Young-Seon Jeong

Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions

Most literature on short-term traffic flow forecasting focused mainly on normal, or non-incident, conditions and, hence, limited their applicability when traffic flow forecasting is most needed, i.e., incident and atypical conditions. Accurate prediction of short-term traffic flow under atypical conditions, such as vehicular crashes, inclement weather, work zone, and holidays, is crucial to effective and proactive traffic management systems in the context of intelligent transportation systems (ITS) and, more specifically, dynamic traffic assignment (DTA). To this end, this paper presents an application of a supervised statistical learning technique called Online Support Vector machine for Regression, or OL-SVR, for the prediction of short-term freeway traffic flow under both typical and atypical conditions. The OL-SVR model is compared with three well-known prediction models including Gaussian maximum likelihood (GML), Holt exponential smoothing, and artificial neural net models. The resultant performance comparisons suggest that GML, which relies heavily on the recurring characteristics of day-to-day traffic, performs slightly better than other models under typical traffic conditions, as demonstrated by previous studies. Yet OL-SVR is the best performer under non-recurring atypical traffic conditions. It appears that for deployed ITS systems that gear toward timely response to real-world atypical and incident situations, OL-SVR may be a better tool than GML.

Weighted dynamic time warping for time series classification

Dynamic time warping (DTW), which finds the minimum path by providing non-linear alignments between two time series, has been widely used as a distance measure for time series classification and clustering. However, DTW does not account for the relative importance regarding the phase difference between a reference point and a testing point. This may lead to misclassification especially in applications where the shape similarity between two sequences is a major consideration for an accurate recognition. Therefore, we propose a novel distance measure, called a weighted DTW (WDTW), which is a penalty-based DTW. Our approach penalizes points with higher phase difference between a reference point and a testing point in order to prevent minimum distance distortion caused by outliers. The rationale underlying the proposed distance measure is demonstrated with some illustrative examples. A new weight function, called the modified logistic weight function (MLWF), is also proposed to systematically assign weights as a function of the phase difference between a reference point and a testing point. By applying different weights to adjacent points, the proposed algorithm can enhance the detection of similarity between two time series. We show that some popular distance measures such as DTW and Euclidean distance are special cases of our proposed WDTW measure. We extend the proposed idea to other variants of DTW such as derivative dynamic time warping (DDTW) and propose the weighted version of DDTW. We have compared the performances of our proposed procedures with other popular approaches using public data sets available through the UCR Time Series Data Mining Archive for both time series classification and clustering problems. The experimental results indicate that the proposed approaches can achieve improved accuracy for time series classification and clustering problems.

AADT prediction using support vector regression with data-dependent parameters

Traffic volume is a fundamental variable in several transportation engineering applications. For instance, in transportation planning, the annual average daily traffic (AADT) is a primary element that has to be estimated for the year of horizon of the analysis. The huge amounts of money to be invested in designed transportation systems are strongly associated with the traffic volumes expected in the system, which means that it is important that the AADT should be accurately predicted. In this paper, a modified version of a pattern recognition technique known as support vector machine for regression (SVR) to forecast AADT is presented. The proposed methodology computes the SVR prediction parameters based on the distribution of the training data. Therefore, the proposed method is called SVR with data-dependent parameters (SVR-DP). Using 20 years of AADT for both rural and urban roads in 25 counties in the state of Tennessee, the performance of the SVR-DP was compared with those of Holt exponential smoothing (Holt-ES) and of ordinary least-square linear regression (OLS-regression). SVR-DP performed better than both methods; although the Holt-ES also presented good results.

Supervised Weighting-Online Learning Algorithm for Short-Term Traffic Flow Prediction

Prediction of short-term traffic flow has become one of the major research fields in intelligent transportation systems. Accurately estimated traffic flow forecasts are important for operating effective and proactive traffic management systems in the context of dynamic traffic assignment. For predicting short-term traffic flows, recent traffic information is clearly a more significant indicator of the near-future traffic flow. In other words, the relative significance depending on the time difference between traffic flow data should be considered. Although there have been several research works for short-term traffic flow predictions, they are offline methods. This paper presents a novel prediction model, called online learning weighted support-vector regression (OLWSVR), for short-term traffic flow predictions. The OLWSVR model is compared with several well-known prediction models, including artificial neural network models, locally weighted regression, conventional support-vector regression, and online learning support-vector regression. The results show that the performance of the proposed model is superior to that of existing models.

A Hybrid Recommendation Method with Reduced Data for Large-Scale Application

Most recommendation algorithms attempt to alleviate information overload by identifying which items a user will find worthwhile. Content-based (CB) filtering uses the features of items, whereas collaborative filtering (CF) relies on the opinions of similar customers to recommend items. In addition to these techniques, hybrid methods have also been suggested to improve the performance of recommendation algorithms. However, even though recent hybrid methods have helped to avoid certain limitations of CB and CF, scalability and sparsity are still major problems in large-scale recommendation systems. In order to overcome these problems, this paper proposes a novel hybrid recommendation algorithm HYRED, which combines CF using the modified Pearsons binary correlation coefficients with CB filtering using the generalized distance-to-boundary-based rating. In the proposed recommendation system, the nearest and farthest neighbors of a target customer are utilized to yield a reduced dataset of useful information by avoiding scalability and sparsity problem when confronted by tremendous volumes of data. The use of reduced datasets enables us not only to lessen the computing effort, but also to improve the performance of recommendations. In addition, a generalized method to combine CF and CB system into a hybrid recommendation system is proposed by developing on the normalization metric. We have used this HYRED algorithm to experiment with all possible combination of CF and statistical-learning-based CB filtering. These experiments have shown that the use of reduced datasets saves computational time, and neighbor information improves performance.

Support vector-based algorithms with weighted dynamic time warping kernel function for time series classification

In this paper, we propose support vector-based supervised learning algorithms, called multiclass support vector data description with weighted dynamic time warping kernel function (MSVDD-WDTWK) and multiclass support vector machines with weighted dynamic time warping kernel function (MSVM-WDTWK), which provides a flexible and robust kernel function for time series classification between non-aligned time series data resulting in improved accuracy. The proposed WDTW kernel function provides an optimal match between two time series data by not only allowing a non-linear mapping between two data sequences, but also considering relative significance depending on the phase difference between points on time series data. We validate the proposed approaches using extensive numerical experiments on a number of multiclass UCR time series data mining archive, and demonstrate that our proposed methods provide lower classification error rates compared with existing techniques.

A New Feature Selection Method for One-Class Classification Problems

Feature selection is a data processing method that is used to select a few important features among many input features and to remove any irrelevant one. Although feature selection in classification problems has been the focus of much research, few feature selection methods are available for use in one-class classification problems (i.e., anomaly detection). In particular, existing feature selection methods cannot be applied for the feature selection of the one-class classification problem when there are no available observations for the anomaly (or the second class). In this study, we propose two support vector data description (SVDD)-based feature selection methods: SVDD-radius-recursive feature elimination (RFE) and SVDD dual-objective RFE. The SVDD-radius-RFE method can be used to minimize the size of the boundary of describing normal observations measured through the value of its radius squared and the SVDD-dual-objective-RFE method can be applied to obtain a compact description in the dual space of SVDD. Experimental results using both simulated and real-life datasets demonstrate that the proposed methods show the improved performance compared with existing support vector machine RFE methods even for the classification problems when available observations for the anomaly are few.

Improved prediction of biomass composition for switchgrass using reproducing kernel methods with wavelet compressed FT-NIR spectra

Fourier transform near-infrared (FT-NIR) technique is an effective approach to predict chemical properties and can be applied to online monitoring in bio-energy industry. High dimensionality and collinearity of the FT-NIR spectral data makes it difficult in some applications to construct the reliable prediction model. In this study, two nonlinear kernel methods with wavelet-compressed data, Kernel Partial Least Squares (KPLS) regression and Kernel Ridge Regression (KRR), are presented to resolve those data into a few predictors and then, more sophisticated models are created to capture the nonlinear relationships between the spectral data and concentrations determined by wet chemistry. A wavelet transform is adopted as a preprocessing procedure to reduce the data size for supporting real-time implementation of assessing biomass properties with FT-NIR spectroscopy. A real-life data of switchgrass is presented to illustrate the performance of the developed models and the results advocated that the use of nonlinear kernel procedure with wavelet compression improved the prediction performance of the model.

A two-leveled symbiotic evolutionary algorithm for clustering problems

Because of its unsupervised nature, clustering is one of the most challenging problems, considered as a NP-hard grouping problem. Recently, several evolutionary algorithms (EAs) for clustering problems have been presented because of their efficiency for solving the NP-hard problems with high degree of complexity. Most previous EA-based algorithms, however, have dealt with the clustering problems given the number of clusters (K) in advance. Although some researchers have suggested the EA-based algorithms for unknown K clustering, they still have some drawbacks to search efficiently due to their huge search space. This paper proposes the two-leveled symbiotic evolutionary clustering algorithm (TSECA), which is a variant of coevolutionary algorithm for unknown K clustering problems. The clustering problems considered in this paper can be divided into two sub-problems: finding the number of clusters and grouping the data into these clusters. The two-leveled framework of TSECA and genetic elements suitable for each sub-problem are proposed. In addition, a neighborhood-based evolutionary strategy is employed to maintain the population diversity. The performance of the proposed algorithm is compared with some popular evolutionary algorithms using the real-life and simulated synthetic data sets. Experimental results show that TSECA produces more compact clusters as well as the accurate number of clusters.

Pattern Recognition Approaches for Identifying Subcortical Targets during Deep Brain Stimulation Surgery

This paper presents the approach for identifying subcortical targets during deep brain stimulation surgery.Pattern recognition approaches can help localize neural targets for therapeutic neurostimulation, such as deep brain stimulation of the subthalamic nucleus in Parkinsons disease. A variety of neurophysiological signals are routinely collected from patients with brain diseases in the hope that such signals contain meaningful patterns that reflect underlying pathological brain functions. However, little is understood about the underlying mechanisms of brain diseases because those data are often massive and noisy. Data processing tools might help extract meaningful, yet hidden, information from massive neuro physiological data for both clinical and scientific uses.