|
|
Chalioris, C. E., A. Papadopoulos, N., Sapidis, G., C. Naoum, M., & Golias, E. (2023). EMA-based Monitoring Method of Strengthened Beam-Column Joints. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 853–873). Omaha, USA: University of Nebraska at Omaha.
Abstract: Reinforced concrete (RC) beam-column joints (BCJ) are crucial structural components, primarily during seismic excitations, so their structural health monitoring (SHM) is essential. Additionally, BCJ of existing old RC frame structures usually exhibits brittle behavior due to insufficient transverse reinforcement. To alter the brittle behavior of BCJ, an innovative reinforcing technique has been employed, accompanied by a real-time SHM system. Carbon fiber-reinforced polymer (C-FRP) rope as near surface-mounted (NSM) reinforcement has been utilized as external reinforcement of the column and the joint panel. The use of piezoelectric lead zirconate titanate (PZT) transducers for real-time SHM of BCJ sub-assemblages was investigated. Statistical damage indices, such as RMSD and MAPD, were employed to quantify the damage. Furthermore, an innovative approach based on hierarchical clustering was introduced. The experiment results revealed that the damage level of the reference and the retrofitted specimens were successfully diagnosed with PZT transducers.
|
|
|
|
Jendreck, M., Hellriegel, J., Allmann, J., Restel, H., Pfennigschmidt, S., Meissen, U., et al. (2023). ROBUST communication platform – A decentralized, distributed communi cation platform for the earthquake early warning system ROBUST. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 822–836). Omaha, USA: University of Nebraska at Omaha.
Abstract: Strong earthquakes of great intensity pose a severe threat to human life and property. Earthquake early warning systems are designed to give people in endangered areas valuable seconds to save their lives and property. The basis of an efficient warning system is a communication infrastructure that provides high-speed and reliable communication between the components of the warning system. This paper presents the distributed, decentralized communication platform for the ROBUST project. It discusses the key challenges and requirements such as resilience, real-time capability and target group-specific information distribution that are placed on such a communication platform. In addition, it presents the conception of the communication platform, which is based on a subscriber procedure between autonomous, decentralized peers (nodes), in order to be able to realize the requirements. Finally, it details the technical implementation, practical realization, and evaluation of the communication platform.
|
|
|
|
Ramsey, A., Kale, A., Kassa, Y., Gandhi, R., & Ricks, B. (2023). Toward Interactive Visualizations for Explaining Machine Learning Models. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 837–852). Omaha, USA: University of Nebraska at Omaha.
Abstract: Researchers and end users generally demand more trust and transparency from Machine learning (ML) models due to the complexity of their learned rule spaces. The field of eXplainable Artificial Intelligence (XAI) seeks to rectify this problem by developing methods of explaining ML models and the attributes used in making inferences. In the area of structural health monitoring of bridges, machine learning can offer insight into the relation between a bridge’s conditions and its environment over time. In this paper, we describe three visualization techniques that explain decision tree (DT) ML models that identify which features of a bridge make it more likely to receive repairs. Each of these visualizations enable interpretation, exploration, and clarification of complex DT models. We outline the development of these visualizations, along with their validity by experts in AI and in bridge design and engineering. This work has inherent benefits in the field of XAI as a direction for future research and as a tool for interactive visual explanation of ML models.
|
|
