A KNN based random subspace ensemble classifier for detection and discrimination of high impedance fault in PV integrated power network

Swarna, K.S.V.; Vinayagam, Arangarajan; Ananth, M. Belsam Jeba; Kumar, P. Venkatesh; Veerasamy, Veerapandiyan; Radhakrishnan, Padmavathi

doi:10.1016/j.measurement.2021.110333

Cited by 77 publications

(36 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, ensemble learning algorithms has received extensive attention to process large amounts of high-dimensional data and improve the model prediction [21]. The integrated frameworks of bagging [22], AdaBoost [23], MultiBoost [24], random forest (RF) [25], rotating forest [26], and random subspace [27] are based on the C4.5 decision tree with minimal experience risk as to the base classifier, but it is easy to overfit the training dataset. Some scholars use support vector machines as the basic classifier of the ensemble learning structure, which can avoid overfitting the training dataset, but reduce the ability of the ensemble learning framework to interpret the results [28].…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Logistic Model Tree-Based Ensemble Learning Algorithms for Landslide Susceptibility Mapping

et al. 2022

View full text Add to dashboard Cite

Landslide susceptibility prediction (LSP) is the key technology in landslide monitoring, warning, and evaluation. In recent years, a lot of research on LSP has focused on machine learning algorithms, and the ensemble learning algorithm is a new direction to build the optimal prediction. Logistic model tree (LMT) combines the advantages of decision tree and logistic regression, which is smaller and more robust than ordinary algorithms. The main aim of this study is to construct and test LMT-based random forest (RF) and selected ensemble learning algorithms including bagging and boosting algorithms to compare their performance. Firstly, taking the county of Ziyang, China, as the study area, through historical reports, aerial-photo interpretations, and field investigations, 690 inventory maps of landslide locations were constructed and randomly divided into the 70/30 ratio for a training and validation dataset. Secondly, considering geological conditions, and landslide-induced disease and its characteristics, 14 landslide-conditioning factors was selected. Thirdly, the variance-inflation factor (VIF) and tolerance (TOL) were used to analyze the 14 factors, and the prediction ability was calculated with information-gain technology. Ultimately, the receiver-operating-characteristic (ROC) curve was applied to verify and compare model performance. Results showed that the LMT-RF model (0.897) was superior to other models, and the performance of LMT single model (0.791) was the worst. Therefore, it can be inferred that the LMT-RF model is a promising model, and the outcome of this study will be useful to planners and scientists in landslide sensitivity studies in similar situations.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Logistic Model Tree-Based Ensemble Learning Algorithms for Landslide Susceptibility Mapping

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Table 3 shows the results obtained using different methods. For example, the DWT-based algorithm reported in [13] considers five decomposition levels and em- method based on principal component analysis (PCA) is performed, where only the most significant six features are employed for the classification process producing a effectiveness of 98.8273 %. Another similar approach is discussed in [28], where eight features are taken into consideration for the classification approach; in this case, the authors used five decomposition levels and Daubechies 5 as the mother wavelet.…”

Section: Classification Resultsmentioning

confidence: 99%

“…Another way to deal with HIFs in distribution networks is based on power spectral density (PSD) estimation from a multiresolution analysis by using the DWT [12], in which the detection and classification process is carried out in a radial distribution system. In [13] a DWT-based ensemble Random Subspace (RS) classifier is proposed for discriminating HIFs in distribution grids with a photovoltaic system, using three classifiers, namely K-nearest neighbour (KNN), logistic regression (LR), and random tree (RT).…”

mentioning

confidence: 99%

Hermite Transform Based Algorithm for Detection and Classification of High Impedance Faults

et al. 2022

View full text Add to dashboard Cite

This work proposes a new algorithm to classify high impedance faults (HIFs) in distribution systems. HIFs can be represented by small current magnitudes with non-linear variations, which complicate their detection in distribution grids. The proposed method uses the Hermite transform (HT) as a signal processing technique that offers several advantages, one of the more important being the ability to analyze the signal at multiple resolution levels and at different frequency bands thanks to their filter functions based on Gaussian derivatives. The Hermite coefficients are used to extract signal features that allow efficient identification of the transient behaviour related to HIFs and other typical faults. In this sense, a multichannel approach based on the Hermite transform is proposed to classify different types of faults and HIFs. This analysis is carried out in a distribution network considering photovoltaic (PV) systems considering three different classifiers, which are also used to compare our results with the discrete wavelet transform (DWT) as signal decomposition model; the comparison suggests that our proposal presents better performance discriminating HIFs from typical faults.

show abstract

“…It forms a geopolymer bond, unlike regular concrete, which forms a calcium silicate hydrate bond. The geopolymer bond does not contain water in its final state [27][28][29].…”

Section: Introductionmentioning

confidence: 99%

Design and CFD Simulation of Supersonic Nozzle by Komega turbulence model for Supersonic Wind Tunnel

Raman,

Vinod Kumar,

Reddy

et al. 2024

E3S Web of Conf.

View full text Add to dashboard Cite

This paper presents an impressive design of a convergent divergent (C-D) nozzle using the method of characteristics for a Mach number 2 test section. The nozzle’s geometry was meticulously crafted in SolidWorks, and its performance was evaluated through a CFD simulation in Ansys Fluent R22 software. Results showed excellent agreement between the simulation and analytical data, with the Mach number ranging from 1.78 to 2. The study also compared turbulence modeling techniques, concluding that the k-omega model produced superior results. The supersonic wind tunnel achieved remarkable efficiency, completing a run at 1.8 Mach number in just 6 seconds. Overall, the study showcased exceptional accuracy and meticulousness.

show abstract

A KNN based random subspace ensemble classifier for detection and discrimination of high impedance fault in PV integrated power network

Cited by 77 publications

References 41 publications

Performance Analysis of Logistic Model Tree-Based Ensemble Learning Algorithms for Landslide Susceptibility Mapping

Performance Analysis of Logistic Model Tree-Based Ensemble Learning Algorithms for Landslide Susceptibility Mapping

Hermite Transform Based Algorithm for Detection and Classification of High Impedance Faults

Design and CFD Simulation of Supersonic Nozzle by Komega turbulence model for Supersonic Wind Tunnel

Contact Info

Product

Resources

About