A Hybrid Data Fusion Architecture for BINDI: A Wearable Solution to Combat Gender-Based Violence
Currently, most of the affective computing research is about modifying and adapting the machine behavior based on the human emotional state. Although, the use of the affective state inference can be extended to provide a tool for other fields more society
- PDF / 516,107 Bytes
- 15 Pages / 439.37 x 666.142 pts Page_size
- 48 Downloads / 147 Views
artamento de Teor´ıa de la Se˜ nal y Comunicacionones, Universidad Carlos III de Madrid, 28911 Legan´es, Spain {erituert,cpelaez}@ing.uc3m.es 2 Departamento de Tecnolog´ıa Electr´ onica, Universidad Carlos III de Madrid, 28911 Legan´es, Spain {jmiranda,mcanabal,jlanza,celia}@ing.uc3m.es http://portal.uc3m.es/portal/page/portal/inst estudios genero/ proyectos/UC3M4Safety
Abstract. Currently, most of the affective computing research is about modifying and adapting the machine behavior based on the human emotional state. Although, the use of the affective state inference can be extended to provide a tool for other fields more society related such as gender violence detection, which is a real global emergency. Based on the World Health Organization (WHO) statistics, one in three women worldwide experiences gender-based violence, often from an intimate partner. Due to this motivation, the authors developed BINDI, which is a wearable solution for detecting automatically those situations. It uses affective computing together with short-term physiological and physical observations. It represents a step toward an autonomous, embedded, non-intrusive, and wearable system for detecting those situations and connecting the victim with a trusted circle. In this work, and as a response for improving the detection capability of BINDI, a novel hybrid data fusion architecture is proposed. This new architecture is intended to improve the already implemented decision level fusion architecture. Further details of the uni-modal systems and the different approaches needed to be explored in the future are given. Keywords: Gender violence · Machine learning · Physiological signals · Speech · Data fusion · Cognitive computing
1
Introduction
Gender-based violence is one of the biggest social problems in the world, whose cultural origins make it an invisible phenomenon still tolerated by part of the E. Rituerto-Gonz´ alez and J. A. Miranda—These authors contributed equally to this work. c Springer Nature Switzerland AG 2020 A. Dziech et al. (Eds.): MCSS 2020, CCIS 1284, pp. 223–237, 2020. https://doi.org/10.1007/978-3-030-59000-0_17
224
E. Rituerto-Gonz´ alez et al.
society. Thus, statistics say that 35% of women worldwide have experienced either physical and/or sexual violence at some point in their lives [33]. Women are subject to different types of violence caused by their sentimental couples and even by the social environment, ranging from psychological control and disrespect to physical and sexual aggression. Thus, gender violence affects women of any religion, age, as well as economic and social conditions, taking place anywhere, such as their homes, workplaces, and public places. This situation means that combating gender-based violence is a real global emergency, which needs to be fought with actions, such as making prevention campaigns, changing school education for future generations, and providing help and resources to victims. These educational actions could be also combined with technological solutions, which could help to detect
Data Loading...
