In the recent years, several supervised and unsupervised approaches to fall detection have been presented in the literature. These are generally based on a corpus of examples of human falls that are, though, hard to collect. For this reason, fall detection algorithms should be designed to gather as much information as possible from the few available data related to the type of events to be detected. The one-shot learning paradigm for expert systems training seems to naturally match these constraints, and this inspired the novel Siamese Neural Network (SNN) architecture for human fall detection proposed in this contribution. Acoustic data are employed as input, and the twin convolutional autoencoders composing the SNN are trained to perform a suitable metric learning in the audio domain and, thus, extract robust features to be used in the final classification stage. A large acoustic dataset has been recorded in three real rooms with different floor types and human falls performed by four volunteers, and then adopted for experiments. Obtained results show that the proposed approach, which only relies on two real human fall events in the training phase, achieves a F1 -Measure of 93.58% during testing, remarkably outperforming the recent supervised and unsupervised state-of-art techniques selected for comparison.

Audio Metric Learning by Using Siamese Autoencoders for One-Shot Human Fall Detection / Droghini, Diego; Squartini, Stefano; Principi, Emanuele; Gabrielli, Leonardo; Piazza, Francesco. - In: IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE. - ISSN 2471-285X. - ELETTRONICO. - 5:1(2021), pp. 8891779.108-8891779.118. [10.1109/TETCI.2019.2948151]

Audio Metric Learning by Using Siamese Autoencoders for One-Shot Human Fall Detection

Droghini, Diego;Squartini, Stefano
;
Principi, Emanuele;Gabrielli, Leonardo;Piazza, Francesco
2021-01-01

Abstract

In the recent years, several supervised and unsupervised approaches to fall detection have been presented in the literature. These are generally based on a corpus of examples of human falls that are, though, hard to collect. For this reason, fall detection algorithms should be designed to gather as much information as possible from the few available data related to the type of events to be detected. The one-shot learning paradigm for expert systems training seems to naturally match these constraints, and this inspired the novel Siamese Neural Network (SNN) architecture for human fall detection proposed in this contribution. Acoustic data are employed as input, and the twin convolutional autoencoders composing the SNN are trained to perform a suitable metric learning in the audio domain and, thus, extract robust features to be used in the final classification stage. A large acoustic dataset has been recorded in three real rooms with different floor types and human falls performed by four volunteers, and then adopted for experiments. Obtained results show that the proposed approach, which only relies on two real human fall events in the training phase, achieves a F1 -Measure of 93.58% during testing, remarkably outperforming the recent supervised and unsupervised state-of-art techniques selected for comparison.
File in questo prodotto:
File Dimensione Formato  
paperTETCI.pdf

accesso aperto

Descrizione: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Tipologia: Documento in post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza d'uso: Licenza specifica dell’editore (allegare)
Dimensione 6.01 MB
Formato Adobe PDF
6.01 MB Adobe PDF Visualizza/Apri
Audio_Metric_Learning_by_Using_Siamese_Autoencoders_for_One-Shot_Human_Fall_Detection.pdf

Solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza d'uso: Tutti i diritti riservati
Dimensione 1.86 MB
Formato Adobe PDF
1.86 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/271986
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 10
social impact