Katherine R. Dearstyne

Trenton W. Ford, William Theisen, Michael Yankoski et al.

This article presents a beta-version of MEWS (Misinformation Early Warning System). It describes the various aspects of the ingestion, manipulation detection, and graphing algorithms employed to determine--in near real-time--the relationships between social media images as they emerge and spread on social media platforms. By combining these various technologies into a single processing pipeline, MEWS can identify manipulated media items as they arise and identify when these particular items begin trending on individual social media platforms or even across multiple platforms. The emergence of a novel manipulation followed by rapid diffusion of the manipulated content suggests a disinformation campaign.

Katherine R. Dearstyne, Alberto D. Rodriguez

The following paper investigates the effectiveness of incorporating human salience into the task of calorie prediction from images of food. We observe a 32.2% relative improvement when incorporating saliency maps on the images of food highlighting the most calorie regions. We also attempt to further improve the accuracy by starting the best models using pre-trained weights on similar tasks of mass estimation and food classification. However, we observe no improvement. Surprisingly, we also find that our best model was not able to surpass the original performance published alongside the test dataset, Nutrition5k. We use ResNet50 and Xception as the base models for our experiment.

Katherine Dearstyne, Pedro, Alarcon Granadeno et al.

Cyber-Physical Systems (CPS) often leverage Reinforcement Learning (RL) techniques to adapt dynamically to changing environments and optimize performance. However, it is challenging to construct safety cases for RL components. We therefore propose the SAFE-RL (Safety and Accountability Framework for Evaluating Reinforcement Learning) for supporting the development, validation, and safe deployment of RL-based CPS. We adopt a design science approach to construct the framework and demonstrate its use in three RL applications in small Uncrewed Aerial systems (sUAS)