149,942 Hits in 7.5 sec

A tool for creating predictive performance models from user interface demonstrations

Scott E. Hudson, Bonnie E. John, Keith Knudsen, Michael D. Byrne
1999 Proceedings of the 12th annual ACM symposium on User interface software and technology - UIST '99  
A central goal of many user interface development tools has been to make the construction of high quality interfaces easy enough that iterative design approaches could be a practical reality.  ...  This paper will consider techniques used by the system to produce predictive models (keystroke level models and simplified GOMS models) from demonstrations of sample tasks in a fraction of the time needed  ...  the support for all aspects of the implement-evaluate "loop", making iterative design a practical reality.  ... 
doi:10.1145/320719.322590 dblp:conf/uist/HudsonJKB99 fatcat:efltylngnjgxtfy2olnuw2ubeu


Dario D. Salvucci, Mark Zuber, Ekaterina Beregovaia, Daniel Markley
2005 Proceedings of the SIGCHI conference on Human factors in computing systems - CHI '05  
The core engine of the system relies on a rigorous cognitive model of driver performance, which the system integrates with models of behavior on the prototyped interfaces to generate predictions of distraction  ...  The paper includes two sample studies that demonstrate the system's ability to account for effects of input modality and driver age on performance.  ...  ACKNOWLE DG ME NTS This work was supported in part by grants from the Office of Naval Research (#N00014-03-1-0036) and Ford Motor Company to the first author. RE FE RE NCE S  ... 
doi:10.1145/1054972.1055052 dblp:conf/chi/SalvucciZBM05 fatcat:acj3eezlhbcfppgoqbdxd6pnpm

Predictive human performance modeling made easy

Bonnie E. John, Konstantine Prevas, Dario D. Salvucci, Ken Koedinger
2004 Proceedings of the 2004 conference on Human factors in computing systems - CHI '04  
In this paper we describe a development system in which designers generate predictive cognitive models of user behavior simply by demonstrating tasks on HTML mock-ups of new interfaces.  ...  Using a query-entry user interface as an example [19] , we demonstrate that this new system enables more rapid development of predictive models, with more accurate results, than previously published models  ...  ACKNOWLEDGMENTS All authors were supported by grants from the Office of Naval Research: Bonnie John under N00014-03-1-0086, Konstantine Prevas and Ken Koedinger under N00014-03-1-0220, and Dario Salvucci  ... 
doi:10.1145/985692.985750 dblp:conf/chi/JohnPSK04 fatcat:wji5yntmendglfs3hc6rgy3pba

Multipurpose Prototypes for Assessing User Interfaces in Pervasive Computing Systems

B.E. John, D.D. Salvucci
2005 IEEE pervasive computing  
CogTool automatically produces quantitative predictions of skilled user performance time through demonstration, making human performance modeling more accessible to system designers.  ...  skilled user performance.  ...  for HCI at CMU for their efforts using CogTool for modeling assignments.  ... 
doi:10.1109/mprv.2005.80 fatcat:faz3ddclmzf4zpgfbbpl4c5x7i

Prediction Factory: automated development and collaborative evaluation of predictive models [article]

Gaurav Sheni, Benjamin Schreck, Roy Wedge, James Max Kanter, Kalyan Veeramachaneni
2018 arXiv   pre-print
To assess the system's impact, we implemented 3 different interfaces for creating predictive modeling projects: baseline automation, full automation, and optional automation.  ...  With a dataset of online grocery shopper behaviors, we divided data scientists among the interfaces to specify prediction problems, learn and evaluate models, and write a report for domain experts to judge  ...  Creating predictive models For data scientists who create predictive models, automating both prediction engineering and feature engineering speeds up many steps in the data science process, from defining  ... 
arXiv:1811.11960v1 fatcat:epqaxvbl4jc5layxn7db7k6luu

Modeling Tools for Predicting Driver Distraction

Dario D. Salvucci
2005 Proceedings of the Human Factors and Ergonomics Society Annual Meeting  
This paper highlights four recent approaches to predicting driver distraction from in-vehicle interfaces as secondary tasks: hand-crafted modeling with the full-fledged ACT-R architecture, handcrafted  ...  While all four use an integrated-model approach and a rigorous driver model, each approach illustrates different advantages and disadvantages of simplifying cognitive modeling for purposes of rapid prototyping  ...  The tool allows a user to mock-up new interfaces in HTML and create models by demonstration -that is, clicking through the interface to demonstrate sample task processes.  ... 
doi:10.1177/154193120504901211 fatcat:doh3x6hawneellnv5fb77o226m

Embodied models as simulated users: introduction to this special issue on using cognitive models to improve interface design

2001 International Journal of Human-Computer Studies  
Existing uses of models include predicting time and errors for users to perform tasks, acting as embedded assistants to help users perform their tasks, and serving as surrogate users.  ...  Cognitive models provide a means for applying what is known from psychology to the design of interfaces, thereby improving their quality and usability.  ...  Descriptive cognitive models have been developed for making predictions about user performance (such as time and actions to perform a task) at the computer interface.  ... 
doi:10.1006/ijhc.2001.0471 fatcat:ik26c2pylzal5h4xmw4k4egnfu

Modeling task performance for a crowd of users from interaction histories

Steven Gomez, David Laidlaw
2012 Proceedings of the 2012 ACM annual conference on Human Factors in Computing Systems - CHI '12  
We present TOME, a novel framework that helps developers quantitatively evaluate user interfaces and design iterations by using histories from crowds of end users.  ...  An unimplemented design change can be evaluated by perturbing a TOME task model in CogTool to reflect the change, giving a new performance prediction.  ...  DESIGN EVALUATION BY PERFORMANCE MODELING Models of human performance with a tool can be used to guide design choices.  ... 
doi:10.1145/2207676.2208412 dblp:conf/chi/GomezL12 fatcat:wtjwseydcnhdxlgctyyveuwk4y

Integrating user performance time models in the design of tangible UIs

Paul Holleis, Dagmar Kern, Albrecht Schmidt
2007 CHI '07 extended abstracts on Human factors in computing systems - CHI '07  
One of the aspects that are important for judging an application is the time an experienced user needs to complete a task. This can be assessed by a Keystroke-Level Model (KLM) of that task.  ...  We provide versatile, easily extensible tools and examples that give developers quick access to KLM data for their prototypes and applications.  ...  Summary and Conclusions We presented an approach to use Keystroke-Level Modeling (KLM) to calculate predictions on skilled user performance time for interactions with tangible interfaces.  ... 
doi:10.1145/1240866.1241018 dblp:conf/chi/HolleisKS07 fatcat:i5ih5mczujgn3kfdo6k74iy7vi

Human performance regression testing

Amanda Swearngin, Myra B. Cohen, Bonnie E. John, Rachel K. E. Bellamy
2013 2013 35th International Conference on Software Engineering (ICSE)  
Cognitive modeling tools such as CogTool provide some help by computing predictions of user performance, but they still require manual effort to describe the user interface and tasks, limiting regression  ...  of human performance predictions for the same task.  ...  ACKNOWLEDGMENTS We thank Peter Santhanam (IBM Research) for pointing out the connection between usability and functional GUI testing and Atif Memon (University of Maryland) for providing us with the newest  ... 
doi:10.1109/icse.2013.6606561 dblp:conf/icse/SwearnginCJB13 fatcat:teoyxfq6rfawxphegfiwssj43y

Support for modeling interaction with automotive user interfaces

Stefan Schneegaß, Bastian Pfleging, Dagmar Kern, Albrecht Schmidt
2011 Proceedings of the 3rd International Conference on Automotive User Interfaces and Interactive Vehicular Applications - AutomotiveUI '11  
In this paper, we provide models and tools for rapid prototyping and the evaluation of user interfaces in this context.  ...  The presented model is the foundation for the MI-AUI prototyping tool that we implemented for permitting the creation of automotive interfaces using tangible controls.  ...  At the moment, the presented automotive KLM can be applied to the most common elements of automotive user interfaces.  ... 
doi:10.1145/2381416.2381428 dblp:conf/automotiveUI/SchneegassPKS11 fatcat:x7f5n2ob35f4ve7cr4yyewcwom

Easing the generation of predictive human performance models from legacy systems

Amanda Swearngin, Myra Cohen, Bonnie John, Rachel Bellamy
2012 Proceedings of the 2012 ACM annual conference on Human Factors in Computing Systems - CHI '12  
With the rise of tools for predictive human performance modeling in HCI comes a need to model legacy applications.  ...  A design walkthrough with experienced CogTool users reveal that CogTool-Helper resonates with a "pain point" of real-world modeling and provide suggestions for future work.  ...  ACKNOWLEDGMENTS We would like to thank Peter Santhanam from IBM Research for pointing out the connection between usability and functional GUI testing and Atif Memon from the University of Maryland for  ... 
doi:10.1145/2207676.2208415 dblp:conf/chi/SwearnginCJB12 fatcat:sfmuvz4x2fcrhbjc2cb7ocmudq

Usability Makeover of a Cognitive Modeling Tool

Changxu Wu, Yili Liu
2007 Ergonomics in design  
Using this new modeling tool, in most cases, users can model and predict human performance and workload by clicking buttons to select options without needing to learn a new programming language.  ...  FEATURE AT A GLANCE: In this article, we describe a new software tool that was developed for modeling human performance and mental workload in single-and dual-task situations.  ...  From the interface shown in Figure 3 , users simply demonstrate a task to be modeled with the storyboard method they already know.  ... 
doi:10.1177/106480460701500201 fatcat:gatj53iddjgwfdu5xibtqlyhna

Direct manipulation for comprehensible, predictable and controllable user interfaces

Ben Shneiderman
1997 Proceedings of the 2nd international conference on Intelligent user interfaces - IUI '97  
Dramatic opportunities exist to develop direct manipulation programming to create end-user programming tools, dynamic queries to perform information search in large databases, and information visualization  ...  This strategy can lead to user interfaces that are comprehensible, predictable and controllable.  ...  Several word processors allow users to create macros by simply performing a sequence of commands that is stored for later use.  ... 
doi:10.1145/238218.238281 dblp:conf/iui/Shneiderman97 fatcat:z7cau54g45g7npdh4a2pna7rqy

Scalable Workflow-Driven Hydrologic Analysis in HydroFrame [chapter]

Shweta Purawat, Cathie Olschanowsky, Laura E. Condon, Reed Maxwell, Ilkay Altintas
2020 Lecture Notes in Computer Science  
As a part of HydroFrame, we seek to design innovative workflow solutions that create pathways to enable hydrologic analysis for three target user groups: the modeler, the analyzer, and the domain science  ...  We demonstrate how different modules of the workflow can be reused and repurposed for the three target user groups.  ...  This work is supported by NSF OAC CSSI 1835855, and DOE DE-SC0012630 for IPPD.  ... 
doi:10.1007/978-3-030-50371-0_20 fatcat:c6632vj24nd25dcdq73i6bxhyu
« Previous Showing results 1 — 15 out of 149,942 results