47325 research outputs found
Sort by
Automated short-answer grading and misconception detection using large language models
Get PDFAs education technology continues to evolve, the domains of Automatic Short-Answer Grading (ASAG) and Automated Misconception Detection (AMD) stand at the forefront of innovative approaches to educational assessment. We explore the transformative potential of Large Language Models (LLMs) in revolutionizing these critical areas. Leveraging the remarkable capabilities of LLMs in semantic inference, contextual understanding, and transfer learning, we embark on a comprehensive journey to enhance both ASAG and AMD. On ASAG, we illuminate the efficacy of transfer learning by fine-tuning RoBERTa Large, a state-of-the-art LLM, on task-related corpora, e.g. the Multi-Genre Natural Language Inference (MNLI) corpus. The model\u27s adaptability across unseen questions and domains on the minority class, coupled with its narrowed performance gap from unseen answers, highlights the profound impact of transfer learning on grading diverse student responses. In the emerging realm of AMD, we pioneer a dataset and methodology that inaugurates a new era in misconception detection. Framing the task as Recognizing Textual Entailment (RTE), our approach with RoBERTa Large MNLI captures nuanced misconceptions, unveiling the untapped potential of LLMs in unraveling the intricate landscape of automated misconception detection. The synergy between these endeavors presents a holistic view of the transformative role anticipated for LLMs in automated educational assessment. Our research, spanning adaptability in short-answer grading and groundbreaking advancements in misconception detection, establishes a foundation for a future where LLMs excel not only in understanding nuanced student responses but also in pinpointing and rectifying misconceptions with unparalleled precision. These insights contribute significantly to the dynamic field of educational technology, heralding a new era wherein the full potential of LLMs is utilized to shape the trajectory of educational assessment
Menstrual cycle prediction from physiological data using machine learning
No full textThis thesis aims to enhance understanding of women’s reproductive function by employing several machine learning algorithms to predict menstrual cycle phases based on physiological signals. Traditional self-reporting methods have proven error-prone, necessitating a data-driven alternative. Unlike existing approaches, this study utilizes a comprehensive set of multimodal features, including wrist skin temperature, electrodermal activity (EDA), interbeat interval (IBI), and heart rate variations recorded using a wristband. The inclusion of these features enables the prediction of next-day physiological data and menstrual cycle phases for both regular and irregular cycles. For next-day physiological data prediction, Autoregressive Integrated Moving Average (ARIMA) and Random Forest algorithms were applied to predict mean temperature, heart rate (HR), IBI, and EDA tonic values of all 15 subjects(43 cycles). ARIMA demonstrated strong performance in predicting temperature, HR, IBI, and EDA tonic, with RMSE values of 0.136 ± 0.098 (C°), 1.254 ± 0.412 (bpm), 0.015 ± 0.007 (s), and 0.171 ± 0.161 (µS), respectively. Simultaneously, Random Forest predicted the same signals with RMSE values of 0.133 ± 0.055 (C°), 1.348 ± 0.330 (bpm), 0.019 ± 0.007 (s), and 0.425 ± 0.215 (µS). The comparative analysis highlighted their complementary strengths, offering a robust framework for precise next-day predictions in daily subject cycles. Menstrual cycle phase prediction involved 33 cycles recorded from 11 ovulating subjects. Random Forest consistently achieved a robust accuracy of 91% when predicting three phases (P, O, L) using aggregated data from earlier cycles and testing on the last. Logistic Regression demonstrated commendable accuracy at 88%. Long Short-Term Memory (LSTM) models showed promise, achieving a superior accuracy of 91% with a comprehensive training set. These findings highlight the potential of both traditional machine learning and deep learning in menstrual cycle phase prediction
Exploring of user experience and evaluating mobility benefits of micromobility systems and golf carts: Case study of Florida
No full textMicromobility devices and golf carts (GCs)/Low speed vehicles(LSVs) are urban transportation solutions that provide short-distance travel options, including first- and last-mile trips. They mostly operate at speeds of 15 mi/h to 35 mi/h. The micromobility devices include e-scooters and e-bikes. The micromobility devices and golfcarts are increasing rapidly in the transportation system, and thus, it is necessary to explore their various factors. The objective of this study is to explore the user experience and evaluate the mobility benefits of the micromobility systems in Florida.
A survey was conducted in various cities with a substantial user base of micromobility devices. Various descriptive and inferential analyses were done to show user behavior trends and patterns and analyze the factors influencing user adoption and satisfaction. The survey was focused on golf carts, e-scooters, and e-bike users. The study found that most golf carts (GC) are privately owned, and they are used daily for various purposes, such as everyday commuting, everyday errands, and transporting children to school. The golf carts are mainly driven on the right-hand side of the road or in a shared road lane, depending on the infrastructure present. Golf carts have numerous benefits, such as being easy to operate and drive, with good acceleration and handling, and ease of access.
Regarding e-scooters and e-bikes, the results indicate that most users get their vehicles by using sharing apps, and they are also mostly used for everyday commuting and entertainment purposes. The e-scooters and e-bikes are mostly driven on bike lanes and sidewalks, reducing the possibility of crashes with other modes of transport. Both e-scooters and e-bikes have numerous advantages, such as being easy to ride, good for the environment, cheaper transportation, and ease of access. A chi-square test was conducted, and the results show that user characteristics have an impact on the purpose of using micromobility devices. Furthermore, a Decision Tree ensemble model shows that everyday errands, daily use, and ownership are the most important variables affecting the choice of using LSV/GC, and gender is the least important factor affecting the choice of using LSV/GC.
To evaluate the mobility benefits of micromobility devices, a VISSIM microscopic simulation and travel time reliability study were done in separate areas. For the VISSIM microscopic simulation, a VISSIM model was created where golfcart and other private vehicles were compared in terms of relative delay, travel times, and queue delay. The study was done in the Nocatee Community, a GC community in Jacksonville, Florida. The simulation results show that as the GC composition increases, the travel time, relative delay, and queue delay for private vehicles decrease. The findings of this study shed light on the potential benefits of incorporating GCs into transportation systems, particularly in school zones.
Travel time reliability study was conducted in Gainesville, where a travel time comparison of three modes of transport (Buses, Private cars, and e-scooters) was done. The analysis used a buffer index(BI) factor for evaluation. The BI represents the extra time that a traveler should allocate to their journey to ensure a 95% probability of arriving on time. The results show that Micromobility is the most reliable mode of transportation, boasting a BI of 12.0%, which means that choosing micromobility guarantees more consistent travel times when navigating the selected route. Furthermore, an ANOVA test was done, and its results confirm that there is a significant statistical difference between the mean travel times for the modes of transportation. The findings from the study indicate that opting for micromobility services as the mode of transportation within the campus offers a more reliable and consistent travel experience compared to private cars and transit, as it may lead to travel time savings and thus minimizing delay. The findings from this study will be useful for transportation agencies, manufacturers, and service providers to improve their services
List, Handwritten Note
Get PDFNote: Handwritten list of names and monetary amounts. Includes a list of expenses. Written on the back of Holmes-Walker letterhead. Circa 1932-1933. No date given
Note to Mr. Jacob Goodman
Get PDFCorrespondence: To Jacob Goodman. Mr. Jacob Goodman. Dear sir- I hope I am not [annoying] you by asking you. Will you please send me a check for March Rent. I [know] it was an over [sight] is why you haven\u27t send it. Thanking you in advance. I bef to remain very truly [illegible
Rosie Holmes Walker- Mr. Jacob Goodman, No Date Given
Get PDFCorrespondence and Deed: Partial letter to Jacob Goodman regarding the management of properties owned by Rosa G. Holmes Walker in New York City, New York. Includes deed to property 254 131st Street, New York, New York. J. Goodman - 67 W. 125 St. handwritten on the front. Stamped on top of deed: November 23, 1925. Circa 192
Longitudinal analysis of cigar use patterns among US youth and adults, 2013-2019
No full textBACKGROUND: Cigars are available in a range of pack quantities, which contrasts regulations requiring cigarettes to be sold in packs of 20 or greater. Smaller packages may be associated with increases in initiation while larger packs may lead consumers to smoke more. The purpose of this study was to inform pack quantity regulations by examining whether usual cigar pack quantity purchased was associated with use, initiation, and discontinuation among youth and adults for four cigar types: premium cigars, large cigars, cigarillos, and filtered cigars. METHODS: We analyzed waves 1-5 (2013-2019) of the adult and waves 2-5 (2014-2019) of the youth Population Assessment of Tobacco and Health (PATH) Study. Samples included those responding to the item on pack quantity and providing data at all waves (adults: premium cigars [N = 536], large cigars [N = 1,272], cigarillos [N = 3,504], filtered cigars [N = 1,281]; youth: premium cigars [N = 55], large cigars [N = 217], cigarillos [N = 1514], filtered cigars [N = 266]). Generalized estimating equation models examined the population-averaged effects of pack quantity on cigar use, initiation, and discontinuation. RESULTS: Adult pack quantity was positively associated with the days used per month for premium cigars (b: 0.23, 95% CI: 0.11, 0.34), large cigars (b: 0.17, 95% CI: 0.08, 0.25), cigarillos (b: 0.12, 95% CI: 0.003, 0.24), and filtered cigars (b: 0.07, 95% CI: 0.04, 0.10), and positively associated with amount smoked per day for all cigar types. Youth pack quantity was positively associated with days used per month for premium cigars (b: 0.88, 95% CI: 0.33, 1.43), large cigars (b: 0.79, 95% CI: 0.43, 1.15), and cigarillos (b: 0.17, 95% CI: 0.01, 0.34). Adult initiation was associated with pack quantity for filtered cigars (b: -2.22, 95% CI: -4.29, -0.13), as those who initiated purchased smaller pack quantities compared to those who did not initiate that wave. Pack quantity was not associated with discontinuation for adults or youth. CONCLUSIONS: Cigar use increased as usual pack quantity purchased increased across cigar types for youth and adults. Small increases in pack quantity (e.g., one additional cigar) are likely to result in consuming less than one additional day per month, though larger increases (e.g., 10 additional cigars per pack) may result in greater use
Physical Health and Well-being: Updates and the Way Ahead
No full textINTRODUCTION: The Women in Combat Summit 2021 Forging the Future: How Women Enhance the Fighting Force took place during February 9-11, 2021, via a virtual conference platform. The third and final day of the Summit regarded the physical health and well-being of military women and included the topics of urogenital health, nutrition and iron-deficiency anemia, unintended pregnancy and contraception, and traumatic brain injury. MATERIALS AND METHODS: After presentations on the topics earlier, interested conference attendees were invited to participate in focus groups to discuss and review policy recommendations for physical health and well-being in military women. Discussions centered around the topics discussed during the presentations, and suggestions for future Women in Combat Summits were noted. Specifics of the methods of the Summit are presented elsewhere in this supplement. RESULTS: We formulated research and policy recommendations for urogenital health, nutrition and iron-deficiency anemia, contraception and unintended pregnancy, and traumatic brain injury. CONCLUSIONS: In order to continue to develop the future health of military women, health care providers, researchers, and policymakers should consider the recommendations made in this supplement as they continue to build on the state of the science and forge the future
Fear and anxiety is what I recall the best. : A phenomenological examination of mothers\u27 pregnancy experiences during COVID-19 in the United States
No full textOBJECTIVE: The purpose of this phenomenological study is to understand mothers\u27 lived pregnancy experiences during the COVID-19 pandemic. DESIGN: A qualitative, phenomenological study SETTING: Participants completed the demographic survey online and semi-structured interviews, via video conferencing between November and December 2021 PARTICIPANTS: A sample of 28 mothers who were pregnant during the COVID-19 pandemic participated in the study. METHODS AND RESULTS: An inductive, thematic approach was used to analyze the data. Two central themes and eight subthemes emerged from the six-phase thematic analysis. The first central theme, Depth of Knowledge About COVID-19, included the following subthemes: 1) Vaccines and 2) Uncertainty for Exposure. The second central theme, Impacts of COVID-19, had six subthemes: 1) Types of Support Received, 2) COVID-19 Restrictions, 3) Childcare, 4) Mental Health, 5) Spending More Time at Home, and 6) Isolation. CONCLUSIONS: Findings of this study revealed mothers experienced a significant amount of stress and anxiety related to the coronavirus pandemic during their pregnancy. IMPLICATIONS FOR PRACTICE: Our findings highlight the need to provide pregnant mothers comprehensive care, including mental health services, adequate access to social support, and providing clear information regarding COVID-19 vaccination and its impacts on pregnancy
Eartha M.M. White, Parkway Ballroom
No full textPhotograph: Eartha White at Parkway Ballroom in Chicago, Illinois. Undated.https://digitalcommons.unf.edu/eartha_images/1775/thumbnail.jp