Browsing by Subject "Active learning"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Data Mining of Traffic Video Sequences
    (University of Minnesota Center for Transportation Studies, 2009-09) Joshi, Ajay J.; Papanikolopoulos, Nikolaos
    Automatically analyzing video data is extremely important for applications such as monitoring and data collection in transportation scenarios. Machine learning techniques are often employed in order to achieve these goals of mining traffic video to find interesting events. Typically, learning-based methods require significant amount of training data provided via human annotation. For instance, in order to provide training, a user can give the system images of a certain vehicle along with its respective annotation. The system then learns how to identify vehicles in the future - however, such systems usually need large amounts of training data and thereby cumbersome human effort. In this research, we propose a method for active learning in which the system interactively queries the human for annotation on the most informative instances. In this way, learning can be accomplished with lesser user effort without compromising performance. Our system is also efficient computationally, thus being feasible in real data mining tasks for traffic video sequences.
  • Thumbnail Image
    Item
    The Effect of Incorporating Active Learning In Calibration Exercises On Intra and Interrater Reliability Among Dental Hygiene Faculty
    (2019-09) Hotzler, Bridget
    ABSTRACT Purpose/Objective: The purpose of this study was to investigate if incorporating active learning into calibration exercises increased the level of intra- and interrater reliability among dental hygiene faculty. Methods: The study used a two-group randomized experimental design with a convenience sample consisting of ten dental hygiene faculty members from the division of dental hygiene at the University of Minnesota (n=10). Baseline training in motivational interviewing (MI) was provided to all faculty at a day-long continuing education course. One month later, all faculty viewed three videos of students performing MI during an OSCE and graded their performance using a standardized grading rubric. The treatment group then engaged in the identical motivational interviewing OSCE required of the students. One month later, both study groups viewed the same three videos and graded the students’ MI performance using the identical standardized grading rubric. (See Appendix C). Results: The overall intra-rater reliability was calculated using Cohen’s Kappa statistic, pre-and post-intervention for both the control and treatment groups. Results revealed moderate to weak intra-rater reliability for both groups (.494). Fleiss’ kappa statistic was used to assess interrater reliability. The treatment group achieved higher levels of agreement verses the control group on six of the ten questions. Only one question (See Figure 1: R06) had perfect or near perfect agreement in both study groups. Conclusion: There was no statistically significant difference found in intra- and interrater reliability scores between the control and treatment groups following an active learning intervention. Even though statistical significance was not achieved, individual faculty data suggests active learning did have an effect on the faculty in the treatment group. Post intervention, faculty in the treatment group had greater variations in scores indicating the experience had challenged their frame of knowledge and may have become more empathetic to the challenges of motivational interviewing having conducted an MI session themselves.
  • Thumbnail Image
    Item
    Serious Gaming as an Active Method of Learning Applied Antibiotherapy in Swine Veterinary Medicine
    (Education in the Health Professions journal, 2020-07) Zhitnitskiy, Perle E
    Background: Serious games have been increasing in popularity within health sciences education. Games can improve learning by increasing students’ engagement and by developing their analytical, critical thinking, and teamwork skills. Objective: The objective of this study was to evaluate the efficacy of a board game to teach applied swine antibiotherapy to veterinary students in their clinical year. Methods: Students were quizzed pre- and postclass to evaluate their knowledge retention. An anonymous seven-question survey was given to the students at the end of class to assess their satisfaction with the board game. Results: Students’ quiz scores increased by 1.34 points on average between the beginning and end of class (P = 0.03). Students unanimously enjoyed playing the board game and recommended that it continued to be used in the next iteration of the course. Discussion: Using serious gaming proved to be an enjoyable method of reviewing antibiotherapy and applying it to swine clinical cases in this population of veterinary students. Implementing serious gaming in health sciences education requires a time investment for preparation but provides a richer experience for students and faculty alike.