An Accurate Mathematical Epidemiological Model (SEQIJRDS) to Recommend Public Health Interventions Related to COVID-19 in Sri Lanka.

Abstract

COVID-19 has been causing negative impacts on various sectors in Sri Lanka as a result of the public health interventions that government had to implement in order to reduce the spreading of the disease. Equivalent work carried out in this context is outdated and close to ideal models. This research is carried out in a crucial time which the daily deaths are rapidly increasing which arise the requirement for an accurate and practical model to predict the mortality in order to take decisions regarding public health interventions. This paper presents a mathematical epidemiological model called SEQIJRDS to predict on COVID-19. The model has been validated for the COVID 19 pandemic in Sri Lanka. The results show that the model outstands many of the state-of-the-art SEIR epidemiological models such as Imperial, IHME once properly parameterized. At the end; this work recommends public health interventions at this crucial time to save people's lives based on the predictions of the proposed model. Specifically, 3 recommendations called minimal, sub-optimal and optimal recommendations are provided for public health interventions.

A Comprehensive Survey on Knowledge-Defined Networking

“…A Deep Neural Network (DNN) is an ANN that necessarily consists of one or more hidden layers between the input layer and the output layer of the ANN [99]. The weights and biases of the neurons are adjusted to minimize a user-defined loss function during DNN training in order to find a mathematical relationship between the inputs and the outputs [100]. Deep learning has been used for detecting network intrusions and for flow-based anomaly detection in the centralized controller, where deep learning has resulted in better performance (except for accuracy) compared to an approach using a Recurrent Neural Network (RNN) [101].…”

A Machine Learning-Aided Network Contention-Aware Link Lifetime- and Delay-Based Hybrid Routing Framework for Software-Defined Vehicular Networks

“…Given that the output (wireless link lifespan or one-hop channel delay) is non-categorical (continuous) and positive, we used the Rectified Linear Unit (ReLU) as the activation function for both the inner layers and the output layer [71]. The loss function for the neural network is a mean squared error, as both problems are non-linear regression models [72]. Using the Adam optimizer with an "Early stop callback" to terminate training if the training loss fails to decrease during the past 3 epochs, we trained the DNNs at an initial learning rate of 0.0001 that deteriorated by 3 percent each epoch for 175 epochs.…”

A Review of Blockchain Technology in Knowledge-Defined Networking, Its Application, Benefits, and Challenges

“…As another option, KDN has been put forth by academics as a framework for implementing artificial intelligence (AI) in SDN [35]. Knowledge-based networking, also known as the KDN paradigm, combines data and information to create understanding by employing AI models or rule-based models, such that KDN represents knowledge-based networking in all types of networks [36]. Despite the fact that the idea of a knowledge plane was first put forward in [37] almost 20 years ago, KDN has lately attracted interest because of the challenges associated with moving directly from regular networks to KDN and current developments in artificial intelligence.…”