Search for: All records

Animal-borne acoustic sensors provide valuable insights into wildlife behavior and environments but face significant power and storage constraints that limit deployment duration. We present a novel adaptive acoustic monitoring system designed for long-term, real-time observation of wildlife. Our approach combines low-power hardware, configurable firmware, and an unsupervised machine learning algorithm that intelligently filters acoustic data to prioritize novel or rare sounds while reducing redundant storage. The system employs a variational autoencoder to project audio features into a low-dimensional space, followed by adaptive clustering to identify events of interest. Simulation results demonstrate the system’s ability to normalize the collection of acoustic events across varying abundance levels, with rare events retained at rates of 80–85% while frequent sounds are reduced to 3–10% retention. Initial field deployments on caribou, African elephants, and bighorn sheep show promising application across diverse species and ecological contexts. Power consumption analysis indicates the need for additional optimization to achieve multi-month deployments. This technology enables the creation of novel wilderness datasets while addressing the limitations of traditional static acoustic monitoring approaches, offering new possibilities for wildlife research, ecosystem monitoring, and conservation efforts. 

Despite its potential for STEM education, educational robotics remains out of reach for many classrooms due to upfront purchase costs, maintenance requirements, storage space, and numerous other barriers to entry. As demonstrated previously, these physical robot limitations can be reduced or eliminated through simulation. This work presents a new version of RoboScape Online, a browser-based networked educational robotics simulation platform that aims to make robotics education more accessible while expanding both the breadth and depth of topics taught. Through cloud-hosted simulations, this platform enables distant students to collaborate and compete in real-time. Integration with NetsBlox, a block-based programming environment, allows students at any level to participate in computer science activities. By incorporating a virtual machine for running NetsBlox code into the server, RoboScape Online enables scenarios to be built using the same syntax and abstractions used to program the robots. This approach enables more creative curriculum activities while proving that block-based programming is a valuable development tool, not just a “toy language”. Classroom case studies demonstrate RoboScape Online’s potential to improve students’ computational thinking skills and foster positive attitudes toward STEM subjects, with especially significant improvements in attitudes toward self-expression and creativity within the realm of computer science. 

Computer Science (CS) Frontiers is a 4-module curriculum, 9 weeks each, designed to bring the frontiers of computing to high school girls for exploration and development. Our prior work has showcased the work in developing and piloting our first three modules, Distributed Computing, Artificial Intelligence (AI), and the Internet of Things (IoT). During the summer of 2022, we piloted the completed curricula, including the new Software Engineering module, with 56 high school camp attendees. This poster reports on the newly developed software engineering module, the experiences of 7 teachers and 11 students using the module, and our plans for improving this module prior to its release in formal high school classrooms. Initial survey and interview data indicate that teachers became comfortable with facilitating the open-endedness of the final projects and that students appreciated the connections to socially relevant topics and the ability of their projects to help with real-world problems such as flood prevention and wheelchair accessibility. The CS Frontiers curriculum has been added to course offerings in Tennessee and adoption through the North Carolina Department of Public Instruction is currently underway. Teachers from Tennessee, North Carolina, Massachusetts, and New York have piloted the materials. Together with researchers, we are working to package the course and curricula for widespread adoption as additional support to students as they try out computing courses in their high school pathways. Our aim is to increase the interest and career awareness of CS for high school girls so they may have an equitable footing to choose CS as a potential major or career. 

Robots are a popular and engaging educational tool for teaching computational thinking, but they often have significant costs and limitations for classroom use. Switching to a simulated environment can eliminate many of these difficulties. By also providing students with a block-based programming environment, the barrier to entry can be further reduced. This paper presents a networked virtual robotics platform designed to create an environment which is highly accessible for novice students and their teachers alike, along with components of a curriculum designed to teach computational thinking skills through robotics programming challenges, including autonomous challenges and in-class competitions. Students access this platform through an extension of the same web interface used for programming their robots, which allows students to collaborate on code and view a shared simulated virtual space. Previously, this virtual robotics platform was used only to facilitate distance education. This paper demonstrates its use in an in-person class during the Spring 2022 semester, illustrating the affordances of a virtual robotics environment for face-to-face learning contexts as well. Students' computational thinking skills were evaluated with assessments both before and after the class, along with surveys and interviews given to determine their opinions and outlooks regarding computer science. The results show that students had a significant improvement in both attitudes and aptitudes. 

Distributed computing, computer networking, and the Internet of Things (IoT) are all around us, yet only computer science and engineering majors learn the technologies that enable our modern lives. This paper introduces PhoneIoT, a mobile app that makes it possible to teach some of the basic concepts of distributed computation and networked sensing to novices. PhoneIoT turns mobile phones and tablets into IoT devices and makes it possible to create highly engaging projects through NetsBlox, an open-source block-based programming environment focused on teaching distributed computing at the high school level. PhoneIoT lets NetsBlox programs—running in the browser on the student’s computer—access available sensors. Since phones have touchscreens, PhoneIoT also allows building a Graphical User Interface (GUI) remotely from NetsBlox, which can be set to trigger custom code written by the student via NetsBlox’s message system. This approach enables students to create quite advanced distributed projects, such as turning their phone into a game controller or tracking their exercise on top of an interactive Google Maps background with just a few blocks of code.