The Design of an Agent Based Model of Human Activities and Communications in Cardiac Resuscitation

Mancheva, Lyuba; Dugdale, Julie

doi:10.1109/hicss.2015.34

Cited by 2 publications

(6 citation statements)

References 23 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition our network size is 78 times smaller than the benchmark model, making it also suitable for embedding into artificial drones and robots [26]. The recognition module enhances the level 1 capabilities which is necessary for sophisticated artificial agents' decision making [13,15,16].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations

Buettner¹,

Baumgartl²

2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Using convolutional neural networks we extend the work by Dugdale's group on socially relevant multi-agent systems in crisis and emergency situations by giving the artificial agent the ability to precisely recognize escape signs, doors and stairs for escape route planning. We build an efficient recognition module consisting of three blocks of a depth-wise separable convolutional layer, a max-pooling layer, and a batchnormalization layer before dense, dropout and classifying the image. A rigorous evaluation based on the MCIndoor20000 dataset shows excellent performance values (e.g. over 99.81 percent accuracy). In addition, our module architecture is 78 times smaller than the MCIndoor20000 benchmark-making it suitable for embedding in operational drones and robots.

show abstract

Section: Resultsmentioning

confidence: 99%

“…(p. 36). The combination of BDI architecture and Situational Awareness theory by Dugdale's group leads to better agent decisions [15,16]. Research has shown that the implementation of sophisticated behavioral models (BDI, Situational Awareness theory, etc.)…”

Section: Introductionmentioning

confidence: 99%

A Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations

Buettner¹,

Baumgartl²

2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…Note that the terms 'good' and 'bad' were expressly chosen by the resuscitation team trainer (a physician); this indicates the importance placed on communication by the trainer. Also shown in the rightmost column is an example of how we have translated the good communications into a logic-based message that forms part of our model [21] [22]. It is possible with our formalism also to represent bad communications.…”

Section: Checkbackmentioning

confidence: 99%

“…Concerning the field studies, since we cannot collect data on communications during real-life CPR procedures for ethical reasons, we have been collaborating with the local hospital training centre for the region to collect data on their simulation exercises. We analysed the communications exchanged during the training simulations and found that they heavily affected the success of the team [21,22].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Understanding Communications in Medical Emergency Situations

Mancheva

Dugdale

2016

2016 49th Hawaii International Conference on System Sciences (HICSS)

Self Cite

View full text Add to dashboard Cite

Good communication is essential within teams dealing with emergency situations. In this paper we look at communications within a resuscitation team performing cardio-pulmonary resuscitation. Communication underpins efficient collaboration, joint coordination of work, and helps to construct a mutual awareness of the situation. Poor communication wastes valuable time and can ultimately lead to lifethreatening mistakes. Although training sessions frequently focus on medical knowledge and procedures, soft skills, such as communication receive less attention. This paper analyses communication problems in the case of CPR and proposes an architecture that merges a situation awareness model and the belief-desire-intention (BDI) approach in multi-agent systems. The architecture forms the basis of an agent-based simulator used to assess communication protocols in CPR teams. Communications and MSAMany studies identify the solid link between communication, and SA and MSA that strongly affects a team's performance [15].Communication failures maybe classified along several dimensions: the content (messages are unclear or unstructured) [7] the entities themselves (members of the team do not always share the same communication code [3], and the intended purpose of the communication (members do not always correctly interpret the message). Other reasons for communication failures arise from an excessively noisy environment, stress, and the lack of accurate communication strategies in a particular critical situation, etc. [26].The Agency for Healthcare Research and Quality (AHRQ) in the United States recommends several information exchange standards for effective communication that will increase MSA [2] (Table 1)

show abstract

The Design of an Agent Based Model of Human Activities and Communications in Cardiac Resuscitation

Cited by 2 publications

References 23 publications

A Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations

A Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations

Understanding Communications in Medical Emergency Situations

Contact Info

Product

Resources

About