Applying Ontology and Probabilistic Model to Human Activity Recognition from Surrounding Things
スポンサーリンク
概要
- 論文の詳細を見る
This paper proposes human activity recognition based on the actual semantics of the humans current location. Since no predefined semantics of location can adequately identify human activity, we automatically identify the semantics from things by focusing on the association between things and human activities with the things. Ontology is used to deal with the various possible representations (terms) of each thing, identified by a RFID tag, and a multi-class Naive Bayesian approach is applied to detect multiple actual semantics from the terms. Our approach is suitable for automatically detecting possible activities even given a variety of object characteristics including multiple representations and variability. Simulations with actual thing datasets and experiments in an actual environment demonstrate its noise tolerance and ability to rapidly detect multiple actual semantics from existing things.
著者
-
Sakamoto Kenji
Ntt Docomo Inc.
-
Yamazaki Kenichi
Ntt Docomo Inc.
-
Kunito Goro
Ntt Docomo Inc.
-
Yamada Naoharu
Ntt Docomo Inc.
-
Isoda Yoshinori
Ntt Docomo Inc.
-
Tanaka Satoshi
Docomo Technology Inc.
関連論文
- B-6-105 A partitioned programming model for network-assisted distributed operations
- Applying Ontology and Probabilistic Model to Human Activity Recognition from Surrounding Things(Mobile Computing)
- Applying Ontology and Probabilistic Model to Human Activity Recognition from Surrounding Things
- B-14-7 Inferring Method for Human Activities using Relationship between Nouns and Verbs
- B-7-61 An Automatic Method of Determining Field Characteristics in Ubiquitous Computing Environment
- B-7-60 Grouping Method for Active Tag in Ubiquitous Computing Environment
- B-7-51 A Stray Object Detection Method Based on Active Tags
- B-7-77 Tag Based Service Configuration in Ubiquitous Computing Environment
- B-7-76 Selection Method of Multiple Tags in Ubiquitous Computing Environment
- Packet Size Based Routing for Stable Data Delivery in Mobile Ad-Hoc Networks
- Applying Ontology and Probabilistic Model to Human Activity Recognition from Surrounding Things
- Automatic configuration of sensor locations by tracking human movement (日韓合同ワークショップ 1st Korea-Japan Joint Workshop on Ubiquitous Computing and Networking Systems (ubiCNS 2005))
- A-7-23 Information Storing and Disclosure Scheme for User Privacy Protection in Ubiquitous Services(A-7. 情報セキュリティ, 基礎・境界)
- B-6-57 Collecting and distributing context for a ubiquitous service
- B-7-9 Context distribution network for ubiquitous services
- B-11-5 Subjective Assessment of Service Transfer
- B-7-72 SIP-based Message Protocol for Service Transfer across Terminals
- B-7-71 System architecture of the seamless service environment platform
- M-43 Service state description for seamless service environment
- B-5-282 Relative Distance Routing in High Density Network with Multiple Gateways