Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu...

45
Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik

Transcript of Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu...

Page 1: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Interactively Evolving User Interfaces

Juan QuirozCommittee:

Dr. Sushil LouisDr. Sergiu Dascalu

Dr. Swatee Naik

Page 2: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Outline

• Motivation

• Related work: GAs, IGAs, UI Design

• User fatigue in IGAs

• UI evolution

• Experiments

• Results

• Future Work

Page 3: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Motivation

• User interface design is a complex, expensive, time consuming process

• Iterative process

• Users and contexts of use are numerous

• Streamline and improve UI design

• End-user customization

Page 4: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

IGA for UI Evolution

• IGA to explore the space of UIs– Creativity and insight

• Evolution is guided by both the user preferences and coded guideline metrics

• Pick best and worst

Page 5: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Genetic Algorithms

• Population based search technique– Natural selection– Survival of the fittest

Page 6: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Interactive Genetic Algorithms (IGAs)

• Fashion design (Kim 2000)• Micromachine design (Kamalian 2005)• Music, editorial design (Takagi 2001)

• Traveling salesman problem (Louis 1999)

Page 7: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

User Evaluation: Subjective Fitness

100 75 15

8020 8

3853 82

Page 8: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

User Evaluation: Ranking

1 5 6

93 2

48 7

Page 9: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

User Evaluation: Tournaments

A B

Fitness A > Fitness B

Page 10: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

User Fatigue in IGAs

• GAs tend to rely on:– Large populations– Many generations

• Suboptimal solutions

• Noisy fitness landscapes

Page 11: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Alleviating User Fatigue

• Use small population sizes

• Display a subset of population

• Accelerate convergence through prediction (Llora 2005)

Just what I had in mind!

Page 12: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

UI Design Support

• GUI toolkits and libraries

Page 13: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Guidelines of Style

• Microsoft, Apple, Java, KDE, Gnome

• Define a common look and feel for applications

• Discuss the use of color, layout of widgets, the use of fonts

• Interpreting the guidelines is itself a challenge– Too vague or too specific

Page 14: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Ambiguity in Guidelines

“Use color to enhance the visual impact of your widgets” – Apple’s Human Interface Guidelines

Page 15: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

XUL User Interfaces

• XML User Interface Language

• Mark-up language for UIs– Buttons, textboxes, sliders

menubars, toolbars

Page 16: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Related Work: UI Evolution

• Evolution of style sheets (Monmarché et al)– Font and links color, paragraph spacing, font

family, font decoration

• We allow both the user and the coded guidelines to guide the evolution

Page 17: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Related Work: User Fatigue

• SVMs to combat user fatigue (Llora 2005)

• Kamalian et al. (2005)– User evaluation every tth generation– Demote or promote reaction to individuals– Validity constraint is used to determine viable

and meaningful designs

Page 18: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Interactive Genetic Algorithms in UI Design

Page 19: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Lagoon MoveTo Panel

Page 20: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

UI Representation

• Two chromosomes– Widget chromosome– Layout chromosome

Page 21: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Genetic Operators for UI IGA

• Single point crossover

• Bit flip mutation

• PMX – partial mapped crossover

• Swap mutation

Page 22: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Widget Color

• RGB color model– Red = (255, 0, 0), Green = (0, 255, 0), Blue =

(0, 0, 255)

• 224 color space for each widget

• HSV– Same gamut as RGB– No significant efficiency difference in RGB

and HSV

Page 23: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Fitness Evaluation

1. Ask the user to select the best and worst UIs from the subset displayed

2. Interpolate the subjective fitness of individuals in population

3. Compute the objective metrics taken from guidelines of style

4. Fitness = w1 * subjective

+ w2 * objective

Page 24: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

1: Fitness Evaluation

Best

Worst

Page 25: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

2: Subjective Fitness Interpolation

• Compare to best

• Compare to worst

Best Worst

Page 26: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

3. Objective Fitness Computation

• High contrast between widget colors and background color

• Low contrast between widget colors

Page 27: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Fitness = w1 * subjective fitness

+

w2 * objective fitness

Page 28: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Research Questions

• Which selection type is the most effective for this problem?

• Who from the population do we display for user evaluation?

• How often should we ask for user input?

Page 29: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Experimental Setup

• Greedy simulated user• 30 independent runs, 200 generations• Population size of 100

• Roulette wheel vs. tournament

• Display method comparison: best 10, random 10, best 5 and worst 5

• User input every 1, 5, 10, 20, 40, 80 generations

Page 30: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Which selection type is the most effective for this problem?

Page 31: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Who from the population do we display for user evaluation?

Fitness Convergence Convergence to Blue UIs

Page 32: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

How often do we ask for user input?User input every tth generation

Fitness convergenceHigh values of tLow values of t

Page 33: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

How often do we ask for user input?User input every tth generation

Convergence to blue UIs

High values of tLow values of t

Page 34: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Experimental Setup: Actual Users

• Three users

• 30 generations

• Pick the one they like the best and the one they like the least

• 5 sessions– User input every 1, 3, 5, 10, 15 generations– 30, 10, 6, 3, and 2 user evaluations

respectively

Page 35: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Results

Page 36: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

What leads to the drop in average performance?

• Two sessions with a user– Comparison to user selected worst turned on– Comparison to user selected worst turned off

• Always pick the same UI as the best

• Ask for user input every 3 generations

Page 37: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

What leads to the drop in average performance?

Page 38: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Generated UIs: Simulated User

Page 39: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Generated UIs: Simulated User

Page 40: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Generated UIs: User3

Page 41: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Generated UIs: User3

Page 42: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Future Work

• Ask user to select the best/worst UI only• Varying the frequency of user input during a

session• Convergence acceleration with neuroevolution

or SVMs• Integration with a GUI toolkit or library• User studies!

– Task completion• Explore color representations• Specify the type of data that needs to be

represented

Page 43: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Contributions

• We can use IGAs to evolve UIs

• Our simulated user and actual users are able to effectively bias the evolution of UIs

• UIs reflect coded guidelines of style

• Reduce user fatigue– Interpolation technique– Asking for less user input

Page 44: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Demo

Page 45: Interactively Evolving User Interfaces Juan Quiroz Committee: Dr. Sushil Louis Dr. Sergiu Dascalu Dr. Swatee Naik.

Questions?

• www.cse.unr.edu/~quiroz

[email protected]