Convolutional neural networks for ultrasound corrosion profile time series regression

Cantero‐Chinchilla, Sergio; Simpson, Christopher J.; Ballisat, Alexander; Croxford, Anthony J.; Wilcox, Paul D.

doi:10.1016/j.ndteint.2022.102756

Cited by 7 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…InceptionTime essentially serves as a CDNN model designed for time series classification [76]. Its structural foundation is rooted in Google's Inception module for image classification.…”

Section: Forecasting Models 341 Inceptiontime Modelmentioning

confidence: 99%

Application of GIS and IoT Technology based MCDM for Disaster Risk Management: Methods and Case Study

AbdelAziz,

Eldrandaly,

Al-Saeed

et al. 2023

Decis. Mak. Appl. Manag. Eng.

View full text Add to dashboard Cite

This study proposes a two-phase framework to enhance disaster management strategies for flooding using Geographic Information System (GIS) and Internet of Things (IoT) real-time data obtained using drones. The first phase aims to predict the governorate most prone to flooding using GIS and four forecasting models. The second phase involves selecting optimal locations for drone takeoff and landing using GIS with multi-criteria decision making. The neutrosophic ordinal priority approach is used to weight the criteria for selecting the best locations. A case study from the Egyptian Mediterranean Coast is used to measure the effectiveness and applicability of the framework. Results indicate that the Port Said governorate is the most vulnerable to flooding, and the top 10 suitable sites for drone takeoff and landing are suggested for this governorate. The limitations of the case study are discussed, such as data availability and reliability, as well as potential biases in the methodology. This study suggests future research directions to address these limitations and enhance the effectiveness of the proposed framework. Overall, this study contributes to the field of disaster risk management by providing a practical and innovative approach to enhance disaster preparedness and response using GIS and IoT technologies.

show abstract

“…InceptionTime essentially serves as a CDNN model designed for time series classification [76]. Its structural foundation is rooted in Google's Inception module for image classification.…”

Section: Forecasting Models 341 Inceptiontime Modelmentioning

confidence: 99%