On the suitability of generalized regression neural networks for GNSS position time series prediction for geodetic applications in geodesy and geophysics

Shahvandi, Mostafa Kiani

doi:10.48550/arxiv.2005.11106

Cited by 4 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GP algorithm is the most accurate machine learning method, since it has the lowest values of mean(RM SE) and M ASE. On the other hand, as [4] also asserts, the RBF algorithm is the least accurate method. Once again it is confirmed that the RBF algorithm is not suitable for the GNSS position time series prediction.…”

Section: Explanation Of the Algorithmmentioning

confidence: 93%

“…• Use of time series in different atmospheric and tidal conditions. We use the same choice of stations in [4], which are taken from [28]. Hence, based on the points mentioned above, the following table represents the result of applying the algorithm (and its aiding machine learning algorithms) to the permanent GNSS stations mentioned in .…”

Section: Explanation Of the Algorithmmentioning

confidence: 99%

“…One way to do this is to use the traditional statistical methods like Theta [3]. However, experiences with these methods [4] have shown that they are not as strong as machine learning methods, schemes the usage of which enable us to predict the next outcomes of the time series with higher accuracy, speed, and efficiency [5], [6]. Based on this, we have devised a new method for this special problem.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A precise machine learning aided algorithm for land subsidence or upheave prediction from GNSS time series

Kiani

2020

Preprint

Self Cite

View full text Add to dashboard Cite

This paper is aimed at the problem of predicting the land subsidence or upheave in an area, using GNSS position time series. Since machine learning algorithms have presented themselves as strong prediction tools in different fields of science, we employ them to predict the next values of the GNSS position time series. For this reason, we present an algorithm that takes advantage of the machine learning algorithms for the prediction of positions in a GNSS time series. The proposed algorithm has two steps-preprocessing and prediction. In the preprocessing phase, the periodic tidal and atmospheric signals in the time series are removed and coordinates are transferred to the local coordinate system. In the prediction phase, eight different machine learning algorithms are used, namely, multilayer perceptron, Bayesian neural network, radial basis functions, Gaussian processes, k-nearest neighbor, generalized regression neural network, classification and regression trees, and support vector regression. We show the superiority of the Gaussian processes algorithm, compared to other methods, in 14 different real GNSS time series studies. The proposed algorithm can achieve up to 4 millimeters in accuracy, with the average accuracy as 2 centimeters across all time series.

show abstract

Section: Explanation Of the Algorithmmentioning

confidence: 93%

Section: Explanation Of the Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A precise machine learning aided algorithm for land subsidence or upheave prediction from GNSS time series

Kiani

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning prediction algorithms are increasingly gaining attention in the field of geoscience [1], [2]. These methods are different from the traditional, statistical methods for approximation and interpolation [4]- [12].…”

Section: Introductionmentioning

confidence: 99%

“…Machine learning algorithms are even more powerful than the statistical methods such as Theta [3] for prediction purposes [1], [2]. In [1], an analysis for the efficiency of the Generalized Regression Neural Networks (GRNN) for the prediction of GNSS time series values is presented.…”

Section: Introductionmentioning

confidence: 99%

Lateral land movement prediction from GNSS position time series in a machine learning aided algorithm

Kiani

2020

Preprint

Self Cite

View full text Add to dashboard Cite

We investigate the accuracy of conventional machine learning aided algorithms for the prediction of lateral land movement in an area using the precise position time series of permanent GNSS stations. The machine learning algorithms that are used are tantamount to the ones used in [1], except for the radial basis functions, i.e. multilayer perceptron, Bayesian neural network, Gaussian processes, k-nearest neighbor, generalized regression neural network, classification and regression trees, and support vector regression. A comparative analysis is presented in which the accuracy level of the mentioned machine learning methods is checked against each other. It is shown that the most accurate method for both of the components of the time series is the Gaussian processes, achieving up to 9.5 centimeters in accuracy.

show abstract

Performance Prediction Method for Stream Computing Platform Based on Time Series

Lü

2021

IEEE Access

View full text Add to dashboard Cite

As one of the most popular high-performance data processing technology, existing task and resource scheduling strategies for stream computing platforms are suffering from the problem of triggering hysteresis, which seriously affects the cluster performance. To address this problem, the idea of performance prediction based on timeline series data is proposed. Firstly, the performance variation rule of the stream processing platform is analyzed, which provides a basis for proposing the performance prediction model. Secondly, the basic topology paradigm, periodic load prediction model, and real-time throughput prediction model are proposed as the theoretical foundation for performance prediction. Thirdly, the performance prediction algorithm is proposed to predict the variation trend of the processing load and throughput of the cluster. The processing load is predicted periodically while the throughput of the cluster is predicted in a real-time manner. Finally, the performance evaluation algorithm is proposed to evaluate the cluster performance based on the prediction results and trigger the corresponding scheduling strategies in advance. The experimental results showed that the prediction accuracy of the proposed algorithm meets the requirements in practical applications. Meanwhile, the proposed method improves the performance of stream computing performance by triggering the scheduling strategies in advance.INDEX TERMS Big data, stream computing, performance prediction, processing load, and throughput.

show abstract

On the suitability of generalized regression neural networks for GNSS position time series prediction for geodetic applications in geodesy and geophysics

Cited by 4 publications

References 19 publications

A precise machine learning aided algorithm for land subsidence or upheave prediction from GNSS time series

A precise machine learning aided algorithm for land subsidence or upheave prediction from GNSS time series

Lateral land movement prediction from GNSS position time series in a machine learning aided algorithm

Performance Prediction Method for Stream Computing Platform Based on Time Series

Contact Info

Product

Resources

About