Knowledge and emotion dual-driven method for crowd evacuation

Tian, Zena; Zhang, Guijuan; Hu, Chunyu; Lu, Dianjie; Liu, Hong

doi:10.1016/j.knosys.2020.106451

Cited by 40 publications

(27 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper uses RVO for handling many agents. The related models of the papers by Li and Qin, Juniastuti et al, Muhammad et al, and Tian et al focus on the evacuation context of room and exit evacuation (17)(18)(19)(20). The related models of the paper by Sudkhot and Sombattheera focus on the evacuation context of outdoor building evacuation (21).…”

Section: Related Workmentioning

confidence: 99%

“…Muhammad et al proposed a crowd simulation model using the agent-based RVO method ( 19 ). Tian et al adopt quantitative individual knowledge and emotion combined with the RVO model to build a knowledge and emotion dual-driven crowd evacuation model ( 20 ). Sudkhot and Sombattheera present a multiagent-based framework for crowd simulation in large urban spaces on a standalone PC ( 21 ).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Crowd Evacuation Simulation Research Based on Improved Reciprocal Velocity Obstacles (RVO) Model with Path Planning and Emotion Contagion

Jun

Zhang

2021

Transportation Research Record

View full text Add to dashboard Cite

Crowd evacuation simulation is an important research topic for designing reasonable building layout and effective evacuation routes. The reciprocal velocity obstacles (RVO) model is a pedestrian motion model which is used, but it does not work when complex and multiple obstacles are present in the scene. This paper proposes an improved RVO model with path planning and emotion contagion for crowd evacuation simulation. The model uses the vertices of the obstacles to construct pedestrian path nodes for planning pedestrian evacuation paths. To make the pedestrian evacuation paths simulation results more reasonable, the safety and congestion of the path nodes are considered, to plan the shortest evacuation path. Finally, a contagious disease model is introduced to study the impact of emotion contagion on the evacuation process. A crowd evacuation simulation system is developed, and simulations have been carried out in a variety of scenarios. Experiments show that the model can effectively simulate crowd evacuation, providing a powerful reference for building and layout design.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Crowd Evacuation Simulation Research Based on Improved Reciprocal Velocity Obstacles (RVO) Model with Path Planning and Emotion Contagion

Jun

Zhang

2021

Transportation Research Record

View full text Add to dashboard Cite

show abstract

“…Many studies 4–8 have shown that the efficiency of individual evacuation under guidance is higher, that is, the leader‐follower mode. In fact, the leader‐follower mode represents reality well.…”

Section: Related Workmentioning

confidence: 99%

Multiagent evacuation framework for a virtual fire emergency scenario based on generative adversarial imitation learning

Zhou

Wen-ying

Jie

et al. 2021

Computer Animation & Virtual

View full text Add to dashboard Cite

One of the most common solutions for the prevention of fire accidents is to conduct extensive fire evacuation drills in crowded places. However, there are multiple salient advantages to using virtual reality technology to simulate emergency solutions, for instance, saving costs and greatly decreasing uncertain risks or accidents. Therefore, in this article, a multiagent evacuation framework for complex virtual fire scenarios is proposed and effectively used to simulate a multiagent evacuation procedure to approximate the goal of fire drills in a less costly manner. Specifically, the concept of a multihierarchy agent group model is proposed; that is, the evacuation of multiple agents is separated into leader‐follower and freedom modes. Additionally, several complex actions of individual humans in actual fire drills are fully considered, and a multiaction agent schema is presented to characterize the associated real effects. In addition, generative adversarial imitation learning is adopted to obtain the evacuation path of the leader‐agent by training numerous learning epochs. Finally, extensive experiments are conducted to validate the feasibility of our proposed method. The results show that the proposed method is superior to other methods and that it realistically and reasonably shows the procedure of multiagent evacuation in complex fire emergency scenarios.

show abstract

“…For instance, in Reference [21], the authors indicated that they grouped emotions into positives, which included joy and surprised, and negatives, which included sadness, fear, anger, and disgust. In another study, 22 they classified joy, trust, surprise, and anticipation as positive emotions, and they classified fear, disgust, anger, and sadness as negatives emotions. In this regard, Wang et al 23 studied and reviewed the different states and models of emotions.…”

Section: Introductionmentioning

confidence: 99%

Optimal feature selection based speech emotion recognition using two‐stream deep convolutional neural network

Mustaqeem

Kwon

2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Speech signal processing is an active area of research, the most dominant source of exchanging information among human beings, and the best way for human–computer interaction (HCI). Human behavior assessments and emotion recognition from a speech signal, such as speech emotion recognition (SER) is an emerging HCI area of exploration with various real time claims. The performance of an efficient SER system depends on feature learning, which include salient and discriminative information such as high‐level deep features. In this paper, we proposed a two‐stream deep convolutional neural network with an iterative neighborhood component analysis (INCA) to learn mutually spatial‐spectral features and select the most discriminative optimal features for the final prediction. Our model is composed of two channels, and each channel is associated with the convolutional neural network structure to extract cues from the oral signals. The first channel extracts feature from the spectral domain, and the second channel extracts features from the spatial domain, which are then fused and fed to the INCA to remove the severance and select the optimal features for the final model training. The joint refine features are passed from the fully connected network with a softmax classifier to yield the predictions of the different emotions. We trained our proposed system using three benchmarks, which included the EMO‐DB, SAVEE, and RAVDESS emotional speech corpora, and we tested the prediction performance to secure 95%, 82%, and 85% recognition rates. The performance of the system shows the effectiveness and significance of the proposed system.

show abstract

Knowledge and emotion dual-driven method for crowd evacuation

Cited by 40 publications

References 36 publications

Crowd Evacuation Simulation Research Based on Improved Reciprocal Velocity Obstacles (RVO) Model with Path Planning and Emotion Contagion

Crowd Evacuation Simulation Research Based on Improved Reciprocal Velocity Obstacles (RVO) Model with Path Planning and Emotion Contagion

Multiagent evacuation framework for a virtual fire emergency scenario based on generative adversarial imitation learning

Optimal feature selection based speech emotion recognition using two‐stream deep convolutional neural network

Contact Info

Product

Resources

About