Artificial intelligence can be useful to detect fear of abused women

The Government Delegation against Gender Violence in Spain has recognized the work of Esther Rituerto, a Spanish researcher, in the latest edition of its awards for doctoral theses on violence against women, for “deepening the use of audio technology and artificial intelligence (AI) to prevent and combat” sexist abuse.

Rituerto explained to EFE that her work aimed to use speech and acoustic signals that surround a woman to detect when a situation may be dangerous for her.

In other words, the mission of their work was to detect fear in the voice to know if they are at risk of being attacked by their attacker. Additionally, recognize sounds in the environment that can warn of other dangers such as accelerated footsteps in the early morning, knocks, breaking objects, among others.

For this reason, the Spanish government delegation highlights from its thesis that it uses AI to understand women’s reactions to situations of risk or danger, with the aim of being able to generate automatic mechanisms for detecting these situations from the auditory modality in particular.

The organization also highlighted that the investigation methodology is rigorous, as well as respectful of the victims. The institution, dependent on the Ministry of Equality, considers that “The medium-term impact of this research on protection systems for victims of gender violence can be very relevant.”

Functionality

Rituerto’s thesis was born within UC3M4Safety, a project of the Carlos III University of Madrid that seeks to use technology in the prevention, detection, protection and fight against gender violence.

To develop it, a research team was assembled with profiles from various disciplines to develop electronic devices capable of detecting fear in a victim of gender violence through their voice or vital signs (temperature, pulse or sweating).

It was intended that these reactions would trigger the smartphone Send an alert to the emergency services and the Police or to a close circle of the victim.

Rituerto, audiovisual systems engineer, points out that the devices (a pendant with a microphone to capture sounds) and a bracelet (to detect biological markers) are linked to a smartphone that in turn is connected to a cloud system. Thus, AI helps determine when a situation is risky and an automatic response must be sent to help the victim.

The researcher specifies that these devices may be in operation in a few years (for the moment the tests have been limited to the laboratory) and that in the near future they will begin to be tested on the street.

Conditions of the victims

It was in another investigation in which Rituerto was involved regarding AI where this advanced technology was used to detect the status of a victim of gender violence through voice, that is, this technology is capable of determining if a woman has suffered abuse analyzing his voice. The developed system achieved an accuracy of 73%.

Rituerto highlights from this product that an algorithm trained from victim data was able to discern palpable differences between women who were victims and those who were not, which had to do with the rhythm of the voice, the intensity, the number of words used. and the speed of speech.

“We saw that he was able to separate between victims and non-victims because there is something in his voice that differentiates them”he points out.

Currently, the researcher works at the LMU Klinikum University Hospital and the Max Planck Institute of Psychiatry in Germany, where she researches to detect mental illnesses using artificial intelligence in brain magnetic resonance images.

Topics related to artificial intelligence

Incorporating AI in talent management: a risk for Human Resources?

Google blocks ads for potential virtual scams with artificial intelligence

What may be at stake for Apple after the launch of the Vision Pro