Скачать презентацию Visual Computing Lecture 2 Visualization Data and Process Скачать презентацию Visual Computing Lecture 2 Visualization Data and Process

fa2225eae3c60ca67163835f93829bcf.ppt

  • Количество слайдов: 36

Visual Computing Lecture 2 Visualization, Data, and Process Visual Computing Lecture 2 Visualization, Data, and Process

Pipeline 1 High Level Visualization Process 1. 2. 3. 4. 5. Data Modeling Data Pipeline 1 High Level Visualization Process 1. 2. 3. 4. 5. Data Modeling Data Selection Data to Visual Mappings Scene Parameter Settings (View Transforms) Rendering

Pipeline 2 Computer Graphics 1. 2. 3. 4. 5. 6. Modeling Viewing Clipping Hidden Pipeline 2 Computer Graphics 1. 2. 3. 4. 5. 6. Modeling Viewing Clipping Hidden Surface Removal Projection Rendering

Pipeline 3 Visualization Process Pipeline 3 Visualization Process

Pipeline 4 Knowledge Discovery (Data Mining) Pipeline 4 Knowledge Discovery (Data Mining)

A Data Analysis Pipeline Raw Data Processed Data Hypotheses Models Results D Cleaning Filtering A Data Analysis Pipeline Raw Data Processed Data Hypotheses Models Results D Cleaning Filtering Transforming A Statistical Analysis Pattern Rec Knowledge Disc Validation B C

Where Does Visualization Come In? • All stages can benefit from visualization • A: Where Does Visualization Come In? • All stages can benefit from visualization • A: identify bad data, select subsets, help choose transforms (exploratory) • B: help choose computational techniques, set parameters, use vision to recognize, isolate, classify patterns (exploratory) • C: Superimpose derived models on data (confirmatory) • D: Present results (presentation)

What do we need to know to do Information Visualization? • Characteristics of data What do we need to know to do Information Visualization? • Characteristics of data – Types, size, structure – Semantics, completeness, accuracy • Characteristics of user – Perceptual and cognitive abilities – Knowledge of domain, data, tasks, tools • Characteristics of graphical mappings – What are possibilities – Which convey data effectively and efficiently • Characteristics of interactions – Which support the tasks best – Which are easy to learn, use, remember

Visualization Components • Human Abilities • • Design Principles Visual perception • Visual display Visualization Components • Human Abilities • • Design Principles Visual perception • Visual display • Cognition • Interaction • Motor skills Imply • • Frameworks • Data types • Tasks Constrain design • Techniques • Graphs & plots • Maps • Trees & Networks • Volumes & Vectors • … • Iterative design • Inform design Design Process Design studies • Evaluation

Issues Regarding Data • Type may indicate which graphical mappings are appropriate – – Issues Regarding Data • Type may indicate which graphical mappings are appropriate – – – – • • Nominal vs. ordinal Discrete vs. continuous Ordered vs. unordered Univariate vs. multivariate Scalar vs. vector vs. tensor Static vs. dynamic Values vs. relations Trade-offs between size and accuracy needs Different orders/structures can reveal different features/patterns

Types of Data • Quantitative (allows arithmetic operations) - 123, 29. 56, … • Types of Data • Quantitative (allows arithmetic operations) - 123, 29. 56, … • Categorical (group, identify & organize; no arithmetic) Nominal (name only, no ordering) • Direction: North, East, South, West Ordinal (ordered, not measurable) • First, second, third … • Hot, warm, cold Interval (starts out as quantitative, but is made categorical by subdividing into ordered ranges) • Time: Jan, Feb, Mar • 0 -999, 1000 -4999, 5000 -9999, 10000 -19999, … Hierarchical (successive inclusion) • Region: Continent > Country > State > City • Animal > Mammal > Horse Adapted from Stone & Zellweger 11

Quantitative Data • Characterized by its dimensionality and the scales over which the data Quantitative Data • Characterized by its dimensionality and the scales over which the data has been measured • Data scales comprise: – Interval scales - real data values such as degrees Celsius, but do not have a natural zero point. – Ratio data scales - like interval scales, but have a natural zero point and can be defined in terms of arbitrary units. – Absolute data scales - ratio scales that are defined in terms of non-arbitrary units.

Data Dimensions • Scalar - single value – e. g. Speed. It specifies how Data Dimensions • Scalar - single value – e. g. Speed. It specifies how fast an object is traveling. • Vector – multi value – e. g Velocity. It tells the speed and direction. • Tensor – multi value – Scalars and vectors are special cases of tensors with degree (n) equal to 0 and 1 respectively. – The number of tensor components is given as dn, where d is the dimensionality of the coordinate system. – In a three dimensional coordinate system (d=3), a scalar (n=0) requires three values; and a tensor (n=2) requires 9 values. – There is a difference between a vector and a collection of scalars. – A multidimensional vector is a unified entity, the components of which are physically related. – The three components of a velocity vector of particle moving through three-space are coherently linked; while a collection scalar measurements such a weight, temperature, and index of refraction, are not.

Metadata • Metadata provides a description of the data and the things it represents. Metadata • Metadata provides a description of the data and the things it represents. – e. g. , a data value of 98. 6 o. F has two metadata attributes: temperature and temperature scale. – The value 98. 6 has little meaning without the metadata attribute of temperature. – By adding Fahrenheit the attribute, we know the Fahrenheit sale is used. • Metadata may also include descriptions of experimental conditions and documentation of data accuracy and precision.

Issues Regarding Mappings • Variables include shape, size, orientation, color, texture, opacity, position, motion…. Issues Regarding Mappings • Variables include shape, size, orientation, color, texture, opacity, position, motion…. • Some of these have an order, others don’t • Some use up significant screen space • Sensitivity to occlusion • Domain customs/expectations

www 3. sympatico. ca/blevis/Image 10. gif www 3. sympatico. ca/blevis/Image 10. gif

Importance of Evaluation • • Easy to design bad visualizations Many design rules exist Importance of Evaluation • • Easy to design bad visualizations Many design rules exist – many conflict, many routinely violated 5 E’s of evaluation: effective, efficient, engaging, error tolerant, easy to learn Many styles of evaluation (qualitative and quantitative): – Use/case studies – Usability testing – User studies – Longitudinal studies – Expert evaluation – Heuristic evaluation

Categories of Mappings • Based on data characteristics – Numbers, text, graphs, software, …. Categories of Mappings • Based on data characteristics – Numbers, text, graphs, software, …. • Logical groupings of techniques (Keim) – Standard: bars, lines, pie charts, scatterplots – Geometrically transformed: landscapes, parallel coordinates – Icon-based: stick figures, faces, profiles – Dense pixels: recursive segments, pixel bar charts – Stacked: treemaps, dimensional stacking • Based on dimension management (Ward) – Dimension subsetting: scatterplots, pixel-oriented methods – Dimension reconfiguring: glyphs, parallel coordinates – Dimension reduction: PCA, MDS, Self Organizing Maps – Dimension embedding: dimensional stacking, worlds within worlds

Scatterplot Matrix • • • Each pair of dimensions generates a single scatterplot All Scatterplot Matrix • • • Each pair of dimensions generates a single scatterplot All combinations arranged in a grid or matrix, each dimension controls a row or column Look for clusters, outliers, partial correlations, trends

Parallel Coordinates • • • Each variable/dimension is a vertical line Bottom of line Parallel Coordinates • • • Each variable/dimension is a vertical line Bottom of line is low value, top is high Each record creates a polyline across all dimensions Similar records cluster on the screen Look for clusters, outliers, line angles, crossings

Star Glyph • Glyphs are shapes whose attributes are controlled by data values • Star Glyph • Glyphs are shapes whose attributes are controlled by data values • Star glyph is a set of N rays spaced at equal angles • Length of each ray proportional to value for that dimension • Line connects all endpoints of shape • Lay glyphs out in rows and columns • Look for shape similarities and differences, trends

Other Types of Glyphs Other Types of Glyphs

Dimensional Stacking • • Break each dimension range into bins Break the screen into Dimensional Stacking • • Break each dimension range into bins Break the screen into a grid using the number of bins for 2 dimensions Repeat the process for 2 more dimensions within the subimages formed by first grid, recurse through all dimensions Look for repeated patterns, outliers, trends, gaps

Pixel-Oriented Techniques • • Each dimension creates an image Each value controls color of Pixel-Oriented Techniques • • Each dimension creates an image Each value controls color of a pixel Many organizations of pixels possible (raster, spiral, circle segment, space-filling curves) Reordering data can reveal interesting features, relations between dimensions

Methods to Cope with Scale • Many modern datasets contain large number of records Methods to Cope with Scale • Many modern datasets contain large number of records (millions and billions) and/or dimensions (hundreds and thousands) • Several strategies to handle scale problems – Sampling – Filtering – Clustering/aggregation • Techniques can be automated or usercontrolled

Examples of Data Clustering Examples of Data Clustering

Example of Dimension Clustering Example of Dimension Clustering

Example of Data Sampling Example of Data Sampling

The Visual Data Analysis (VDA) Process • • • Overview Filter/cluster/sample Scan Select “interesting” The Visual Data Analysis (VDA) Process • • • Overview Filter/cluster/sample Scan Select “interesting” Details on demand Link between different views

Issues Regarding Users • What graphical attributes do we perceive accurately? • What graphical Issues Regarding Users • What graphical attributes do we perceive accurately? • What graphical attributes do we perceive quickly? • Which combinations of attributes are separable? • Coping with change blindness • How can visuals support the development of accurate mental models of the data? • Relative vs. absolute judgements – impact on tasks

Role of Perception MC Escher Role of Perception MC Escher

Consider the Following Consider the Following

Role of Perception • Users interact with visualizations based on what they see. (e. Role of Perception • Users interact with visualizations based on what they see. (e. g. black spots at intersection of white lines) • Must understand how humans perceive images. • Primitive image attributes: shape, color, texture, motion, etc.

Visualization Example Op Art - Victor Vasarely Op. Glyph (Marchese) Visualization Example Op Art - Victor Vasarely Op. Glyph (Marchese)

Gestalt Psychology Rules of Visual Perception Principles of Art & Design Proximity Similarity Continuity Gestalt Psychology Rules of Visual Perception Principles of Art & Design Proximity Similarity Continuity Closure Symmetry Foreground & Background Size Emphasis / Focal Point Balance Unity Contrast Symmetry / Asymmetry Movement / Rhythm Pattern / Repetition

Issues Regarding Interactions • Interaction critical component • Many categories of techniques – Navigation, Issues Regarding Interactions • Interaction critical component • Many categories of techniques – Navigation, selection, filtering, reconfiguring, encoding, connecting, and combinations of above • Many “spaces” in which interactions can be applied – Screen/pixels, data structures, graphical objects, graphical attributes, visualization structures