Papers by Huibo Bi
—Previous queueing theory based emergency navigation algorithms in built environments normally tr... more —Previous queueing theory based emergency navigation algorithms in built environments normally treat each significant location (such as doorways and staircases) as an " independent " queue and all the evacuees in a homogeneous manner. Hence, the interactions among linked queues caused by the rerouting instructions generated by the emergency navigation system, the panic behaviours such as evacuees not following the evacuation instructions, as well as the influence of diverse mobilities of evacuees are ignored. In this paper, we employ a Cognitive Packet Network based algorithm to customise distinct paths for diverse categories of evacuees. A G-network based model is used to analyse the latency on a path via capturing the dynamics of diverse categories of evacuees under the influence of panic and rerouting decisions from the navigation system. Moreover, by modelling the probabilistic choices of evacuees towards all the linked queues, the G-network model closely approximates the movement of the evacuees under the instructions of the Cognitive Packet Network based algorithm. The simulation results indicate that the use of the G-network model can improve the survival rates and ease the congestion during an evacuation process when there is a certain likelihood that evacuees do not follow evacuation instructions due to panic.
Previous queueing theory based emergency navigation algorithms in built environments normally tre... more Previous queueing theory based emergency navigation algorithms in built environments normally treat each significant location (such as doorways and staircases) as an "independent" queue and all the evacuees in a homogeneous manner. Hence, the interactions among linked queues caused by the re-routing instructions generated by the emergency navigation system, the panic behaviours such as evacuees not following the evacuation instructions, as well as the influence of diverse mobilities of evacuees are ignored. In this paper, we employ a Cognitive Packet Network based algorithm to customise distinct paths for diverse categories of evacuees. A G-network based model is used to analyse the latency on a path via capturing the dynamics of diverse categories of evacuees under the influence of panic and re-routing decisions from the navigation system. Moreover, by modelling the probabilistic choices of evacuees towards all the linked queues, the Gnetwork model closely approximates the movement of the evacuees under the instructions of the Cognitive Packet Network based algorithm. The simulation results indicate that the use of the G-network model can improve the survival rates and ease the congestion during an evacuation process when there is a certain likelihood that evacuees do not follow evacuation instructions due to panic.
Emergency Navigation in Confined Spaces Using Dynamic Grouping
2015 9th International Conference on Next Generation Mobile Applications, Services and Technologies, 2015
biHuiboGelenbePernem 2014 2
2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), 2015
Evacuee routing algorithms in emergency typically adopt one single criterion to compute desired p... more 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 multipath 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.
2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), 2015
State-of-the-art emergency navigation approaches are designed to evacuate civilians during a disa... more State-of-the-art emergency navigation approaches are designed to evacuate civilians during a disaster based on real-time decisions using a pre-defined algorithm and live sensory data. Hence, casualties caused by the poor decisions and guidance are only apparent at the end of the evacuation process and cannot then be remedied. Previous research shows that the performance of routing algorithms for evacuation purposes are sensitive to the initial distribution of evacuees, the occupancy levels, the type of disaster and its as well its locations. Thus an algorithm that performs well in one scenario may achieve bad results in another scenario. This problem is especially serious in heuristic-based routing algorithms for evacuees where results are affected by the choice of certain parameters. Therefore, this paper proposes a simulation-based evacuee routing algorithm that optimises evacuation by making use of the high computational power of cloud servers. Rather than guiding evacuees with a predetermined routing algorithm, a robust Cognitive Packet Network based algorithm is first evaluated via a cloud-based simulator in a fasterthan-real-time manner, and any "simulated casualties" are then re-routed using a variant of Dijkstras algorithm to obtain new safe paths for them to exits. This approach can be iterated as long as corrective action is still possible.
Information Sciences and Systems 2014, 2014
The use of wireless sensor networks (WSNs) for emergency navigation systems suffer disadvantages ... more The use of wireless sensor networks (WSNs) for emergency navigation systems suffer disadvantages such as limited computing capacity, restricted battery power and high likelihood of malfunction due to the harsh physical environment. By making use of the powerful sensing ability of smart phones, this paper presents a cloud-enabled emergency navigation framework to guide evacuees in a coordinated manner and improve the reliability and resilience in both communication and localization. By using social potential fields (SPF), evacuees form clusters during an evacuation process and are directed to egresses with the aid of a Cognitive Packet Networks (CPN) based algorithm. Rather than just rely on the conventional telecommunications infrastructures, we suggest an Ad hoc Cognitive Packet Network (AHCPN) based protocol to prolong the life time of smart phones, that adaptively searches optimal communication routes between portable devices and the egress node that provides access to a cloud server with respect to the remaining battery power of smart phones and the time latency.
Routing Emergency Evacuees with Cognitive Packet Networks
Lecture Notes in Electrical Engineering, 2013
ABSTRACT Providing optimal and safe routes to evacuees in emergency situations requires fast and ... more ABSTRACT Providing optimal and safe routes to evacuees in emergency situations requires fast and adaptive algorithms. The common approaches are often too slow to converge, too complex, or only focus on one aspect of the problem, e.g. finding the shortest path. This paper presents an adaptation of the Cognitive Packet Network (CPN) concept to emergency evacuation problems. Using Neural Networks, CPN is able to rapidly explore a network and allocate overhead in proportion to the perceived likelihood of finding an optimal path there. CPN is also flexible, as it can operate with any user-defined cost function, such as congestion, path length, safety, or even compound metrics. We compare CPN with optimal algorithms such as Dijkstra’s Shortest Path using a discrete-event emergency evacuation simulator. Our experiments show that CPN reaches the performance of optimal path-finding algorithms. The resulting side-effect of such smart or optimal algorithms is in the greater congestion that is encountered along the safer paths; therefore we indicate how the quality of service objective used by CPN can also be used to avoid congestion for further improvements in evacuee exit times.
Routing Diverse Evacuees with the Cognitive Packet Network Algorithm
Future Internet, 2014
ABSTRACT This paper explores the idea of smart building evacuation when evacuees can belong to di... more ABSTRACT This paper explores the idea of smart building evacuation when evacuees can belong to different categories with respect to their ability to move and their health conditions. This leads to new algorithms that use the Cognitive Packet Network concept to tailor different quality of service needs to different evacuees. These ideas are implemented in a simulated environment and evaluated with regard to their effectiveness.
Sensors (Basel, Switzerland), 2014
Emergency navigation systems for buildings and other built environments, such as sport arenas or ... more Emergency navigation systems for buildings and other built environments, such as sport arenas or shopping centres, typically rely on simple sensor networks to detect emergencies and, then, provide automatic signs to direct the evacuees. The major drawbacks of such static wireless sensor network (WSN)-based emergency navigation systems are the very limited computing capacity, which makes adaptivity very difficult, and the restricted battery power, due to the low cost of sensor nodes for unattended operation. If static wireless sensor networks and cloud-computing can be integrated, then intensive computations that are needed to determine optimal evacuation routes in the presence of time-varying hazards can be offloaded to the cloud, but the disadvantages of limited battery life-time at the client side, as well as the high likelihood of system malfunction during an emergency still remain. By making use of the powerful sensing ability of smart phones, which are increasingly ubiquitous, ...
Emergency navigation algorithms for evacuees in
confined spaces typically treat all evacuees in a... more Emergency navigation algorithms for evacuees in
confined spaces typically treat all evacuees in a homogeneous
manner, using a common metric to select the best exit paths. In
this paper, we present a quality of service (QoS) driven routing
algorithm to cater to the needs of different types of evacuees
based on age, mobility, and level of resistance to fatigue and
hazard. Spatial information regarding the location and the spread
of hazards is also integrated into the routing metrics to avoid
situations where evacuees may be directed towards hazardous
zones. Furthermore, rather than persisting with a single decision
algorithm during an entire evacuation process, we suggest that
evacuees may adapt their course of action with regard to their
ongoing physical condition and environment. A widely tested
routing protocol known as the Cognitive Packet Network (CPN)
with random neural networks (RNN) and reinforcement learning
is employed to collect information and provide advice to evacuees,
and is beneficial in emergency navigation owing to its low
computational complexity and its ability to handle multiple QoS
metrics in its search for safe exit paths. 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’ by category, and routing algorithms that have regard for their on-going health conditions and mobility, can achieve higher survival rates.
Drafts by Huibo Bi
Previous queueing theory based emergency navigation algorithms in built environments normally tre... more Previous queueing theory based emergency navigation algorithms in built environments normally treat each significant location (such as doorways and staircases) as an "independent" queue and all the evacuees in a homogeneous manner. Hence, the interactions among linked queues caused by the rerouting instructions generated by the emergency navigation system, the panic behaviours such as evacuees do not follow the evacuation instructions, as well as the influence of diverse mobilities of evacuees are ignored. In this paper, we employ a Cognitive Packet Network based algorithm to customise distinct paths for diverse categories of evacuees. A G-network based model is used to analyse the latency on a path via capturing the dynamics of diverse categories of evacuees under the influence of panic and rerouting decisions from the navigation system. Moreover, by modelling the probabilistic choices of evacuees towards all the linked queues, the G-network model closely approximates the movement of the evacuees under the instructions of the Cognitive Packet Network based algorithm. The simulation results indicate that the use of the G-network model can improve the survival rates and ease the congestion during an evacuation process when there is a certain likelihood that evacuees do not follow evacuation instructions due to panic.
Thesis Chapters by Huibo Bi
The increasing concentration of human populations in modern urbanised societies has aggravated th... more The increasing concentration of human populations in modern urbanised societies has aggravated the frequency and destruction of both natural and manmade disasters, and has motivated considerable research over the last few decades. Accompanying the development of computing technology, emergency navigation algorithms in built environment have evolved from off-line algorithms that direct evacuees in accordance with pre-deployed static evacuation plans to online algorithm that dynamically calculate egress paths for evacuees. However, these algorithms normally consider evacuees in a homogeneous manner and ignore the different requirements and relative risk of death among different groups of people caused by different mobilities, physical strength, health conditions and level of resistance to hazard. To this purpose, this work aims to develop systems and algorithms to dynamically customise distinct paths for different categories of evacuees. To this end, we borrow the concept of Cognitive Packet Network and adapt it to a wireless sensor network based emergency navigation system. On top of the Cognitive Packet Network framework, we design several routing metrics to calculate distinct egress paths for different categories of evacuees. Since destructive crowd behaviours such as clogging and trampling are common occurrences during an evacuation process, a congestion-ease mechanism is proposed and embedded into the routing metrics. To improve the inter and intra-group coordination, several cooperative strategies are proposed to further optimise the routes calculated by the proposed routing algorithm.
Due to the limited computing capacity and battery power of a wireless sensor network, as well as the increasing popularity and tremendous computing power of cloud computing, we transplant the proposed Cognitive Packet Network based routing algorithm to the cloud computing environment and present several cloud-enabled emergency navigation systems and the associated algorithms to meet different emergency situations and scenarios. In the first scenario, we propose an infrastructure-less, indoor emergency response system to evacuate civilians with the aid of smart handsets and cloud servers. A coordinated emergency navigation algorithm is proposed to guide evacuees in loose groups to increase the likelihood for trapped evacuees to receive assistance from other evacuees. An ad hoc cognitive Packet Network based energy-efficient protocol is also presented to prolong the lifetime of smart handsets owing to the considerable energy consumption during the communication processes between the cloud and smart phones. In the second scenario, under the assumption that a data center with numerous inter-connected servers is in use, we propose a simulation based algorithm to optimise an evacuation process by performing faster-then-real-time simulations in the data center and re-calculate optimal paths for perished civilians in the simulation. To provide a more accurate prediction to the congestion level of each egress path during an evacuation process under the effect of panic behaviours, in the third scenario, we combine the Cognitive Packet Network based routing algorithm with a G-network model to analyse the congestion level on a path via capturing the dynamics of diverse categories of evacuees under the influence of panic and re-routing decisions from the navigation system. Finally, we extend our work to large scale evacuations, and propose a cloud based navigation algorithm to direct vehicles to safe areas in the aftermath of a large-scale disaster in an energy and time efficient manner. A G-network model is used by the algorithm to mimic the movement of vehicles and their interactions with the navigation system. To reduce the overall fuel consumption and evacuation time, re-routing decisions at intersections are computed based on a compound routing metric, and gradually optimised using a gradient descent algorithm.
Uploads
Papers by Huibo Bi
confined spaces typically treat all evacuees in a homogeneous
manner, using a common metric to select the best exit paths. In
this paper, we present a quality of service (QoS) driven routing
algorithm to cater to the needs of different types of evacuees
based on age, mobility, and level of resistance to fatigue and
hazard. Spatial information regarding the location and the spread
of hazards is also integrated into the routing metrics to avoid
situations where evacuees may be directed towards hazardous
zones. Furthermore, rather than persisting with a single decision
algorithm during an entire evacuation process, we suggest that
evacuees may adapt their course of action with regard to their
ongoing physical condition and environment. A widely tested
routing protocol known as the Cognitive Packet Network (CPN)
with random neural networks (RNN) and reinforcement learning
is employed to collect information and provide advice to evacuees,
and is beneficial in emergency navigation owing to its low
computational complexity and its ability to handle multiple QoS
metrics in its search for safe exit paths. 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’ by category, and routing algorithms that have regard for their on-going health conditions and mobility, can achieve higher survival rates.
Drafts by Huibo Bi
Thesis Chapters by Huibo Bi
Due to the limited computing capacity and battery power of a wireless sensor network, as well as the increasing popularity and tremendous computing power of cloud computing, we transplant the proposed Cognitive Packet Network based routing algorithm to the cloud computing environment and present several cloud-enabled emergency navigation systems and the associated algorithms to meet different emergency situations and scenarios. In the first scenario, we propose an infrastructure-less, indoor emergency response system to evacuate civilians with the aid of smart handsets and cloud servers. A coordinated emergency navigation algorithm is proposed to guide evacuees in loose groups to increase the likelihood for trapped evacuees to receive assistance from other evacuees. An ad hoc cognitive Packet Network based energy-efficient protocol is also presented to prolong the lifetime of smart handsets owing to the considerable energy consumption during the communication processes between the cloud and smart phones. In the second scenario, under the assumption that a data center with numerous inter-connected servers is in use, we propose a simulation based algorithm to optimise an evacuation process by performing faster-then-real-time simulations in the data center and re-calculate optimal paths for perished civilians in the simulation. To provide a more accurate prediction to the congestion level of each egress path during an evacuation process under the effect of panic behaviours, in the third scenario, we combine the Cognitive Packet Network based routing algorithm with a G-network model to analyse the congestion level on a path via capturing the dynamics of diverse categories of evacuees under the influence of panic and re-routing decisions from the navigation system. Finally, we extend our work to large scale evacuations, and propose a cloud based navigation algorithm to direct vehicles to safe areas in the aftermath of a large-scale disaster in an energy and time efficient manner. A G-network model is used by the algorithm to mimic the movement of vehicles and their interactions with the navigation system. To reduce the overall fuel consumption and evacuation time, re-routing decisions at intersections are computed based on a compound routing metric, and gradually optimised using a gradient descent algorithm.