Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts

To implement fine-grained context recognition that is accurate and affordable for general households, we present a novel technique that integrates multiple image-based cognitive APIs and light-weight machine learning. Our key idea is to regard every image as a document by exploiting “tags&...

Full description

Bibliographic Details
Main Authors:	Sinan Chen, Sachio Saiki, Masahide Nakamura
Format:	Article
Language:	English
Published:	MDPI AG 2020-01-01
Series:	Sensors
Subjects:	context recognition image cognitive apis machine learning majority voting score voting range voting smart home
Online Access:	https://www.mdpi.com/1424-8220/20/3/666

id	doaj-8fd81e16794f4eec98a39601dd3ca2a0
record_format	Article
spelling	doaj-8fd81e16794f4eec98a39601dd3ca2a02020-11-25T01:38:58ZengMDPI AGSensors1424-82202020-01-0120366610.3390/s20030666s20030666Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home ContextsSinan Chen0Sachio Saiki1Masahide Nakamura2Graduate School of System Informatics, Kobe University, 1-1 Rokkodai-cho, Nada, Kobe 657-8501, JapanGraduate School of System Informatics, Kobe University, 1-1 Rokkodai-cho, Nada, Kobe 657-8501, JapanGraduate School of System Informatics, Kobe University, 1-1 Rokkodai-cho, Nada, Kobe 657-8501, JapanTo implement fine-grained context recognition that is accurate and affordable for general households, we present a novel technique that integrates multiple image-based cognitive APIs and light-weight machine learning. Our key idea is to regard every image as a document by exploiting “tags” derived by multiple APIs. The aim of this paper is to compare API-based models’ performance and improve the recognition accuracy by preserving the affordability for general households. We present a novel method for further improving the recognition accuracy based on multiple cognitive APIs and four modules, fork integration, majority voting, score voting, and range voting.https://www.mdpi.com/1424-8220/20/3/666context recognitionimagecognitive apismachine learningmajority votingscore votingrange votingsmart home
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Sinan Chen Sachio Saiki Masahide Nakamura
spellingShingle	Sinan Chen Sachio Saiki Masahide Nakamura Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts Sensors context recognition image cognitive apis machine learning majority voting score voting range voting smart home
author_facet	Sinan Chen Sachio Saiki Masahide Nakamura
author_sort	Sinan Chen
title	Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts
title_short	Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts
title_full	Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts
title_fullStr	Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts
title_full_unstemmed	Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts
title_sort	integrating multiple models using image-as-documents approach for recognizing fine-grained home contexts
publisher	MDPI AG
series	Sensors
issn	1424-8220
publishDate	2020-01-01
description	To implement fine-grained context recognition that is accurate and affordable for general households, we present a novel technique that integrates multiple image-based cognitive APIs and light-weight machine learning. Our key idea is to regard every image as a document by exploiting “tags” derived by multiple APIs. The aim of this paper is to compare API-based models’ performance and improve the recognition accuracy by preserving the affordability for general households. We present a novel method for further improving the recognition accuracy based on multiple cognitive APIs and four modules, fork integration, majority voting, score voting, and range voting.
topic	context recognition image cognitive apis machine learning majority voting score voting range voting smart home
url	https://www.mdpi.com/1424-8220/20/3/666
work_keys_str_mv	AT sinanchen integratingmultiplemodelsusingimageasdocumentsapproachforrecognizingfinegrainedhomecontexts AT sachiosaiki integratingmultiplemodelsusingimageasdocumentsapproachforrecognizingfinegrainedhomecontexts AT masahidenakamura integratingmultiplemodelsusingimageasdocumentsapproachforrecognizingfinegrainedhomecontexts
_version_	1725051159889051648

Integrating Multiple Models Using Image-as-Documents Approach for Recognizing Fine-Grained Home Contexts

Similar Items