In this article, we study a fractional-order mathematical model representing tritrophic interaction amongst plants, herbivores, and carnivores with Caputo derivative. The existence and uniqueness of the system are investigated by fixed point theory, while the stability is studied by Hyers-Ulam and generalized Hyers-Ulam stability analysis. The Adams-Bashforth-Moulton scheme is used for numerical calculations. From numerical simulations, it is observed that when the fractional order decreases the system converges to a stable state. It is observed that for a small value of fractional order, the system approaches a stable state rapidly as compared to the integer order. The chaotic behaviour of the system is studied using the Lyapunov spectrum. It is noted that two positive exponents of the proposed model show that the system is hyper-chaotic. It is also observed that a small value of attraction constant disrupts the system due to volatile organic compounds.

A widely used method that constructs features with the incorporation of so-called grammatical evolution is proposed here to predict the COVID-19 cases as well as the mortality rate. The method creates new artificial features from the original ones using a genetic algorithm and is guided by BNF grammar. After the artificial features are generated, the original data set is modified based on these features, an artificial neural network is applied to the modified data, and the results are reported. From the comparative experiments done, it is clear that feature construction has an advantage over other machine-learning methods for predicting pandemic elements.