文章基本信息

标题：Transfer Learning for Improved Audio-Based Human Activity Recognition
本地全文：下载
作者：Stavros Ntalampiras ; Ilyas Potamitis
期刊名称：Biosensors
电子版ISSN：2079-6374
出版年度：2018
卷号：8
期号：3
页码：60
DOI：10.3390/bios8030060
语种：English
出版社：MDPI Publishing
摘要：Human activities are accompanied by characteristic sound events, the processing of which might provide valuable information for automated human activity recognition. This paper presents a novel approach addressing the case where one or more human activities are associated with limited audio data, resulting in a potentially highly imbalanced dataset. Data augmentation is based on transfer learning; more specifically, the proposed method: (a) identifies the classes which are statistically close to the ones associated with limited data; (b) learns a multiple input, multiple output transformation; and (c) transforms the data of the closest classes so that it can be used for modeling the ones associated with limited data. Furthermore, the proposed framework includes a feature set extracted out of signal representations of diverse domains, i.e., temporal, spectral, and wavelet. Extensive experiments demonstrate the relevance of the proposed data augmentation approach under a variety of generative recognition schemes.
关键词：transfer learning; generalized audio recognition; multidomain features; hidden Markov model; echo state network transfer learning ; generalized audio recognition ; multidomain features ; hidden Markov model ; echo state network