Shiliang Sun

A bayesian network approach to traffic flow forecasting

A new approach based on Bayesian networks for traffic flow forecasting is proposed. In this paper, traffic flows among adjacent road links in a transportation network are modeled as a Bayesian network. The joint probability distribution between the cause nodes (data utilized for forecasting) and the effect node (data to be forecasted) in a constructed Bayesian network is described as a Gaussian mixture model (GMM) whose parameters are estimated via the competitive expectation maximization (CEM) algorithm. Finally, traffic flow forecasting is performed under the criterion of minimum mean square error (mmse). The approach departs from many existing traffic flow forecasting models in that it explicitly includes information from adjacent road links to analyze the trends of the current link statistically. Furthermore, it also encompasses the issue of traffic flow forecasting when incomplete data exist. Comprehensive experiments on urban vehicular traffic flow data of Beijing and comparisons with several other methods show that the Bayesian network is a very promising and effective approach for traffic flow modeling and forecasting, both for complete data and incomplete data

The Selective Random Subspace Predictor for Traffic Flow Forecasting

Traffic flow forecasting is an important issue for the application of Intelligent Transportation Systems. Due to practical limitations, traffic flow data may be incomplete (partially missing or substantially contaminated by noises), which will aggravate the difficulties for traffic flow forecasting. In this paper, a new approach, termed the selective random subspace predictor (SRSP), is developed, which is capable of implementing traffic flow forecasting effectively whether incomplete data exist or not. It integrates the entire spatial and temporal traffic flow information in a transportation network to carry out traffic flow forecasting. To forecast the traffic flow at an object road link, the Pearson correlation coefficient is adopted to select some candidate input variables that compose the selective input space. Then, a number of subsets of the input variables in the selective input space are randomly selected to, respectively, serve as specific inputs for prediction. The multiple outputs are combined through a fusion methodology to make final decisions. Both theoretical analysis and experimental results demonstrate the effectiveness and robustness of the SRSP for traffic flow forecasting, whether for complete data or for incomplete data

Traffic flow forecasting using a spatio-temporal Bayesian network predictor

A novel predictor for traffic flow forecasting, namely spatiotemporal Bayesian network predictor, is proposed. Unlike existing methods, our approach incorporates all the spatial and temporal information available in a transportation network to carry our traffic flow forecasting of the current site. The Pearson correlation coefficient is adopted to rank the input variables (traffic flows) for prediction, and the best-first strategy is employed to select a subset as the cause nodes of a Bayesian network. Given the derived cause nodes and the corresponding effect node in the spatio-temporal Bayesian network, a Gaussian Mixture Model is applied to describe the statistical relationship between the input and output. Finally, traffic flow forecasting is performed under the criterion of Minimum Mean Square Error (M.M.S.E.). Experimental results with the urban vehicular flow data of Beijing demonstrate the effectiveness of our presented spatio-temporal Bayesian network predictor.

A Bayesian network approach to time series forecasting of short-term traffic flows

A novel approach based on Bayesian networks for short-term traffic flow forecasting is proposed. A Bayesian network is originally used to model the causal relationship of time series of traffic flows among a chosen link and its adjacent links in a road network. Then, a Gaussian mixture model (GMM), whose parameters are estimated through competitive expectation maximization (CEM) algorithm, is applied to approximate the joint probability distribution of all nodes in the constructed Bayesian network. Finally, traffic flow forecasting of the current link is performed under the rule of minimum mean square error (MMSE). To further improve the forecasting performance, principal component analysis (PCA) is also adopted before carrying out the CEM algorithm. Experiments show that, by using a Bayesian network for short-term traffic flow forecasting, one can improve the forecasting accuracy significantly, and that the Bayesian network is an attractive forecasting method for such kinds of forecasting problems.

Short-term traffic flow forecasting using Sampling Markov Chain method with incomplete data

Short-term traffic flow forecasting is an important problem in the research area of intelligent transportation system. In practical situations, flow data may be incomplete, that is, partially missing or unavailable, where few methods could implement forecasting successfully. A method called Sampling Markov Chain is proposed to deal with this circumstance. In this paper, the traffic flow is modeled as a high order Markov Chain; and the transition probability from one state to the other state is approximated by Gaussian Mixture Model (GMM) whose parameters are estimated with Competitive Expectation Maximum (CEM) algorithm. The incomplete data in forecasting the trend of Markov Chain is represented by enough points sampled using the idea of Monte Carlo integration. Experimental results show that the Sampling Markov Chain method is applicable and effective for short-term traffic flow forecasting in case of incomplete data.

Assessing features for electroencephalographic signal categorization

The classification of electroencephalographic (EEG) signals is an important issue in the ongoing research of brain-computer interface (BCI) technology. One such BCI uses slow cortical potential measures to infer user intent from the original brain activity. Seven features based on the standard low-level signal properties are evaluated for their ability to classify brain activities, and thus make up for the scarcity of signal features for the current EEG signal categorization. In addition, a paradigm is proposed to select effective low-level features for EEG signal classification. Combining the features selected by the paradigm with the DC value of slow cortical potentials for categorization based on a Bayesian classifier, we obtained significant improvement on classification accuracy for data set Ia of the BCI competition 2003, which is a typical representative of one kind of BCI data.

Learning on-line classification via decorrelated LMS algorithm: application to brain-computer interfaces

The classification of time-varying neurophysiological signals, e.g., electroencephalogram (EEG) signals, advances the requirement of adaptability for classifiers. In this paper we address the challenge of neurophysiological signal classification arising from brain-computer interface (BCI) applications and propose an on-line classifier designed via the decorrelated least mean square (LMS) algorithm. Based on a Bayesian classifier with Gaussian mixture models, we derive the general formulation of gradient descent algorithms under the criterion of LMS. Further, to accelerate convergence, the decorrelated gradient instead of the instantaneous gradient is adopted for updating the parameters of the classifier adaptively. Utilizing the presented classifier for the off-line analysis of practical classification tasks in brain-computer interface applications shows its effectiveness and robustness compared to the stochastic gradient descent classifier which uses the instantaneous gradient directly.

Bayesian network methods for traffic flow forecasting with incomplete data

Traffic flow forecasting is an important issue in the field of Intelligent Transportation Systems. Due to practical limitations, traffic flows recorded can be partially missing or unavailable. In this case few methods can deal with forecasting successfully. In this paper two methods based on the concept of Bayesian networks are originally proposed to cope with this matter. A Bayesian network model and a two-step Bayesian network model are constructed respectively to describe the causal relationship among traffic flows, and then the joint probability distribution between the cause and effect nodes with its dimension reduced by Principal Component Analysis is approximated through a Gaussian Mixture Model. The parameters of the Gaussian Mixture Model are learned through the Competitive EM algorithm. Experiments show that the proposed Bayesian network methods are applicable and effective for traffic flow forecasting with incomplete data.

Short-Term Traffic Flow Forecasting Using Expanded Bayesian Network for Incomplete Data

In this paper expanded Bayesian network method for short-term traffic flow forecasting in case of incomplete data is proposed. Expanded Bayesian network model is constructed to describe the causal relationship among traffic flows, and then the joint probability distribution between the cause and effect nodes with dimension reduced by Principal Component Analysis (PCA) is approximated through Gaussian Mixture Model (GMM). The parameters of the GMM are learned through Competitive EM algorithm. Experiments show that the expanded Bayesian network method is appropriate and effective for short-term traffic flow forecasting with incomplete data.

On the on-line learning algorithms for EEG signal classification in brain computer interfaces

The on-line update of classifiers is an important concern for categorizing the time-varying neurophysiological signals used in brain computer interfaces, e.g. classification of electroencephalographic (EEG) signals. However, up to the present there is not much work dealing with this issue. In this paper, we propose to use the idea of gradient decorrelation to develop the existent basic Least Mean Square (LMS) algorithm for the on-line learning of Bayesian classifiers employed in brain computer interfaces. Under the framework of Gaussian mixture model, we give the detailed representation of Decorrelated Least Mean Square (DLMS) algorithm for updating Bayesian classifiers. Experimental results of off-line analysis for classification of real EEG signals show the superiority of the on-line Bayesian classifier using DLMS algorithm to that using LMS algorithm.