12 June 2019 in IEEE Geoscience and Remote Sensing Letters
Ground vibration monitoring with microelectromechanical systems (MEMS) sensors is very effective and promising for alerting geological disasters. In this letter, explicitly considering and effectively addressing several specific issues related to practical MEMS sensors, we develop a novel ground vibration monitoring scheme for MEMS sensed data based on a deep convolutional neural network (CNN). Experiments are then conducted on the synthetic and real data sets. Experimental results on both data sets demonstrate that the proposed scheme significantly outperforms the other comparable schemes. For the synthetic data set, the proposed scheme achieves a very high overall accuracy of 98.82%. Also, for the real data set, the proposed scheme achieves a high overall accuracy of 81.64%, which is about 7% higher than that reported in the literature.
30 March 2021 in IEEE Geoscience and Remote Sensing Letters
This letter studies deep learning-based efficient ground vibration monitoring systems. In this work, artificial intelligence (AI) techniques are adopted to effectively deal with practical issues of data collection and classification. Specifically, we develop a novel energy-efficient data collection scheme by adopting deep Q-network-based reinforcement learning. Also, we propose an enhanced joint recurrent neural network (RNN) and convolutional neural network (CNN) approach for ground vibration classification. The performance of the proposed scheme is evaluated using real-world ground vibration data. The experimental results show that the proposed classification scheme outperforms the best existing scheme with CNN by more than 13% in terms of classification accuracy. It is also shown that the proposed energy management scheme can improve the accuracy of the proposed ground vibration monitoring system by 7.6% over the comparable scheme using equal power allocation.
1 October 2019 in Journal of the Korean Society of Mineral and Energy Resources Engineers