Search for: All records

Supported by the National Science Foundation's Improving Undergraduate STEM Education: Hispanic-Serving Institutions (IUSE-HSI) Program, a collaborative summer research internship initiative united a public four-year institution with two local community colleges to offer community college students significant engineering research opportunities and hands-on experiences. In summer 2023, four students from the community college in computer science and engineering participated in a eight-week research internship project in a research lab at the four-year university. This internship project aimed to develop and implement of real-time computer vision on energy-efficient cortex-m microprocessor. This projet explores a unique approach to engage community college students in the realm of artificial intelligence research. By focusing on the development and implementation of real-time computer vision on energy-efficient Cortex-M microprocessors, we offer a practical and educational avenue for students to delve into the burgeoning field of AI. Through a combination of theoretical understanding and practical application, students are empowered to explore AI concepts, gain proficiency in low-power computing, and contribute to real-world AI projects. Furthermore, the project offered student interns a valuable opportunity to refine their research capabilities, particularly in the realms of scientific writing and presentation, while simultaneously boosting their self-assurance and enthusiasm for pursuing STEM careers in the field of AI. 

This paper summarizes the main results and contributions of the MagNet Challenge 2023, an open-source research initiative for data-driven modeling of power magnetic materials. The MagNet Challenge has (1) advanced the stateof-the-art in power magnetics modeling; (2) set up examples for fostering an open-source and transparent research community; (3) developed useful guidelines and practical rules for conducting data-driven research in power electronics; and (4) provided a fair performance benchmark leading to insights on the most promising future research directions. The competition yielded a collection of publicly disclosed software algorithms and tools designed to capture the distinct loss characteristics of power magnetic materials, which are mostly open-sourced. We have attempted to bridge power electronics domain knowledge with state-of-the-art advancements in artificial intelligence, machine learning, pattern recognition, and signal processing. The MagNet Challenge has greatly improved the accuracy and reduced the size of data-driven power magnetic material models. The models and tools created for various materials were meticulously documented and shared within the broader power electronics community.