Edge computing is evolving to include heterogeneous compute nodes with distinct characteristics. Graphic processing units (GPU) and field-programmable gate arrays (FPGA) can execute demanding deep learning (DL) tasks while meeting the deadlines of time-sensitive applications. However, FPGAs require reconfiguration to execute different tasks. In this paper, we first demonstrate that FPGAs can be reconfigured in real-time. Additionally, we propose ELEVATE as a novel scheduling algorithm for reconfigurable heterogeneous edge computing platforms targeting Industry 4.0 post-production quality control. ELEVATE design focusses on optimising the reconfiguration of the FPGA unit for heterogeneous quality inspection tasks. Our simulations indicate that ELEVATE reduces task waiting time by up to two orders of magnitude and achieves energy savings of up to 25 % compared to a statically configured FPGA unit.

This Innovative Practice Full Paper presents a new digitized Draw-A-Scientist Test (DAST) tool and discusses the results of deploying it to minority students in at-risk schools. Pervasive science stereotypes, particularly stereotypes of scientists, continue to negatively affect minoritized students' perceptions of science and commitment to pursuing STEM-related careers. One helpful tool for better understanding students' perceptions of scientists through projective tests is Chambers's DAST, initially created in 1983. The original protocol for deploying the DAST in a research setting asked students to “draw a scientist” on paper. Then, researchers could assess the seven indicators of stereotypical scientists (i.e., eyeglasses, facial hair, white lab coats, symbols of knowledge, symbols of research, technology, and captions). However, to improve inter-rater reliability and capture a more accurate reflection of students' perceptions of scientists, Finson, Beaver, and Cramond reenvisioned DAST scoring and assessment in 1995 to include eight additional indicators (i.e., indicators of danger, indicators of secrecy, mythic figures, presence of light bulbs, sex indicator for male, Caucasian, middle-aged or elderly, and scientists working indoors). Finson and team called the new DAST scoring rubric the DAST-C, which remains the most widely used one. However, methodological issues still impact DAST assessments, and updated tools for technology have made paper/pencil tasks obsolete, even for young students. With support from the National Science Foundation's Innovative Technology Experiences for Students and Teachers (NSF ITEST) program, our collaborative interdisciplinary team infused technology-rich STEM learning modules that incorporated a proof-of-concept digitized version of the DAST into at-risk 3rd–5th-grade classrooms serving minoritized students. We compared findings from the digitized DAST with a priori paper/pencil data to highlight critical differences in DAST implementation and scoring. The current study had two primary objectives related to updating the DAST as a tool and in terms of streamlining DAST scoring: 1) digitizing the DAST to bring the paper/pencil version into the 21st century and 2) streamlining DAST assessment by integrating digital assessment tools into the new digitized DAST tool. Here, we discuss digitizing the DAST tool, assessing indicators of stereotypical scientists, and deploying the digitized DAST to a population of minoritized students studying in at-risk schools in America.