Rajasthan Technical University

Yadav M., Perumal M., Srinivas M.

In this paper, we are working on a pandemic of novel coronavirus (COVID-19). COVID-19 is an infectious disease, it creates severe damage in the lungs. COVID-19 causes illness in humans and has killed many people in the entire world. However, this virus is reported as a pandemic by the World Health Organization (WHO) and all countries are trying to control and lockdown all places. The main objective of this work is to solve the five different tasks such as I) Predicting the spread of coronavirus across regions. II) Analyzing the growth rates and the types of mitigation across countries. III) Predicting how the epidemic will end. IV) Analyzing the transmission rate of the virus. V) Correlating the coronavirus and weather conditions. The advantage of doing these tasks to minimize the virus spread by various mitigation, how well the mitigations are working, how many cases have been prevented by this mitigations, an idea about the number of patients that will recover from the infection with old medication, understand how much time will it take to for this pandemic to end, we will be able to understand and analyze how fast or slow the virus is spreading among regions and the infected patient to reduce the spread based clear understanding of the correlation between the spread and weather conditions. In this paper, we propose a novel Support Vector Regression method to analysis five different tasks related to novel coronavirus. In this work, instead of simple regression line we use the supported vectors also to get better classification accuracy. Our approach is evaluated and compared with other well-known regression models on standard available datasets. The promising results demonstrate its superiority in both efficiency and accuracy.

Kumar S., Sharma B., Sharma V.K., Sharma H., Bansal J.C.

Agriculture is one of the prime sources of economy and a large community is involved in cropping various plants based on the environmental conditions. However, a number of challenges are faced by the farmers including different diseases of plants. The detection and prevention of plant diseases are the serious concern and should be treated well on time for increasing the productivity. Therefore, an automated plant disease detection system can be more beneficial for monitoring the plants. Generally, the most diseases may be detected and classified from the symptoms appeared on the leaves. For the same, extraction of relevant features plays an important role. A number of methods exists to generate high dimensional features to be used in plant disease classification problem such as SPAM, CHEN, LIU, and many more. However, generated features also include unrelated and inessential features that lead to degradation in performance and computational efficiency of a classification problem. Therefore, the choice of notable features from the high dimensional feature set is required to increase the computational efficiency and accuracy of a classifier. This paper introduces a novel exponential spider monkey optimization which is employed to fix the significant features from high dimensional set of features generated by SPAM. Furthermore, the selected features are fed to support vector machine for classification of plants into diseased plants and healthy plants using some important characteristics of the leaves. The experimental outcomes illustrate that the selected features by Exponential SMO effectively increase the classification reliability of the classifier in comparison to the considered feature selection approaches.

Mishra A.M., Purohit S.D., Owolabi K.M., Sharma Y.D.

In this article, we develop a mathematical model considering susceptible, exposed, infected, asymptotic, quarantine/isolation and recovered classes as in case of COVID-19 disease. The facility of quarantine/isolation have been provided to both exposed and infected classes. Asymptotic individuals either recovered without undergo treatment or moved to infected class after some duration. We have formulated the reproduction number for the proposed model. Elasticity and sensitivity analysis indicates that model is more sensitive towards the transmission rate from exposed to infected classes rather than transmission rate from susceptible to exposed class. Analysis of global stability for the proposed model is studied through Lyapunov's function.

Shekhawat S.S., Sharma H., Kumar S., Nayyar A., Qureshi B.

Feature selection is a technique commonly used in Data Mining and Machine Learning. Traditional feature selection methods, when applied to large datasets, generate a large number of feature subsets. Selecting optimal features within this high dimensional data space is time-consuming and negatively affects the system's performance. This paper proposes a new binary Salp Swarm Algorithm (bSSA) for selecting the best feature set from transformed datasets. The proposed feature selection method first transforms the original data-set using Principal Component Analysis (PCA) and fast Independent Component Analysis (fastICA) based hybrid data transformation methods; next, a binary Salp Swarm optimizer is used for finding the best features. The proposed feature selection approach improves accuracy and eliminates the selection of irrelevant features. We validate our technique on fifteen different benchmark data sets. We conduct an extensive study to measure the performance and feature selection accuracy of the proposed technique. The proposed bSSA is compared to Binary Genetic Algorithm (bGA), Binary Binomial Cuckoo Search (bBCS), Binary Grey Wolf Optimizer (bGWO), Binary Competitive Swarm Optimizer (bCSO), and Binary Crow Search Algorithm (bCSA). The proposed method attains a mean accuracy of 95.26% with 7.78% features on PCA-fastICA transformed datasets. The results show that bSSA outperforms the existing methods for the majority of the performance measures.

Singh P., Meena N.K., Yang J., Vega-Fuentes E., Bishnoi S.K.

The optimal integration of distributed energy resources (DERs) is a multiobjective and complex combinatorial optimization problem that conventional optimization methods cannot solve efficiently. This paper reviews the existing DER integration models, optimization and multi-criteria decision-making approaches. Further to that, a recently developed monarch butterfly optimization method is introduced to solve the problem of DER mix in distribution systems. A new multiobjective DER integration problem is formulated to find the optimal sites, sizes and mix (dispatchable and non-dispatchable) for DERs considering multiple key performance objectives. Besides, a hybrid method that combines the monarch butterfly optimization and the technique for order of preference by similarity to ideal solution (TOPSIS) is proposed to solve the formulated large-scale multi-criteria decision-making problem. Whilst the meta-heuristic optimization method generates non-dominated solutions (creating Pareto-front), the TOPSIS approach selects that with the most promising outcome from a large number of alternatives. The effectiveness of this approach is verified by solving single and multiobjective dispatchable DER integration problems over the benchmark 33-bus distribution system and the performance is compared with the existing optimization methods. The proposed model of DER mix and the optimization technique significantly improve the system performance in terms of average annual energy loss reduction by 78.36%, mean node voltage deviation improvement by 9.59% and average branches loadability limits enhancement by 50%, and minimized the power fluctuation induced by 48.39% renewable penetration. The proposed optimization techniques outperform the existing methods with promising exploration and exploitation abilities to solve engineering optimization problems. • Introduces Monarch butterfly optimization for solving DER integration problems. • A novel mix with technique for order of preference by similarity to ideal solution. • A new multi-criteria decision-making problem for DER mix in distribution networks. • Comparison of proposed and existing methods on standard 33-bus distribution system. • Notable annual energy loss reduction (78.36%) with improved stability and voltages.

Khatti J., Grover K.S.

A comparison between deep learning and standalone models in predicting the compaction parameters of soil is presented in this research. One hundred and ninety and fifty-three soil samples were randomly picked up from two hundred and forty-three soil samples to create training and validation datasets, respectively. The performance and accuracy of the models were measured by root mean square error (RMSE), coefficient of determination (R2), Pearson product-moment correlation coefficient (r), mean absolute error (MAE), variance accounted for (VAF), mean absolute percentage error (MAPE), weighted mean absolute percentage error (WMAPE), a20-index, index of scatter (IOS), and index of agreement (IOA). Comparisons between standalone models demonstrate that the model MD 29 in Gaussian process regression (GPR) and model MD 101 in support vector machine (SVM) can achieve over 96% of accuracy in predicting the optimum moisture content (OMC) and maximum dry density (MDD) of soil, and outperformed other standalone models. The comparison between deep learning models shows that the models MD 46 and MD 146 in long short-term memory (LSTM) predict OMC and MDD with higher accuracy than ANN models. However, the LSTM models outperformed the GPR models in predicting the compaction parameters. The sensitivity analysis illustrates that fine content (FC), specific gravity (SG), and liquid limit (LL) highly influence the prediction of compaction parameters.

Saini P., Gidwani L.

Battery energy storage system technique work as alternative load during low demand situation by storing the excess generation and work as alternative power generation source by discharging the stored generation during peak demand. In this work, a comprehensive assessment is performed for battery energy storage system installation and their capacities selection by utilizing the Photovoltaics (PV) output in radial distribution network by considering commercial, residential and industrial time varying load models. The objective of proposed the work is to reduce annual energy losses, mitigate reverse power flow and overvoltage problem and provide peak power dispatch during peak demand in distribution network. A comparative investigation is performed by considering PV and PV-BESS case for each type of load model. Furthermore, the battery energy storage system (BESS) function developed that decide the time and capacity of charging and discharging in order to manage PV penetration and improve the voltage profile, minimize the daily energy losses and control the reverse power flow in the distribution system without deviating the operational limits. A voltage based sensitivity method is developed at initial step to find out the most prominent node in distribution network for BESS installation. The objective of the problem is resolved by genetic algorithm to find out the optimal solution and to assess the comparison of technical parameters between considered cases. The simulation results on IEEE 69 bus test system show that the proposed methodology for BESS placement decreases the annual energy losses, enhances the PV penetration and reduces the overvoltage and mitigate the reverse power flow. Results of this paper also shows that it is possible to dispatch peak power during the peak load hours for each type of load model. • A technical assessment is performed for optimal allocation of BESS in distribution network. • Time varying load models are considered for BESS allocation in distribution network. • A sensitivity-based method is used to identify the prominent location for BESS allocation. • BESS charging and discharging function is formulated for optimal daily scheduling of BESS units.

Shyamsunder, Bhatter S., Jangid K., Abidemi A., Owolabi K.M., Purohit S.D.

This study proposes a new fractional mathematical model to study the impact of vaccination on COVID-19 outbreaks by categorizing infected people into non-vaccinated, first dose-vaccinated, and second dose-vaccinated groups and exploring the transmission dynamics of the disease outbreaks. We present a non-linear integer order mathematical model of COVID-19 dynamics and modify it by introducing Caputo fractional derivative operator. We start by proving the good state of the model and then calculating its reproduction number. The Caputo fractional-order model is discretized by applying a reliable numerical technique. The model is proven to be stable. The classical model is fitted to the corresponding cumulative number of daily reported cases during the vaccination regime in India between 01 August 2021 and 21 July 2022. We explore the sensitivities of the reproduction number with respect to the model parameters. It is shown that the effective transmission rate and the recovery rate of unvaccinated infected individuals are the most sensitive parameters that drive the transmission dynamics of the pandemic in the population. Numerical simulations are used to demonstrate the applicability of the proposed fractional mathematical model via the memory index at different values of 0.7,0.8,0.9 and 1. We discuss the epidemiological significance of the findings and provide perspectives on future health policy tendencies. For instance, efforts targeting a decrease in the transmission rate and an increase in the recovery rate of non-vaccinated infected individuals are required to ensure virus-free population. This can be achieved if the population strictly adhere to precautionary measures, and prompt and adequate treatment is provided for non-vaccinated infectious individuals. Also, given the ongoing community spread of COVID-19 in India and almost the pandemic-affected countries worldwide, the need to scale up the effort of mass vaccination policy cannot be overemphasized in order to reduce the number of unvaccinated infections with a view to halting the transmission dynamics of the disease in the population.

Agrawal P., Dadheech P.K., Jat R.N., Nisar K.S., Bohra M., Purohit S.D.

In the current framework, a computational simulation for 2-D γ − A L 2 O 3 nanofluid flow over a stretching surface with Marangoni convection embedded in porous medium is presented. Here the magnetic field and nonlinear thermal radiation is also applied with heat source/sink. A comparative analysis is presented for water and ethylene glycol based γ − A L 2 O 3 nanofluids. A mathematical model of the present problem with appropriate boundary conditions is given in terms of partial differential equations. Numerical calculation of this model is computed by the Runge-Kutta method of order four with shooting technique by utilizing the suitable similarity transformations. Temperature and velocity fields are studied analytically and illustrated by the graphs for various flow control parameters. Results shows that the temperature profile of the γ − A l 2 O 3 − H 2 O nanofluid is always higher than the γ − A l 2 O 3 − C 2 H 6 O 2 nanofluid hence γ − A l 2 O 3 − C 2 H 6 O 2 nanofluid becomes more significant in cooling process then γ − A l 2 O 3 − H 2 O nanofluid.

Singh J., Kumar D., Purohit S.D., Mishra A.M., Bohra M.