Here are the hyperparameters for a random forest classifer: (i) n_estimators: the forest contains 100 trees (ii) criterion: "gini" is the function used to measure the quality of a split (iii) min_samples_split: an internal node can only be split if it has at least 2 samples (iv) min_samples_leaf: a leaf node must have at least 1 sample (v) min_weight_fraction_leaf: a leaf node must have a minimum weighted fraction of the sum total of weights, which is set to 0 by default 3.4.Performance Analysis.Various performance metrics are essential for evaluating classifcation models and assessing the efectiveness of their predictions.One commonly used metric is the confusion matrix, which provides a correlation between the true labels and the model's predictions.In the confusion matrix, each row represents the projected instances of a particular class, while each column represents the actual instances of that class.It serves as a foundation for deriving other performance statistics.While the confusion matrix itself is not a performance statistic, it serves as a crucial starting point for calculating various metrics.In Table 4, an example of a confusion matrix for a binary classifcation problem is presented.Tese metrics enable us to assess the classifcation model's performance from different angles and determine its accuracy, precision, recall, and other relevant measures.By utilizing these performance metrics, we gain valuable insights into the model's classifcation capabilities and its ability to correctly predict the classes of interest.
Te confusion matrix used in this evaluation provides valuable insights into the performance of the classifer.It comprises four evaluation factors: true positive (TP), true negative (TN), false positive (FP), and false negative (FN).Tese factors are depicted in each cell of the confusion matrix.Te accuracy of the classifer, which serves as an overall measure of its performance, is calculated using the 3.4.3.F1-Score.Te F1-score metric takes both precision and recall into account.Te F1-score is calculated using the harmonic mean of equations ( 11) and ( 12).Te equation is as follows:

Results and Discussion
sag, 1 interruption, 10 sags with harmonics, and 2 fickers with harmonics is also a cause of concern.Moreover, 36 fickers with harmonics signals have been mistakenly categorized as 36 notches, and 18 oscillatory transients with harmonics have been incorrectly categorized as 1 ficker, 5 oscillatory transients, and 12 fickers with harmonics.Tere is a misclassifcation of 22 notches with harmonics as 11 harmonics and 11 notches.Finally, 42 sags with fickers have been misclassifed as 3 sags, 8 harmonics, 3 swells with harmonics, 10 interruptions with harmonics, 9 swells with fickers, and 9 interruptions with fickers.In addition, 10 swells with fickers have been misidentifed as swell with harmonics, and 17 interruptions with fickers have been incorrectly categorized as 5 sags, 6 interruptions, and 6 fickers.
Table 7 presents the confusion matrix produced by the SVM; from this, it can be inferred that a total of 16 sag signals, including 6 interruptions, 1 sag with harmonics, and 9 sags with fickers, have been incorrectly categorized.13 interruptions have been misidentifed as 10 sags and 3 interruptions with harmonics.24 harmonics are mistakenly categorized as 2 sags with harmonics and 22 fickers with harmonics.7 fickers are incorrectly categorized as 2 sags and 5 sags with fickers.15  Table 8 presents the confusion matrix for DT, which reveals that 7 sags are incorrectly categorized as 3 interruptions and 4 sags with fickers.Tere is misclassifcation of 24 harmonics as 13 fickers with harmonics and 10 notches with harmonics.11 fickers are incorrectly categorized as 4 sags, 1 swell, and 6 sags with fickers.Tere is   a misclassifcation of 15 sags with harmonics as 7 interruptions with harmonics and 8 fickers with harmonics.4 swells with harmonics are mistakenly categorized as 4 fickers.7 interruptions with harmonics are incorrectly categorized as 7 sags with harmonics.10 fickers with harmonics are wrongly categorized as 2 fickers and 8 interruptions with harmonics.4 oscillatory transients with harmonics are wrongly categorized as 4 sags with fickers.Tere has been a misidentifcation of 7 notches with harmonics as 7 sags with harmonics.7 sags with fickers are incorrectly categorized as 7 harmonics.2 interruptions with fickers are wrongly categorized as 1 ficker and 1 notch with harmonics.
Te RF confusion matrix is represented in Table 9; from this, we observe that 7 of the harmonic signals are incorrectly categorized as fickers with harmonics.15 sags with harmonic signals are misclassifed as 1 harmonics, 11 interruptions with harmonics, and 3 fickers with harmonics.Tere are 8 cases of incorrect classifcation of interruption with harmonic signals as sags with harmonics.17 fickers with harmonic signals are misclassifed as 7 harmonics and 10 interruptions with fickers.7 sags with ficker signals are misclassifed as 5 harmonics and 2 interruptions with harmonics.Figures 2(a)-2(c) depict the performance metrics of RF, including precision, recall, and F-score, respectively.

Overall Comparison (RF vs. DT vs. SVM vs. KNN).
Table 10 summarises the performance of all the algorithms employed in this work.In order to validate the efectiveness of the RF algorithm compared to other ML algorithms, a comparison has been done through a line graph, as shown in Figures 3(a)-3(c).When there is no disturbance, the precision, recall, and F-score values are almost as close to 1.00 as all the algorithms allow.
During swell, we can observe all performance metrics values as 0.98 with the KNN algorithm, whereas the rest retains the same value of 1.00.Te RF algorithm gives performance metrics a value of 1.00 during sag, but other algorithms give a value between 0.86 and 0.99.RF algorithm achieves a precision value of 1.00 during interruption, whereas KNN, SVM, and DT have precision values of 0.94, 0.98, and 0.99, respectively.However, the recall and F-score values for all algorithms ranged from 0.89 to 0.98, with none of them achieving a value of 1.00.During harmonics, we observed varying performance metrics with all four algorithms.Te precision values ranged from 0.90 to 0.97, and none of them reached 1.00.Te RF algorithm performed better in terms of recall and Fscore, with values of 0.98 and 0.99, respectively.KNN, SVM, and DT gave recall values of 0.87, 0.93, and 0.93, respectively.Te F-score of KNN and SVM was 0.89, whereas DT had F-scores of 0.95.In the case of ficker, RF showed high performance with an F-score of 1.0, while KNN and SVM had lower F-scores of 0.95 and 0.99, respectively.Te recall values for DT, KNN, and SVM were 0.97, 0.96, and 0.98, respectively.

Journal of Electrical and Computer Engineering
During the oscillatory transient, RF and DT achieved a perfect F-score of 1.0, while KNN and SVM had lower values.In the case of a notch with harmonics, KNN had the lowest performance metric values compared to the algorithms, while RF, DT, and SVM had perfect values of 1.0.For sag with harmonics, RF had the highest precision value of 0.98, while SVM, KNN, and DT had values of 0.88, 0.96, and 0.96, respectively.Te recall values for the same algorithms were 0.95, 0.92, 0.96, and 0.98, respectively.Te Fscore values were 0.9, 0.95, 0.96, and 1.0, respectively.Except for KNN and SVM, all other algorithms achieved a precision of 1.00 during swell with harmonics, with KNN and SVM obtaining 0.90 and 0.91, respectively.In terms of recall, RF achieved a value of 1.00, while KNN, SVM, and DT obtained 0.9, 0.97, and 0.99, respectively.Te RF algorithm had an Fscore of 1.00, but KNN, SVM, and DT had F-scores of 0.89, 0.94, and 0.99, respectively.During ficker with harmonic performance of all the ML algorithms with precision of 0.99, where RF produces 0.97.Te RF, DT, and KNN all have 0.96 and 0.95, respectively, and the SVM gives 0.9.During oscillatory transients with harmonics, RF performed similarly, with a performance metric value of 1. DT, KNN, and SVM had precision values of 1.0, 0.96, and 0.95, respectively; recall values of 0.99, 0.95, and 0.94, respectively; and F-score values of 0.99, 0.95, and 0.94, respectively.During the notch with harmonics, precision, and recall, the F-score value with the SVM algorithm is noted as 0.94, 0.85, and 0.89, whereas KNN gives 0.92, 0.94, and 0.93.At the same time, RF gives 1.00, while DT moderately performs with precision, recall, and an F-score value of 0.97, 0.98, and 0.97.During sag with ficker, RF achieved a precision value of 1.0, while KNN, SVM, and DT had values of 0.9, 0.91, and 0.96, respectively.Te recall values were 0.98, 0.95, 0.87, and 0.88 for RF, DT, SVM, and KNN, respectively.Te F-score values were 0.99, 0.95, 0.89, and 0.89 for RF, DT, SVM, and KNN, respectively.All algorithms achieved a performance value of 1.00 during swell with ficker.However, KNN had a precision value of 0.94, a recall value of 0.98, and an F-score value of 0.96.
During the interruption with ficker, RF algorithms achieved a higher recall value of 1.00, while KNN, SVM, and DT had recalls of 0.96, 0.98, and 0.99, respectively.Te KNN and DT had F-scores of 0.95 and 0.99, respectively, whereas SVM and RF had the same F-score value of 0.98.
Table 11 shows that the random forest (RF) method is better than k-nearest neighbor (KNN), support vector machine (SVM), and decision tree (DT).Te RF method improves accuracy, precision, recall, and F-score, which are important measures of a model's ability to classify data and make accurate predictions.In summary, these results suggest that the RF technique is a more successful classifcation algorithm than the KNN, SVM, and DT methods.Te RF approach may be utilized by researchers and practitioners to develop accurate and dependable classifcation models.

Comparison with Other
Methods.In this study, the proposed approach is evaluated and compared with recent studies and methods for determining and classifying power quality disturbances.Te evaluation takes into account factors such as the number of signals analysed, sample rates, and accuracy achieved.Te results clearly demonstrate that the proposed ST + DT method outperforms other contemporary approaches, achieving a classifcation accuracy of 98.02 percent.By utilizing the S-transform for feature extraction, the proposed method overcomes limitations associated with fxed-width windows and challenging window function selection thanks to the extended capabilities of the S-transform which combine wavelet and Fourier transforms.Table 12 presents a comparative analysis of the efectiveness of the proposed ST + DT method against the fndings of several recent studies conducted between 2015 and 2022.Te accuracy of the sparse signal decomposition (SSD) with a hybrid dictionary (HD) approach is reported as 95.4 percent for classifying seven PQD classes.In 2018, Saini and Beniwal proposed an FFT + ELM classifer with 95.38 percent accuracy for classifying 12 PQDs.Sahani and Dash     Overall, the results demonstrate the efciency and superiority of the suggested method compared to existing approaches for power quality disturbance detection and classifcation.

Conclusion
Tis research provides a novel approach based on the Stockwell transform (ST) and a random forest classifer for efcient recognition of PQD signals.Firstly, the S-transform technique is used to extract the feature dataset from the produced PQD signals.Sampling frequencies of 3.2 kHz and a signal-to-noise ratio (SNR) of 40 dB are investigated.Seventeen (C1-C17) varieties of distinct PQDs are considered.Te extracted dataset is then trained and evaluated using the suggested random forest method.Te following is a summary of the most important outcome of the output classifcation: (i) it is determined that the overall detection accuracy is 99.01%and (ii) the proposed ST + RF classifcation method outperforms various recent PQD classifcation methods, including KNN, SVM, and DT, with an overall accuracy of 93.41% for KNN, 94.83% for SVM, and 98.09% for DT.Te current work can be expanded in the accompanying directions: (i) evaluating the suggested strategy with regard to real-time PQDs' information, (ii) incorporating additional disorders into the methodology in an attempt to classify more types of disorders, and (iii) implementing and examining deep learning techniques for PQDs' identifcation in a more complicated scenario.

Table 1 :
Summary of detection and classifcation of PQDs.and Computer Engineering is employed.Te RF classifer is a popular ensemble learning algorithm that combines multiple decision trees to achieve robust and accurate classifcation.It leverages the collective decision-making capabilities of individual trees to make predictions based on the extracted features from the PQD signals.

6 2 .
Journal of Electrical and Computer Engineering following equation and is presented as a result of this evaluation: accuracy � TP + TN TP + FP + TN + FN .(10) 3.4.1.Precision.Precision is the ratio of true positives to the total number of positives that were predicted: Recall.Te percentage of true positives to all positives in the ground truth is called the recall: recall � TP TP + FN .(12) oscillatory transients have been misidentifed as 10 swells with harmonics and 5 oscillatory transients with harmonics.30 sags with harmonics are incorrectly categorized as 4 harmonics, 23 interruptions with harmonics, and 3 fickers with harmonics.10 swells with harmonics signals are misidentifed as notches with harmonics.34 interruptions with harmonics are incorrectly categorized as 31 sags, 1 interruption, 1 ficker with harmonics, and 1 interruption with fickers.28 fickers with harmonics are mistakenly categorized as 5 sags, 6 harmonics, 4 oscillatory transients, and 13 oscillatory transients with harmonics.22 oscillatory transients with harmonics are misclassifed as 7 sags with harmonics and 15 notches with harmonics.56 notches with harmonics signals are mistakenly categorized as 35 sags with harmonics and 21 sags with fickers.45 sags with fickers have been misidentifed as 19 swells with harmonics and 26 interruptions with harmonics.8 interruptions with ficker have been misidentifed as 1 ficker and 7 interruptions with harmonics.
Swell ST Contour of Interruption ST Contour of Sag with Swell ST Contour of Swell with Interruption

Figure 2 :
Figure 2: (a) Precision of diferent PQD classes with RF.(b) Recall with RF for diferent PQD classes.(c) F-score with RF for diferent PQD classes.

Figure 3 :
Figure 3: (a) Precision comparison of RF with other algorithms.(b) Recall comparison of RF with other algorithms.(c) F-score comparison of RF with other algorithms.
[21]mala et al.suggested an automatic recognition technique that combines adaptive fltering with a multiclass support vector machine.When dealing with PQDs singly or in tandem, their strategy proved efective, resilient, and accurate[21].Hole and Naik analysed PQ signals based on IEEE 1159-2009 standards, employing mathematical parametric models and the discrete wavelet transform (DWT).
Te features used and the number of features are important parts of making the classifer more accurate and faster.Te nine features (k1-k9) extracted in this work included the newly developed disturbance energy ratio (DER) index and other basic statistical measures such as maximum, minimum, average value, standard deviation, variance, skewness, and kurtosis and more specifc ones such as RMS value and DER (disturbance energy ratio).Te equations shown in Table3were used to derive these features.From the matrix created by performing the S-transform, all values were determined and expressed as absolute values.M and N specifed the rows and columns, respectively, of the matrix.In this work, by utilizing ST, a total of nine features are extracted from the PQDs depicted in Table3.than any single tree, this approach combines the knowledge of several weak learners (decision trees).In a random forest method, every decision tree employs an arbitrary subset of training data and an arbitrary combination of characteristics at each node.Random forest most signifcant characteristics are bootstrap resampling, random feature selection, and out-of-bag error estimation.
phase � ϕ(τ, f) � tan − 1 imag(S[jT, (n/NT)]) real(S[jT, (n/NT)]) .(9) 3.2.Feature Extraction.Te outcome of ST is a 2D complex matrix, which gave valuable time-frequency data from which PQD features were retrieved by calculating several statistics.3.3.Random Forest Classifer.Random forest can be applied to classifcation and regression.It employs numerous decision trees to form a "forest" of trees.To make more accurate predictions

Table 6 :
Confusion matrix of KNN.

Table 7 :
Confusion matrix of SVM.

Table 8 :
Confusion matrix of DT.

Table 9 :
Confusion matrix of random forest.

Table 10 :
Complete performance indices of all algorithms.

Table 11 :
Overall performance indices of all algorithms.

Table 12 :
Comparing the efectiveness of the proposed method in view of other recently published articles.the PQD classifer based on random forest (RF) and DWT, achieving a classifcation accuracy of 96.48% for 21 PQD classes.Te comparative results unequivocally indicate the superior performance of the proposed method. implemented