A data-driven method for accurately predicting reason for flight delays is the goal of the "A Data Driven Approach for Forecasting the Modern Flight Aviation Prediction Using Machine Learning". Travelers and airlines alike may suffer greatly from flight delays, which can result in annoyance, monetary losses, and operational interruptions. Both travelers and airlines may make educated decisions and take the necessary action when delays are anticipated in advance. The previous existing system has found if there is a delay in a flight or not using various techniques like Deep Learning and Ensemble techniques like random forest and gradient boosting machines. The challenges faced in these techniques include the dynamic nature of flight operations, the complexity of interrelated factors contributing to delays, and the need for real-time data processing. Additionally, traditional approaches may not fully capture the intricate patterns and dependencies in flight delay data. Integrating recent techniques in machine learning presents opportunities to overcome these challenges and improve prediction accuracy. The linear regression algorithm will provide the R squared value which will helps to find the proportion of variance in the dependent variable that will be predictable from the independent variable. The comparison of fitted and residuals values will help in assessing the goodness of fit of regression model. The parameters that are focused are Weather delay, arrival delay, departure delay, security delay, aircraft delay, and air system delay which avoids the above faced challenges.
A Data Driven Method for Forecasting the Flight Aviation
24.04.2024
1024069 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
eVTOL Flight: Forecasting Future Training Requirements in an Emerging Aviation Market
British Library Conference Proceedings | 2023
|eVTOL Flight: Forecasting Future Training Requirements in an Emerging Aviation Market
SAE Technical Papers | 2023
|NTIS | 2003