An adaptive framework to enhance microscopic traffic modelling: an online neuro-fuzzy approach

Kazemi, Reza; Abdollahzade, Majid

doi:10.1177/0954407015623890

Cited by 6 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where,   y t and t ŷ are the actual and estimated outputs at sample t, respectively, and N is the number of identified samples. Besides, comparison to the offline LLNF (LLNFoffline) model [29], ANFIS model [32] and adaptive LLNF model (LLNFadaptive) [29] are presented to demonstrate the effectiveness of online approaches for car-following modeling.…”

Section: Simulation Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An Intelligent Evolving Car-Following Model

Abdollahzade

Kazemi

2023

IEEE Access

View full text Add to dashboard Cite

The existing data-driven car-following models do not take structural and range variations of velocity and acceleration into account. This paper develops a new approach to address both structural and range variations in the car-following process through time. The proposed approach relies upon an intelligent evolving time-variant local model (ETLM), capable of changing its structure and adapting its parameters. The evolving model includes a network of temporal local linear models, each covering a range of carfollowing behavior in a microscopic traffic flow. Furthermore, a decision-making procedure is designed to determine if model should evolve to a new structure is sole adaptation of its parameter is sufficient to describe the new behavior of the car-following process. The decision-making is carried out based on the comparison between the current temporal linear behavior of the process and existing temporal local linear models. Results of implementation of the ETLM on several benchmark case studies as well as real traffic data demonstrate the efficacy of the proposed approach.INDEX TERMScar-following behavior, traffic simulation, evolving models.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

“…represent the linear parameters of the model, 3)-( 6), estimation of the linear parameters of the ETLM, i θ , is carried out adaptively by means of a recursive weighted least squares (RWLS) algorithm, as expressed below [29],…”

Section: Evolving Local Time-variant Modelmentioning

confidence: 99%

An Intelligent Evolving Car-Following Model

Abdollahzade

Kazemi

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The performance of SSA was evaluated under both normal (non-incident) and abnormal (incident) traffic conditions using data from a corridor in Central London. Kazemi et al [ 92 ] employed the recursive SSA technique to process traffic state data in an online manner and used denoised traffic state measurements for microscopic time-variant car-following behavior simulation. A practical validation of real-world traffic data collected at the Hollywood freeway section of the US 101 highway was conducted.…”

Section: Decomposition-reconstruction-based Hybrid Modelsmentioning

confidence: 99%

Survey of Decomposition-Reconstruction-Based Hybrid Approaches for Short-Term Traffic State Forecasting

Chen

Wang

Hua

et al. 2022

Sensors

View full text Add to dashboard Cite

Traffic state prediction provides key information for intelligent transportation systems (ITSs) for proactive traffic management, the importance of which has become the reason for the tremendous number of research papers in this field. Over the last few decades, the decomposition-reconstruction (DR) hybrid models have been favored by numerous researchers to provide a more robust framework for short-term traffic state prediction for ITSs. This study surveyed DR-based works for short-term traffic state forecasting that were reported in the past circa twenty years, particularly focusing on how decomposition and reconstruction strategies could be utilized to enhance the predictability and interpretability of basic predictive models of traffic parameters. The reported DR-based models were classified and their applications in this area were scrutinized. Discussion and potential future directions are also provided to support more sophisticated applications. This work offers modelers suggestions and helps to choose appropriate decomposition and reconstruction strategies in their research and applications.

show abstract

“…[5] applied Radial Basis Function (RBF) and Back Propagation (BP) to short-term time series traffic volume prediction. While Kazemi and Abdollahzade [6] proposed local linear neurofuzzy model that is trained offline and adapted to online data using weighted least squares. Another approach by [7] implemented fuzzy-neural model (FNM) to predict the traffic flows in an urban network.…”

Section: Review Of Existing Techniquesmentioning

confidence: 99%

Time Aware Hybrid Hidden Markov Models for Traffic Congestion Prediction

Zaki¹,

Ali-Eldin²,

Hussein³

et al. 2019

IJEEI

View full text Add to dashboard Cite

Traffic Congestion is a socioeconomic problem that swelled in the past few decades. Intelligent Transportation Systems (ITS) has become the cutting edge solution to most traffic problems. One of the important problems is the prediction of the incoming traffic pattern. There are a number of available approaches for traffic congestion prediction. One approach using NeuroFuzzy is discussed here. The approach is modified into a hybrid one using Hidden Markov Models (HMM). HMM is implemented to take into consideration time factor. It is used to select the right NeuroFuzzy network suitable for this particular time period for efficient congestion prediction. The novelty in this research is: 1) showing that the right choice of traffic pattern for training affects the quality of the prediction dramatically. 2) The results from the hybrid model showing 6% MAE rate which outperforms the standard standalone NeuroFuzzy approach of 15% error.

show abstract

An adaptive framework to enhance microscopic traffic modelling: an online neuro-fuzzy approach

Cited by 6 publications

References 27 publications

An Intelligent Evolving Car-Following Model

An Intelligent Evolving Car-Following Model

Survey of Decomposition-Reconstruction-Based Hybrid Approaches for Short-Term Traffic State Forecasting

Time Aware Hybrid Hidden Markov Models for Traffic Congestion Prediction

Contact Info

Product

Resources

About