Explainability is essential for artificial intelligence (AI) systems, especially in high-safety areas like civil aviation. The Local Interpretable Model-agnostic Explanations (LIME) algorithm gives different results for the same input when run multiple times. The different results reduce the reliability of explainable AI in aviation. Therefore, we propose a Bayesian-Enhanced (BE) mechanism. It combines a Bayesian inference module and a prior knowledge module to accomplish robustness to kernel settings. The result can improve the efficiency of LIME and thus can solve the current problems of LIME. By integrating BE mechanism with LIME, we develop a new explainable method named BE-LIME. BE-LIME produces more stable and consistent explanations. We apply BE-LIME to the Landing Approach Runway Detection (LARD) dataset. Experimental results show that BE-LIME resolves the inconsistency issue in LIME. Using F1 scores, AUC, and LIME scores demonstrates that BE-LIME consistently achieves higher stability, greater attribution focus, and improved robustness over LIME, SHAP, and GradCAM. Additionally, BE-LIME aligns with the explainability goals outlined in the European Union Aviation Safety Agency (EASA) concept paper on machine learning guidelines and supports the data-learning assurance process.
n the recent years, probabilistic approaches have been developed to incorporate uncertainties in the dynamic systems. These uncertainties arise due to unknown experimental errors or variability in nominally identical dynamic systems. The majority of these probabilistic methods are based on modal data. These modal data based probabilistic methods do not employ damping matrices and hence cannot be used for accurate prediction of amplitudes of vibrations and complex frequency response functions (FRFs) and also these modal data based do not work well for the closed modes systems. In this paper, a new FRF-based parametric approach is presented which tackles the problem of incorporating damping and closed modes in uncertain dynamic systems. The advantages of using FRF data over modal data for probabilistic model updating are demonstrated. In the proposed FRF-based probabilistic updating approach, the finite element model is updated in such a way that the updated model reflects general damping in the experimental model by considering the updating parameters as complex. The effectiveness of the proposed finite element updating procedure is demonstrated by numerical examples. The results have shown that the proposed damped FRF-based probabilistic model updating procedure can be used to identify and quantify uncertainties in the dynamic systems.
Sulphur Hexafluoride SF6 is an insulating gas widely used in the pulsed power industry. However, it is a strong greenhouse gas with a potential impact 23000 higher than that of CO2. We propose alternative methods to minimize the use of SF6 while maintaining part of its dielectric strength, required to prevent breakdowns. Based on experimental results of different SF6-N2 mixtures, we show that a more environmentally friendly solution can be obtained.
A Registered Apprenticeship at GlobalFoundries (GF) in Malta, NY, has created a pipeline of workers with hands-on mechanical and electrical skills critical to the growing semiconductor industry. This is the first Registered Apprenticeship of its kind in the semiconductor industry and is a proven mechanism to broaden the candidate pipeline, increase retention and advancement, and reach diverse and underserved communities [1]. It can serve as a nationwide model for others to follow as the U.S. faces a critical shortage of qualified talent in this high growth era [2],[3].
De La Salle University is committed to reducing its impact on the environment and to promoting positive action that will help reduce its carbon footprint. In its vision-mission, it emphasizes the need to be “attuned to a sustainable earth.” This paper presents the different initiatives and challenges faced by the university, especially while still in a global pandemic. A number of initiatives have been undertaken to promote energy efficiency in campus operations and climate action, particularly regarding reducing greenhouse gas emissions. However, facing the COVID-19 pandemic and preparing campus operations for the gradual resumption of face-to-face classes have presented new challenges moving into the next normal. The need to address health and safety concerns has resulted in increased consumption of electricity. Challenges are experienced particularly in ensuring improved indoor air quality as well as allowing indoor-outdoor air exchange. The setting up of (a) air purifiers and/or additional auxiliary fans in high foot-traffic areas, (b) installation of HEPA filters and UV-C lamps into HVAC systems, (c) extended use of air conditioning units to allow purging of air before and at the end of activities, and (d) the opening of air exchange dampers in the University’s HVAC systems, are all expected to result in increased demand for electricity.
