An Explainable Multimodal Fusion Approach for Mass Casualty Incidents

Z. Vasileiou, G. Meditskos, S. Vrochidis, N. Bassiliades, "An Explainable Multimodal Fusion Approach for Mass Casualty Incidents", 4th International Workshop on Machine Learning and Knowledge Graphs (MLKgraphs 2022), Workshop of the 33rd DEXA Conference, 22 Aug 2022, Vienna, Austria, in: G. Kotsis et al., Database and Expert Systems Applications - DEXA 2022 Workshops. DEXA 2022. Communications in Computer and Information Science, vol 1633, pp. 375–379, Springer, Cham, 2022.

You are here: Home » Publications » An Explainable Multimodal Fusion Approach for Mass Casualty Incidents

Author(s): Z. Vasileiou, G. Meditskos, S. Vrochidis, N. Bassiliades

Availability:

Appeared In: 4th International Workshop on Machine Learning and Knowledge Graphs (MLKgraphs 2022), Workshop of the 33rd DEXA Conference, 22 Aug 2022, Vienna, Austria, in: G. Kotsis et al., Database and Expert Systems Applications - DEXA 2022 Workshops. DEXA 2022. Communications in Computer and Information Science, vol 1633, pp. 375–379, Springer, Cham, 2022.

Keywords: Pre-hospital life support, Explainable AI, Deep neural network, Neurosymbolic XAI, Mass casualty incident management

Tags:

2022, Bassiliades, Meditskos, Vasileiou, Vrochidis

Abstract: During a Mass Casualty Incident, it is essential to make effective decisions to save lives and nursing the injured. This paper presents a work in progress on the design and development of an explainable decision support system, intended for the medical personnel and care givers, that capitalises on multiple modalities to achieve situational awareness and pre-hospital life support. Our novelty is two-fold: first, we use state-of-the-art techniques for combining static and time-series data in deep recurrent neural networks, and second we increase the trustworthiness of the system by enriching it with neurosymbolic explainable capabilities.