Juan C. Quiroz

Interactive Genetic Algorithms for User Interface Design

We attack the problem of user fatigue in using an interactive genetic algorithm to evolve user interfaces in the XUL interface definition language. The interactive genetic algorithm combines computable user interface design metrics with subjective user input to guide evolution. Individuals in our population represent interface specifications and we compute an individuals fitness from a weighted combination of user input and user interface design guidelines. Results from our preliminary study involving three users indicate that users are able to effectively bias evolution towards user interface designs that reflect both user preferences and computed guideline metrics. Furthermore, we can reduce fatigue, defined by the number of choices needing to be made by the human designer, by doing two things. First, asking the user to pick just two (the best and worst) user interfaces from among a subset of nine shown. Second, asking the user to make the choice once every t generations, instead of every single generation. Our goal is to provide interface designers with an interactive tool that can be used to explore innovation and creativity in the design space of user interfaces.

Co-Evolving Influence Map Tree Based Strategy Game Players

We investigate the use of genetic algorithms to evolve AI players for real-time strategy games. To overcome the knowledge acquisition bottleneck found in using traditional expert systems, scripts, or decision trees we evolve players through co-evolution. Our game players are implemented as resource allocation systems. Influence map trees are used to analyze the game-state and determine promising places to attack, defend, etc. These spatial objectives are chained to non-spatial objectives (train units, build buildings, gather resources) in a dependency graph. Players are encoded within the individuals of a genetic algorithm and co-evolved against each other, with results showing the production of strategies that are innovative, robust, and capable of defeating a suite of hand-coded opponents

A model of creative design using collaborative interactive genetic algorithms

We propose a computational model for creative design based on collaborative interactive genetic algorithms, and present an implem entation for evolving creative floorplans and widget layout/colors for individual UI panels. We map our model and its implementation to earlier models of creativ e design from literature. We also address critical research issues with respect to the model and its implementation ‐ issues relating to creative design spaces, d esign space exploration, design representation, design evaluation (competition), de sign collaboration, and design visualization (for interactivity). Results comparin g collaborative evolution of floorplans to non-collaborative evolution are also presented, and pre-tests using surveys indicate that floorplans developed via coll aboration are more original than those produced by individual non-collaborative evol ution.

Interactive evolution of XUL user interfaces

We attack the problem of user fatigue by using an interactive genetic algorithm to evolve user interfaces in the XUL interface definition language. The interactive genetic algorithm combines a set of computable user interface design metrics with subjective user input to guide the evolution of interfaces. Our goal is to provide user interface designers with a tool that can be used to explore innovation and creativity in the design space of user interfaces and make it easier for end-users to further customize their user interface without programming knowledge. User interface specifications are encoded as individuals in an interactive genetic algorithms population and their fitness is computed from a weighted combination of user interface design guidelines and user input. This paper shows that we can reduce human fatigue in interactive genetic algorithms (the number of choices needing to be made by the designer), by 1) only asking the user to pick two user interfaces from among ten shown on the display and 2) by asking the user to make the choice once every t generations.

Human guided evolution of XUL user interfaces

Graphical user interface design is a time consuming, expensive, and complex software design process. User interface design is both art and science in that we use both objective and subjective design metrics to evaluate interfaces. An automated process that relies on both subjective and objective metrics to guide the evolution of effective, personalized user interfaces could significantly change current GUI development and maintenance practice. This paper uses an interactive genetic algorithm to evolve XUL user interface layouts by combining objective and subjective metrics. The genetic algorithm encodes expert knowledge from prominent usability guidelines as objective heuristics. Further, the graphical user interface developer (or user!) biases and guides the evolution of the interfaces by subjectively evaluating and selecting the.best. and.worst. interfaces from a small set of displayed interface prototypes. We explore how the selection of individuals from the population to be displayed to the user for subjective evaluation affects the convergence of the genetic algorithm and show that our methodology can produce effective interfaces that reflect subjective user-preferred aesthetics.

IGAP: interactive genetic algorithm peer to peer

We present IGAP, a peer to peer interactive genetic algorithm which reflects the real world methodology followed in team design. We apply our methodology to floorplanning. Through collaboration users are able to visualize designs done by peers on the network, while using case injection to allow them to bias their populations and the fitness function to adapt to subjective preferences.

A TRAINING SIMULATION SYSTEM WITH REALISTIC AUTONOMOUS SHIP CONTROL

In this article we present a computational approach to developing effective training systems for virtual simulation environments. In particular, we focus on a Naval simulation system, used for training of conning officers. The currently existing training solutions require multiple expert personnel to control each vessel in a training scenario, or are cumbersome to use by a single instructor. The inability of current technology to provide an automated mechanism for competitive realistic boat behaviors thus compromises the goal of flexible, anytime, anywhere training. In this article we propose an approach that reduces the time and effort required for training of conning officers, by integrating novel approaches to autonomous control within a simulation environment. Our solution is to develop intelligent, autonomous controllers that drive the behavior of each boat. To increase the systems efficiency we provide a mechanism for creating such controllers, from the demonstration of a navigation expert, using a simple programming interface. In addition, our approach deals with two significant and related challenges: the realism of behavior exhibited by the automated boats and their real‐time response to changes in the environment. In this article, we describe the control architecture we developed that enables the real‐time response of boats and the repertoire of realistic behaviors we designed for this application. We also present our approach for facilitating the automatic authoring of training scenarios and we demonstrate the capabilities of our system with experimental results.

Sycophant: An API for Research in Context-Aware User Interfaces

Research in context-aware user interfaces aims to improve human-computer interaction by providing more effective, smarter and user-friendlier solutions for computer applications. Currently, software available for performing such research and developing context-aware interfaces is very limited both in scope and possibilities of extension. Sycophant was designed with two objectives in mind: first, to allow easy insertion of new features and capabilities needed for conducting research and, second, to provide a reusable, readily available programming resource for developing new context-aware interactive software applications. Available as open source software, Sycophants API and the calendaring application we created using it are presented in this paper in terms of functional capabilities, high level architecture, detailed design, and results of use. Procedural steps for developing new context-aware user interfaces using our API are also described in the paper.

Document Design with Interactive Evolution

We present human guided evolution of brochure documents. The user interacts with a genetic algorithm, which evolves placeholders, each placeholder represented with one of three shapes: (1) ellipse, (2) rectangle, and (3) rounded rectangle. The user guides the evolutionary process by evaluating a small subset taken from a large population of documents. Along with the subjective user input, individuals in the population of the genetic algorithm are evaluated on a set of objective heuristics for document design. We present pretest results, including an evaluation of the tool and documents created.

A Computational Model of Collaborative Creativity: A Meta-Design Approach

The role of collaboration in the realm of social creativity has been the focus of cutting edge research in design studies. In this paper, the authors investigate the role of collaboration in the process of creative design and propose a computational model of creativity based on the newly proposed meta-design approach. Meta-design is a unique participatory approach to design that deals with opening up of design solution spaces, and is aimed at creating a viable social platform for collaborative design. A meta-design-based collaborative approach to the design process may achieve ET-creativity by expanding the conceptual space of design beyond what would have been possible by individual, non-collaborative design. The model has been implemented using interactive genetic algorithms, which casts the design problem as an optimization problem and uses a set of collaborative users for subjective fitness evaluation. The design problems investigated include the collaborative design of architectural floorplans and editorial design of brochures.