Ambient-aware continuous aid for mountain rescue activities

TL;DR

This work presents ambient-aware, context-driven assistance for mountain rescue deployed as a Context-Aware-as-a-Service (CAaaS). It defines a context life cycle, categorises contextual data, and formalises threats as regular languages to enable online threat detection and proactive rescue actions, using a SAT-based reasoning engine. A Mountain Environments Simulator validates the approach under five weather scenarios, demonstrating robustness under redundancy and spatial-proximity conditions and showing scalable performance up to thousands of tourists. The study shows CAaaS can transform raw sensor streams into smart decisions with practical implications for disaster management and can be adapted to other domains requiring large-scale, context-aware decision support.

Abstract

Ambient-awareness in conjunction with pervasive computing is a significant challenge for system designers. It follows the necessity of gathering raw, massive and heterogeneous environmental data \newrrr{which we} obtained, while middleware processes must merge context modelling and reasoning seamlessly. We proposed a system supporting mountain rescuers which is demanding due to the large number of environmental objects interacting, as well as high data variability. We presented complex context processing embedded in the proposed context life cycle and implemented it \erarrr{following a proposed workflow for a demanding}\newrrr{in a difficult} mountain environment. We introduced five weather scenarios which are a basis for contextual and perceptual processing during the validation of our model. The system \erarrr{binds together} \newrrr{merges} a message streaming broker for massive data transport, low and high-level processing algorithms, repositories and a logical SAT solver. It constitutes a Context-Aware-as-a-Service (CAaaS) system, offering advanced support for mountain rescue operations. The provided software model defines middleware components which act on a predicted context and transform in situ sensor data into smart decisions, and which could operate as a platform-based cloud computing model. It is an enabler yielding a synergy effect with different software components orchestration when providing pro-activeness and non-intrusiveness concerning smart decisions.

Figures (22)

• Figure 1: Initial research project perspective or a layered view of the problem as its motivation. (Mountain environments which are saturated with sensors & devices, a network which provides a publish/subscribe mechanism, apps which deploy a context reasoning engine and mountain rescuers which are external clients)
• Figure 2: The assumed context model or the categories of contextual information (with the basic threat levels presented, see Tab. \ref{['tab:threat-levels']}), see also Klimek-2018-Access, as well as Fig. \ref{['fig:preliminary-simulation-influence-categories']}, within two constituents $W$ and $S$
• Figure 3: Middleware architecture of the supporting system. (Right side and bottom-up description: Msg. broker -- messages/raw data transporting, A1 -- $PhoneManagement$, A2 -- $WeatherReading$, $Repository$ -- context data, $Alerts$ -- predefined reaction/threat levels, A3 -- $ThreatDetection$, A4 -- $CheckThreat$, SAT solver -- logical reasoning engine, A5 -- $ThreatManager$)
• Figure 4: Context-Aware-as-a-Service CAaaS or from sensor data streams to smart decisions. (For denotations see also Fig. \ref{['fig:middleware-architecture']}, predefined $Alerts'$, $Alerts"$, etc. constitute the different sets of data or constraints, which can be injected, and afterwards they can affect the work of the component providing different alerts)
• Figure 5: Established context life cycle for the supporting system. Gathering geolocation data for monitored objects (Obj) and from sensor stations (Sen), and reasoning for non-weather (N-W) and weather (W) threats