Papers, Posters, Talks, and Workshops.

---

Paper: Dudzik, K. A. T., West, R. L., & Young, J. T. (2018). Developing a macro cognitive common model test bed for Real World Expertise. Procedia Computer Science, ScienceDirect, Elsevier Publishing.145, 691–698.
Abstract:
A central challenge for the common model and for Artificial General Intelligence (AGI) is the development of functional human-like agents capable of performing complex tasks in dynamic real-world environments. The cognitive test-bed model approach is a method of applying Allen Newell’s Single Complex Task Analysis method to create a human-like AGI. In addition to the environment, we include expertise in the test-bed. The expertise is placed in the agent, and the agent is placed within the environment and provided with complex tasks to perform. The agent development process and agent task performance was gauged for backwards compatibility in the performance of open-ended tasks.

Paper: West, R., Ward, L., Dudzik, K., Nagy, N., & Karimi, F. (2018). Micro and macro predictions: Using SGOMS to predict phone app game playing and Emergency Operations Centre Responses. Engineering Psychology and Cognitive Ergonomics, Springer, 501–519.
Abstract:
In this study, we examine the ability of SGOMS models to predict human behaviour on two different scales, in micro cognitive task performance and in high level problem solving roles to better understand strategy use and training. To do this, two experiments were designed to isolate the role of knowledge structures in task performance. The first experiment involves modelling an application-based game, played on mobile phones. Results were compared to two models: the SGOMS model that matched the knowledge structures the players had learned during training, and a model optimized for speed, resulting in the fastest game play possible using ACT-R. In the second experiment we examined SGOMS predictions in a high level problem space of an Emergency Operations Center (EOC) simulation, with many interruptions and communication demands, comparing professional EOC managers and undergraduate performance. By comparing results between tasks, HCI design can be augmented using predictive modeling to inform the design to produce efficient and effective training programs.

Conference Poster:
Detecting Macro Cognitive Influences in Micro Cognition: Using Micro Strategies to Evaluate the SGOMS Macro Architecture as implemented in ACT-R. Detecting Macro Cognitive Influences in Micro Cognition: Using Micro Strategies to Evaluate the SGOMS Macro Architecture as implemented in ACT-R. Poster at the 15th International Conference on Cognitive Modelling, London, U.K. · 2017

Conference Talk:
Generating narrative with ACT-R agents. West, R. L., Dudzik, K, & Greenspan, B. Generating narrative with ACT-R agents. West, R. L., Dudzik, K, & Greenspan, B. Talk at the ACT-R Workshop. London, U.K. · 2017

Conference Talk:
Using Apps and Games to Evaluate Cognitive Architectures. West, R. L., Dudzik, K, Nagy, N., & Karimi F. Using Apps and Games to Evaluate Cognitive Architectures. West, R. L., Dudzik, K, Nagy, N., & Karimi F.ACT-R workshop, London, U.K. · 2017

Conference Workshop:
Autonomous and Interactive Agent Development in Python ACT-R. Dudzik, K, & West, R.L. Autonomous and Interactive Agent Development in Python ACT-R. Dudzik, K, & West, R.L. DHSITE 2017 · 2017

Conference Talk:
Cognitive Engineering and Expertise. Nagy, N., Karimi, F., & Dudzik, K. Talk at the ICS Spring Conference · 2017

Misc.

Product Design: Artificial Intelligence System Designer of Reticle A.I.