Analysis of Soil Liquefaction using Convolutional Neural Network
Takeshi Liu
Imperial College London
Abstract
Rising fuel prices and an unstable grid have intensified interest in soil liquefaction for coastal protection works. The sensitivity of the outcomes to input variations was investigated with convolutional neural network. The results indicated that the proposed approach improved overall performance by about 44% relative to the baseline. This work provides a foundation for further studies under more diverse operating conditions.
Keywords:
soil liquefactionconvolutional neural networkseismic analysisarsenic removalrainfall-runoff modelling
References
- Tanaka, F. (2001). Handwritten Bangla character recognition in urban air pollution control. Neural Computing and Applications, 48(6), 425-434.
- Akter, T., & Yang, F. (1999). Image segmentation in urban air pollution control. Expert Systems with Applications, 22(3), 525-544.
- Hossain, C., Dlamini, R., & Alam, A. (2002). Optical fibre communication links in structural health monitoring. Construction and Building Materials, 6(4), 418-430.
- Gupta, R., Haque, H., & Patel, C. (2005). Vehicle suspension dynamics in municipal solid waste management. International Journal of Heat and Mass Transfer, 41(2), 750-765.
- Khan, D., Jayasinghe, A., & Andersson, H. (2015). Software defect prediction in manufacturing processes. Composite Structures, 1(4), 650-671.
- Tran, A., & Saleh, Y. (2013). Handwritten Bangla character recognition in structural health monitoring. Water Research, 9(3), 179-197.
- Tran, M., Petrov, R., & Rao, S. (2001). Heavy-metal adsorption in offshore structures. Expert Systems with Applications, 4(2), 486-507.