Learn about a summer 2020 research experience for teachers, or RET, experience amid COVID-19 with electrical engineering doctoral student Kristen Jaskie.
IEEE Education Society Seminar with Kristen Jaskie: Summer 2020 NSF Research Experiences for Teachers on Sensors and Machine Learning
Friday, October 16, 2020
Attend on Zoom
The internet of things, the ecosystem of physical objects connected via the internet, has seen rapid growth over recent years and has been enhanced by mobile applications. Machine learning algorithms and sensors are critical to this technology, leading to a demand in developing sensors that are more efficient and less expensive. The summer RET program brings ten high school teachers and two community college instructors together to participate in research activities at Arizona State University. After a hands-on bootcamp centered on key concepts in ML, sensors, and IoT, teachers are immersed in a 6-week research program and mentored by a team of ASU faculty, graduate student advisors, and industry leaders. ASU continues their engagement with teachers throughout the school year and offers assistance and feedback on transferring their research experiences into the classroom. The goal of the RET is to give teachers a deeper understanding of ML and IoT such that they can develop engaging materials around these topics for their classrooms. Moreover, teachers’ experiences motivate and energize their students to engage in STEM activities and career pathways.
The summer 2020 RET presented unique challenges due to Covid-19 and the inability to meet with the students in person. To develop an all online RET experience, we reduced the number of participating teachers from 12 to 2 and developed new online synchronous and asynchronous lessons and material to teach fundamental content and hands-on application of ML algorithms online. Using solar array monitoring as our sensor IoT application, both teachers developed an understanding of ML algorithms and concepts, along with hands on programming in Python using Google Colab. K-means, KNN, linear and logistic regression, SVMs, and neural networks were described, programmed, and evaluated using real-world solar sensor data. Despite the difficult and unusual circumstances, the program was a success and, in this talk, I will discuss this program, the challenges we faced due to Covid-19, strategies we used to overcome these challenges, and the outcomes of the program.
The RET is funded in part by NSF award 1953745 and the Sensor, Signal & Information Processing (SenSIP) Center. Some of the teacher training sessions were collaborative with the CBBG ERC.
About the speaker
Kristen Jaskie is a doctoral student in electrical engineering at ASU, advised by Andreas Spanias and specializing in machine learning and signal processing. She received her bachelor’s degree in computer science from the University of Washington and her master’s degree in computer science specializing in AI and machine learning at the University of California San Diego. She owns her own consulting company and was a faculty member and department chair in Computer Science at Glendale Community College in Glendale, AZ for several years before returning to school to complete her doctorate. She is expecting to graduate in Spring 2021.
Kristen’s main areas of interest are in ML algorithm development ML education. Her research has been focused on semi-supervised learning and solving the Positive Unlabeled learning problem. She is writing a monograph on the subject to be published early next year. Kristen has applied this work to solar panel fault modeling, Covid-19 detection research, and remote sensing. She is also doing research using deep learning algorithms and Quantum Machine Learning using quantum computers.