A Degradation Prediction Algorithm for Maritime Distress Reporting Based on Deep Learning

Owing to the bad weather, equipment immersion with water, antenna difficult to point at the satellite and so on, the accuracy and the reliability of the positional information of the pilot in distress sent by the distress message signal sending device is low, which will be reduced with the increase of working time. In order to improve the reliability of distress message signal sending device based on BeiDou satellite, a prediction method for signal sending time and a prediction method for signal transmitting delay time are firstly proposed based on the deep neural network. In the process of prediction, a lot of sensor information is used, especial in the prediction of signal transmitting delay time, multiple-sampling information from the sensors is adopted. The experimental results show that the probability of successful message signal sending is increased from 36.3% to 73.3%, moreover, the working time of the equipment was extended from 6.0 hours to 8.6 hours.

[1]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[2]  Thomas B. Schön,et al.  Author Correction: Automatic diagnosis of the 12-lead ECG using a deep neural network , 2020, Nature Communications.

[3]  Yandong Luo,et al.  Array-Level Programming of 3-Bit per Cell Resistive Memory and Its Application for Deep Neural Network Inference , 2020, IEEE Transactions on Electron Devices.

[4]  Deepak Gupta,et al.  An Effective Training Scheme for Deep Neural Network in Edge Computing Enabled Internet of Medical Things (IoMT) Systems , 2020, IEEE Access.

[5]  Shie Mannor,et al.  A Tutorial on the Cross-Entropy Method , 2005, Ann. Oper. Res..

[6]  Fei-Fei Li,et al.  Visualizing and Understanding Recurrent Networks , 2015, ArXiv.

[7]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[8]  Fa Zhang,et al.  Breast cancer histopathological image classification using a hybrid deep neural network. , 2020, Methods.

[9]  Haixu Tang,et al.  Full-Spectrum Prediction of Peptides Tandem Mass Spectra using Deep Neural Network. , 2020, Analytical chemistry.

[10]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[11]  Jihong Liu,et al.  PACL: Piecewise Arc Cotangent Decay Learning Rate for Deep Neural Network Training , 2020, IEEE Access.

[12]  Shuo Wang,et al.  Overview of deep learning , 2016, 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC).

[13]  T. Chikama,et al.  Deep Neural Network-Based Method for Detecting Obstructive Meibomian Gland Dysfunction With in Vivo Laser Confocal Microscopy. , 2020, Cornea.