Feature Selection and Parameters Optimization of SVM Using Particle Swarm Optimization for Fault Classification in Power Distribution Systems

Cho, Ming-Yuan; Hoang, Thi Thom

doi:10.1155/2017/4135465

Cited by 55 publications

(34 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Selected degraded fingerprint images from the created and extracted real time database are feature extracted using filter bank approach and the feature excel sheet is created consisting of 152 features of each fingerprint image [14]. The extracted features of 50 real-time online fingerprint images in excel format are used for training and testing of the network.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Real-time online fingerprint image classification using adaptive hybrid techniques

Mishra¹,

Dehuri

2019

IJECE

View full text Add to dashboard Cite

<p class="Abstract">This paper presents three different hybrid classification techniques applied for the first time in real-time online fingerprint classification. Classification of online real time fingerprints is a complex task as it involves adaptation and tuning of classifier parameters for better classification accuracy. To accomplish the optimal adaptation of parameters of functional link artificial neural network (FLANN) for real-time online fingerprint classification, proven and established optimizers, such as Biogeography based optimizer (BBO), Genetic algorithm (GA), and Particle swarm optimizer (PSO) are intelligently infused with it to form hybrid classifiers. The global features of the real-time fingerprints are extracted using a Gabor filter-bank and then passed into adaptive hybrid classifiers for the desired classification as per the Henry system. Three hybrid classifiers, the optimized weight adapted Biogeography based optimized functional link artificial neural network (BBO-FLANN), Genetic algorithm based functional link artificial neural network (GA-FLANN) and Particle swarm optimized functional link artificial neural network (PSO-FLANN), are explored for real-time online fingerprint classification, where the PSO-FLANN technique is showing superior performance as compared to GA-FLANN and BBO-FLANN techniques. The best accuracy observed by the application of PSO-FLANN, is 98% for real-time online fingerprint classification.</p>

show abstract

Section: Resultsmentioning

confidence: 99%

“…where N = number of expanded points for each input element [`12] [13]. In our case, N=11 and I= represents the total number of features in the feature vector [14].The expansion can be represented as [15][16], (1) where,…”

Section: Proposed Methods 21 Introduction To Flann As a Classifiermentioning

confidence: 99%

Real-time online fingerprint image classification using adaptive hybrid techniques

Mishra¹,

Dehuri

2019

IJECE

View full text Add to dashboard Cite

show abstract

“…Where as in [169] the support vector machine as classifier core discriminated the power quality events to perform a satisfactory test in terms of accuracy and speed even in noisy conditions. In [170] the TDR (time-domain reflectometry) technique with PRBS (pseudorandom binary sequence) is used for data set as an appropriate input for PSO based SVM to increase the parameters for classification accuracy. In [171] FIR-DGT and T2FK-SVM is used to enhance the accuracy of classification by reducing the feature size so that less time and memory is required for classification.…”

Section: Classification Based On Support Vector Machinementioning

confidence: 99%

A Three Decades of Marvellous Significant Review of Power Quality Events Regarding Detection & Classification

Ahsan¹,

Pan²,

Li³

2018

JPEE

View full text Add to dashboard Cite

Around the globe, the necessity of green supply with a dedicated standard quality thrust of consumers is increasing day by day. The advancement in technology urges the electrical power system to deliver a high-quality rated undistorted sinusoidal current, the voltage at a constant desired standard frequency to its consumers. The present paper reveals a complete and inclusive study of power quality events, such as automatic classification and signal processing via creative techniques and the noises effect on the detection and classification of power quality disturbances. It's planned to make a possible list for quick reference to obtain an extensive variety on the condition & status of available research for detection and classification for young engineers, designers and researchers who enter in the power quality field. The current extensive study is supported by a critical review of more than 200 publications on detection and classification techniques of power quality disturbances.

show abstract

“…Particle Swarm Optimization (PSO) technique is being used in solar PV system to produce constant output voltage from converter. The application of PSO greatly improves the performance of MPPT and supply enhanced output power [12][13][14]. The reduction in total power generation by entire PV system is being reduces due to mismatch in panel design, grading and partial shading.…”

Section: Introductionmentioning

confidence: 99%

Particle Swarm Optimization Technique for Photovoltaic System

Ansari*,

Thakur,

Saini

2020

IJRTE

View full text Add to dashboard Cite

Day by day the dependency on renewable energy uses has been increasing because of no greenhouse emission and abundant in nature available freely, this paper, presents a comparative analysis of an optimization technique called Particle Swarm Optimization (PSO) along with Perturb & Observe (P&O) for the extraction of maximum power from the PV panel. The performances of P&O and PSO techniques were compared for different insolations and temperatures. A detailed and rigorous mathematical model along with simulation results and its performance for maximum power extraction from the panel were analyzed by using P&O and PSO. It has been observed that the maximum power obtained from PSO model is more than the maximum power obtained from P&O for different insolations and temperatures. Thus PSO is much better and more suitable for extracting maximum power from PV system.

show abstract

Feature Selection and Parameters Optimization of SVM Using Particle Swarm Optimization for Fault Classification in Power Distribution Systems

Cited by 55 publications

References 28 publications

Real-time online fingerprint image classification using adaptive hybrid techniques

Real-time online fingerprint image classification using adaptive hybrid techniques

A Three Decades of Marvellous Significant Review of Power Quality Events Regarding Detection & Classification

Particle Swarm Optimization Technique for Photovoltaic System

Contact Info

Product

Resources

About

Feature Selection and Parameters Optimization of SVM Using Particle Swarm Optimization for Fault Classification in Power Distribution Systems

Cited by 55 publications

References 28 publications

Real-time online fingerprint image classification using adaptive hybrid techniques

Real-time online fingerprint image classification using adaptive hybrid techniques

A Three Decades of Marvellous Significant Review of Power Quality Events Regarding Detection &amp; Classification

Particle Swarm Optimization Technique for Photovoltaic System

Contact Info

Product

Resources

About

A Three Decades of Marvellous Significant Review of Power Quality Events Regarding Detection & Classification