<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Publication:
Domain adaptation for food intake classification with teacher/student learning

Loading...
Thumbnail Image

Departments

School / College / Institute

Item type:Organizational Unit,
Item type:Organizational Unit,

Program

Organization Authors

Co-Authors

Date

Language

Embargo Status

N/A

Journal Title

Journal ISSN

Volume Title

Alternative Title

Abstract

Automatic dietary monitoring (ADM) stands as a challenging application in wearable healthcare technologies. In this paper, we define an ADM to perform food intake classification (FIC) over throat microphone recordings. We investigate the use of transfer learning to design an improved FIC system. Although labeled data with acoustic close-talk microphones are abundant, throat data is scarce. Therefore, we propose a new adaptation framework based on teacher/student learning. The teacher network is trained over high-quality acoustic microphone recordings, whereas the student network distills deep feature extraction capacity of the teacher over a parallel dataset. Our approach allows us to transfer the representational capacity, adds robustness to the resulting model, and improves the FIC through throat microphone recordings. The classification problem is formulated as a spectra-temporal sequence recognition using the Convolutional LSTM (ConvLSTM) models. We evaluate the proposed approach using a large scale acoustic dataset collected from online recordings, an in-house food intake throat microphone dataset, and a parallel speech dataset. The bidirectional ConvLSTM network with the proposed domain adaptation approach consistently outperforms the SVM- and CNN-based baseline methods and attains 85.2% accuracy for the classification of 10 different food intake items. This translates to 17.8% accuracy improvement with the proposed domain adaptation.

Source

Publisher

IEEE-Inst Electrical Electronics Engineers Inc

Citation

item.page.haspartof

Source

IEEE Transactions on Multimedia

item.page.ispartofseries

item.page.edition

DOI

10.1109/TMM.2020.3038315

item.page.datauri

item.page.link

Rights

N/A

Copyrights Note

Rights and licensing

N/A

Endorsement

Review

Supplemented By

Referenced By

Related Patent

Related Goal

Item type:Goal, Access status: Open Access ,
02 - Zero Hunger
Hunger is the leading cause of death in the world. Our planet has provided us with tremendous resources, but unequal access and inefficient handling leaves millions of people malnourished. If we promote sustainable agriculture with modern technologies and fair distribution systems, we can sustain the whole world’s population and make sure that nobody will ever suffer from hunger again.
Google Scholar
Scholar'da Ara ↗
Altmetric
Dimensions
PlumX Metrikleri
BIP! Indicators