No abstract

On March 11, 2020, the World Health Organization declared COVID-19 as a pandemic. Since then, many countries have experienced the rapid transmission of this respiratory disease among their populations and have exercised many strategies to mitigate the spread of this disease. The prediction of the transmission dynamics serves important roles in designing mitigation strategies. However, due to the unknown characteristics of this disease, as well as the geographical and political factors, building efficient models of the dynamics for many countries is difficult. The objective of this study is to develop a transmission dynamics predictor that takes advantage of the time differences among many countries with respect to transmission of this disease, in that some countries experienced earlier outbreaks than others. The primary novelty of the proposed method is that, unlike many existing transmission predictors that require parameters based on prior knowledge of the epidemiology of past viruses, the proposed method only requires the transmission similarities between countries in the publicly available data for this current disease. In this paper, the viability and limitations of the proposed method are reported and discussed.

Kohonen's self-organizing map (SOM) is used to map high-dimensional data into a low-dimensional representation (typically a 2-D or 3-D space) while preserving their topological characteristics. A major reason for its application is to be able to visualize data while preserving their relation in the high-dimensional input data space as much as possible. Here, we are seeking to go further by incorporating semantic meaning in the low-dimensional representation. In a conventional SOM, the semantic context of the data, such as class labels, does not have any influence on the formation of the map. As an abstraction of neural function, the SOM models bottom-up self-organization but not feedback modulation which is also ubiquitous in the brain. In this paper, we demonstrate a hierarchical neural network, which learns a topographical map that also reflects the semantic context of the data. Our method combines unsupervised, bottom-up topographical map formation with top-down supervised learning. We discuss the mathematical properties of the proposed hierarchical neural network and demonstrate its abilities with empirical experiments.

No abstract

No abstract