tinyML for crime prevention: detecting violent conversations

Anwar, A ORCID logoORCID: https://orcid.org/0000-0001-5347-4996 and Kanjo, E ORCID logoORCID: https://orcid.org/0000-0002-1720-0661, 2023. tinyML for crime prevention: detecting violent conversations. Nottingham: Nottingham Trent University.

[thumbnail of 1795526_Kanjo.pdf]
Preview
Text
1795526_Kanjo.pdf - Published version

Download (2MB) | Preview

Abstract

Our work focuses on using tinyML for detecting violent language on edge devices, such as mobile phones and wearables, in the context of preventing domestic violence. Our multimodal algorithm uses natural language processing (NLP) and audio processing to detect violent conversation from short audio-text segments. The algorithm is converted to a tinyML model using TensorFlow Lite, which enables the detection to run on edge devices such as mobile phones and smart home sensors. Our mobile application enables near-real-time detection of violent conversations to enable victims or potential victims to detect and report crimes to close or trust contacts.

Item Type: Working paper
Creators: Anwar, A. and Kanjo, E.
Publisher: Nottingham Trent University
Place of Publication: Nottingham
Date: 25 June 2023
Identifiers:
Number
Type
1795526
Other
Divisions: Schools > School of Science and Technology
Record created by: Jonathan Gallacher
Date Added: 29 Aug 2023 15:50
Last Modified: 29 Aug 2023 15:50
URI: https://irep.ntu.ac.uk/id/eprint/49623

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year