No abstract

We propose a novel heuristic algorithm that performs geographical routing based on a greedy approach. Our proposed scheme first allocates the geographic locations of the source and the destination nodes influenced by their GPS information. A virtual Euclidean path is considered as a reference line to choose appropriate node for routing. Then, a multi-hop technique is adopted to establish routing path between them. The nodes in the routing paths are chosen in a greedy manner, having minimum distance from the Euclidean line and having minimum overlap in coverage area with its immediate predecessor node. The elegance in our proposed method is that it is capable of routing data successfully from the source to the destination, with nominal number of hops, and hence improves power handling capability of the network. Performance analysis of our algorithm is done in terms of routing overhead, and average end-to-end delay measure.

Momordica dioica have proven medicinal potential of antidiabetic, antiviral and immune stimulating properties. Flavonoids and triterpenoids from M. dioica were more extensively investigated for antiviral, antidiabetic and immunomodulatory activities. In this present study, we have predicted the reported bioactive flavonoids and triterpenoids of the plant against the SARS-CoV-2 main protease, RNAdependent RNA polymerase (RdRp), spike protein, angiotensin converting enzyme (ACE-2) receptor and dipeptidyl peptidase (DPP4) receptor through molecular docking and in silico ADME predictions methods. According to the binding affinities, the two triterpenoids, hederagenin and oleanolic acid exhibited the best docking scores with these proteins than the catechin and quercetin with compared to standard remdesivir, favipiravir and hydroxychloroquine. The in vitro protein-drug studies have also showed significant interaction of catechin and quercetin compounds than standard drugs. The in silico binding studies correlated with the in silico binding studies. Further, M. dioica being used as antidiabetic and its metabolite had significant interaction with DDP4, a comorbidity protein involved in aiding the viral entry. Out of all the natural ligands, quercetin was reported relatively good and safe for humans with high gastrointestinal tract permeability and poor blood brain barrier crossing abilities. Hence, M. dioica phytocompounds reflects promising therapeutic properties against SARS-CoV-2 infections under comorbid conditions such as diabetes, cardiovascular disease and kidney disorders.

Financial time-series forecasting, and profit maximization is a challenging task, which has attracted the interest of several researchers and is immensely important for investors. In this paper, we present a deep learning system, which uses a variety of data for a subset of the stocks on the NASDAQ exchange to forecast the stock price. Our framework allows the use of a variational autoencoder (VAE) to remove noise and time-series data engineering to extract higher-level features. A Stacked LSTM Autoencoder is used to perform multi-step-ahead prediction of the stock closing price. This prediction is used by two profit-maximization strategies that include greedy approach and short selling. Besides, we use reinforcement learning as a third profit-enhancement strategy and compare these three strategies to offline strategies that use the actual future prices. Results show that the proposed methods outperform the state-of-the-art time-series forecasting approaches in terms of predictive accuracy and profitability.

No abstract