Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387546650> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4387546650 endingPage "393" @default.
- W4387546650 startingPage "379" @default.
- W4387546650 abstract "Domestic violence has increased globally as the COVID-19 pandemic combines with economic and social stresses. Some works have used traditional feature extractors to identify features from sound signals to detect physical violence. However, these extractors have not performed well at recognizing physical violence in audio. Besides, the use of Machine Learning is limited by the trade-off between collecting more data while keeping users privacy. Federated Learning (FL) is a technique that allows the creation of client-server networks, in which anonymized training result can be uploaded to a central model, responsible for aggregating and keeping the model up to date, and then distribute the updated model to the client nodes. In this paper, we proposed a FL approach to the violence detection problem in audio signals. The framework was evaluated on a newly proposed synthetic dataset, in which audio signals are represented as mel-spectrograms images, augmented with violence extracts. Thereby, it treats it as a problem of image classification using pre-trained Convolutional Neural Networks (CNN). Inception v3, MobileNet v2, ResNet152 v2 and VGG-16 architectures were evaluated, with the MobileNet architecture presenting the best performance, in terms of accuracy (71.9%), with a loss of 3.6% when compared to the non-FL setting." @default.
- W4387546650 created "2023-10-12" @default.
- W4387546650 creator A5002073542 @default.
- W4387546650 creator A5023532492 @default.
- W4387546650 creator A5052269274 @default.
- W4387546650 creator A5074948157 @default.
- W4387546650 creator A5078294323 @default.
- W4387546650 creator A5093046467 @default.
- W4387546650 date "2023-01-01" @default.
- W4387546650 modified "2023-10-12" @default.
- W4387546650 title "Federated Learning and Mel-Spectrograms for Physical Violence Detection in Audio" @default.
- W4387546650 cites W2097117768 @default.
- W4387546650 cites W2097450352 @default.
- W4387546650 cites W2101926813 @default.
- W4387546650 cites W2183341477 @default.
- W4387546650 cites W2194775991 @default.
- W4387546650 cites W2618530766 @default.
- W4387546650 cites W2796900961 @default.
- W4387546650 cites W2918087949 @default.
- W4387546650 cites W2931364255 @default.
- W4387546650 cites W2963163009 @default.
- W4387546650 cites W2966264335 @default.
- W4387546650 cites W2974175488 @default.
- W4387546650 cites W2990239018 @default.
- W4387546650 cites W3011144806 @default.
- W4387546650 cites W3085622513 @default.
- W4387546650 cites W3092684893 @default.
- W4387546650 cites W3094550259 @default.
- W4387546650 cites W3094793624 @default.
- W4387546650 cites W3100321043 @default.
- W4387546650 cites W3131749943 @default.
- W4387546650 cites W3174440551 @default.
- W4387546650 cites W3194457073 @default.
- W4387546650 cites W3214905145 @default.
- W4387546650 cites W4232336823 @default.
- W4387546650 cites W4241727697 @default.
- W4387546650 cites W4252684946 @default.
- W4387546650 doi "https://doi.org/10.1007/978-3-031-45392-2_25" @default.
- W4387546650 hasPublicationYear "2023" @default.
- W4387546650 type Work @default.
- W4387546650 citedByCount "0" @default.
- W4387546650 crossrefType "book-chapter" @default.
- W4387546650 hasAuthorship W4387546650A5002073542 @default.
- W4387546650 hasAuthorship W4387546650A5023532492 @default.
- W4387546650 hasAuthorship W4387546650A5052269274 @default.
- W4387546650 hasAuthorship W4387546650A5074948157 @default.
- W4387546650 hasAuthorship W4387546650A5078294323 @default.
- W4387546650 hasAuthorship W4387546650A5093046467 @default.
- W4387546650 hasConcept C108583219 @default.
- W4387546650 hasConcept C115961682 @default.
- W4387546650 hasConcept C119857082 @default.
- W4387546650 hasConcept C136764020 @default.
- W4387546650 hasConcept C138885662 @default.
- W4387546650 hasConcept C13895895 @default.
- W4387546650 hasConcept C154945302 @default.
- W4387546650 hasConcept C2776401178 @default.
- W4387546650 hasConcept C28490314 @default.
- W4387546650 hasConcept C41008148 @default.
- W4387546650 hasConcept C41895202 @default.
- W4387546650 hasConcept C45273575 @default.
- W4387546650 hasConcept C52622490 @default.
- W4387546650 hasConcept C59404180 @default.
- W4387546650 hasConcept C64922751 @default.
- W4387546650 hasConcept C71901391 @default.
- W4387546650 hasConcept C81363708 @default.
- W4387546650 hasConceptScore W4387546650C108583219 @default.
- W4387546650 hasConceptScore W4387546650C115961682 @default.
- W4387546650 hasConceptScore W4387546650C119857082 @default.
- W4387546650 hasConceptScore W4387546650C136764020 @default.
- W4387546650 hasConceptScore W4387546650C138885662 @default.
- W4387546650 hasConceptScore W4387546650C13895895 @default.
- W4387546650 hasConceptScore W4387546650C154945302 @default.
- W4387546650 hasConceptScore W4387546650C2776401178 @default.
- W4387546650 hasConceptScore W4387546650C28490314 @default.
- W4387546650 hasConceptScore W4387546650C41008148 @default.
- W4387546650 hasConceptScore W4387546650C41895202 @default.
- W4387546650 hasConceptScore W4387546650C45273575 @default.
- W4387546650 hasConceptScore W4387546650C52622490 @default.
- W4387546650 hasConceptScore W4387546650C59404180 @default.
- W4387546650 hasConceptScore W4387546650C64922751 @default.
- W4387546650 hasConceptScore W4387546650C71901391 @default.
- W4387546650 hasConceptScore W4387546650C81363708 @default.
- W4387546650 hasLocation W43875466501 @default.
- W4387546650 hasOpenAccess W4387546650 @default.
- W4387546650 hasPrimaryLocation W43875466501 @default.
- W4387546650 hasRelatedWork W1976719989 @default.
- W4387546650 hasRelatedWork W2011227383 @default.
- W4387546650 hasRelatedWork W2065606036 @default.
- W4387546650 hasRelatedWork W2088854863 @default.
- W4387546650 hasRelatedWork W2530685530 @default.
- W4387546650 hasRelatedWork W2910935116 @default.
- W4387546650 hasRelatedWork W4309346246 @default.
- W4387546650 hasRelatedWork W4316036082 @default.
- W4387546650 hasRelatedWork W4360764600 @default.
- W4387546650 hasRelatedWork W4375868962 @default.
- W4387546650 isParatext "false" @default.
- W4387546650 isRetracted "false" @default.
- W4387546650 workType "book-chapter" @default.