Search

Purpose: The purpose of this paper is to develop a hybrid algorithm, which is a blend of auto-regressive integral moving average (ARIMA) and multilayer perceptron (MLP) for addressing the non-linearity of the load time series. Design/methodology/approach: Short-term load forecasting is a complex process as the nature of the load-time series data is highly nonlinear. So, only ARIMA-based load forecasting will not provide accurate results. Hence, ARIMA is combined with MLP, a deep learning approach that models the resultant data from ARIMA and processes them further for Modelling the non-linearity. Findings: The proposed hybrid approach detects the residuals of the ARIMA, a linear statistical technique and models these residuals with MLP neural network. As the non-linearity of the load time series is approximated in this error modeling process, the proposed approach produces accurate forecasting results of the hourly loads. Originality/value: The effectiveness of the proposed approach is tested in the laboratory with the real load data of a metropolitan city from South India. The performance of the proposed hybrid approach is compared with the conventional methods based on the metrics such as mean absolute percentage error and root mean square error. The comparative results show that the proposed prediction strategy outperforms the other hybrid methods in terms of accuracy. [ABSTRACT FROM AUTHOR]

• Compartment model susceptible-exposed-home quarantine-infected-hospital quarantine-recovered is developed to understand the transmitting behaviour of pandemic COVID-19 in human population. • Local and global asymptotic stability established for the conditions of reproduction number. • Statistical Analysis has been performed to analyse the impact of lockdown in different part of the world badly infected by COVID-19 with India. • Also time series forecasting model for the case fatality rate in India and time series forecasting of actual cases versus predicted cases in India is performed. Pandemic COVID-19 which has infected more than 35,027,546 people and death more than 1,034,837 people in 235 countries as on October 05, 2020 has created a chaos across the globe. In this paper, we develop a compartmental epidemic model to understand the spreading behaviour of the disease in human population with a special case of Bhilwara, a desert town in India where successful control measures TTT (tracking, testing and treatment) was adopted to curb the disease in the very early phase of the spread of the disease in India. Local and global asymptotic stability is established for endemic equilibrium. Extensive numerical simulations with real parametric values are performed to validate the analytical results. Trend analysis of fatality rate, infection rate, and impact of lockdown is performed for USA, European countries, Russia, Iran, China, Japan, S. Korea with a comparative assessment by India. Kruskal - Wallis test is performed to test the null hypothesis for infected cases during the four lockdown phases in India. It has been observed that there is a significant difference at both 95% and 99% confidence interval in the infected cases, recovered cases and the case fatality rate during all the four phases of the lockdown. [ABSTRACT FROM AUTHOR]

• A novel compartmental epidemic model SIPHERD is employed for COVID-19 prediction for India where it has reached at alarming level. • Impact of lockdown and the number of tests conducted per day on predictions of containment is studied. • Purely Asymptomatic cases and spread from them as well as Exposed in incubation period considered. • Increasing the tests per day by 10k every day, stringent measures on social-distancing and strict lockdown in July have significant impact on the disease spread. Originating from Wuhan, China, in late 2019, and with a gradual spread in the last few months, COVID-19 has become a pandemic crossing 9 million confirmed positive cases and 450 thousand deaths. India is not only an overpopulated country but has a high population density as well, and at present, a high-risk nation where COVID-19 infection can go out of control. In this paper, we employ a compartmental epidemic model SIPHERD for COVID-19 and predict the total number of confirmed, active and death cases, and daily new cases. We analyze the impact of lockdown and the number of tests conducted per day on the prediction and bring out the scenarios in which the infection can be controlled faster. Our findings indicate that increasing the tests per day at a rapid pace (10k per day increase), stringent measures on social-distancing for the coming months and strict lockdown in the month of July all have a significant impact on the disease spread. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]