Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Towards Explainable Ai Using Attribution Methods And Image Segmentation, Garrett J. Rocks
Towards Explainable Ai Using Attribution Methods And Image Segmentation, Garrett J. Rocks
Honors Undergraduate Theses
With artificial intelligence (AI) becoming ubiquitous in a broad range of application domains, the opacity of deep learning models remains an obstacle to adaptation within safety-critical systems. Explainable AI (XAI) aims to build trust in AI systems by revealing important inner mechanisms of what has been treated as a black box by human users. This thesis specifically aims to improve the transparency and trustworthiness of deep learning algorithms by combining attribution methods with image segmentation methods. This thesis has the potential to improve the trust and acceptance of AI systems, leading to more responsible and ethical AI applications. An exploratory …
Examining Direct Load Control Within Demand Response Programs, Maria Bonina Zimath
Examining Direct Load Control Within Demand Response Programs, Maria Bonina Zimath
Honors Undergraduate Theses
The power system is a complex entity with unique plant designs, control systems, and market strategies. For many years, engineers have developed advanced technology to keep the grid efficient and balanced. With the rise of renewable sources, some new technology and programs must be developed to keep the quality of the power system. Unlike traditional power plants, renewable energy is highly dependent on environmental factors, such as sunlight and wind, meaning the generation depends on an unpredictable source of fuel. As the grid moves to more sustainable sources, the power market faces a growing challenge of less control over the …