Therapeutic Options for the Treatment of 2019-Novel Coronavirus in India: A Review

Abstract

Purpose: As of from 30 Jan to 31 May, 2020, more than 182,143 confirmed cases reported in India along with 86,984 recovered cases and 5164 deceased cases of COVID-19. More than 53 countries are also affected with this pandemic virus. However, the lack of specific drugs to prevent/treat this pandemic disease is a major problem at this current scenario. In this regard, this systemic review was conducted to identify the therapeutic approaches and researches which are ongoing in India against COVID-19. Methods: We had screened Google Scholar database with the keywords nCoV, corona virus in India, effect of SARS-CoV-2 in India, 2019-nCoV, treatment pattern in India for nCoV and therapy used to treat nCoV in India. In the final review we had included a total of 49 articles. Results: As a result we had found that Indian Council of Medical Research and NIH have given a standard guideline of Hydroxychloroquine and other antiviral drugs for nCoV, and also there are various researches going on related to nCoV treatment like, chemicals from natural products, herbs and spices commonly used in India, combination therapy of lopinavir and ritonavir, ultra-violet radiation therapy, molecular dynamic (MD) simulations of molecules for vaccine preparation, Convalescent plasma transfusion (CPT) therapy and many more. Conclusions: New drugs and therapy are in the premature stage for this hazardous pandemic. We need more time to gain the detailed knowledge of the life cycle of the nCoV, which can speed up the drug/vaccine development process against nCoV.

Research on Traffic Congestion Prediction Based on XGBoost

“…[4] On the one hand, compared to GBDT which only uses first-order derivatives, the XGBoost algorithm carries out second-order derivatives to make the loss function more accurate and adds a regular term in the objective function, Ω(𝑓 𝑘 ) which is used to control the complexity of the model to avoid overfitting; on the other hand, the XGBoost algorithm is an advanced version of the gradient boosting decision tree, which grows the decision tree by constant feature splitting, and in the process of learning the decision tree, it fits the error between the actual value and the predicted value of the model to improve the accuracy of prediction as shown in Figure 1 and Figure 2. [5] Figure 1: XGBoost algorithm integration flow (Left) Figure 1: Flowchart of the gradient boosting decision tree model (Right)…”