Deakin University
Browse

File(s) under permanent embargo

Partial adversarial training for prediction interval

Version 2 2024-06-04, 06:40
Version 1 2019-02-12, 11:52
conference contribution
posted on 2024-06-04, 06:40 authored by HMD Kabir, Abbas KhosraviAbbas Khosravi, Anwar HosenAnwar Hosen, S Nahavandi
© 2018 IEEE. Neural network (NN) based prediction or detection systems often perform excellently with easy problems without considering 1-5% difficult problems. This work proposes an adversarial NN training method for constructing the prediction interval (PI). The proposed training method considers adverse situations where traditional NN based PIs frequently fail. First, the conventional lower upper bound estimation (LUBE) method is applied in parallel for initial training of NNs with different initialization. Each NN based PI fails to cover a few samples. Input combinations of those samples are adversely changed by a small amount to generate the adverse samples. A new dataset is generated by appending adverse samples. Finally, an NN is trained with the adverse dataset. The method is applied to construct the NN for wind power prediction. According to the result analysis, the proposed method performs better in adverse situations.

History

Volume

2018-July

Pagination

1-6

Location

Rio, Brasil

Start date

2018-07-08

End date

2018-07-13

ISBN-13

9781509060146

Language

eng

Publication classification

E Conference publication, E1 Full written paper - refereed

Title of proceedings

IJCNN 2018 : Proceedings of the International Joint Conference on Neural Networks

Event

Neural Networks. Conference (2018 : Rio, Brasil)

Publisher

IEEE

Place of publication

Piscataway, N.J.