應用於行為識別資料擴增之改良生成對抗網路

Application in Activity Recognition Data Augmentation with Modified Generative Adversarial Networks

陳文輝(Wen-Hui Chen) ； 黃玠元(Chieh Yuan Huang)

《先進工程學刊》 13卷3期 (2018/10) Pp. 143-147

摘要

近幾年由於神經網路的蓬勃發展，深度學習網路技術不斷地進步突破。然而，深度學習最重要的就是有充足的資料來達到最佳學習曲線。但在蒐集資料的過程為了確保蒐集資料的正確性足以使用，往往是費時費工的。本文以行為識別為主軸，利用改良的條件生成對抗網路，以感測器資料進行擴增，來建立和原始資料有相似特徵的資料集。和其他方法以及原始資料相比較，其泛化能力及準確度和原始資料集相近。

關鍵字

生成對抗網路 ； 條件生成對抗網路 ； 深度學習 ； 資料擴增

並列摘要

Due to the vigorous development of neural networks in recent years, deep learning network has made progressive breakthrough. However, the most important thing about deep learning is enough datasets to achieve the best learning curve. But the process of data collecting often requires a lot of hard work in order to ensure that the data is correct enough to be used. Our study focuses on activity recognition, using modified conditional generative adversarial network, and augmented data with original data to build a dataset with similar features. Comparing with the data augmentation use of generative adversarial network and the original data, its generalization ability and accuracy have been similar with original dataset's result.

並列關鍵字

generative adversarial network ； conditional generative adversarial network ； deep learning ； data augmentation