A Wireless Actuator-Sensor Neural Network for Evacuation Routing

Abstract

A wireless sensor-actuator network is formed by nodes capable of sensing and acting upon its environment. Typical challenges in designing such networks include distributed signal processing, synchronisation and communication, as well as deployment of network nodes and scalable architectures for these networks. In this paper, we look at the application of neural networks to individual nodes in a wireless network, which result in a wireless sensor-actuator neural network model. We explain how the combination of sensor network and neural network technology can describe a system which maintains desired characteristics such as scalability and adaptability. We show further that such model can be successfully applied to an evacuation routing scenario.

Design and experimental evaluation of an interactive system for pre-movement time reduction in case of fire

“…Another system in real-time building monitoring technologies concerns sensor units and communication network based on wireless Zig-Bee which can also be used in evacuation situations [44][45][46][47], such as those for construction elevator security system [48] or patient localization and environmental monitoring [49]. Localization data can be elaborated by different algorithms [32] in order to give information or stimuli to people evacuating (e.g., appropriate evacuation routes) [50][51][52][53][54]. The interactive module effectively returns information and stimuli to the occupants based on algorithm results.…”

A Survey of Algorithms and Systems for Evacuating People in Confined Spaces

“…Since on-line evacuation wayfinding algorithms require real-time information exchanges with the hazardous environment, these algorithms are usually integrated into evacuation wayfinding systems. With the development of evacuation wayfinding systems, which are detailed in Section 2, various evacuation wayfinding algorithms have been proposed such as network flow-based algorithms [9,[80][81][82][83], geometric algorithms [84,85], queueing model-based algorithms [86][87][88][89][90][91][92], potential-maintenance algorithms [18,20,93], biologically-inspired algorithms [94][95][96], routing protocol-based algorithms [23,[97][98][99] and prediction-based algorithms [100][101][102][103][104].…”

“…Biologically-inspired approaches, which are inspired by simple, but reliable natural mechanisms, employ heuristics to search optimal routes in a computationally-efficient manner. For instance, a feed-forward neural network model was adopted for a wireless sensor-actuator network (WSAN) for evacuation routing in [95]; all physical nodes in the WSAN deployed a neural network with an identical topology: an input layer, a hidden layer and an output layer; the input layer received the latest two coordinates of a pedestrian, and a suggested direction was subsequently generated by the output layer; the neural networks were trained with a back-propagation algorithm [136] in standard situations and were deactivated when an emergency happened; hence evacuees would be directed to exits over their normal walking paths; however, back-propagation algorithms suffer from a slow learning rate and easily converge to local minima; furthermore, this model cannot react to the spreading of a hazard. The study in [96] employed a genetic algorithm [137,138] to minimise the total evacuation time, travel distance and number of congestions encountered during an evacuation process.…”

Emergency Navigation in Confined Spaces Using Dynamic Grouping

“…At the core of these systems, various emergency navigation algorithms have been proposed such as network flow based algorithms [2], [3], queueing model based approaches [4], [5], potential-maintenance algorithms [6], [7], biological-inspired approaches [8], [9], [10]. Network flow based algorithms commonly predict the upper bound of evacuation time and convert the original building model to a time-expanded network by duplicating the original network for each discrete time unit.…”