SPEAKERS: Edul N. Dalal, John C. Handley, Wencheng Wu, Jing Wang ABSTRACT: The experimental design of paired comparisons is often used in image quality evaluations. Psychometric scale values for quality judgments are modeled using Thurstone's Law of Comparative Judgment in which distance in a psychometric space of image quality is a function of the probability of preferring one over the other. Two treatments with probability ½ of preference have distance zero in psychometric space. The greater the probability of preferring one treatment over another, the greater the distance in a psychometric space. The transformation from psychometric space to probability is a cumulative probability distribution such as cumulative normal (Thurstone-Mosteller) or logistic (Bradley-Terry). The major drawback of a complete paired comparison experiment is that every treatment is compared to every other, thus the number of comparisons grows quadratically with the number of treatments. This is especially burdensome for hardcopy image quality work where prints need to be prepared and evaluated. We ameliorate this difficulty by performing paired comparisons in two stages. The first stage estimates precise anchors in the psychometric scale space by using many observations across the entire scale. Anchors are then chosen as treatments extremes of the scale plus those treatments with scale values at least one but no more than two JNDs (just noticeable differences) apart. This guarantees that other treatments are within one jnd of an anchor. We also choose the minimum number of anchors such that this condition holds. In the second stage of the design, we compare new treatments to the anchors in a forced choice experiment. The number of comparisons is now linearly rather than quadratically proportional to the number of treatments. It is known that paired comparisons with Thurstone-Mosteller and Bradley-Terry models correspond to probit and logistic regression, respectively, where the model matrix is a matrix of contrasts and the parameter vector is a vector of scales.  Both of these are special cases generalized linear models (GLM). In the anchored paired comparison model, we have a GLM where the regression equation has a constant offset vector determined by the anchors. The result of this formulation is a straightforward statistical model easily analyzed using any modern statistics package with GLM estimation. This enables model fitting and diagnostics. To test this approach, this psychophysical method was applied to two different types of quality evaluations of color pictorial hardcopy images: perceived color accuracy, and overall preference.  The results were found to be compatible with complete paired comparison experiments, but with significantly less effort for large sample sets.

In this talk I will present a robust association analysis-based method for this task. This proposed method is based on the concept of h-confidence, a measure that can be used to extract groups of objects having high similarity with each other. I will also discuss the anti-monotone and cross support properties of the h-confidence which enables it to discover patterns at a low level of support compared to the standard support-based pruning strategy. The results of experimental evaluation on several protein interaction data sets show that hyperclique-based transformations enhance the performance of standard function prediction algorithms significantly, and thus have merit.

In this project we analyzed the machine data including the service calls and the associated fault codes in the recent 24 hours before the calls for the Nuvera Machines. Different methodologies were utilized to examine the data and our current analyses do not show any significant signal for the current log fault data. I will highlight the data characteristics and the challenges in analyzing the data. This talk will also have a brief demo to visually illustrate the inseparability of the data. Further, I will discuss some of the classification and association mining techniques which we performed on the data and their results. The talk will conclude with future work and guidelines for examination of more available data.

Nuvera MSH (Machine Service Hours) Decision Support - Nuvera Machine Rules Generation

Topic:  Control System Architecture for Matching Color Gamuts of Multiple Digital Production Printers
Speakers:  Prudhvi Gurram
Abstract:  In this talk we review the work done this summer in applying State-Feedback Control loop architecture to match color gamuts of multiple machines using developed mass targets as actuators. We show the virtual printer infrastructure used to simulate the performance. Automatic tuning of parameters of the virtual printer model using spectral measurements, and the use of gain scheduling algorithms with Model Predictive Controller will be presented as additional topics.

Topic:  What I've done, My Market Perspective, and Finding Opportunities
Speakers:  Andy Maier
Abstract:  We will briefly discuss my transitions from psychologist to technologist to product manager. Significant highlights of my career will be discussed including performance testing, capacity planning, application architecture, project management, and gaining executive sponsorship for strategic initiatives. The presentation will focus on the entire lifecycle from opportunity identification, business and program planning, software development, and delivery of these two enterprise systems.
After working on Y2K remediation and integrated criminal justice systems projects, I joined Capital One where I cut my teeth on enterprise software projects including time & labor, ERP, portals, business intelligence, and security. The evolution of collaboration through email, portals, and more will be discussed from this perspective.
My transition into product management to learn the business side of technology will briefly be discussed. My work on improving the value and productivity of the knowledge worker through improved collaboration and social networking capabilities will be discussed. 
The state of the collaborative and social networking markets will be discussed. Xerox and XIG have wonderful opportunities to leverage their innovation, partnerships, and products to drive revenue in the collaboration and social networking space. Conceptual opportunities and approaches for product will be outlined.

The presenter will discuss the unique prototyping methodology he and his teams employ and his successes positioning this capability within his current organization.

Topic:  Image Noise in Dry-Powder Electrophotography
Speakers:  John G. Shaw, Dale Mashtare, Paul Morehouse, Michael Thompson and John Knapp