Multi-source Transfer Learning for Human Activity Recognition in Smart Homes
| Autor: | Kei Yonekawa, Shinya Wada, Hao Niu, Kiyohito Yoshihara, Mori Kurokawa, Duc V. Nguyen |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
business.industry
Computer science Negative transfer 020206 networking & telecommunications 02 engineering and technology Machine learning computer.software_genre Activity recognition Software deployment Home automation 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Word2vec Artificial intelligence Baseline (configuration management) business Transfer of learning computer Multi-source |
| Zdroj: | SMARTCOMP |
| Popis: | With the deployment of smart homes, we find that human activity recognition (HAR) is essentially important to many applications, e.g., child/senior care, intelligent information push and exercise promotion. Although it is always better to build HAR model for each smart home to resolve the practical problem that homes have different floorplans or adopted sensors, it is intractable to acquire labeled data for each home due to cost and privacy. We thus propose a method to transfer the HAR model from multiple labeled source homes to the unlabeled target home. Specifically, we first generate transferable representations for the sensors of these homes, based on which we build the HAR model using the data of labeled source homes. Then, we employ the built HAR model into the unlabeled target home. Experiment results on CASAS dataset illustrate that our proposed method outperforms baseline methods in general and also avoids potential negative transfer caused by using only one source home. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|