Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In Applied soft computing

In 2020, a novel coronavirus disease became a global problem. The disease was called COVID-19, as the first patient was diagnosed in December 2019. The disease spread around the world quickly due to its powerful viral ability. To date, the spread of COVID-19 has been relatively mild in China due to timely control measures. However, in other countries, the pandemic remains severe, and COVID-19 protection and control policies are urgently needed, which has motivated this research. Since the outbreak of the pandemic, many researchers have hoped to identify the mechanism of COVID-19 transmission and predict its spread by using machine learning (ML) methods to supply meaningful reference information to decision-makers in various countries. Since the historical data of COVID-19 is time series data, most researchers have adopted recurrent neural networks (RNNs), which can capture time information, for this problem. However, even with a state-of-the-art RNN, it is still difficult to perfectly capture the temporal information and nonlinear characteristics from the historical data of COVID-19. Therefore, in this study, we develop a novel dendritic neural regression (DNR) method to improve prediction performance. In the DNR, the multiplication operator is used to capture the nonlinear relationships between input feature signals in the dendrite layer. Considering the complex and large landscape of DNR's weight space, a new scale-free state-of-matter search (SFSMS) algorithm is proposed to optimize the DNR, which combines the state-of-matter search algorithm with a scale-free local search. The SFSMS achieves a better global search ability and thus can effectively reduce the possibility of falling into local minima. In addition, according to Takens's theorem, phase space reconstruction techniques are used to discover the information hidden in the high-dimensional space of COVID-19 data, which further improves the precision of prediction. The experimental results suggest that the proposed method is more competitive in solving this problem than other prevailing methods.

Dong Minhui, Tang Cheng, Ji Junkai, Lin Qiuzhen, Wong Ka-Chun

2021-Nov

COVID-19, Neural network, Optimization, Prediction, Regression