In this paper, Deep Learning-based models are used for predicting the number of novel coronavirus (COVID-19) positive reported cases for 32 states and union territories of India. Recurrent neural ...network (RNN) based long-short term memory (LSTM) variants such as Deep LSTM, Convolutional LSTM and Bi-directional LSTM are applied on Indian dataset to predict the number of positive cases. LSTM model with minimum error is chosen for predicting daily and weekly cases. It is observed that the proposed method yields high accuracy for short term prediction with error less than 3% for daily predictions and less than 8% for weekly predictions. Indian states are categorised into different zones based on the spread of positive cases and daily growth rate for easy identification of novel coronavirus hot-spots. Preventive measures to reduce the spread in respective zones are also suggested. A website is created where the state-wise predictions are updated using the proposed model for authorities,researchers and planners. This study can be applied by other countries for predicting COVID-19 cases at the state or national level.
Embedded variable frequency induction motor drives are now an integral part of any industry due to their improved speed regulation and fast dynamic response. Hence, their diagnosis becomes vital to ...avoid downtimes and economic losses. In this paper, a technique based on a recent enhancement on wavelets, known as complex wavelets, is proposed for identifying multiple faults in vector controlled induction motor drives (VCIMDs). Radial, axial, and tangential vibrations are analyzed for diagnostic purpose. Initially, a relatively simple thresholding based method is investigated for feasibility of diagnosis under variable frequency and load conditions. In the second part, the feature extraction and classifier modeling are discussed, in which the nearly shift-invariant complex wavelet based model is compared with the discrete wavelet transform (DWT) for its applicability in detecting multiple faults. The fault conditions considered here are the most prominent ones such as interturn fault, interturn fault under progression, and bearing damage. Comparable performances of support vector machine (SVM) based models and simple technique based on k-nearest neighbor (k-NN) show the importance of efficient representation of input space by analytical wavelet based feature extraction. The performance indexes show the applicability of the scheme for industrial drives under variable frequencies and load conditions.
The electroencephalogram (EEG) signals are commonly used for diagnosis of epilepsy. In this paper, we present a new methodology for EEG-based automated diagnosis of epilepsy. Our method involves ...detection of key points at multiple scales in EEG signals using a pyramid of difference of Gaussian filtered signals. Local binary patterns (LBPs) are computed at these key points and the histogram of these patterns are considered as the feature set, which is fed to the support vector machine (SVM) for the classification of EEG signals. The proposed methodology has been investigated for the four well-known classification problems namely, 1) normal and epileptic seizure, 2) epileptic seizure and seizure free, 3) normal, epileptic seizure, and seizure free, and 4) epileptic seizure and nonseizure EEG signals using publically available university of Bonn EEG database. Our experimental results in terms of classification accuracies have been compared with existing methods for the classification of the aforementioned problems. Further, performance evaluation on another EEG dataset shows that our approach is effective for classification of seizure and seizure-free EEG signals. The proposed methodology based on the LBP computed at key points is simple and easy to implement for real-time epileptic seizure detection.
This paper introduces a humpback whale hunting behavior inspired whale optimization with differential evolution (WODE) technique-based tracking algorithm for the maximum power point tracking in the ...dynamic as well as the steady-state conditions of a partially shaded solar photovoltaic (PV) system. This "WODE" technique is used for quick and oscillation-free tracking of the global best peak position in a few steps. The unique advantage of this algorithm for maximum power point tracking in partially shaded condition is as, it is free from common and generalized problems of other evolutionary techniques, like longer convergence duration, a large number of search particles, steady-state oscillation, heavy computational burden, etc., which creates power loss and oscillations in output. This hybrid algorithm is tested in MATLAB simulation and verified on a developed hardware of the solar PV system, which consists of multiple peaks in voltage-power curve. Moreover, the tracking ability is compared with the state-of-the-art methods. The satisfactory steady-state and dynamic performances of the new hybrid technique under variable irradiance and temperature levels show the superiority over the state-of-the-art control methods.
•Extreme Learning Machines coupled with Wavelet technique to develop a hybrid model.•Ensembling Technique applied for better and reliable predictive performance.•Models are tested with data from ...Ontario, PJM, Italy and New York Market.•MeDE index is found to be more suitable than other indices used contemporarily.
Accurate electricity price forecasting is a formidable challenge for market participants and managers owing to high volatility of the electricity prices. Price forecasting is also the most important management goal for market participants since it forms the basis of maximizing profits. This study investigates the performance of a novel neural network technique called Extreme Learning Machine (ELM) in the price forecasting problem. Keeping in view the risk associated with electricity markets with highly volatile prices, relying on a single technique is not so profitable. Therefore ELM has been coupled with the Wavelet technique to develop a hybrid model termed as WELM (wavelet based ELM) to improve the forecasting accuracy as well as reliability. In this way, the unique features of each tool are combined to capture different patterns in the data. The robustness of the model is further enhanced using the ensembling technique. Performances of the proposed models are evaluated by using data from Ontario, PJM, New York and Italian Electricity markets. The experimental results demonstrate that the proposed method is one of the most suitable price forecasting techniques.
This paper deals with a new version of perturb and observe tracking algorithm for maximum power extraction from the solar photovoltaic panel, which has self-predictive and decision taking ability. ...The working principle of self-predictive perturb and observe (SPP&O) algorithm is based on three consecutive operating points on the power-voltage characteristic. Out of three points, first two points very smartly detects the dynamic condition, as well as in normal condition, quickly searches the maximum power point (MPP) region. Moreover, by using a circular analogy, all points decide the optimal operating position for next iteration, which is responsible for quick MPP tracking as well as improved dynamic performance. Here, in every new iteration, the step-size is reduced by 90% from the previous step-size, which provides an oscillation-free steady-state performance. The effectiveness of the proposed technique is validated by MATLAB simulation as well as tested on hardware prototype. Moreover, comparison between SPP&O algorithm and state of art methods is made. Its satisfactory dynamic and steady-state behaviors with low algorithm complexity as well as the low computational burden of the SPP&O algorithm show the superiority over state of the art methods.
•India’s largest solar energy potential State is being explored here.•Practical data obtained National Institute of Wind Energy and Wind Resource, India.•Data has been pre-processed using three ...different signal decomposition algorithms.•Application of ANFIS technique for Solar Irradiance prediction.•Highly accurate results with less than 2 %MAPE obtained independent of site locations.
In this study, a case study of four Indian cities i.e. Ajmer, Jaipur, Jodhpur and Kota in the state of Rajasthan are considered wherein 30 min ahead data have been obtained via the data site of the National Institute of Wind Energy and Wind Resource (NIWE) on which a proposed Global Horizontal Irradiance (GHI) prediction technique for all seasons is applied. Here, data has been pre-processed using three different signal decomposition algorithms in parallel i.e. Empirical Mode Decomposition (EMD), Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Ensemble Empirical Mode Decomposition (EEMD). Further, based on Pearson’s Correlation Coefficient (PCC), corresponding IMFs & corresponding Residual obtained using the three decomposition algorithms are compared amongst each other respectively and that corresponding IMFs & corresponding Residual are chosen for signal reconstruction which are having highest correlation coefficient values. Thereafter, these selected IMFs and Residual from each algorithm are combined to form single input. In this way, three inputs formed from three decomposition algorithms based on the PCC values are fed to Adaptive Neuro-Fuzzy Inference System (ANFIS) for solar irradiance forecasting. The proposed technique shows significantly higher accurate results with less than 2 % MAPE for different seasons considered at the site locations considered. Further, it terms of performance, the proposed technique is found to be independent of site location.
Interturn fault diagnosis of induction machines has been discussed using various neural network-based techniques. The main challenge in such methods is the computational complexity due to the huge ...size of the network, and in pruning a large number of parameters. In this paper, a nearly shift insensitive complex wavelet-based probabilistic neural network (PNN) model, which has only a single parameter to be optimized, is proposed for interturn fault detection. The algorithm constitutes two parts and runs in an iterative way. In the first part, the PNN structure determination has been discussed, which finds out the optimum size of the network using an orthogonal least squares regression algorithm, thereby reducing its size. In the second part, a Bayesian classifier fusion has been recommended as an effective solution for deciding the machine condition. The testing accuracy, sensitivity, and specificity values are highest for the product rule-based fusion scheme, which is obtained under load, supply, and frequency variations. The point of overfitting of PNN is determined, which reduces the size, without compromising the performance. Moreover, a comparative evaluation with traditional discrete wavelet transform-based method is demonstrated for performance evaluation and to appreciate the obtained results.
The disturbances including harmonics, distortions, transients, fluctuations, and dc offsets in the grid voltages and uncertain load currents, are the most challenging issues in the scenario of ...renewable sources based energy generating systems integrated to the conventional grid. A three-phase, double stage, grid tied solar photovoltaic based distributed generating (SPVDG) system fulfilling multiple objectives, is presented using an adaptive digital disturbance estimator (DDE) and a peak power tracking scheme. The adaptive DDE has the detection proficiency of all the harmonics and lumped disturbances resulting fundamental component estimation of the periodic signals such as grid voltages and load currents. This system deals with objectives such as reactive power compensation, load balancing, peak solar power extraction, operation at grid voltage sags and swells, estimation of harmonics, dc offsets, disturbances, etc. and their elimination. Moreover, this system ensures the active power flow from the SPVDG system to the local loads as well as the grid through a three-phase voltage source converter (VSC). An adaptive technique is used to adjust the dc-link voltage with respect to the grid voltage variation(s) that is advantageous in terms of losses in the VSC. A Lyapunov function candidate is considered to estimate the gains of the disturbance estimator confirming its parameter convergence. Considering the aforementioned objectives, SPVDG system with the proposed DDE-based control scheme, is simulated using Matlab /Simulink environment and then practically implemented using a prototype developed in the laboratory to confirm its performance under steady and dynamic conditions.
The brain tumor is the deadliest disease in adults as it arises due to an abnormal mass of cells that grows rapidly and it alters the proper functioning of the organs. In clinical practice, ...radiographic images of different modalities are used to diagnose types of brain tumors, their size, and location. The proposed work aims to automatically classify, localize, and segment brain tumors from T1W-CE Magnetic Resonance Image (MRI) datasets. The T1W-CE MRI dataset is divided into 8:1:1, i.e., 80% training set, 10% of each validation, and testing set. To address the overfitting issues, the training data set is augmented using 2-levels wavelet decomposition and geometrical operations (scaling, rotation, translation). Performance of pre-trained DarkNet model (DarkNet-19 and DarkNet-53) is evaluated for the multi-class classification and localization of brain tumors. The best performing pre-trained DarkNet model achieved 99.60% of training accuracy and 98.81% of validation accuracy. The performance evaluation parameters confirm the superiority of the proposed methodology in comparison to the state-of-the-art on the T1W-CE MRI dataset. On 1070 T1W-CE testing images, the best-performing pre-trained DarkNet-53 model obtained a testing accuracy of 98.54% and Area Under Curve (AUC) of 0.99. The tumor is segmented using a 2-D superpixel segmentation technique with an average dice index of 0.94 ± 2.6% on the 793 brain tumor testing data. To prove the superiority of the proposed technique, it is implemented on MRI images from the BraTS2018 dataset. The comparative analysis of performance evaluation parameters of the proposed methodology with the state-of-the-art technique proves its robustness and clinical significance.
•Address the data overfitting issue by augmenting training data using geometrical and 2-levels of wavelet decomposition techniques.•Multi-class classification framework for tumor classification in all the three views for multiple modality.•Superpixel techniques is used for effective discrimination of tumor tissue regions.