Model Of Crowd Behavior Research Articles

Developing a Predictive Model of Crowd Behavior at Music Concerts and Festivals (MCF): A Proposal for a Research Framework

Music Concerts and Festivals (MCF) have experienced steady growth each year, transforming these events into large-scale international gatherings from their humble beginnings in the 1980s. The trend of increasing attendance by festival-goers and concert-goers at MCF has prominently emerged in the 21st century. The attendance of MCF contributes to the formation of crowds, which are indirectly influenced by risky behavior. Consequently, this trend has led to numerous incidents related to risky behavior at MCF. However, there is insufficient research on such behavior, and few existing studies address any predictive models specific to MCF. As a result, there has been a slight increase in aggressive behavioral incidents among festival-goers and concert-goers. This issue has demonstrated the importance of studying crowd behavior among those attending musical concerts and festivals. Therefore, this paper will focus on the important variables related to risky behavior that can cause crowd behavior and bridge the gap by identifying risky behavior among crowds. Additionally, this study will propose a research framework for the development of a crowd behavioral predictive model to anticipate future risk behavior among attendees. This research will employ a mixed-methods approach comprising both qualitative and quantitative methodologies as its method of investigation. The research framework will then be used to develop a predictive model of crowd behavior among attendees of MCF that will help to provide significant information for event and concert organizers to understand potential risky behavior among the crowd, hence, help in mitigating or preventing unwanted crowd safety incidents at MCF.

Integrated infection and crowd behaviour model for COVID-19 infection risk assessment onboard large passenger vessels

The development of the global COVID-19 pandemic from 2020 onward has had significant impact on the world and specifically the maritime industry. Striking examples were COVID-19 outbreaks onboard the Diamond Princess cruise vessel and the U.S.S. Theodore Roosevelt aircraft carrier at the start of the pandemic. Contagious disease management onboard large passenger ships remains a complex issue, amplified by the international character of the industry, confined environment and shared facilities. This paper therefore presents an integrated infection and crowd behavior model used to calculate agent-specific infection risk, incorporating guest and crew circulation through a passenger ship layout. The integrated model is used to investigate the effect of ship layout design, capacity reduction and mask wearing on COVID-19 airborne infection risk onboard large passenger vessels.

HAPC Model of Crowd Behavior during Crises

The dynamics of pedestrian crowds during exceptional tragic events are very complex depending on a series of human behaviors resulting from combinations of basic interaction principles and self-organization. The Alert–Panic–Control (APC) model is one of the mathematical models in the literature for representing such complicated processes, mainly focusing on psychologists’ points of view (i.e., emotion contagion). This work proposes a Hybrid APC (HAPC) model including new processes, such as the effect of resonance, the victims caused by people in state of panic, new interactions between populations based on imitation and emotional contagion phenomena and the ability to simulate multiple disaster situations. Results from simulated scenarios showed that in the first 5 min 54.45% of population move towards a state of alert, 13.82% enter the control state and 31.73% pass to the state of panic, highlighting that individuals respond to a terrible incident very quickly, right away after it occurs.

Environment-sensitive crowd behavior modeling method based on reinforcement learning

Environment-sensitive crowd behavior modeling method based on reinforcement learning

A Scientometric Research on Applications and Advances of Fire Safety Evacuation in Buildings

Fire safety evacuation has been used in numerous different kinds of buildings. This research conducts a scientometric review of fire safety evacuation applications and advances in the buildings to clarify the research trends of fire evacuation in the future and provide guidance for relevant research. A total of 3312 journals and conference proceedings were analyzed through different dimensions. The result proves that evacuation environments concentrate mainly on residential building, commercial building, school, and railway station. The characteristics of the evacuee have been gradually refined in recent years, including children, the elderly, patients, and vulnerable groups. The main experimental approaches of fire safety evacuation are evacuation drills, site records, and VR/AR experiments. The crowd behavior models mainly consist of six types: a cellular automata model, a social force model, a lattice gas model, a game-theoretic model, an animal agent-based model, and a computer agent-based model. The analysis results in the theoretical method are becoming gradually closer to the behavioral characteristics and movement data of the crowd during the actual evacuation with improvements of practical considerations. The study of evacuation drills, disaster rescue, emergencies, and other external environmental factors will become the forefront of future research, and subway stations, airports, high-rise building, and other personnel places will be the focus of the study of crowd evacuation.

Guiding crowds when facing limited compliance: Simulating strategies.

At traffic hubs, it is important to avoid congestion of pedestrian streams to ensure safety and a good level of service. This presents a challenge, since distributing crowds on different routes is much more difficult than opening valves to, for example, regulate fluid flow. Humans may or may not comply with re-directions suggested to them typically with the help of signage, loudspeakers, apps, or by staff. This remains true, even if they perceive and understand the suggestions. Yet, simulation studies so far have neglected the influence of compliance. In view of this, we complement a state-of-the-art model of crowd motion and crowd behavior, so that we can vary the compliance rate. We consider an abstracted scenario that is inspired by a metro station in the city of Munich, where traffic regulators wish to make some passengers abandon the obviously shortest route so that the flow evens out. We investigate the effect of compliance for two very simple guiding strategies. In the first strategy, we alternate routes. In the second strategy, we recommend the path with the lowest crowd density. We observe that, in both cases, it suffices to reroute a small fraction of the crowd to reduce travel times. But we also find that taking densities into account is much more efficient when facing low compliance rates.

Development of a mathematical model of virtual crowd behavior

Development of a mathematical model of virtual crowd behavior

On the expenditure of changing the principles of public order protection by the Ukrainian police during mass events: the experience of European states

The article attempts to substantiate the expediency of changing the principles and methods of protection of public order by the police of Ukraine during mass events on the basis of European experience. The activities of the police to ensure public safety are considered in line with the application of three main practices (models): a) classical; b) an improved model of crowd behavior; c) models of «good practice». A detailed review of the models allowed us to trace the evolution of approaches to policing to ensure public order and security. The paper analyzes the research of scientists who have studied the «psychology of the crowd», analyzes the experience of the police of European countries during mass events and riots. The necessity of changes in the principles of work of the National Police of Ukraine on protection of public order has been determined. The concept of public safety and policing should be based on four key principles: 1) knowledge – possession of verified information about different groups of participants, their in-tentions, purpose, values and means of achieving the goal, as well as information about persons who may be considered as a source of risk; 2) assistance – a strategy of the police, aimed primarily at assisting the organizers and participants of the peaceful assembly in achieving their legal goal in a lawful manner; 3) communication – communication between the police and the organizers and participants of the peaceful assembly at all stages of its preparation and conduct to prevent conflicts, as well as the occurrence of possible offenses; 4) differentiation – consideration of participants in a peaceful assembly not as a crowd, but as a set of individuals who may have different views, objectives, goals and ways to achieve them.

Dimensionally Aware Multi-Objective Genetic Programming for Automatic Crowd Behavior Modeling

One limitation of current data-driven automatic crowd modeling methods is that the models generated have low interpretability, which limits the practical applications of the models. In this article, we propose a new data-driven crowd modeling approach that can generate universal behavior rules with better interpretability. Higher interpretability helps people better understand and analyze the rules. Furthermore, the proposed approach considers both static and dynamic features during modeling to generate a realistic crowd, based on the assumption that humans tend to consider different features with respect to their states. In the proposed method, the automatic behavior rule generation problem is formulated as a symbolic regression problem. Then, the problem is solved by multi-objective genetic programming. On one hand, to improve the interpretability of the behavior rules found, a new mechanism is proposed to guide the algorithm to find concise and dimensionally consistent solutions. On the other hand, decisions made by considering static and dynamic features respectively are combined to improve the generated crowd realism. To validate the effectiveness of the proposed method, three real-world datasets are utilized for training and testing. The simulation results demonstrate that the proposed method is able to find universal behavior rules that are competitive to previous work in accuracy while having better interpretability.

The application of crowd behavior models for the environmental and economic processes management

The application of crowd behavior models for the environmental and economic processes management

Both optical expansion and depth information are used to control 2D pedestrian following

Collective motion in human crowds emerges from local interactions between individuals, in which pedestrian follows their near neighbors (Rio, Dachner, & Warren, PRSB, 2018). In previous work, we found that a follower’s speed and heading are controlled by nulling the optical expansion and angular velocity of a leader, depending on the leader’s position. This model explains following one neighbor (Dachner & Warren, VSS 2017; Bai & Warren, VSS 2018, 2019) and following crowds (Dachner & Warren, VSS 2018), based on visual information. However, our previous experiments isolated optical expansion and angular velocity, removing distance information. Here we add depth information (vergence, binocular disparity, declination angle from the horizon), and put it in conflict with optical expansion. 10 participants walked in a virtual environment while head position and orientation were recorded at 90 Hz. They were instructed to follow a virtual target (speckled pole, 40 cm diameter) that rested on a textured ground plane. The target appeared in three initial positions relative to the participant (0°, 30°, 60° from straight ahead), two initial distances (1m, 4m), and moved forward in the walking direction at 0.8 m/s. After 5 seconds, the pole changed its expansion rate, heading direction (+/− 35°), or both. Although its position and motion on the ground plane were consistent with its trajectory, the pole’s width expanded or contracted as if it changed speed (+/− 0.2 m/s). Participants changed speed in response to this expansion; this effect was significantly reduced by the inclusion of depth information (36% less compared to control, t(9)=3.77, p< 0.01). As well, head pitch angle indicated that participants centered their field of view at the target’s base. These results imply that following is controlled by both optical expansion and declination angle of neighbors. We plan to integrate this into our visual model of crowd behavior.

Affective analytics of demonstration sites

Multiple-criteria decision-making (MCDM) typically assumes that crowds make completely rational decisions. In MCDM, a crowd as a whole, or its individual members, generally make decisions free from any influence of valence, arousal, emotional state or environment. In contrast, various theories dealing with crowd psychology (Gustave Le Bon, Freudian, Deindividuation, Convergence, Emergent norm, Social identity) analyze, in one form or another, the emotions of the crowd. According to above theories, crowd is influenced by a range of behavioral factors, such as physical, social, psychological, culture, norms, and emotions. It can be argued that the emotional state, valence and arousal of crowds affect their decision making to a considerable degree and multiple criteria crowd behavior modeling must, therefore, consider this impact as well. In this light, the integration of crowd simulation and biometric methods, behavioral operations research and emotions in decision making has taken a prominent place as it leads to a better understanding of crowd emotions and crowd decision making. In this context, the authors developed the Affective Analytics of Demonstration Sites (ANDES) that added to this body of research in four ways. The crowd analysis and simulations conducted with ANDES used a neuro decision matrix. The matrix contains a detailed description of demonstration sites (public spaces) in question and the emotions, valence, arousal and physiological parameters of people present there. With ANDES’s Remote Sensor Network, emotional (emotions, valence, arousal) and physiological (average crowd facial temperature, crowd composition by gender and age group, etc.) parameters of people present at demonstration sites can be mapped. ANDES can assist experts in more effective implementations of public spaces planning and a participation process by attendees by collecting and examining various layers of data on the emotional and physiological parameters of visitors based on a visitors-centric public spaces planning approach. ANDES can determine the public space and real estate values.

Convolutional Neural Networks for Subjective Face Attributes

Describable visual facial attributes are now commonplace in human biometrics and affective computing, with existing algorithms even reaching a sufficient point of maturity for placement into commercial products. These algorithms model objective facets of facial appearance, such as hair and eye color, expression, and aspects of the geometry of the face. A natural extension, which has not been studied to any great extent thus far, is the ability to model subjective attributes that are assigned to a face based purely on visual judgments. For instance, with just a glance, our first impression of a face may lead us to believe that a person is smart, worthy of our trust, and perhaps even our admiration — regardless of the underlying truth behind such attributes. Psychologists believe that these judgments are based on a variety of factors such as emotional states, personality traits, and other physiognomic cues. But work in this direction leads to an interesting question: how do we create models for problems where there is only measurable behavior? In this paper, we introduce a convolutional neural network-based regression framework that allows us to train predictive models of crowd behavior for social attribute assignment. Over images from the AFLW face database, these models demonstrate strong correlations with human crowd ratings.

3D visual simulation of individual and crowd behavior in earthquake evacuation

Simulation of behaviors in emergencies is an interesting subject that helps to understand evacuation processes and to give out warnings for contingency plans. Individual and crowd behaviors in the earthquake are different from those under normal circumstances. Panic will spread in the crowd and cause chaos. Without considering emotion, most existing behavioral simulation methods analyze the movement of people from the point of view of mechanics. After summarizing existing studies, a new simulation method is discussed in this paper. First, 3D virtual scenes are constructed with the proposed platform. Second, an individual cognitive architecture, which integrates perception, motivation, behavior, emotion, and personality, is proposed. Typical behaviors are analyzed and individual evacuation animations are realized with data captured by motion capture devices. Quantitative descriptions are presented to describe emotional changes in individual evacuation. Facial expression animation is used to represent individuals’ emotions. Finally, a crowd behavior model is designed on the basis of a social force model. Experiments are carried out to validate the proposed method. Results showed that individuals’ behavior, emotional changes, and crowd aggregation can be well simulated. Users can learn evacuation processes from many angles. The method can be an intuitional approach to safety education and crowd management.

Toward Modeling Emotional Crowds

This paper presents an Emotion Network structure for modeling crowd emotions to simulate socially emotional crowds. The emotion model focuses on entire crowds, builds individual emotion spaces as network nodes, embodies psychological linkages with relationship arcs, and clusters emotionally homogeneous crowds into EmotionTrees. According to the maximum value of the emotion component and the psychological distance, crowds are initialized as different trees. With relational distributions of crowd changes, agents move between different subgroups. Then, we construct emotion-oriented commands with subgroup constraints according to intergroup emotion theory. For execution, motion variables are calculated from emotion commands (i.e., emotion source-oriented orientation, and velocity and emotion strength-based motion clip selection). Experiments on bystanders, football fans, violent protestors, and guided marching behaviors demonstrate that the Emotion Network can improve crowd behavior modeling with particular attention to the impacts of group constraints and emotional characteristics, which can reflect environment stimuli and changes. The model can be integrated into physical crowd simulators as a high-level emotion manager, providing intelligent emotional support in improving the realism of human-like crowds.

Application of the genetic algorithm for agent-based modeling of the object behavior while leaving the flaming room

The article deals with the implementation of the genetic algorithm for training and optimization of the neural network and its application to the tasks related to agent-based modelling of human behaviour. After the analysis of existing agent-based modelling programs, several drawbacks were noticed. The main problem of other systems for crowd modelling was the missing of information about the psychoemotional state of people, who are in crowd. According to the other sources, moods in crowd influence its behaviour the most; therefore, we decided to propose another method of creating more realistic crowd behaviour. The system that implements training of agents by selecting the most effective strategies of behaviour from the existing set of strategies using the genetic algorithm was proposed. In addition, this article highlights the detailed development of one agent behaviour module based on the neural network, which help the agent to navigate in the environment on condition of being trained enough. Due to created training method, it was mentioned, that training environment affects whole training process, and so several surveys were made at different environment configurations. As a base for the system, single-layer perceptron was chosen because of its simplicity and small number of connections. Final variant of agent casts seven rays into different vectors from his centre. If any other object interferes those rays, the distance to him comes as input to the neural network. Another two inputs take amount of distance to the exit and angle between agent and exit. Right rotate and left rotate forces of agent are used as outputs for neural network. Genetic algorithm was used for selecting the proper weights between the neurons. The most important indicator that some genome should be chosen for future generations is the fitness of that genome. The main purpose for the agent is finding the exit and in case of hitting the flame, it will fail. That is why agent will be rewarded for reaching the exit and get penalty for hitting the flame or staying in the room for too long. During the first launch, 30 initial genomes get involved with the values of weights generated at random. Each of them passes five iterations of training, after which the total gene is written to the database. By the results of current generation training, the five most adapted genomes that will create next generation will be selected. The following genomes remain in the population and form their modified copies by mitosis. Both genomes are divided on a specific point and exchange parts of the genetic code. That process forms two other genomes, which inherit parts of the parents. As for the training environment, there are four different exits from the room but only one of them opens randomly during the iteration. The implemented software system is used to research and train the agent model bypass the obstacles and get to the endpoint. The work of the neural system with a different structure was considered: one runs with the characteristics given above, in the other system configuration, the exit was only one and stayed in constant place, the agent had only four rays, and for staying in the room for more than five seconds he was rewarded. The development of the environment for such training is described and the results of training are presented for various environmental configurations. The main goal and mission of such approach implementation is using trained agents to develop a system for crowd behaviour modelling in the building, which was set on fire. Ref. 11, fig. 6, tabl. 4.

Understanding differences in emergency escape and experimental pedestrian crowd egress through quantitative comparison

Models of pedestrian crowd behavior in panic or emergency situations rarely have complementary empirical data to calibrate or validate the model's prediction. Till date, there is no systematic study that has attempted to conduct a quantitative comparison of emergency escape with the laboratory experimental data for the underlying differences in crowd behavior.In this paper, an attempt is made to explore the differences between experimental data on pedestrian crowd egress and emergency egress at a bottleneck and their implication for crowd safety. The laboratory experiments consist of pedestrians passing through a bottleneck of varying widths. The emergency egress data has been extracted from the publicly available rare video footage of panic escape at a shopping center during an Earthquake in China. The extracted data are then used to test a force-based crowd simulation model.It was found that there are underlying differences on the crowd egress behavior (headway distribution and flow) under emergency conditions as compared to controlled laboratory experiment. There is significant number of group exits and less lone exits in emergency egress. It was observed that the force-based model was able to replicate the normal egress as well as panic egress. It is recommended that any pedestrian crowd evacuation simulation model be tested to reproduce this fundamental headway distribution as observed in this study which includes >85% of headway as short headway (≤0.5s) with predominately group exits (0–0.1s headway) rather than lone exits for the bottleneck widths between 1.7 and 2.1m.

Crowd behavior representation: an attribute-based approach.

In crowd behavior studies, a model of crowd behavior needs to be trained using the information extracted from video sequences. Most of the previous methods are based on low-level visual features because there are only crowd behavior labels available as ground-truth information in crowd datasets. However, there is a huge semantic gap between low-level motion/appearance features and high-level concept of crowd behaviors. In this paper, we tackle the problem by introducing an attribute-based scheme. While similar strategies have been employed for action and object recognition, to the best of our knowledge, for the first time it is shown that the crowd emotions can be used as attributes for crowd behavior understanding. We explore the idea of training a set of emotion-based classifiers, which can subsequently be used to indicate the crowd motion. In this scheme, we collect a large dataset of video clips and provide them with both annotations of “crowd behaviors” and “crowd emotions”. We test the proposed emotion based crowd representation methods on our dataset. The obtained promising results demonstrate that the crowd emotions enable the construction of more descriptive models for crowd behaviors. We aim at publishing the dataset with the article, to be used as a benchmark for the communities.

Cellular Automata as the basis of effective and realistic agent-based models of crowd behavior

The Cellular Automata (CA) paradigm has been recognized as an effective approach used in the modeling and simulation of complex systems. However, its classical form of a homogeneous and synchronous CA has a limited field of applications. For practical applications, non-homogeneous and asynchronous CAs with hybrid technological construction are especially useful in modeling and simulation. In this article, the authors focus on crowd simulations based on CA and agent-based modeling approaches. Basic technical aspects of large-scale crowd simulations are presented: specifically proposed architecture, our view on synchronization patterns, as well as hierarchy of objects in logic and data layer. A new method of agent conflict resolution is also proposed. Such an approach was successfully applied in the Allianz Arena stadium model, and other large-scale simulations developed by the authors. Thus, finally, practical applications of the models are presented.

An agent model of crowd behavior in emergencies

An agent model of crowd (ensemble) behavior in emergencies was presented. This model is distinguished for the allowance for dynamics of each agent from the ensemble under consideration. The crowd effect manifests itself mostly as attraction or repulsion of closely set agents with a probability depending on the agent's psychological type. Consideration was given to the effects associated with the crowd turbulence. Operation of the intelligent rescue agents was simulated. The impact of the configuration of spatial agent allocation on the dynamics of their evacuation in emergencies was analyzed. The influence of the intelligent rescue agents on the system was studied, and an adaptive procedure for training such agents was developed.