Aabel™ NG Development Timeline: What's New?

Aabel NG Logo

January 2016: Release of Aabel™ NG2, v5 x64

June 2014: Release of Aabel™ NG1, v4 x64

Aabel™ NG2, v5 x64: Additions & Enhancements

A Unique Solver for Kernel Density Estimate With AMISE Optimal Bandwidth Analyzer
  • Efficient use of Kernel density estimate, which is widely used in data mining and pattern recognition, depends on computation of the optimal bandwidth of the kernel. While AMISE (Asymptotic Mean Integrated Squared Error) optimal bandwidth can provide the best estimation, it involves extensive and time-consuming computation.
  • Gigawiz has developed a unique hybrid solver for processing the data and estimating the corresponding AMISE optimal bandwidth by:
    • Computing the univariate density derivatives for each data point implementing the recommended methodology published by Raykar and Duraiswami (2005), followed by using the Sheather and Jones method (1991) for the actual bandwidth estimation.
    • The Gigawiz hybrid solver has been stress tested using 10000 data sets, including both real world and simulated data.
Gaussian Kernel Density Trace Charts

Gaussian kernel density trace charts including:

  • A graph type whose plotting involves processing the data and computing the AMISE optimal bandwidth (using the Gigawiz hybrid solver) while generating the resulting chart on the fly
  • A graph type with the rule of thumb bandwidth selectors (i.e., Silverman's approach and percentage of sample range), for exploratory visualization of the effect of bandwidth on kernel density estimation
  • Z-Score kernel density trace

(a) Kernel Density Trace With AMISE Optimal Bandwidth

Kernel Density Trace With AMISE Optimal Bandwidth

(b) Estimated AMISE Optimal Bandwidth for the Same Data in Stats Analyzer

AMISE Optimal Kernel Bandwidth Estimate

LOWESS (Robust Locally Weighted Regression) With Weighted Confidence Interval (CI)
  • LOWESS is an outlier resistant, robust locally weighted regression and scatter smoothing, in which the fitted value of xk is the value of a polynomial fit to the data using weighted least squares, where the weight for (xi, yi) is large if xi is close to xk and small if xi is far from xk.
  • The features and graph types include:
    • Exploratory LOWESS Charts
    • LOWESS Residual Dependence Graph
    • Adding Weighted Confidence Interval (CI) to LOWESS Curves
    • Using the LOWESS of Residuals as a Diagnostic Tool*
    • * The residual plot can provide information for choosing a reasonable value for the local smoothing width).

An Example of Standard Linear Regression and the Corresponding 95% CI Band

Standard Linear Regression

Robust LOWESS Fit to the Same Data and the Corresponding Weighted 95% CI

Robust LOWESS Fit

Weighted Mean
Violin Charts

    A violin chart comprises a combination of box plot and density trace; violin chart types include:

  • One-way violin
  • Two-way violin
  • Three-way violin
  • Bandwidth Selector Options:

  • For interactive, exploratory visualization, you can choose one of the following options:
    • Silverman's approach using alpha
    • Silverman's approach using IQR
    • Percentage of sample range (for this option, you can obtain the AMISE optimal bandwidth estimate (as well as the corresponding scaling factor) in the Stats Analyzer and use the output for providing the user-defined scaling factor)

Violin Chart Graphical Information

A Two-Way Violin Chart

XY and Multi-profile Scatter-Line Combination Charts

XY Scatter-line combination charts*:

  • With data objects connected along the sorted values of Y-axis
  • With data objects connected along the sorted values of X-axis

* Why Combining XY Scatter and Line Chart Properties?

    • In an XY scatter chart, the data points represent groups of data objects that are plotted in the pipeline order (i.e., the order they are stored in the worksheet)
    • In a line chart, the data points represent variables plotted along the sorted values of the Y- or X-axis.
    • Combination graph types enable plotting a line chart in which the data points represent groups of data objects.

Multi-profile scatter-line Combination Charts:

  • Trends of multiple X-variables plotted across the sorted values of a common Y-axis
  • Trends of multiple Y-variables plotted across the sorted values of a common X-axis
Group-based n-Dimensional REE/Multi-Elements Diagrams
  • The newly added diagrams to specialized module of geochemical data provide flexibility for exploratory visualization of n-dimensional spidergrams generated from large data sets.
  • Group-based n-dimensional REE or multi-elements diagrams include:
    • Group-based spidergrams differentiated by data object markers and/or line attributes taken from the object marker color properties
    • Group-based spidergrams differentiated by color bands
Example of Multi-Elements, Primitive Mantle-Normalized)
Open-GL Based 3D Grid Data Processor Utility
  • This Open-GL utility is designed for:
    • Subtracting a grid Z-values from another (e.g., generating a grid for an isopach map)
    • Subtracting a grid Z-values from a user-defined XY plane
    • Subtracting a user-defined XY plane from a grid Z-values
    • Multiplying a grid Z-values by a constant, e.g., converting the Z-values from feet to meter
    • Re-sampling the displayed grid by user-defined number of grid cells along the X and Y coordinates (e.g., for increasing resolution of a grid for volume or area calculations)

Generating a Grid for an Isopach Map

Generating a Grid for an Isopach Map)

Subtracting a Grid Z-Values From an XY Plane

Subtracting a Grid Z-Values From an XY Plane)

Open-GL Based 3D Grid Volume & Area Calculator Utility
  • This utility is designed for calculating a number of parameters from a matrix by applying the calculations to:

    • A user-defined polygon path comprising straight segments
    • The total data coverage
Enhancement of Utility Windows
  • The utility windows were re-designed to be modeless for not blocking any other activities of the application.
Optimization of Functions Interacting With Mac OS X Subsystems
  • The main enhancements include:
    • Making the application more resilient to design errors of the Apple HFS+ file system
    • Workaround for enhancing the graphic performance that is affected by low-performing parts of the Quartz Graphic System

Transformation Leap From the Legacy v3 Product to Aabel™ NG

NG1, v4 x64: The Result of a 5-Year Special Project (2009 to June 2014)

In 2009, Gigawiz committed to a 5-year special project and massive development effort, rewriting millions lines of code to transform Aabel™, the Gigawiz flagship product, into an icon of power and simplicity for professional users via:

  • Modernization and optimization of the main processing code
  • Complete Carbon (32-bit)-to-Cocoa (64-bit) transformation
  • The state of the art in new design and modeless simplicity (see Design of the New Interface)
  • Unmatched integration of statistics and multivariate data analysis, exploratory analytics, charting and thematic mapping, data processing utilities, practical use and graphic quality
  • Minimizing overhead between the user interface and the main processing code (a crucial step for sustainability and future development)
  • Replacement of high-level Cocoa classes with Aabel NG-specific code, a key alteration for any part of the application that requires high performance with large data sets
  • Addition of numerous new features
Design of the New Interface
  • Over 90% of all panels and windows of Aabel NG are designed to be modeless, giving instantaneous feedback while not blocking any other activities of the application.
  • Viewer document is designed with continuous pages, which makes it possible to generate any number of statistical output, view them by scrolling throughout the pages, use them for live presentation purposes, or export them using different options (including exporting all viewer pages as a single PDF document)
  • User-controlled managing of data flow through Statistics and Visualization Pipelines adds power and simplicity to data analysis.
  • The Stats Analyzer panel has been redesigned using a modern, intuitive interface:
    • See the ease of use of Stats Analyzer interface in the video "Statistical Analysis" below.
  • All chart types and their interface controls are now present in a single modeless panel (Chart Designer):
    • See the ease of use of the Chart Designer interface in the video "Interactive Graphing" below.
  • The new design of the viewer interface combined with the application pipeline architecture and related exploratory tools provides a new standard of data analysis design:
    • See an example in the video "Exploratory Analytics" below.
Statistical Analysis

Interactive Graphing

Exploratory Analytics

Added Features (Statistics, Multivariate Analysis, Graph Types, Etc.)
Added Statistics and Multivariate Analysis Methods:
  • Added: GLM-based n-way between-subjects analysis of variance (ANOVA)
  • Added: Test of simple main effects for analyzing n-way interactions in between-subjects analysis of variance
  • Added: GLM-based n-way within-subjects (repeated measures) analysis of variance
  • Added: GLM-based n-way mixed between-within subjects analysis of variance (ANOVA)
  • Added: GLM-based n-way between-subjects analysis of covariance (ANCOVA)
  • Additions to pairwise multiple comparisons:
    • Dunn-Sidak Test
    • Dunnett' C Test
    • Games Howell Test
  • Added: D'Agostino-Pearson test
  • Added: Levene test
  • Added: Brown-Forsythe test
  • Added: Cochran's C test
  • Added: Canonical correlation analysis module, providing:
    • Canonical correlation results
    • Canonical coefficients (weights)
    • Canonical scores
    • Eigenvalues
    • Structure coefficients
    • Redundancy analysis
    • D'Agostino-Pearson test on observed variables and canonical scores
  • Added: Hierarchical cluster analysis module, including:
    • Single Linkage (Nearest neighbor)
    • Complete Linkage (Furthest Neighbor)
    • McQuitty's Method (WPGMA)
    • UPGMA: Average Linkage Between Groups (Unweighted)
    • Gower's Method (Median)
    • Ward's method
    • Centroid Method
  • Additions to Principal component analysis:
    • Added: Bartlett's test of sphericity
    • Added: Partial coefficient matrix
    • Added: Kaiser-Meyer-Olkin (KMO) measure of sampling adequacy
  • Additions to factor analysis:
    • Added: Bartlett's test of sphericity
    • Added: Partial coefficient matrix
    • Added: Kaiser-Meyer-Olkin (KMO) measure of sampling adequacy
  • Added: Multiple regression with categorical predictors
  • Added: Nelson-Aalen survival analysis
  • Added: Cox proportional hazard regression
  • Added: Kaplan-Meier and Nelson-Aalen charts, with option of plotting the survival curves With 95% pointwise confidence intervals
  • Added: Cumulative hazard rate chart
  • Added: Hazard ratio chart
  • Added: Cox regression chart
  • Added: Bray-Curtis Dissimilarity
  • Added: Zero-Adjusted Bray-Curtis Dissimilarity
  • Added: n-Way descriptive statistics (generating tables from 2D slices)
  • Added: One-Way binning analysis of continuous data
  • Added: Two-Way binning analysis of continuous data
  • Added: Correlation matrix with pairwise significance test
Added Statistical and Multivariate Charts:
  • Added: Exploratory parallel coordinates
  • Added: Binned density-based parallel coordinates
  • Added: Sigma- or CI-based parallel coordinates
  • Added: Factorial parallel coordinates
  • Added: Exploratory Heatmaps with:
    • Hierarchical clustering methods
    • Principal component analysis (PCA)
  • Added: Exploratory outlier analysis chart
  • Added: Factor scree chart
  • Added: Factor cumulative (%) variance chart
  • Added: 2D histogram of continuous data
  • Added: Multi-profile histograms
  • Added: The ability to display the relative proportion of groups of data objects on univariate and multi-profile histograms
  • Added: Quantile-quantile (Q-Q) Chart
  • Added: Parallel-axes dot plot of unpaired samples
  • Added: Three-way box & whisker
  • Added: Three-way box-percentile
Added Thematic map diagrams:
  • Added: Thematic symbol chart
  • Added: Thematic contour of matrix data
  • Added: Thematic heatmap
Added Windrose Module:
  • Added: Wind Rose Using Raw Wind Data (projecting a large quantity of data in a simple graphical plot that summarize the occurrence of winds, showing their speed, direction and frequency in a polar coordinate grid)
Added Other Chart Types:
  • Added: Ternary Bubble Chart
  • Added: Contour of matrix data using binned scale
  • Added: 3D mesh (wire frame) requiring matrix data
  • Added: Group-based voronoi
  • Added: Group-based bubble chart
  • Added: Supporting regression in bubble Chart
  • Added: Stacked (univariate) bubble chart
  • Added: XY scatter stacked bubble chart
  • Added: Candlestick and bar stock charts with the option of displaying Bollinger band
Added or Enhanced Graphing Features:
  • Added: important user-controlled functions to Visualization & Statistics Pipelines from within the graphic viewer, via a modeless panel that allows:
    • Creating new data pipelines in an existing viewer document, so that you can perform the same or different analysis with different data sets and switch between them with a few clicks
    • Viewing how many data pipelines are linked to a viewer document
    • Viewing which pipeline is the viewer active pipeline
    • Making an inactive data pipeline active
    • Deleting unwanted inactive data pipelines
    • Viewing the list of worksheet members of each pipeline
  • Added: Supporting both RGB and CMYK color models
  • Added: Duplication of a chart pane with all its customized features
  • Added: EPS graphic export
  • Enhanced: Export of bitmap formats with a resolution up to 1200 dpi
  • Added: Exporting the content of multiple viewer pages as a single document
  • Enhanced: Replacement and redesign of all axis and legend customizing dialogs by modeless panels
  • Added: Label Stylizer modeless panel
  • Enhanced: Redesign of user-defined, non-linear curve fit panel interface
  • Enhanced: Ability to modify the secondary attributes of marker symbol outlines on a viewer-specific basis.
  • Added: Table Stylizer modeless panel for customizing tables.
  • Added: System Text Editor for creating/editing multiple-lines text, which provides Rich Text and Unicode support and has ability to format paragraphs
  • Added: Pen tool for drawing paths composed of curved or straight segments plus other drawing functions
  • Added: Appearance Panel for adding background fill (solid color, gradient, or vector patterns) to selected objects plus other customizing functions
  • Added: Ability to create and use gradient in the viewer color themes
  • Added: A viewer-specific Comment panel (saved with each viewer file)
  • Added: Graphic Organizer panel that has several essential functions (for example, for each table generated from a statistical method, it keeps a record of the method and the settings one have used for performing the analysis)
Added Features for Data Import and Use of Worksheet:
  • Added: Import of SPSS.sav files
  • Added: Change of data importer to a document, making it possible importing new data files using the settings last saved for a given importer
  • Enhanced: Separating categorical variable types to nominal and string variables
  • Enhanced: Simplification of map projection utility
  • Enhanced: Ability to view distribution and properties of all variables of a worksheet within a single dialog (by moving through the list of variables)
  • Added: Ability to view the X-zoom state of different data objects in the source worksheet
Added Data Processing Utilities:
  • Added: Profile extractor utility allowing to extract a profile from a matrix and generate a worksheet from the length and Z values of the defined profile
  • Added: Polygon data merger/data optimizer utility, with the following functions:
    • Merging polygons into a single polygon, allowing to generate spatial mask data (required for plotting thematic contours or thematic heatmaps)
    • Optimizing polygon data for reducing the file size of worksheets storing the polygon coordinate data, while keeping the data-point resolution above what is required for thematic mapping, data analysis, and visualization purposes
  • Added: Trans-worksheet calculator utility (allowing to compute formulas across multiple Aabel worksheets that are members of a Data Processing Pipeline)
  • Added: k-nearest neighbor and natural neighbor gridder utility with a dynamic interface (for creating a continuous surface from an unevenly spaced XYZ data set)
    • This utility provides the ability for algorithm mixing using the k-Nearest Neighbor (kNN) or Natural Neighbor end members (e.g., 100% kNN or 100% Delaunay, or any combination of the two)
    • It stores the gridding results in a new worksheet
  • Added: Polynomial trend surface gridder utility (allowing to derive a continuous smooth surface from irregular data or isolate regional trends from local variations)
  • Gridding Irregularly Spaced XYZ Data to a Regularly Spaced Matrix

Extracting a Profile From Matrix Data

Utility for Generating Spatial Mask Data

Utility for Generating Spatial Mask Data

  • Added: Multi-worksheets sequential data merger utility (merging data from multiple worksheets into a single worksheet)
  • Sequential Data Mergering

  • Added: Matrix cell-wise normalizer utility, allowing to:
    • Transform cell values of a matrix to Z-scores
    • Normalize the cell values relative to user-defined min. and max.values
  • Added: Matrix-to-matrix cell-wise operator utility (this must not be confused with matrix arithmetic)
  • Matrix cell-Wise Operations

  • Added: Variable-based data transformer utility, generating a new worksheet with transformed version of data for selected variables:
    • Having twelve transformation options
    • Honoring X-zoomed state of worksheet rows (i.e., the data outside the X-zoomed area are excluded from the transformation)