Fuzzy-Neural Network Traffic Prediction Framework with Wavelet Decomposition

Xiao, Heng; Sun, Hongyu; Ran, Bin; Oh, Yung-Hwan

doi:10.3141/1836-03

Cited by 46 publications

(31 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since early 1980s, univariate time series models, mainly Box-Jenkins Auto-Regressive Integrated Moving Average (ARIMA) [3] and Holt-Winters Exponential Smoothing (ES) models [15], [22], have been widely used in traffic prediction. In the last decade, Neural Network (NNet) models also has been extensively used in forecasting of various traffic parameters, including speed [23], [10], travel time [21], and traffic flow [19], [17]. Nowadays, ARIMA, ES and NNet models are used as benchmarking methods for short-term traffic prediction [17], [16].…”

Section: ) Data Mining Techniquesmentioning

confidence: 99%

Utilizing Real-World Transportation Data for Accurate Traffic Prediction

Pan

Demiryurek

Shahabi

2012

2012 IEEE 12th International Conference on Data Mining

170

View full text Add to dashboard Cite

Abstract-For the first time, real-time high-fidelity spatiotemporal data on transportation networks of major cities have become available. This gold mine of data can be utilized to learn about traffic behavior at different times and locations, potentially resulting in major savings in time and fuel, the two important commodities of the 21st century. As a first step towards the utilization of this data, in this paper, we study the real-world data collected from Los Angeles County transportation network in order to incorporate the data's intrinsic behavior into a time-series mining technique to enhance its accuracy for traffic prediction. In particular, we utilized the spatiotemporal behaviors of rush hours and events to perform a more accurate prediction of both shortterm and long-term average speed on road-segments, even in the presence of infrequent events (e.g., accidents). Our result shows that taking historical rush-hour behavior we can improve the accuracy of traditional predictors by up to 67% and 78% in short-term and long-term predictions, respectively. Moreover, we can incorporate the impact of an accident to improve the prediction accuracy by up to 91%.

show abstract

Section: ) Data Mining Techniquesmentioning

confidence: 99%

Utilizing Real-World Transportation Data for Accurate Traffic Prediction

Pan

Demiryurek

Shahabi

2012

2012 IEEE 12th International Conference on Data Mining

170

View full text Add to dashboard Cite

show abstract

“…Note that an SWT using the Haar does suffer from boundary problems, although minimally (2 j values at scale j are affected by the boundary). Renaud et al [18] and Xiao et al [26] suggest a "backward implemented" SWT that uses a non-symmetric Haar filter for the purpose of forecasting a series using SWT with the Haar. This implementation only uses past values of the time-series to compute coefficients.…”

Section: Prospective Monitoringmentioning

confidence: 99%

“…A similar type of model was also used by Goldenberg et al [3] to model series arising from a redundant wavelet transform of over-the-counter medication sales. Using an autoregressive model to forecast detail levels has also been suggested in other applications [e.g., 18,26]. The autoregressive model is used to forecast the coefficient (or its reconstruction) in the next point.…”

Section: Handling Scale-level Autocorrelationmentioning

confidence: 99%

Wavelet-Based Monitoring for Biosurveillance

Shmueli

2013

Axioms

View full text Add to dashboard Cite

Biosurveillance, focused on the early detection of disease outbreaks, relies on classical statistical control charts for detecting disease outbreaks. However, such methods are not always suitable in this context. Assumptions of normality, independence and stationarity are typically violated in syndromic data. Furthermore, outbreak signatures are typically of unknown patterns and, therefore, call for general detectors. We propose wavelet-based methods, which make less assumptions and are suitable for detecting abnormalities of unknown form. Wavelets have been widely used for data denoising and compression, but little work has been published on using them for monitoring. We discuss monitoring-based issues and illustrate them using data on military clinic visits in the USA

show abstract

“…The complexity revealed from the traffic measurements has led to the suggestion that the network traffic cannot be analyzed in the current framework of existing models [1][2][3]. Other reliable traffic models and tools for quality assessment and control have been developed in [4][5][6][7][8][9].…”

mentioning

confidence: 99%

“…A framework of a traffic prediction model was proposed in [8] for eliminating the noises caused by random travel conditions, where the influence of special factors was calculated quantitatively. This framework combined several artificial intelligence technologies, e.g., wavelet transform, neural network, and fuzzy logic.…”

mentioning

confidence: 99%

Ensemble of Flexible Neural Tree and Ordinary Differential Equations for Small-time Scale Network Traffic Prediction

Yang¹,

Jiang²,

Chen³

et al. 2013

JCP

View full text Add to dashboard Cite

Abstract-Accurate models play important roles in capturing the salient characteristics of the network traffic, analyzing and simulating for the network dynamic, and improving the predictive ability for system dynamics. In this study, the ensemble of the flexible neural tree (FNT) and system models expressed by the ordinary differential equations (ODEs) is proposed to further improve the accuracy of time series forecasting. Firstly, the additive tree model is introduced to represent more precisely ODEs for the network dynamics. Secondly, the structures and parameters of FNT and the additive tree model are optimized based on the Genetic Programming (GP) and the Particle Swarm Optimization algorithm (PSO). Finally, the expected level of performance is verified by using the proposed method, which provides a reliable forecast model for small-time scale network traffic. Experimental results reveal that the proposed method is able to estimate the small-time scale network traffic measurement data with decent accuracy.Index Terms-hybrid evolutionary method, small-time scale network traffic, the additive tree models, ordinary differential equations, ensemble learning

show abstract

Fuzzy-Neural Network Traffic Prediction Framework with Wavelet Decomposition

Cited by 46 publications

References 16 publications

Utilizing Real-World Transportation Data for Accurate Traffic Prediction

Utilizing Real-World Transportation Data for Accurate Traffic Prediction

Wavelet-Based Monitoring for Biosurveillance

Ensemble of Flexible Neural Tree and Ordinary Differential Equations for Small-time Scale Network Traffic Prediction

Contact Info

Product

Resources

About