Industry and academia have repeatedly demonstrated the transformative potential of Augmented Reality (AR) guided assembly instructions. In the past, however, computational and hardware limitations often dictated that these systems were deployed on tablets or other cumbersome devices. Often, tablets impede worker progress by diverting a user's hands and attention, forcing them to alternate between the instructions and the assembly process. Head Mounted Displays (HMDs) overcome those diversions by allowing users to view the instructions in a hands-free manner while simultaneously performing an assembly operation. Thanks to rapid technological advances, wireless commodity AR HMDs are becoming commercially available. Specifically, the pioneering Microsoft HoloLens, provides an opportunity to explore a hands-free HMD's ability to deliver AR assembly instructions and what a user interface looks like for such an application. Such an exploration is necessary because it is not certain how previous research on user interfaces will transfer to the HoloLens or other new commodity HMDs. In addition, while new HMD technology is promising, its ability to deliver a robust AR assembly experience is still unknown. To assess the HoloLens' potential for delivering AR assembly instructions, the cross-platform Unity 3D game engine was used to build a proof of concept application. Features focused upon when building the prototype were: user interfaces, dynamic 3D assembly instructions, and spatially registered content placement. The research showed that while the HoloLens is a promising system, there are still areas that require improvement, such as tracking accuracy, before the device is ready for deployment in a factory assembly setting.

With the movement in education towards collaborative learning, it is becoming more important that learners be able to work together in groups and teams. Intelligent tutoring systems (ITSs) have been used successfully to teach individuals, but so far only a few ITSs have been used for the purpose of training teams. This is due to the difficulty of creating such systems. An ITS for teams must be able to assess complex interactions between team members (team skills) as well as the way they interact with the system itself (task skills). Assessing team skills can be difficult because they contain social components such as communication and coordination that are not readily quantifiable. This article addresses these difficulties by developing a framework to guide the authoring process for team tutors. The framework is demonstrated using a case study about a particular team tutor that was developed using a military surveillance scenario for teams of two. The Generalized Intelligent Framework for Tutoring (GIFT) software provided the team tutoring infrastructure for this task. A new software architecture required to support the team tutor is described. This theoretical framework and the lessons learned from its implementation offer conceptual scaffolding for future authors of ITSs.

Machine Learning (ML) is increasingly being used by companies like Google, Amazon and Apple to help identify market trends and predict customer behavior. Continuous improvement and maturing of these ML tools will help improve decision making across a number of industries. Unfortunately, before many ML strategies can be utilized the methods often require large amounts of data. For a number of realistic situations, however, only smaller subsets of data are available (i.e. hundreds to thousands of points). This work explores this problem by investigating the feasibility of using meta-models, specifically Kriging and Radial Basis Functions, to generate data for training a BN when only small amounts of original data are available. This paper details the meta-model creation process and the results of using Particle Swarm Optimization (PSO) for tuning parameters for four network structures trained using three relatively small data sets. Additionally, a series of experiments augment these small datasets by generating ten thousand, one-hundred thousand, and a million synthetic data points using the Kriging and RBF meta-models as well as intelligently establishing prior probabilities using PSO. Results show that augmenting limited existing datasets with meta-model generated data can dramatically affect network accuracy. Overall, the exploratory results presented in this paper demonstrate the feasibility of using meta-model generated data to increase the accuracy of small sample set trained BN. Further developing this method will help underserved areas with access to only small datasets make use of the powerful predictive analytics of ML.

College football recruiting is a competitive process. Athletic administrations attempt to gain an edge by bringing recruits to a home game, highlighting the atmosphere unique to campus. This is however not always possible since most recruiting efforts happen off-season. So, they relate the football game experience through video recordings and visits to football facilities. While these substitutes provide a general idea of a game, they cannot capture the feeling of playing while cheered on by a crowd of 55,000 people. To address this challenge and improve the recruitment process, the Iowa State University (ISU) athletic department and the Virtual Reality Applications Center (VRAC) teamed up to build an alternative to the game-day experience using the world's highest resolution six-sided virtual reality (VR) environment -the C6, and a portable low-cost headmounted display (HMD) system. This paper presents techniques used in the development of the immersive and portable VR environments followed by validation of the work through quantifying immersion and presence through a formal user study. Results from the user study indicate that both the HMD and C6 are an improvement over the standard practice of showing videos to convey the atmosphere of an ISU Cyclone football game. In addition, both the C6 and HMD were scored similar in immersion and presence categories. This indicates that the low-cost portable HMD version of the application produces minimal trade off in experience for a fraction of the cost. RightsCopyright 2015 SPIE-IS&T. One print of electronic copy may be made for personal use only. Systematic electronic or print reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. ABSTRACTCollege football recruiting is a competitive process. Athletic administrations attempt to gain an edge by bringing recruits to a home game, highlighting the atmosphere unique to campus. This is however not always possible since most recruiting efforts happen off-season. So, they relate the football game experience through video recordings and visits to football facilities. While these substitutes provide a general idea of a game, they cannot capture the feeling of playing while cheered on by a crowd of 55,000 people. To address this challenge and improve the recruitment process, the Iowa State University (ISU) athletic department and the Virtual Reality Applications Center (VRAC) teamed up to build an alternative to the game-day experience using the world's highest resolution six-sided virtual reality (VR) environmentthe C6, and a portable low-cost head-mounted display (HMD) system. This paper presents techniques used in the development of the immersive and portable VR environments followed by validation of the work through quantifying immersion and presence through a formal user study. Results from the user study indicate that both the HMD and C6 are an improvement over the standard practice of showing videos...