Papers by Rita Kovordányi
Due to the chaotic nature of accidents and crisis, emergency responses tend to unfold in a highly... more Due to the chaotic nature of accidents and crisis, emergency responses tend to unfold in a highly dynamic fashion. It is therefore of key importance that emergency service staff are continually trained on being mindful of risks and to spot early signs of things that could go wrong during an emergency response. This need is confirmed by an initial focus group interview with accident investigators who express a general need for training of flexible thinking and mindfulness. To meet this need, foresight training is being tried out in healthcare. Similar ideas, i.e. to base training on “what-if ” discussions of typical risk scenarios, have been implemented in the mining industry, off-shore oil and gas companies, and in other high reliability organizations. We suggest a way for foresight training to be integrated into regular emergency response exercises as part of the after action review (when the emergency response exercise is debriefed). The material for foresight training could be ba...
Exercise managers and instructors have a particularly challenging task in monitoring and controll... more Exercise managers and instructors have a particularly challenging task in monitoring and controlling on-going exercises, which may involve multiple response teams and organizations in highly complex and continuously evolving crisis situations. Managers and instructors must handle potentially incomplete and conflicting fieldobservation data and make decisions in real-time in order to control the flow of the exercise and to keep it in line with the training objectives. In simulation-based exercises, managers and instructors have access to a rich set of realtime data, with an increased potential to closely monitor the trainees’ actions, and to keep the exercise on track. To assist exercise managers and instructors, data about the on-going exercise can be filtered, aggregated and refined by real-time decision-support systems. We have developed a model and a prototype decision-support system, using stream-based reasoning to assist exercise managers and instructors in real-time. The appro...
Cyclone Tracking and Forecasting in Bangladesh Using Satellite Images without Supplementary Data
The cost of Bangladesh is extremely exposed to tropical cyclones because of its long costal line ... more The cost of Bangladesh is extremely exposed to tropical cyclones because of its long costal line containing shallow deltas and densely populated offshore islands. This entails that tropical cyclones will have a particularly severe impact causing high fatality mostly among the poor people on the costal region. In spite of regular attack of devastating cyclones in Bangladesh coast, it-s impact on human lives as well as infrastructure and natural resources have been reduced considerably. The damage reduction reached at a level which is now difficult to down further because of two reasons. First is the insufficient information for early preparedness and second is the ineffective after-cyclone damage restoration system. It is therefore especially important in this part of the world that cyclones can be predicted well in advance before landfall. Normally, cyclone tracking and forecasting is based on satellite images supplemented with data collected using floating buoys, naval ships, drops...
Due to the chaotic nature of accidents and crisis, emergency responses tend to unfold in a highly... more Due to the chaotic nature of accidents and crisis, emergency responses tend to unfold in a highly dynamic fashion. It is therefore of key importance that emergency service staff are continually trained on being mindful of risks and to spot early signs of things that could go wrong during an emergency response. This need is confirmed by an initial focus group interview with accident investigators who express a general need for training of flexible thinking and mindfulness. To meet this need, foresight training is being tried out in healthcare. Similar ideas, i.e. to base training on “what-if” discussions of typical risk scenarios, have been implemented in the mining industry, off-shore oil and gas companies, and in other high reliability organizations. We suggest a way for foresight training to be integrated into regular emergency response exercises as part of the after action review (when the emergency response exercise is debriefed). The material for foresight training could be bas...
Advanced Decision Support in Simulator-Based Training for Crisis Management
This paper describes the development of a decision support and knowledge management system as par... more This paper describes the development of a decision support and knowledge management system as part of an EU FP7 funded project, CRISIS. In its final form, the decision support and knowledge management system was implemented as an Android app that uses Esper for complex event processing. The reasoning engine of the decision support and knowledge management system is backed with an ontology and knowledge representation implemented in Topic Maps.
Simulator-based training is often more information-intensive and mentally overloading―both for th... more Simulator-based training is often more information-intensive and mentally overloading―both for the trainees and for the exercise staff―than a corresponding live exercise would be. In particular, massive amounts of data are produced from the simulation core, and these data are often too detailed, and too low-level to be of direct use for the human eye. The present paper describes a decision support system aimed at helping exercise instructors maintain an overview of how the exercise is progressing and how the trainees are performing. The paper describes our experience with implementing a real-time, low-key decision support system employing complex event processing, with focus on meeting the special technical challenges that are associated with the novel approach of implementing high-end, real-time processing on a low-power, 6-inch, mobile Android platform.
In crisis management exercises the instructor’s performance is critical to the success of the tra... more In crisis management exercises the instructor’s performance is critical to the success of the training. It is their responsibility to monitor and evaluate the exercise, as well as appropriately adjust and adapt the scenario to the unfolding events. Despite the importance of the instructor’s skills in crisis management training little has been documented regarding successful methods or common pitfalls. The study presented in this paper is exploratory and aimed at investigating how instructors monitor and control large scale crisis management exercises. The results are intended to be used as a basis for further investigation on how instructors can be supported in virtual reality training systems. A summary of results from interviews is presented and followed by observations reports from two live exercises. Finally, key areas for instructor support in virtual-reality training systems are identified.
Tropical Cyclone and Track Forecasting
Is mental imagery symbolic? : Exploratory simulations in an interactive activation model
Full factorial simulation modeling of selective attention in mental imagery
Modeling and simulating inhibitory mechanisms in mental image reinterpretation : towards cooperative human-computer creativity
With the accelerating development of computer and software technology, human-computer cooperation... more With the accelerating development of computer and software technology, human-computer cooperation issues are becoming more and more centered on the human user's abilities and weaknesses. The cognitive characteristics of visual communication and reasoning, and how these affect the way users take advantage of the richness of visually represented information comprise one area which needs to be further explored within this context.The work reported in this thesis aims to identify cognitive mechanisms which might inhibit the creative interpretation of visual information, and thereby indicate which aspects of visual creativity may benefit from support in a cooperative human-computer system.We approached this problem by initially focusing on one central mechanism, selective attention, with an analysis of its constraining role in mental image reinterpretation. From this kernel, a partial model of mental image reinterpretation was developed. Given this framework, a family of related, yet...
Tropical Cyclone Track Forecasting
Tropical cyclones are large-scale low-pressure systems that form over warm tropical and subtropic... more Tropical cyclones are large-scale low-pressure systems that form over warm tropical and subtropical waters. These low-pressure systems are characterized by high-speed surface wind circulation, rota ...
The construction and evaluation of cognitive models can, and often do, lead to novel insights int... more The construction and evaluation of cognitive models can, and often do, lead to novel insights into what might constitute a valid account for an empirical phenomenon. These insights constrain the space of viable models, and could be useful also on a theoretical plane, by promoting a deeper understanding of the studied phenomenon. We propose the factorial method for deriving novel, that is, not theory–based constraints in a principled way during model development. The method is based on a systematic comparison of alternative models, realized through a cross–combination of model components in a generic cognitive model. We illustrate the method by describing an application in the area of mental imagery. We conclude by discussing ways to increase the generalizability of results that can be obtained using the factorial method.
Problem area The training of crisis management personnel is a complex task that involves many dif... more Problem area The training of crisis management personnel is a complex task that involves many different agencies and participants. This is usually carried out in full-scale incident training exercises every couple of years with smaller scale sessions in between. This leads to infrequent training sessions of the full crisis management team that would be involved in handling a full-scale incident such as an aircraft or railway accident.
CRISIS : Virtual-reality-based training for emergency management
... For example, Rudinsky and Hvannberg [1] list a range of simulation-based training tools that ... more ... For example, Rudinsky and Hvannberg [1] list a range of simulation-based training tools that are currently used for emergency response training. ... REFERENCES [1] J. Rudinsky and ETHvannberg, Initial User Requirements, technical note, CRISIS. 2010. ...
Recurrent hierarchical networks form the basis of human vision, and have been demonstrated to be ... more Recurrent hierarchical networks form the basis of human vision, and have been demonstrated to be efficient in visual feature extraction. We have evaluated the generalization capability of a recurrent hierarchical network, used for recognition of cloud patterns in satellite images, through systematic testing of the amount of Hebbian learning used for training. Hebbian learning turned out to be essential for generalization. As some form of backpropagation of error is necessary for task learning, we recommend a mixture of error-driven and Hebbian learning in these networks.
In Emergency Management (EM) teams are faced with dynamic and complex situations, often involving... more In Emergency Management (EM) teams are faced with dynamic and complex situations, often involving multiple teams and organizations working together under stressful circumstances. One of the key issues observed in emergency responses is inadequate communication. The communicative difficulties stem from various areas such as political, personal or jurisdictional. In order to improve communication and coordination, we need to gain a profound understanding of what the communication problems are and, further, we need to provide meaningful inter-organizational training regimes targeting these issues. We suggest episode analysis , a qualitative research method, to better understand the communication taking place during an emergency response. Episode analysis provides a way to code and analyze data involving multiple teams and organizations as well as a way to study more informal communicative functions that would otherwise be difficult to capture. Moreover, we suggest that episode analyses...
SmartWork: An IoT Enabled Unobtrusive Worker Health, Well-being and Functional Ability Monitoring Framework
Proceedings of the 13th International Joint Conference on Computational Intelligence
Collecting Data for Machine Learning on Office Workers’ Attention, Fatigue, Overload, and Stress during Computer Use
Proceedings of the 13th International Joint Conference on Computational Intelligence
Conceptual architecture of a multi-dimensional modeling framework for older office workers
Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments
There is an alarming rise/increase of older people in EUs population, with an expected percentage... more There is an alarming rise/increase of older people in EUs population, with an expected percentage of people over 65 at 30% by 2060, and the majority of older workers willing to work past their traditional retirement age. The concept of Work Ability, which has been developed as an important multi-factor concept that can be used to identify workers at risk for an imbalance between health, personal resources and work demands, has the potential to mitigate the decrease in work ability of office workers while aging. The framework for modeling the work ability of the office worker, described at a conceptual level in this work, is grounded in a holistic multidimensional model which accounts for both the cognitive and physical resources of the individual, and factors related to work and the environment outside of work. AI tools for prediction and risk assessment allow for dimension specific decision support and intervention, including on-the-fly flexible work management, coping with stress at work, and on-demand training.
Uploads
Papers by Rita Kovordányi