• 沒有找到結果。

The Learning-based Approach to Forecasting the Flight Load Factor

N/A
N/A
Protected

Academic year: 2021

Share "The Learning-based Approach to Forecasting the Flight Load Factor"

Copied!
1
0
0

加載中.... (立即查看全文)

全文

(1)

2019 智慧企業資訊應用發展國際研討會 台灣,2019/06/29(六)

The Learning-based Approach to Forecasting the Flight Load Factor

Wei-Ting, Liang

National Chengchi University, Taipei, Taiwan liang0962054@gmail.com

Hsuan-Yun, Chang

National Chengchi University, Taipei, Taiwan zas473412@gmail.com

Rua-Huan, Tsaih

National Chengchi University, Taipei, Taiwan tsaih@mis.nccu.edu.tw

Abstract

To effectively forecast the flight load factor is pivotal in the aviation industry. This study proposes the cramming, softening and integrating (CSI) algorithm, a sequentially-learning-based algorithm, to forecast the flight load factor. The proposed CSI learning algorithm has the following features: (1) the implementation of new data-driven algorithm using adaptive single-hidden layer feed-forward neural networks, (2) the usage of least trimmed squares principle to speed up the training time, (3) the practice of cramming mechanism to precisely learning all training data, and (4) the implementations of the regularization term and the softening and integrating mechanism to alleviate the obtained model from the overfitting pain. An experiment with real data from one of Taiwan aviation companies has been conducted to explore whether the proposed CSI learning algorithm can (1) predict the flight load factor better than other methods in the current literature, the Littlewood's rule, (2) perfectly learn thorough training data, as it claims, and (3) alleviate the overfitting pain through the regularization term and the softening and integrating mechanism. The experimental results are promising.

Keywords: CSI learning, cramming mechanism, softening and integrating mechanism, least trimmed squares, flight load factor

參考文獻

相關文件

Hsuan-Tien Lin (NTU CSIE) Machine Learning Foundations 16/22.. If we use E loocv to estimate the performance of a learning algorithm that predicts with the average y value of the

Coefficients Extraction from Infant Cry for Classification of Normal and Pathological Infant with Feed-Forward Neural Networks”, Proceedings of the International Joint Conference

Real Schur and Hessenberg-triangular forms The doubly shifted QZ algorithm.. Above algorithm is locally

Then, it is easy to see that there are 9 problems for which the iterative numbers of the algorithm using ψ α,θ,p in the case of θ = 1 and p = 3 are less than the one of the

In this chapter we develop the Lanczos method, a technique that is applicable to large sparse, symmetric eigenproblems.. The method involves tridiagonalizing the given

volume suppressed mass: (TeV) 2 /M P ∼ 10 −4 eV → mm range can be experimentally tested for any number of extra dimensions - Light U(1) gauge bosons: no derivative couplings. =>

• Formation of massive primordial stars as origin of objects in the early universe. • Supernova explosions might be visible to the most

Like the proximal point algorithm using D-function [5, 8], we under some mild assumptions es- tablish the global convergence of the algorithm expressed in terms of function values,