University of Memphis Digital Commons
Not a member yet
43176 research outputs found
Sort by
A low cost, semi-autonomous phenotyping cart for late growth stages of tall crops
No full textWith an increasing focus on precision agriculture to maximize crop yields and minimize ecological impacts, remote sensing for agriculture has required the deployment of more advanced sensors and processing algorithms. Traditionally, unmanned aerial systems (UAS\u27s) have been the primary choice for phenotyping crops, but these systems are limited in endurance, power, payload, and legality. Medium to large, unmanned ground vehicles (UGV\u27s), however, are not hampered by these limitations. Previous research in the application of phenotyping UGV\u27s for tall crops has been focused on either small systems or very large gantry systems. Described here is a medium sized, low-cost, adjustable UGV that provides a solution by demonstrating the capability to image tall crops into late growth states. It incorporates a sliding mechanism to allow for a greater range in height than previous phenotyping UGV\u27s with the same payload capacity.The UGV\u27s capabilities are analyzed theoretically and practically, including its structural rigidity, handling, and endurance. An overview of parts and assembly is presented to facilitate replication and proliferation of the vehicle. Additionally, the vehicle is primarily fabricated using off-the-shelf components. The few custom components are used based on common materials and simple geometries and can be replicated with standard metalworking equipment. To further reduce costs, a dual RTK-GNSS system is utilized to control the UGV in a semi-autonomous fashion. A Future goal is to use the gathered datasets to produce an algorithm for fully autonomous capabilities
Exploring The Effectiveness of Reading vs. Tutoring For Enhancing Code Comprehension For Novices
No full textThis paper presents a comparison of two instructional strategies meant to help learners better comprehend code and learn programming concepts: reading code examples annotated with expert explanation (worked-out examples) versus scaffolded self-explanation of code examples using an automated system (Intelligent Tutoring System). A randomized controlled trial study was conducted with 90 university students who were assigned to either the control group (reading worked-out examples, a passive strategy) or the experimental group where participants were asked to self-explain and received help, if needed, in the form of questions from the tutoring system(scaffolded self-explanation, an interactive strategy).We found that students with low prior knowledge in the experimental condition had significantly higher learning gains than students with high prior knowledge. However, in the control condition, this distinction in learning outcomes based on prior knowledge was not observed. We also analyzed the effect of self-efficacy on learning gains and the nature of self-explanation. Low self-efficacy students learn almost twice as much in the interactive condition versus the passive condition although the difference was not significant probably because of low sample size. We also found that high self-efficacy students tend to provide more relational explanations whereas low self-efficacy students provide more multi-structural or line-by-line explanations
Imaging Sensor Band Comparison for Situational Awareness in Wildfires
No full textIn recent decades, wildfires have become increasingly widespread and hazardous. Dryer, hotter weather combined with more frequent heat waves leave forest areas susceptible to sudden, intense, and fast-growing forest fires. To protect private property and mitigate the damage, Hot Shot fire fighters are deployed into these dangerous situations. Extensive satellite and aerial platforms possess optical techniques for monitoring wildfire risks and boundary tracking. sUAS (small unmanned aerial system) based EO/IR systems provide a solution for real-time, high resolution, targeted response to acquire information critical to the safety and efficacy of wildfire mitigation. Real-time imagery from a sUAS of the position of Hot Shots and the progression of the fire boundary would be easily obtained and offer a method of ensuring safe deployment. An ideal sensor system for situational awareness in this environment would be able to image the ambient terrain and firefighters with good contrast while also detecting fire signatures and imaging through the smoke. The longer wavelength infrared bands have demonstrated imaging through the smoke of forest fires. However, near the wildfire where the Hot Shots work, they also receive strong radiometric signal from the temperature of the smoke. The emitted signal of the smoke can obscure the line of sight similarly to the scattering effect of wildfire smoke in the visible spectrum. The reflective and emissive components of a wildfire scene are studied and compared in the visible (VIS, 0.4 – 0.7μm), shortwave infrared (SWIR, 1.0-1.7μm), extended SWIR (eSWIR, 2.0-2.5μm), and longwave infrared (LWIR, 8-14μm). Both a radiometric model and calibrated field measurements find a band that has the highest probability for a continuous line of sight for terrain, firefighters, and fire signatures in a wildfire scene
A Cybersecurity Summer Camp for High School Students Using Autonomous R/C Cars
No full textCybersecurity is critical for national infrastructure, governments at all levels, the military, industry, and individual privacy. Both the government and industrial sectors in the U.S. foresee a substantial need for a proficient cybersecurity workforce. To tackle this challenge, the National Security Agency (NSA) and the National Science Foundation (NSF) jointly sponsored the GenCyber program with the goal of sparking K-12 students\u27 interest in cybersecurity and enhancing their knowledge of cybersecurity practices and safe online behavior. In support of the GenCyber program, this paper presents the first-of-its-kind autonomous R/C car-based cybersecurity summer camp for high school students, featuring an inclusive curriculum that seamlessly integrates concepts of machine learning (ML)/artificial intelligence (AI) and cybersecurity through the lens of an important ML application-autonomous vehicles. Beginning with an introduction to basic cybersecurity topics and technical concepts, the curriculum enables students to explore ML through hands-on experiences such as collecting front-camera images and training an autonomous driving ML model. Additionally, a series of engaging cybersecurity projects are developed focusing on secure shell (SSH) password cracking, buffer overflow attacks, and man-in-the-middle attacks. These projects are designed to launch various cybersecurity attacks against the students\u27 self-built autonomous driving models, enhancing the teaching effectiveness and awareness of cybersecurity. Our pre- and post-camp surveys demonstrate that the camp significantly boosted students\u27 confidence in computing, cybersecurity, and ML/AI
Automated Assessment of Students’ Code Comprehension using LLMs
No full textAssessing students’ answers, particularly natural language answers, is a crucial challenge in the field of education. Advances in transformer-based models such as Large Language Models (LLMs), have led to significant progress in various natural language tasks. Nevertheless, amidst the growing trend of evaluating LLMs across diverse tasks, evaluating LLMs in the realm of automated answer assessment has not received much attention. To address this gap, we explore the potential of using LLMs for automated assessment of student’s short and open-ended answers in program comprehension tasks. Particularly, we use LLMs to compare students’ explanations with expert explanations in the context of line-by-line explanations of computer programs. For comparison purposes, we assess both decoder-only Large Language Models (LLMs) and encoder-based Semantic Textual Similarity (STS) models in the context of assessing the correctness of students’ explanation of computer code. Our findings indicate that decoder-only LLMs, when prompted in few-shot and chain-of-thought setting perform comparable to fine-tuned encoder-based models in evaluating students’ short answers in the programming domain
Enhancing active learning through collaboration between human teachers and generative AI
No full textTo address the increasing demand for AI literacy, we introduced a novel active learning approach that leverages both teaching assistants (TAs) and generative AI to provide feedback during in-class exercises. This method was evaluated through two studies in separate Computer Science courses, focusing on the roles and impacts of TAs in this learning environment, as well as their collaboration with ChatGPT in enhancing student feedback. The studies revealed that TAs were effective in accurately determining students’ progress and struggles, particularly in areas such as “backtracking”, where students faced significant challenges. This intervention\u27s success was evident from high student engagement and satisfaction levels, as reported in an end-of-semester survey. Further findings highlighted that while TAs provided detailed technical assessments and identified conceptual gaps effectively, ChatGPT excelled in presenting clarifying examples and offering motivational support. Despite some TAs’ resistance to fully embracing the feedback guidelines-specifically their reluctance to provide encouragement-the collaborative feedback process between TAs and ChatGPT improved the quality of feedback in several aspects, including technical accuracy and clarity in explaining conceptual issues. These results suggest that integrating human and artificial intelligence in educational settings can significantly enhance traditional teaching methods, creating a more dynamic and responsive learning environment. Future research will aim to improve both the quality and efficiency of feedback, capitalizing on unique strengths of both human and AI to further advance educational practices in the field of computing
Sleep Disruption Moderates the Daily Dynamics of Affect and Pain in Sickle Cell Disease
No full textPersons with sickle cell disease (SCD) often experience pain that can interfere with quality of life and daily activities. Pain can modulated by affect and sleep continuity; however, few studies have explored how these factors complementarily influence pain in adults with SCD. The study aims were to investigate 1) whether pain levels were heightened on days characterized by low positive affect and high negative affect, and 2) whether the relationship between affect and pain was intensified following nights of disrupted sleep. Adults with SCD (N = 25) completed ecological momentary assessments and daily sleep diaries. Mixed models were used to analyze the main and interactive effects of daily affect (positive affect and negative affect) and sleep disruption (wake after sleep onset and frequency of awakenings) on both daily average pain and daily maximum pain. Results suggested that daily average pain and maximum pain tended to be higher on days of low positive affect and high negative affect. Furthermore, the frequency of nocturnal awakenings moderated the relationship between positive affect and pain. On days where there were higher frequencies of nocturnal awakenings, low positive affect was associated with both average and maximum pain; however, this association was not observed with lower frequencies of nocturnal awakenings. The association between negative affect and maximum pain was also stronger at higher levels of awakenings. Results highlight the relevance of adjunctive interventions that target affect among populations with SCD and further suggest that sleep continuity may further facilitate these interventions, highlighting the importance of multimodal treatments. Perspective: This study examined the effects of affect and sleep on pain among adults with sickle cell disease (SCD). Higher pain occurred on days of low positive affect and high negative affect, particularly following nights of more frequent awakenings. These findings emphasize the importance of addressing affect and sleep in SCD treatment
Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation
No full textWearable sensors enable health researchers to continuously collect data pertaining to the physiological state of individuals in real-world settings. However, such data can be subject to extensive missingness due to a complex combination of factors. In this work, we study the problem of imputation of missing step count data, one of the most ubiquitous forms of wearable sensor data. We construct a novel and large scale data set consisting of a training set with over 3 million hourly step count observations and a test set with over 2.5 million hourly step count observations. We propose a domain knowledge-informed sparse self-attention model for this task that captures the temporal multi-scale nature of step-count data. We assess the performance of the model relative to baselines and conduct ablation studies to verify our specific model designs
Vehicle Detection using Drone-Mounted Optically Pumped Magnetometers
No full textMagnetic sensing has applications in diverse technological domains including geology and geophysics, structural inspection, geospatial navigation, and vehicle detection and avoidance. At-range detection of large assets such as vehicles, specifically, can be executed using UAV-deployed magnetometers to safely determine the presence or identity of vehicles even if they are visually obscured. However, several challenges must be overcome and, in particular, the electromagnetic noise generated by the aircraft motors and other onboard electronics sets the signal-to-noise ratio and thereby limits the effective range of such an application. Here, we present UAV integration with a compact optically pumped magnetometer (QuSpin QTFM) and characterize its performance in vehicle sensing from the drone platform. We first characterize magnetic noise produced by the drone rotors to understand the detection limits it imposes on SNR. We then demonstrate vehicle detection at standoff distances of 5 and 10m. We utilize a volumetric magnetic field background subtraction method in order to enhance vehicle detection, and we characterize the impact of UAV velocity on field detection
Use of Force in Tennessee 2023
No full texthttps://digitalcommons.memphis.edu/govpubs-tn-bureau-investigation-use-of-force/1001/thumbnail.jp