This paper employs the acoustic modality to address the human activity recognition (HAR) problem. The cornerstone of the proposed solution is the YAMNet deep neural network, the embeddings of which comprise the input to a fully-connected linear layer trained for HAR. Importantly, the dataset is publicly available and includes the following human activities: preparing coffee, frying egg, no activity, showering, using microwave, washing dishes, washing hands, and washing teeth. The specific set of activities is representative of a standard home environment facilitating a wide range of applications. The performance offered by the proposed transfer learning-based framework surpasses the state of the art, while being able to be executed on mobile devices, such as smartphones, tablets, etc. In fact, the obtained model has been exported and thoroughly tested for real-time HAR on a smartphone device with the input being the audio captured from its microphone.
Lightweight Audio-Based Human Activity Classification Using Transfer Learning / M. Nicolini, F. Simonetta, S. Ntalampiras - In: Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods / [a cura di] M. De Marsico, G. Sanniti di Baja, A. Fred. - [s.l] : ScitePress, 2023. - ISBN 978-989-758-626-2. - pp. 783-789 (( Intervento presentato al 12. convegno International Conference on Pattern Recognition Applications and Methods tenutosi a Lisbon nel 2013 [10.5220/0011647900003411].
Lightweight Audio-Based Human Activity Classification Using Transfer Learning
F. SimonettaSecondo
;S. Ntalampiras
Ultimo
2023
Abstract
This paper employs the acoustic modality to address the human activity recognition (HAR) problem. The cornerstone of the proposed solution is the YAMNet deep neural network, the embeddings of which comprise the input to a fully-connected linear layer trained for HAR. Importantly, the dataset is publicly available and includes the following human activities: preparing coffee, frying egg, no activity, showering, using microwave, washing dishes, washing hands, and washing teeth. The specific set of activities is representative of a standard home environment facilitating a wide range of applications. The performance offered by the proposed transfer learning-based framework surpasses the state of the art, while being able to be executed on mobile devices, such as smartphones, tablets, etc. In fact, the obtained model has been exported and thoroughly tested for real-time HAR on a smartphone device with the input being the audio captured from its microphone.File | Dimensione | Formato | |
---|---|---|---|
ICPRAM_2023_39_CR.pdf
accesso riservato
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
2.68 MB
Formato
Adobe PDF
|
2.68 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
116479.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Dimensione
2.88 MB
Formato
Adobe PDF
|
2.88 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.