Incorporation of Duffing Oscillator and Wigner-Ville Distribution in Traffic Flow Prediction

Mrgole, Anamarija L.; Sever, Drago

doi:10.7307/ptt.v29i1.2116

Cited by 6 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on its unique characteristics, employment of Du ng's equation is natural selection. Researchers, such as Mrgole & Drago [3], use a Du ng's system mathematically expressed in the following form for the investigations in identifying and analyzing the nonlinear patterns in tra c ow prediction.…”

Section: Governing Equation and Numerical Solutionsmentioning

confidence: 99%

“…However, as a random system in general, many factors a ect tra c ow. The tra c ow therefore involves uncertainty and complexity [3]. Currently, there exist many tra c ow prediction systems and models conducted by peer researchers and engineers.…”

Section: Introductionmentioning

confidence: 99%

“…A short term prediction of tra c ow was conducted with applications of Arti cial Neural Network (ANN) and the past tra c data. Wigner-Ville distribution was applied recently by Mrgole & Drago [3] for identifying chaotic patterns in tra c ow prediction, where a Duing system was used. By solving the Du ng's system and transferring the results by Wigner-Ville transform, the reliable chaotic pattern in the tra c ow can be successfully recognized.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Nonlinear analysis of high accuracy and reliability in traffic flow prediction

Dai

Wang

2020

Nonlinear Engineering

View full text Add to dashboard Cite

AbstractFor quantitatively identifying the chaotic patterns in traffic flow prediction, certain types of Duffing systems can be used. The accuracy and reliability of numerical results of the system’s solution have significant influence on the traffic flow prediction. The nonlinear dynamic behavior of Duffing system used for the traffic flow prediction is investigated in this research. The solutions of the system are developed and solved numerically by using the P-T method. The regular and irregular responses of the system considered are graphically illustrated with the newly developed P-R method. Based on the results of the research, the frequency and amplitude of the external excitations applied on the system significantly affecting the nonlinear dynamic behavior therefore the traffic flow prediction in transferring the results by Wigner-Ville transform. Additionally, a comparison between the P-T and Runge-Kutta method is conducted in regarding the accuracy and reliability of the methods.

show abstract

Section: Governing Equation and Numerical Solutionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Nonlinear analysis of high accuracy and reliability in traffic flow prediction

Dai

Wang

2020

Nonlinear Engineering

View full text Add to dashboard Cite

show abstract

“…For instance, a form of the equation for Duffing's oscillator considered in ref. [1] was utilized as a chaotic pattern and the generated time-relevant dataset was further transformed by the way the optimized Wigner-Ville frequency distribution to predict traffic congestion in a more efficient and accurately way. L. Wang, L. Dai, et al [2,3] studied the vibro-acoustic DOI: 10.1002/adts.202300148 behavior of reinforced graphite sandwich structure based on the results of the Rayleigh integral which used the structural forced nonlinear dynamic responses as an input.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, a form of the equation for Duffing's oscillator considered in ref. [1] was utilized as a chaotic pattern and the generated time‐relevant dataset was further transformed by the way the optimized Wigner‐Ville frequency distribution to predict traffic congestion in a more efficient and accurately way. L. Wang, L. Dai, et al.…”

Section: Introductionmentioning

confidence: 99%

Chaotic Time Series Prediction of Multi‐Dimensional Nonlinear System Based on Bidirectional LSTM Model

Wang

Dai

2023

Advcd Theory and Sims

View full text Add to dashboard Cite

The current work proposes a hybrid data‐driven model—Convolutional bidirectional long–short term memory (CNN‐BLSTM) for predicting chaotic behavior of three‐coupled Duffing oscillator nonlinear system, in which the CNN is for efficiently extracting the more robust and informative representations of chaotic sequences while the BLSTM is for holding the long‐term dependencies combining the past and future contexts. Different from traditional analytical and numerical approaches, the proposed prediction model features the benefit of focusing on the measured data solely without extensive professional domain knowledge. Additionally, three more recurrent neural network (RNN) models, including simple RNNs, stack LSTMs, and BLSTM, are built and comparisons of generalization performances to the CNN‐BLSTM are conducted. From the findings so far, the CNN‐BLSTM is able to learn the pattern of chaotic time sequence data with less training time and apply the acquired knowledge to the unseen dataset with lower errors. Moreover, the current work decently demonstrates that the proposed model outperforms other three models in terms of stability at different noise levels from two evaluation criteria. The CNN‐BLSTM provides useful guidance for the consideration of predicting multi‐dimensional nonlinear chaotic behavior.

show abstract

Design and Implementation of Urban Traffic Flow Resource Data Management System Based on Deep Learning Algorithm

Ye¹

2020

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Incorporation of Duffing Oscillator and Wigner-Ville Distribution in Traffic Flow Prediction

Abstract: ABSTRACT

Cited by 6 publications

References 20 publications

Nonlinear analysis of high accuracy and reliability in traffic flow prediction

Nonlinear analysis of high accuracy and reliability in traffic flow prediction

Chaotic Time Series Prediction of Multi‐Dimensional Nonlinear System Based on Bidirectional LSTM Model

Design and Implementation of Urban Traffic Flow Resource Data Management System Based on Deep Learning Algorithm

Contact Info

Product

Resources

About