Temporal Characteristics of the Chinese Aviation Network and their Effects on the Spread of Infectious Diseases

Airline flight delays using artificial intelligence in COVID-19 with perspective analytics

This study envisages assessing the effects of the COVID-19 on the on-time performance of US-airlines industry in the disrupted situations. The deep learning techniques used are neural network regression, decision forest regression, boosted decision tree regression and multi class logistic regression. The best technique is identified. In the perspective data analytics, it is suggested what the airlines should do for the on-time performance in the disrupted situation. The performances of all the methods are satisfactory. The coefficient of determination for the neural network regression is 0.86 and for decision forest regression is 0.85, respectively. The coefficient of determination for the boosted decision tree is 0.870984. Thus boosted decision tree regression is better. Multi class logistic regression gives an overall accuracy and precision of 98.4%. Recalling/remembering performance is 99%. Thus multi class logistic regression is the best model for prediction of flight delays in the COVID-19. The confusion matrix for the multi class logistic regression shows that 87.2% flights actually not delayed are predicted not delayed. The flights actually not delayed but wrongly predicted delayed are12.7%. The strength of relation with departure delay, carrier delay, late aircraft delay, weather delay and NAS delay, are 94%, 53%, 35%, 21%, and 14%, respectively. There is a weak negative relation (almost unrelated) with the air time and arrival delay. Security delay and arrival delay are also almost unrelated with strength of 1% relationship. Based on these diagnostic analytics, it is recommended as perspective to take due care reducing departure delay, carrier delay, Late aircraft delay, weather delay and Nas delay, respectively, considerably with effect of 94%, 53%, 35%, 21%, and 14% in disrupted situations. The proposed models have MAE of 2% for Neural Network Regression, Decision Forest Regression, Boosted Decision Tree Regression, respectively, and, RMSE approximately, 11%, 12%, 11%, respectively.

From data to complex network control of airline flight delays

Many critical complex systems and networks are continuously monitored, creating vast volumes of data describing their dynamics. To understand and optimize their performance, we need to discover and formalize their dynamics to enable their control. Here, we introduce a multidisciplinary framework using network science and control theory to accomplish these goals. We demonstrate its use on a meaningful example of a complex network of U.S. domestic passenger airlines aiming to control flight delays. Using the real data on such delays, we build a flight delay network for each airline. Analyzing these networks, we uncover and formalize their dynamics. We use this formalization to design the optimal control for the flight delay networks. The results of applying this control to the ground truth data on flight delays demonstrate the low costs of the optimal control and significant reduction of delay times, while the costs of the delays unabated by control are high. Thus, the introduced here framework benefits the passengers, the airline companies and the airports.