Marjorie Darrah

Using Genetic Algorithms for Tasking Teams of Raven UAVs

Control of multiple unmanned aerial vehicles is of importance given that so many have been deployed in the field. This work discusses how genetic algorithms (GA) have been applied to the cooperative tasking of the AeroVironment’s Raven unmanned aerial vehicle (UAV) engaged in an intelligence, reconnaissance, and surveillance (ISR) mission. Mission assumptions, development of the GA, the method used to test for convergence, and the outcome of preliminary testing are all discussed.

A method for measuring consensus within groups

This paper presents a new index of disagreement (or measure of consensus) for comparison of data collected using Likert items. This new index, which assesses the level of disagreement among group members, exploits the conditional distribution of the variance for a given mean. The variance is often used as a measure of disagreement, with high variance seen as a high disagreement in a group. However, since the range of the variance is a function of the mean, this implies that for a mean close to the end points of the scale, the range of the variance is relatively small and for a mean at the center of the scale the range of the variance is larger. The index of disagreement introduced in this paper takes into account both the mean and the variance and provides a way to compare two groups that is more meaningful than just considering the variance or other measures of disagreement or consensus that only depend on the variance.

Haptics-Based Apps for Middle School Students with Visual Impairments

Twenty haptics-based computer applications (apps) have been created to utilize a low-cost, force feedback haptic device, the Novint Falcon, to provide students with tactile and kinesthetic sensations while learning about math and science. These low-cost apps, developed specifically for students with visual impairments (yet practical for all students), add to the accessible resources available for math and science. This article outlines the motivation, development, and testing of these PC-based applications that incorporate computer haptics, auditory cues, and high-contrast visuals. Included is a brief overview of two of the apps, one with science content and one with math content, in order to provide the reader with some insight into the student experience. The results of testing six of the apps in classroom settings show that the device and software are feasible for teachers to implement and significant learning gains can be achieved for students who use them. Student attitudes toward the apps were positive, implying that not only are the apps useful in the classroom, but engaging as well.

Framework for K-12 education haptic applications

While haptic technology has been utilized for decades in various fields, it has yet to be fully utilized in K-12 education. The main barriers to its use have been the cost of the devices and the specialized programming skills required to quickly produce applications for the classroom. This paper discusses the development of a framework that can be used to reduce the time to develop haptic-based applications for the K-12 classroom. While the project discussed focuses on producing applications for students who are blind or visually impaired, the framework developed is general, but embeds aspects that make the applications accessible to the target audience. This framework assists in eliminating the barriers to using haptics in K-12 education by reducing the time and specialized knowledge needed to develop applications and by employing a low-cost force-feedback haptic device.

Optimized flight path for 3D mapping of an area with structures using a multirotor

This paper presents an optimized method to employ a multirotor for collecting images to generate a 3D map of an area of interest with attention to man-made structures in the area. A genetic algorithm is combined with space partitioning methods to find an optimized path to ensure complete coverage of a desired area with necessary overlap for generating a 3D map. This path provides for the collection of detailed information of man-made structures within the area and also consider areas of avoidance and adjust for problematic terrain (such as tall vegetation). The result is a flight path for a multirotor that includes waypoint, altitude, heading, and camera angle for all points along the flight path. This allows for the collection of all necessary images to produce a 3D map of the area with high resolution models of the buildings within the area.

A comprehensive program for expanding pathways to IT careers

The Expanding Pathways for Educational Development and Information Technology Experiences (ExPEDITE) Project is creating a smooth transition to an information technology (IT) career for students in West Virginia. This National Science Foundation funded project brought together a secondary school system, community and technical college, university and companies in the technology industry to create a model for addressing the growing need for IT professionals. The ExPEDITE project was designed to meet the growing workforce demand for IT professionals, and improve the technology education of students and the educators who prepare them. Based on comprehensive research and an evaluation of career skills and workforce needs, the project partners are enhancing current secondary and higher education IT related programs. They are developing and approving articulation agreements between secondary school, community college, and university. The project team has developed and implemented a comprehensive IT internship/mentoring program for students, secondary teachers and college professors. They have also developed and are using IT awareness materials to attract and retain students to IT career paths. The team has created an IT career continuing education course for online dissemination to secondary school counselors and teachers. The ExPEDITE project processes are reproducible and effectively provide pathways for secondary and post-secondary students to learn IT skills while exposing them to expanding IT career opportunities.

Fitness function changes to improve performance in a GA used for multi-UAV tasking

Various methods have been utilized for the cooperative tasking of unmanned aerial vehicles (UAVs), with the genetic algorithm (GA) being a technique that has proven to be versatile and effective for this use. The design and implementation of a GA is both an art and a science that brings together creativity, theoretical foundations and engineering. The focus of this paper is to show how the fitness function for a GA has been improved to meet variable mission constraints and also improve performance of the system designed to provide support for a ground station to fly cooperative missions with teams of small UAVs.

Analyses of Crime Patterns in NIBRS Data Based on a Novel Graph Theory Clustering Method: Virginia as a Case Study

This paper suggests a novel clustering method for analyzing the National Incident-Based Reporting System (NIBRS) data, which include the determination of correlation of different crime types, the development of a likelihood index for crimes to occur in a jurisdiction, and the clustering of jurisdictions based on crime type. The method was tested by using the 2005 assault data from 121 jurisdictions in Virginia as a test case. The analyses of these data show that some different crime types are correlated and some different crime parameters are correlated with different crime types. The analyses also show that certain jurisdictions within Virginia share certain crime patterns. This information assists with constructing a pattern for a specific crime type and can be used to determine whether a jurisdiction may be more likely to see this type of crime occur in their area.

Using a Computational Approach for Generalizing a Consensus Measure to Likert Scales of Any Size n

There are many consensus measures that can be computed using Likert data. Although these measures should work with any number n of choices on the Likert scale, the measurements have been most widely studied and demonstrated for n = 5. One measure of consensus introduced by Akiyama et al. for n = 5 and theoretically generalized to all n depends on both the mean and variance and gives results that can differentiate between some group consensus behavior patterns better than other measures that rely on either just the mean or just the variance separately. However, this measure is more complicated and not easy to apply and understand. This paper addresses these two common problems by introducing a new computational method to find the measure of consensus that works for any number of Likert item choices. The novelty of the approach is that it uses computational methods in -dimensional space. Numerical examples in three-dimensional (for n=6) and four-dimensional (for n=7) spaces are provided in this paper to assure the agreement of the computational and theoretical approach outputs.

Optimized 3D mapping of a large area with structures using multiple multirotors

This paper presents an optimized method to employ a team of multirotors for collecting images to generate a 3D map of an area with emphasis on special features (e.g. man-made structures) and areas of avoidance. When an area is too large to be mapped by one multirotor within its battery life, then either several flights or several multirotors need to be employed to complete the job. This paper introduces a method for equitably dividing the task of collecting images utilizing multiple vehicles to map a large area with man-made structures, which need to be mapped with high resolution. First, the number of vehicles or flights required must be determined and then the special features within the area that require more time must be considered. A parallel flood fill algorithm incorporating game theory is used to determine the best way to divide the tasking.