Sannistha Banerjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sannistha Banerjee has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Subhajit Maur
Ramkrishna Mahato Government Engineering College
6 shared publications - Chandan Jana
Hooghly Engineering and Technology College
5 shared publications - Sovan Dalai
Electrical Engineering Department, Jadavpur University, Kolkata, India
5 shared publications Partha Sarathee Bhowmik
2 shared publications- Partha Sarathee Bhowmik
National Institute of Technology Durgapur
2 shared publications - Aashish Kumar Bohre
Department of Electrical Engineering, National Institute of Technology Durgapur, Durgapur, India
1 shared publication
Latest Publications
- 14 May 2026
- Published by Elsevier in Next Research
- Vol. 10
IoT-based real-time power system disturbances detection using CNN-aided BiLSTM
- 14 May 2026
- Published by Elsevier in Next Research
- Vol. 10
IoT-based real-time power system disturbances detection using CNN-aided BiLSTM
- 29 March 2025
- Published by Springer Nature
- p. 391-402
Reliable Protection Scheme for Distributed Generator-Based Network Using KNN and Ensemble Bagged Tree Classifier
- 29 March 2025
- Published by Springer Nature
- p. 391-402
Reliable Protection Scheme for Distributed Generator-Based Network Using KNN and Ensemble Bagged Tree Classifier
- 2 January 2025
- Published by Taylor & Francis in Smart Science
- Vol. 13 (1) , 109-119
A comparative study of decision tree-based learners to classify the switching transient disturbances in real microgrid network
- 2 January 2025
- Published by Taylor & Francis in Smart Science
- Vol. 13 (1) , 109-119
A comparative study of decision tree-based learners to classify the switching transient disturbances in real microgrid network
- 25 December 2024
- Published by Elsevier in Electric Power Systems Research
- Vol. 241
Customized CNN based classification of power system disturbances using recurrence plots
- 25 December 2024
- Published by Elsevier in Electric Power Systems Research
- Vol. 241
Customized CNN based classification of power system disturbances using recurrence plots
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (21) , 35191-35198
Sensing of Power System Disturbances Using CNN-Aided Tailored BiLSTM Model
Fast and accurate detection of power system disturbance-creating events is very much essential for the safe and reliable operation of today’s power distribution network. This task becomes more challenging when two events occur simultaneously. In this work, a deep learning network-based classifier has been proposed to classify the events that are likely to occur in the power system. Here, a few normal events like switching, load changing, all feasible faults, and five dual events have been considered. All acquired disturbance signals are allowed to go through three major stages. At the initial stage, signal-to-image conversion takes place using continuous wavelet transform (CWT) followed by a couple of convolution operations for feature extraction, and then, the extracted time series data have been fed to the input of Bidirectional Long Short Term Memory (BiLSTM) module. Finally, the softmax output classifier has been applied. Few other popular classifiers have also been studied for comparison. Using this proposed method, 98.57% accuracy has been achieved considering twenty-one feasible events.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (21) , 35191-35198
Sensing of Power System Disturbances Using CNN-Aided Tailored BiLSTM Model
Fast and accurate detection of power system disturbance-creating events is very much essential for the safe and reliable operation of today’s power distribution network. This task becomes more challenging when two events occur simultaneously. In this work, a deep learning network-based classifier has been proposed to classify the events that are likely to occur in the power system. Here, a few normal events like switching, load changing, all feasible faults, and five dual events have been considered. All acquired disturbance signals are allowed to go through three major stages. At the initial stage, signal-to-image conversion takes place using continuous wavelet transform (CWT) followed by a couple of convolution operations for feature extraction, and then, the extracted time series data have been fed to the input of Bidirectional Long Short Term Memory (BiLSTM) module. Finally, the softmax output classifier has been applied. Few other popular classifiers have also been studied for comparison. Using this proposed method, 98.57% accuracy has been achieved considering twenty-one feasible events.
- 22 August 2024
- Published by Elsevier in Measurement
- Vol. 240
Machine learning based classifiers for dynamic and transient disturbance classification in smart microgrid system
- 22 August 2024
- Published by Elsevier in Measurement
- Vol. 240
Machine learning based classifiers for dynamic and transient disturbance classification in smart microgrid system
- 14 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 8 (6) , 1-4
Power System Disturbance Classification Using CWT Guided Customized AlexNet CNN
This letter aims at designing a convolution neural network (CNN)-based classifier that detects and classifies 13 different types of power system events causing poor power quality. Early and accurate detection of those classes of disturbances helps power engineers take quick and suitable measures to protect power system components and to supply uninterrupted power to the consumers. The whole process comprises of the sensing of disturbance creating current signals from experimental setup, filtration by unsupervised $k$ -mean machine learning to remove noisy data, Big Data generation, architectural modification of AlexNet CNN, time–frequency informative image creation by continuous wavelet transform followed by convolution using kernel filters, and classification and performance evaluation. The proposed customized CNN has been compared with other benchmark CNN architectures. The method has shown 98.46 ${\%}$ accuracy with minimum computational time.
- 14 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 8 (6) , 1-4
Power System Disturbance Classification Using CWT Guided Customized AlexNet CNN
This letter aims at designing a convolution neural network (CNN)-based classifier that detects and classifies 13 different types of power system events causing poor power quality. Early and accurate detection of those classes of disturbances helps power engineers take quick and suitable measures to protect power system components and to supply uninterrupted power to the consumers. The whole process comprises of the sensing of disturbance creating current signals from experimental setup, filtration by unsupervised $k$ -mean machine learning to remove noisy data, Big Data generation, architectural modification of AlexNet CNN, time–frequency informative image creation by continuous wavelet transform followed by convolution using kernel filters, and classification and performance evaluation. The proposed customized CNN has been compared with other benchmark CNN architectures. The method has shown 98.46 ${\%}$ accuracy with minimum computational time.
- 22 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (11) , 18035-18042
Mathematical Morphology-Based Sensing of Power System Disturbances Using PCA-Aided Support Vector Machine
This paper introduces a methodology of Mathematical Morphology (MM) based Power System Disturbances (PSD) sensing using Principal Component Analysis aided Support Vector Machine (SVM). The PSD data is acquired from a real time laboratory based isolated Distributed Generator (DG) having a grid synchronization arrangement where a large number of system disturbances have been created to develop and validate the model. The statistical features are extracted from the acquired data using Mathematical Morphology (MM). The high dimensional correlated feature variables are transformed into a smaller set of uncorrelated variables called principal components using Principal Component Analysis (PCA). Finally, a Support Vector Machine (SVM) based Machine Learning (ML) algorithm has been proposed using a quadratic polynomial kernel function to classify the disturbances and the performance of the algorithm has also been assessed. The results show that the performance of the proposed method is acceptable for sensing PSD. The present method is generic in nature and can be implemented for similar problems.
- 22 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (11) , 18035-18042
Mathematical Morphology-Based Sensing of Power System Disturbances Using PCA-Aided Support Vector Machine
This paper introduces a methodology of Mathematical Morphology (MM) based Power System Disturbances (PSD) sensing using Principal Component Analysis aided Support Vector Machine (SVM). The PSD data is acquired from a real time laboratory based isolated Distributed Generator (DG) having a grid synchronization arrangement where a large number of system disturbances have been created to develop and validate the model. The statistical features are extracted from the acquired data using Mathematical Morphology (MM). The high dimensional correlated feature variables are transformed into a smaller set of uncorrelated variables called principal components using Principal Component Analysis (PCA). Finally, a Support Vector Machine (SVM) based Machine Learning (ML) algorithm has been proposed using a quadratic polynomial kernel function to classify the disturbances and the performance of the algorithm has also been assessed. The results show that the performance of the proposed method is acceptable for sensing PSD. The present method is generic in nature and can be implemented for similar problems.
- 24 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 306-309
Wavelet Aided KNN Based Power System Disturbances Classification
In this work, few most commonly occurring Power System Disturbances (PSD) have been considered for their detection and classification with the help of K Nearest Neighbor (KNN) based Machine Learning (ML) technique. Experimentally created disturbance signals have been processed using Discrete Wavelet Transform (DWT) to obtain time and frequency domain information before they have been fed to KNN based classifiers. The switching, line faults and load change have been chosen as disturbing creating events. The performance of the proposed method has been compared with linear discriminant and linear support vector machine based methods. The accuracy level of the proposed method has been shown to be 97.1%.
- 24 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 306-309
Wavelet Aided KNN Based Power System Disturbances Classification
In this work, few most commonly occurring Power System Disturbances (PSD) have been considered for their detection and classification with the help of K Nearest Neighbor (KNN) based Machine Learning (ML) technique. Experimentally created disturbance signals have been processed using Discrete Wavelet Transform (DWT) to obtain time and frequency domain information before they have been fed to KNN based classifiers. The switching, line faults and load change have been chosen as disturbing creating events. The performance of the proposed method has been compared with linear discriminant and linear support vector machine based methods. The accuracy level of the proposed method has been shown to be 97.1%.
- 10 September 2023
- Published by Taylor & Francis in Smart Science
- Vol. 11 (4) , 744-758
Multiclass transient event classification in hybrid distribution network based on co-training of fine KNN and ensemble KNN classifier
- 10 September 2023
- Published by Taylor & Francis in Smart Science
- Vol. 11 (4) , 744-758
Multiclass transient event classification in hybrid distribution network based on co-training of fine KNN and ensemble KNN classifier