Managing Emergencies Optimally Using a Random Neural Network-Based Algorithm

Han, Qiang

doi:10.3390/fi5040515

Cited by 6 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another interesting area is the use of such infrastructure-less communication technologies in the optimum deployment and use of emergency resources [26,27]. Graph theoretical and analytical modelling methods would also prove useful in the identification of critical paths in evacuation [28] and of essential components in emergency support systems [29], and enable fast performance evaluation and more varied parameter studies.…”

Section: Discussionmentioning

confidence: 99%

No way out: Emergency evacuation with no internet access

Görbil

2015

2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops)

View full text Add to dashboard Cite

In urban emergencies and disasters, Internet connectivity is commonly unavailable to a large number of civilians in the affected area since the cellular network infrastructure and WiFi systems are either congested, or they have partially or completely failed. In this paper, we discuss how short-range wireless communications among mobile devices, e.g., smartphones, can be leveraged to construct an ad hoc and disruption tolerant evacuation support system in these typical emergency scenarios. Opportunistic communications among mobile devices are employed to gather and disseminate information on the emergency, such as hazard locations, and personalized evacuation directions are provided to each civilian using this partial information. We evaluate the performance of an opportunistic communications based evacuation support system in both indoor and outdoor evacuations of urban areas using simulation experiments, and show the improvement that can be offered. We also discuss how such a system can be protected against either malicious or inadvertent dissemination of false information, quantifying the effect of false information and the protection offered by our proposed method.

show abstract

Section: Discussionmentioning

confidence: 99%

No way out: Emergency evacuation with no internet access

Görbil

2015

2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops)

View full text Add to dashboard Cite

show abstract

“…In our simulations, each DN stores information relevant to evaluating the path metrics given in (7) and (9). Therefore, a DN should compute the following values:…”

Section: Routing Metricsmentioning

confidence: 99%

“…Li et al [8] implement a WSN consisting of sensors that continuously monitor the environment and distribute a dangerlevel map across the network. Optimization methods have been suggested [9] using distributed decision making with random neural networks [10], [11] to overcome the huge complexity of decision making for a large number of agents in the presence of spatial information to help select exit routes and decide about the appropriate allocation of rescuers and technical assets.…”

Section: Related Workmentioning

confidence: 99%

Routing diverse crowds in emergency with dynamic grouping

Akinwande

2015

2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops)

View full text Add to dashboard Cite

Evacuee routing algorithms in emergency typically adopt one single criterion to compute desired paths and ignore the specific requirements of users caused by different physical strength, mobility and level of resistance to hazard. In this paper, we present a quality of service (QoS) driven multi-path routing algorithm to provide diverse paths for different categories of evacuees. This algorithm borrows the concept of Cognitive Packet Network (CPN), which is a flexible protocol that can rapidly solve optimal solution for any user-defined goal function. Spatial information regarding the location and spread of hazards is taken into consideration to avoid that evacuees be directed towards hazardous zones. Furthermore, since previous emergency navigation algorithms are normally insensitive to sudden changes in the hazard environment such as abrupt congestion or injury of civilians, evacuees are dynamically assigned to several groups to adapt their course of action with regard to their on-going physical condition and environments. Simulation results indicate that the proposed algorithm which is sensitive to the needs of evacuees produces better results than the use of a single metric. Simulations also show that the use of dynamic grouping to adjust the evacuees' category and routing algorithms with regard for their on-going health conditions and mobility, can achieve higher survival rates.

show abstract

“…Consequently, human behavior becomes unpredictable due to the imposed uncertainty by the public safety system [3]. Thus, evacuation planning becomes an even more complicated process, especially if a large number of coevacuees [4] and available evacuation routes are included within humans' decision map [5].…”

Section: Introductionmentioning

confidence: 99%

ESCAPE: Evacuation Strategy through Clustering and Autonomous Operation in Public Safety Systems

2019

View full text Add to dashboard Cite

Natural disasters and terrorist attacks pose a significant threat to human society, and have stressed an urgent need for the development of comprehensive and efficient evacuation strategies. In this paper, a novel evacuation-planning mechanism is introduced to support the distributed and autonomous evacuation process within the operation of a public safety system, where the evacuees exploit the capabilities of the proposed ESCAPE service, towards making the most beneficial actions for themselves. The ESCAPE service was developed based on the principles of reinforcement learning and game theory, and is executed at two decision-making layers. Initially, evacuees are modeled as stochastic learning automata that select an evacuation route that they want to go based on its physical characteristics and past decisions during the current evacuation. Consequently, a cluster of evacuees is created per evacuation route, and the evacuees decide if they will finally evacuate through the specific evacuation route at the current time slot or not. The evacuees’ competitive behavior is modeled as a non-co-operative minority game per each specific evacuation route. A distributed and low-complexity evacuation-planning algorithm (i.e., ESCAPE) is introduced to implement both the aforementioned evacuee decision-making layers. Finally, the proposed framework is evaluated through modeling and simulation under several scenarios, and its superiority and benefits are revealed and demonstrated.

show abstract

Managing Emergencies Optimally Using a Random Neural Network-Based Algorithm

Cited by 6 publications

References 44 publications

No way out: Emergency evacuation with no internet access

No way out: Emergency evacuation with no internet access

Routing diverse crowds in emergency with dynamic grouping

ESCAPE: Evacuation Strategy through Clustering and Autonomous Operation in Public Safety Systems

Contact Info

Product

Resources

About