Next Article in Journal
Application of Biosensors Based on Lipid Membranes for the Rapid Detection of Toxins
Next Article in Special Issue
The Importance of Multifrequency Impedance Sensing of Endothelial Barrier Formation Using ECIS Technology for the Generation of a Strong and Durable Paracellular Barrier
Previous Article in Journal
Nanoscale Biosensors Based on Self-Propelled Objects
Previous Article in Special Issue
Breathing Pattern Interpretation as an Alternative and Effective Voice Communication Solution
Article Menu

Export Article

Open AccessArticle
Biosensors 2018, 8(3), 60; https://doi.org/10.3390/bios8030060

Transfer Learning for Improved Audio-Based Human Activity Recognition

1
Music Informatics Laboratory, Department of Computer Science, Università degli Studi di Milano, via Comelico 39, 20135, Milan, Italy
2
Technological Educational Institute of Crete, E. Daskalaki, Perivolia, 74100, Rethymno, Greece
*
Author to whom correspondence should be addressed.
Received: 29 May 2018 / Revised: 14 June 2018 / Accepted: 21 June 2018 / Published: 25 June 2018
(This article belongs to the Special Issue Smart Biomedical Sensors)
View Full-Text   |   Download PDF [366 KB, uploaded 27 June 2018]   |  

Abstract

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. View Full-Text
Keywords: 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
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Ntalampiras, S.; Potamitis, I. Transfer Learning for Improved Audio-Based Human Activity Recognition. Biosensors 2018, 8, 60.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Biosensors EISSN 2079-6374 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top