Despite the growivtgpopularity of robotics competitions such as FIRST LEGO League, robotics activities are typically not found in regular K-12 classrooms. We speculate that, among other reasons, limited t!.doption is due to the lack of empirical evid~nce demonstrating the effect of robotics activitie: on curricular goals. This paper presents a mixed methods study exploring the impact cf a s-..mzmer robotics camp on middle school students' physics content knowledge and scientific inquiry skills. It was found that the camp enhanced students' physics content knowledge but fai!ed to improve their skills in conducting scientific inquiry. Qualitative data provided an explanation of the findings. (
Artificial intelligence (AI) systems hold great promise to improve healthcare over the next decades. Specifically, AI systems leveraging multiple data sources and input modalities are poised to become a viable method to deliver more accurate results and deployable pipelines across a wide range of applications. In this work, we propose and evaluate a unified Holistic AI in Medicine (HAIM) framework to facilitate the generation and testing of AI systems that leverage multimodal inputs. Our approach uses generalizable data pre-processing and machine learning modeling stages that can be readily adapted for research and deployment in healthcare environments. We evaluate our HAIM framework by training and characterizing 14,324 independent models based on HAIM-MIMIC-MM, a multimodal clinical database (N = 34,537 samples) containing 7279 unique hospitalizations and 6485 patients, spanning all possible input combinations of 4 data modalities (i.e., tabular, time-series, text, and images), 11 unique data sources and 12 predictive tasks. We show that this framework can consistently and robustly produce models that outperform similar single-source approaches across various healthcare demonstrations (by 6–33%), including 10 distinct chest pathology diagnoses, along with length-of-stay and 48 h mortality predictions. We also quantify the contribution of each modality and data source using Shapley values, which demonstrates the heterogeneity in data modality importance and the necessity of multimodal inputs across different healthcare-relevant tasks. The generalizable properties and flexibility of our Holistic AI in Medicine (HAIM) framework could offer a promising pathway for future multimodal predictive systems in clinical and operational healthcare settings.
We describe the development of the Intelligent Towing Tank, an automated experimental facility guided by active learning to conduct a sequence of vortex-induced vibration (VIV) experiments, wherein the parameters of each next experiment are selected by minimizing suitable acquisition functions of quantified uncertainties. This constitutes a potential paradigm shift in conducting experimental research, where robots, computers, and humans collaborate to accelerate discovery and to search expeditiously and effectively large parametric spaces that are impracticable with the traditional approach of sequential hypothesis testing and subsequent train-and-error execution. We describe how our research parallels efforts in other fields, providing an orders-of-magnitude reduction in the number of experiments required to explore and map the complex hydrodynamic mechanisms governing the fluid-elastic instabilities and resulting nonlinear VIV responses. We show the effectiveness of the methodology of “explore-and-exploit” in parametric spaces of high dimensions, which are intractable with traditional approaches of systematic parametric variation in experimentation. We envision that this active learning approach to experimental research can be used across disciplines and potentially lead to physical insights and a new generation of models in multi-input/multi-output nonlinear systems.
Abstract. HydroViz is a Web-based, student-centered, educational tool designed to support active learning in the field of Engineering Hydrology. The design of HydroViz is guided by a learning model that is based on learning with data and simulations, using real-world natural hydrologic systems to convey theoretical concepts, and using Web-based technologies for dissemination of the hydrologic education developments. This model, while being used in a hydrologic education context, can be adapted in other engineering educational settings. HydroViz leverages the free Google Earth resources to enable presentation of geospatial data layers and embed them in web pages that have the same look and feel of Google Earth. These design features significantly facilitate the dissemination and adoption of HydroViz by any interested educational institutions regardless of their access to data or computer models. To facilitate classroom usage, HydroViz is populated with a set of course modules that can be used incrementally within different stages of an engineering hydrology curriculum. A pilot evaluation study was conducted to determine the effectiveness of the HydroViz tool in delivering its educational content, to examine the buy-in of the program by faculty and students, and to identify specific project components that need to be further pursued and improved. A total of 182 students from seven freshmen and senior-level undergraduate classes in three universities participated in the study. HydroViz was effective in facilitating students' learning and understanding of hydrologic concepts and increasing related skills. Students had positive perceptions of various features of HydroViz and they believe that HydroViz fits well in the curriculum. In general, HydroViz tend to be more effective with students in senior-level classes than students in freshmen classes. Lessons gained from this pilot study provide guidance for future adaptation and expansion studies to scale-up the application and utility of HydroViz and other similar systems into various hydrology and water-resource engineering curriculum settings. The paper presents a set of design principles that contribute to the development of other active hydrology educational systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.