Road condition judgment system of railway transportation based on artificial intelligence recognition technology

Liang, Cao

doi:10.1007/s13198-021-01509-w

“…Potential applications of curve fitting are countless and encompass virtually all scientific disciplines. Examples include biosynthesis, 6 thermoluminescence, 7 solar energy, 8 materials science and technology, 9 agriculture, 10 cancer research, 11 kinetics, 12 thermal engineering, 13 transportation, 14 soil science, 15 remote sensing of ecosystems, 16 epidemiology, 17 power and energy engineering, 18 population growth 19 and spectroscopy, 20 to name just a few. The disagreement metrics to minimize during the fit depends on the properties of the noise and possibly on prior information on the parameters to fit.…”

Section: Mainmentioning

confidence: 99%

Correcting Systematic Errors by Hybrid 2D Correlation Loss Functions in nonlinear inverse modelling

Mayerhöfer

¹

,

Noda

²

,

Pahlow

³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently a new family of loss functions called smart error sums has been suggested. These loss functions account for correlations within experimental data and force modeled data to obey these correlations. As a result, multiplicative systematic errors of experimental data can be revealed and corrected. The smart error sums are based on 2D correlation analysis which is a comparably recent methodology for analyzing spectroscopic data that has found broad application. In this contribution we mathematically generalize and break down this methodology and the smart error sums to uncover the mathematic roots and simplify it to craft a general tool beyond spectroscopic modelling. This reduction also allows a simplified discussion about limits and prospects of this new method including one of its potential future uses as a sophisticated loss function in deep learning. To support its deployment, the work includes computer code to allow reproduction of the basic results.

show abstract

“…Potential applications of curve fitting are countless and encompass virtually all scientific disciplines. Examples include biosynthesis [ 9 ], thermoluminescence [ 10 ], solar energy [ 11 ], materials science and technology [ 12 ], agriculture [ 13 ], cancer research [ 14 ], kinetics [ 15 ], thermal engineering [ 16 ], transportation [ 17 ], soil science [ 18 ], remote sensing of ecosystems [ 19 ], epidemiology [ 20 ], power and energy engineering [ 21 ], population growth [ 22 ] and spectroscopy [ 23 ], to name just a few. The disagreement metrics to minimize during the fit depends on the properties of the noise and possibly on prior information on the parameters to fit.…”

Section: Introductionmentioning

confidence: 99%

Correcting systematic errors by hybrid 2D correlation loss functions in nonlinear inverse modelling

Mayerhöfer

¹

,

Noda

²

,

Pahlow

³

et al. 2023

View full text Add to dashboard Cite

Recently a new family of loss functions called smart error sums has been suggested. These loss functions account for correlations within experimental data and force modeled data to obey these correlations. As a result, multiplicative systematic errors of experimental data can be revealed and corrected. The smart error sums are based on 2D correlation analysis which is a comparably recent methodology for analyzing spectroscopic data that has found broad application. In this contribution we mathematically generalize and break down this methodology and the smart error sums to uncover the mathematic roots and simplify it to craft a general tool beyond spectroscopic modelling. This reduction also allows a simplified discussion about limits and prospects of this new method including one of its potential future uses as a sophisticated loss function in deep learning. To support its deployment, the work includes computer code to allow reproduction of the basic results.

show abstract

“…Xu, JP et al use artificial intelligence to empower the power allocation for Smart Railway [8]. Cao uses artificial intelligence recognition technology and combines dynamic time warping distance to the accuracy evaluation of tram track recognition, which effectively improves the effect of railway transportation road condition recognition [9]. Andrea et al integrated the prototype of the real-time monitoring Artificial intelligence Camera Prototype into the multi-sensor monitoring system to detect the falling rocks along the railway, so as to improve the early warning system for managing the landslide site risk, and carried out relevant tests prove that the system is reliability [10].…”

Section: Introductionmentioning

confidence: 99%

Research on elevated orbit noise propagation based on AI algorithm and propagation path analysis

Ling-Xiao,

Xiao-Yan,

Kun

2023

Front. Phys.

0

View full text Add to dashboard Cite

With the rapid development of high-speed railway, noise reduction is becoming more and more important. At the same time, the study of elevated rail noise is also very important for the engineering field. The noise reduction of elevated rail noise is a part of the engineering construction, which is conducive to the economic development and the improvement of people’s life, and the reduction of noise has an impact on residents’ life. This article aims to investigate the analysis of the vibration and noise transmission path of the elevated railway. An optimized transmission path analysis method, which is based on the artificial intelligence algorithms, is used to optimize the path analysis, so as to trace the source of the noise and analyze the noise reduction. This method performs well in the analysis of vibration and noise of elevated railways. After this optimization, the contribution degree and frequency response function in the path analysis have better analysis performance. Through the actual measurement and analysis of the noise of the elevated railway, it can be proved that the traditional path method can better analyze the noise source. The environmental noise caused by high-speed trains passing bridges easily exceeds the acoustic environmental standards. After noise reduction, it can be reduced by about 5–10 dB.

show abstract

Road condition judgment system of railway transportation based on artificial intelligence recognition technology

Cited by 4 publications

References 17 publications

Correcting Systematic Errors by Hybrid 2D Correlation Loss Functions in nonlinear inverse modelling

Correcting Systematic Errors by Hybrid 2D Correlation Loss Functions in nonlinear inverse modelling

Correcting systematic errors by hybrid 2D correlation loss functions in nonlinear inverse modelling

Research on elevated orbit noise propagation based on AI algorithm and propagation path analysis

Contact Info

Product

Resources

About