- Hits: 141
Multi-core Deployment Optimization Using Simulated Annealing and Ant Colony Optimization
|This work introduces a hybrid metaheuristic algorithm for solving the problem of multi-core deployment optimization (MCDO). It extends prior work using Ant Colony Optimization to solve MCDO by initially seeding the pheromone matrix with the output of a Simulated Annealing metaheuristic. This work also removes a number of critical simplifying assumptions from the MCDO model. Across 28,800 different algorithm inputs, the hybridized algorithm is shown to have a median improvement in makespan time of 7.2% versus the nonhybrid version, as well as a median reduction of 74% in execution time. On a dataset of 50 MCDO problems with known optimal solutions, the median hybrid algorithm solution is 16.5% worse than known optimal.||
- Hits: 766
Call For Papers: Proceedings of the IEEE, Special Issue on Applications of Augmented Reality Environments
A key challenge in cyber-physical computing is that users cannot see the cyber information needed to make decisions about physical world elements and processes directly in the physical context that they are relevant. For example, as a construction worker walks around a site, they cannot see the 3D building plan for the project directly overlaid on the walls in front of them to determine if elements are built as planned. Instead, the construction worker may use a tablet or laptop to call up the relevant parts of the plan and then mentally compare what he is looking at with the 3D model on the screen. Mistakes can be made because the construction worker cannot directly see what is supposed to be built on top of what is actually built in the physical world.
Mobile augmented reality and virtual reality are new approaches to visualizing cyber information that seeks to bridge this cyber-physical disconnect. With mobile augmented reality, a mobile device’s camera, such as an iPhone or Android phone camera, is used to capture imagery, which is fused with virtual information, such as highlighted regions of the image, and displayed one the device’s touchscreen. Users can see the virtual information directly rendered on top of the imagery captured by the camera. Virtual reality provides users with an immersive interaction experience with cyber-information.
Augmented reality and virtual reality are showing significant promise to overcome cyber-physical visualization challenges in numerous domains, such as medicine, construction, advertising, manufacturing, and gaming. Despite the promise of these techniques and their early application to many domains, there are still significant research challenges related to localization, sensor noise, indoor localization, social information sharing, information fusion, complex information visualization, and computational complexity. This special issue plans to explore both cutting edge research applications of augmented and virtual reality, as well as advances in the underlying computer vision, indoor/outdoor localization, and human computer interaction techniques that make it possible.
The articles in this special issue will explore the next generation of virtual and augmented reality within the context of its applications to high impact domains, such as manufacturing and medicine, and the research challenges of providing immersive experiences. The following topics are of particular interest:
• Multi-disciplinary applications of virtual and augmented reality
• Case studies on the use of augmented and virtual reality in critical applications
• Computer vision approaches to virtual and augmented reality
• Architectures and approaches for supporting augmented and virtual reality with cloud computing
• Sensor data analysis techniques for context detection and delivery of relevant cyber information for display in virtual and augmented reality applications
• Social network approaches for sharing augmented reality data and discovering relevant cyber information
• Comparative studies of virtual and augmented reality approaches
• Novel augmented reality approaches for providing other augmented sensor outputs, such as sound augmentation to alert blind people of nearby hazards
Prospective authors should prepare their papers in accordance with the guidelines of the Proceedings of the IEEE.
Submission of full papers: June 30, 2013
First decision notification: Aug 30, 2013
Submission revised papers: Sep 30, 2013
Final decision notification: Oct 31, 2013
Submission camera-ready papers: Nov 15, 2013
Dr. Jules White, Virginia Tech
Dr. Mani Golparvar-Fard, University of Illinois
Dr. Douglas C. Schmidt, Vanderbilt University
For full author guidelines: http://www.ieee.org/publications_standards/publications/authors/author_submission.html
To submit an article: http://mc.manuscriptcentral.com/pieee
- Hits: 457
Construction site activities require access to large amounts of cyber-information, such as Building Information Models (BIM) and project specifications. Field personnel carry around large stacks of project documents, or frequently travel to a trailer to lookup this information. Recently, several context-aware techniques have been proposed to deliver relevant information to on-site users by intelligent interpretation of their environment. These techniques primarily rely on GPS and/or wireless localization, which typically does not provide sufficient precision in congested construction sites. To address these limitations, this paper extends our work on Hybrid 4-Dimensional Augmented Reality (HD4AR), a high-precision mobile augmented reality system that allows field personnel to query and access semantically-rich 3D cyber-information and see it overlaid on top of real-world imagery. With our proposed method, field personnel can use mobile devices to take pictures of building elements and be presented, on-site, with a detailed list of related cyber-information in an augmented reality (AR) format. In contrast to previous techniques, our proposed vision-based method localizes the user purely based on image matching and provides more accurate positioning. With HD4AR, the image captured by the field personnel using a mobile device is sent to a server to conduct GPU-based feature extraction and matching against pre-collected images from the jobsite. The mobile device’s 3D position and orientation is then accurately derived by solving for the Direct Linear Transform followed by a Levenberg-Marquardt optimization against an underlying Structure-from-Motion 3D point cloud model. The paper further validates the HD4AR localization method for several practical metrics. Particularly it presents the accuracy of GPU-based localization and further reduction in 3D reconstruction and localization time from our previous CPU-based method. The perceived benefits and limitations of the HD4AR system for on-site context-aware applications are discussed in detail.
Bibliographic Info:Hyojoon Bae, Mani Golparvar-Fard, & Jules White, ENHANCED HD4AR (HYBRID 4-DIMENSIONAL AUGMENTED REALITY) FOR UBIQUITOUS CONTEXT-AWARE AEC/FM APPLICATIONS, CONVR2012.
- Hits: 1022
Title: Deployment Optimization for Embedded Flight Avionics Systems
Loosely-coupled publish/subscribe messaging systems facilitate optimized deployment of software applications to hardware processors. Intelligent algorithms can be used to refine system deployments to reduce system cost and resource requirements, such as memory and processor utilization. This article describes how we applied a computer assisted deployment optimization tool to reduce the required processors and network bandwidth consumption of a legacy flight avionics system.
Brian Dougherty, Jules White, Douglas C. Schmidt, Russell Kegley, Jonathan Preston, Deployment Optimization for Embedded Flight Avionics Systems, CrossTalk Journal, (to appear). This research has been funded in part by a grant from the Air Force Research Laboratories.
- Hits: 551
Title: Smartphone Computing in the Classroom
Smartphones, such as the iPhone and Google Android, have become extremely popular and constitute an ever-increasing share of computing platforms. For example, in the third quarter of 2010, 88.3 million PCs were sold worldwide. In that same quarter, 80 million smartphones were purchased. Roughly 20 million Android devices and 14.1 million iOS phones were sold. Moreover, whereas there was only a 7.6% growth in PC sales from the previous quarter, smartphones platform sales experienced approximately 30% growth.
The processing capabilities of these smartphone devices have generated significant interest in—and development of—third-party applications. Most notably, the Apple application store contains more than 100,000 applications and has had more than 1 billion downloads to iPhones. It reached the 500 million download mark in January 2009 and the billion download mark by April 2009. These devices possess impressive hardware capabilities, as well as powerful software distribution, upgrade, and maintenance platforms supported by these application stores. Already, many of these applications possess cyber- physical1 qualities and supporting cloud services.2 For example, Google’s Latitude service uses a client- side application to capture location information from GPS sensors and intelligently aggregates information through a centralized cloud service that provides features, such as alerting you when you are near other friends that use Latitude.
Given the increasing use of and excitement surrounding smartphone computing platforms, a key question is how they can be leveraged to enhance computing education. Here, we describe the ECE 4564 Network Application Design course at Virginia Tech, which we structured to use a combination of smartphone platforms, cloud computing, and open-ended assignments. We present the challenges that we faced when designing the course, our solutions to those challenges, and data measuring independent learn- ing outside of the classroom. Our experience teaching ECE 4564 and the results of our analyses of student learning show that smartphones have significant potential for improving self-directed student learning outside the classroom.
Jules White, Hamilton Turner,Smartphone Computing in the Classroom, IEEE Pervasive Computing, April-June, 2011