Use of context-based adaptation to defuse threatening situations in times of a pandemic

Abstract The COVID-19 pandemic has demonstrated the limitations of traditional contact tracing in containing infectious disease outbreaks due to both scalability issues and low adoption rates. To enhance proactive responses, this paper proposes a novel digital infection prevention system focused on identifying and mitigating threatening situations posing a risk of infection. Unlike contact tracing, this approach uses near real-time context-aware adaptation to evaluate and respond to immediate risks based on individual situational data and proximity to potential infection sources. The approach leverages digital contact tracing technologies, such as BLE-based distance estimation, but advances them by integrating context-aware adaptation that considers direct and indirect transmission paths. Prevention profiles provide the system with pathogen-specific guidelines for detecting and interpreting threat levels and recommending protection measures. An extensible ontology-based context model facilitates a uniform approach to represent situational information and adapts flexibly to evolving pathogen and environmental dynamics. This study also presents the architecture, data flow, and intervention cycle of the proposed system, validated by a prototype Android application. Findings suggest that the proposed approach is both feasible and promising for managing infectious disease threats. Future work could focus on improving sensor integration, ensuring privacy-preserving data sharing for epidemiological insights, and further empirical testing in real-world settings.