11115 research outputs found
Sort by
Envisioning AI-powered Learning Stemming from Piloted Personalized Education
No full textLearning systems can potentially transform education and training by allowing educators to encourage behavioural changes and internalization of concepts in learners. This paper introduces such an AI-powered model for a personalized learning system, building on our success of hand-curated learning paths to support individualized education. We utilize a network science approach as a construct to create an environment that is supportive of an individualized learning process, presenting an AI-powered framework. This framework is informed by student and faculty interactions with two custom created learning systems, experiences that shaped goals and expectations of the proposed AI-powered method since 2018. This paper contributes to advancing the conversation around AI-powered learning systems and personalizing educational experiences. Our AI-powered model engages learners in their educational journey through individualized and adaptive learning paths, while meeting each learners’ specific learning outcomes. We conclude with open research problems that surfaced from this vision
Scalar Potential Formulation in Spherical Coordinates
No full textA scalar potential formulation for an anisotropic gyrotropic medium containing sources is developed. The formulation results in two forced coupled scalar Helmholtz-like equations. The results simplify to well-known relations upon specialization to an isotropic medium. A radial magnetically-biased ferrite is proposed for possible application manifesting non-reciprocal behavior for controlling electromagnetic radiation and scattering
Nowcasting Solar EUV Irradiance With Photospheric Magnetic Fields and the Mg II Index
Get PDFA new method to nowcast spectral irradiance in extreme ultraviolet (EUV) and far ultraviolet (FUV) bands is presented here, utilizing only solar photospheric magnetograms and the Mg II index (i.e., the core-to-wing ratio). The EUV and FUV modeling outlined here is a direct extension of the SIFT (Solar Indices Forecasting Tool) model, based on Henney et al. (2015, https://doi.org/10.1002/2014sw001118). SIFT estimates solar activity indices using the earth-side solar photospheric magnetic field sums from global magnetic maps generated by the ADAPT (Air Force Data Assimilative Photospheric Flux Transport) model. Utilizing strong and weak magnetic field sums from ADAPT maps, Henney et al. (2015, https://doi.org/10.1002/2014sw001118) showed that EUV & FUV observations can also be well modeled using this technique. However, the original forecasting method required a recent observation of each SIFT model output to determine and apply a 0-day offset. The new method described here expands the SIFT and ADAPT modeling to nowcast the observed Mg II index with a Pearson correlation coefficient of 0.982. By correlating the Mg II model-observation difference with the model-observation difference in the EUV & FUV channels, Mg II can be used to apply the 0-day offset correction yielding improvements in modeling each of the 37 studied EUV & FUV bands. With daily global photospheric magnetic maps and Mg II index observations, this study provides an improved method of nowcasting EUV & FUV bands used to drive thermospheric and ionospheric modeling
Tension–Compression Fatigue of a Hybrid Polymer-Matrix/Ceramic-Matrix Composite at Elevated Temperature
Get PDFFully reversed tension–compression fatigue of a hybrid material comprising polymer matrix composite (PMC) co-cured with a ceramic matrix composite (CMC) was investigated. The PMC portion had a polyimide matrix reinforced with 15 plies of carbon fibers woven in an eight-harness satin weave (8HSW). The CMC portion had three plies of a quartz-fiber 8HSW fabric in a zirconia-based ceramic matrix. The hybrid PMC/CMC was developed for use in aerospace thermal protection systems (TPS). Hence, the experimental setup aimed to simulate the TPS service environment—the CMC side was kept at 329 °C, whereas the PMC side was open to laboratory air. Compression stress–strain response was studied, and compressive properties were measured at room and elevated temperature. Tension–compression fatigue tests were conducted at elevated temperature at 1.0 Hz. The evolution of tensile and compressive strains with fatigue cycles, as well as changes in the stress–strain hysteresis behavior and stiffness were examined. The tension–compression fatigue of a PMC with the same constituents and fiber architecture as the PMC portion of the PMC/CMC was studied for comparison. Tension–compression fatigue was found to be more damaging than tension–tension fatigue for both materials. The PMC outperformed the PMC/CMC in tension–compression fatigue. Post-test examination showed widespread delamination and striking non-uniform deformation modes of the PMC/CMC
Innovation Challenges in the Air Force SBIR Program: From the Small Businesses\u27 Perspective
Get PDFEvery year the United States invests $3.2 billion in the Small Business Innovation Research (SBIR) program to promote innovation among the nation’s small businesses. Half of this investment is from the DoD. This research considers the challenges faced by small businesses innovating with the DoD, particularly those awarded SBIR contracts with the United States Air Force. The authors surveyed 286 unique small businesses that were previously awarded an Air Force SBIR contract. By asking the survey respondents open-ended questions and categorizing their responses, they pinpoint unaddressed challenges from the small business perspective. By categorizing survey responses through Qualitative Content Analysis, they further identify five categories of challenges: Solver- Seeker Disconnect, Funding, Engagement, Processes, and Seeker Education. With this new insight, the authors seek to inform SBIR policies and improve the program’s effectiveness
Personalized Learning Path Problem Variations: Computational Complexity and AI Approaches
Get PDFE-learning courses often suffer from high dropout rates and low student satisfaction. One way to address this issue is to use personalized learning paths (PLPs), which are sequences of learning materials that meet the individual needs of students. However, creating PLPs is difficult and often involves combining knowledge graphs (KGs), student profiles, and learning materials. Researchers typically assume that the problem of creating PLPs belong to the nondeterministic polynomial (NP)-hard class of computational problems. However, previous research in this field has neither defined the different variations of the PLP problem nor formally established their computational complexity. Without clear definitions of the PLP variations, researchers risk making invalid comparisons and conclusions when they use different metaheuristics for different PLP problems. To unify this conversation, this article formally proves the NP-completeness of two common PLP variations and their generalizations and uses them to categorize recent research in the PLP field. It then presents an instance of the PLP problem using real-world data and shows how this instance can be cast into two different NP-complete variations. This article then presents three artificial intelligence (AI) strategies, solving one of the PLP variations with back-tracking and branch and bound heuristics and also converting the PLP variation instance to XCSP, an intermediate constraint satisfaction language to be resolved with a general constraint optimization solver. This article solves the other PLP variation instance using a greedy search heuristic. The article finishes by comparing the results of the two different PLP variations
Towards Systems that Dynamically Change and Evaluate Abstractions
No full textAbstraction levels can be explicitly studied, changed and analyzed with metrics on their impact for a given problem. Also different methods for analyzing abstraction levels and their metrics can lead to different conclusions. Hence researchers usually iteratively experiment with these different methods to find the right abstraction level and metric for specific problems. To illustrate these points, we first study the use of Quad-Trees to characterize swarms, and then compare different methods using the metrics efficacy and efficiency. The goal of this work is to create an architecture and processes that will enable a self-aware system to conduct these types of experiments, and use these methods and metrics for analyzing the appropriateness and the impact of abstraction levels in order to improve its own performance
The Impact of Film Cooling on the Heat Release within a Rotating Detonation Combustor
Get PDFRotating detonation combustors establish a detonation wave that continuously circulates inside a small annulus. The presence of the detonation wave and the downstream oblique shock within the small annulus coupled with high mass flow induces a high heat load to the combustor wall. Preliminary analysis shows that for higher thermal power, internal air cooling alone is not sufficient to remove the heat out of the walls to maintain them below the maximum temperature of the metal. A possible solution is to use film cooling to reduce the heat flux to the combustor walls. One issue, though, is that the introduction of film cooling provides additional air into the system that can influence the combustion process as well as providing a location for secondary combustion
Strategies to Alleviate Flickering: Bayesian and Smoothing Methods for Deep Learning Classification in Video
Get PDFExcerpt: Increasing reliance on autonomous systems requires confidence in the accuracies produced from computer vision classification algorithms. Computer vision (CV) for video classification provides phenomenal abilities, but it often suffers from “flickering” of results. Flickering occurs when the CV algorithm switches between declared classes over successive frames. Such behavior causes a loss of trust and confidence in their operations
Applying Machine‐Learning Methods to Laser Acceleration of Protons: Lessons Learned From Synthetic Data
Get PDFIn this study, we consider three different machine-learning methods—a three-hidden-layer neural network, support vector regression, and Gaussian process regression—and compare how well they can learn from a synthetic data set for proton acceleration in the Target Normal Sheath Acceleration regime. The synthetic data set was generated from a previously published theoretical model by Fuchs et al. 2005 that we modified. Once trained, these machine-learning methods can assist with efforts to maximize the peak proton energy, or with the more general problem of configuring the laser system to produce a proton energy spectrum with desired characteristics. In our study, we focus on both the accuracy of the machine-learning methods and the performance on one GPU including memory consumption. Although it is arguably the least sophisticated machine-learning model we considered, support vector regression performed very well in our tests