Probabilistic Demand Prediction Model for En-Route Sector

Abstract

Abstract-Although airspace congestion is becoming more and more serious with the increase of the air traffic flow, there have been still no mature and effective methods and models developed for measuring the uncertainty of the air traffic flow, so that the air traffic prediction is lack of accuracy. Thus, in this paper we extract the numerical characteristics of the random variables during the flight process, and then establish the probability density functions and en-route sector demand prediction model based on the probability distributions. Through comparing the actual operation data and the prediction data of the aircraft, the variation of the sector traffic flow demand and its probability can be obtained based on the model proposed in the paper. The model in this paper remedies the insufficiency of the traditional flow prediction methods which merely provide static prediction results, and thus can be a useful decision support tool for the air traffic flow managers to dynamically know about the sector traffic demand and its accuracy in the future.Index Terms-Air traffic management, en-route sector demand, probabilistic prediction, uncertianty measuring.

Augmented Machine Intelligence with Human Intelligence for Cryptocurrency Price Prediction

“…To model a regression problem, we predicted the price at a specific time as a function of some previous data points [12], using a sliding window with a window size/ time step of 20 days to predict the data at the end of those points [13]. We selected the value of 20 days based on prior experimentation with different values.…”

Sustainable Smart University: A Short-Term Deep Learning Framework for Energy Consumption Forecast

“…Beyond academic study, we consider temporal and environmental elements like temperature and humidity. Many studies have been conducted pertaining to the application of machine learning and deep learning across diverse domains [4][5][6][7][8][9][10]. Deep learning may transform unstructured data in a smart campus into information that helps decision-makers in university towns be more energy-conscious.…”