Abstract-In many Intelligent Transportation System (ITS)applications that crowd-source data from probe vehicles, a crucial step is to accurately map the GPS trajectories to the road network in real time. This process, known as mapmatching, often needs to account for noise and sparseness of the data because (1) highly precise GPS traces are rarely available, and (2) dense trajectories are costly for live transmission and storage.We propose an online map-matching algorithm based on the Hidden Markov Model (HMM) that is robust to noise and sparseness. We focused on two improvements over existing HMM-based algorithms: (1) the use of an optimal localizing strategy, the variable sliding window (VSW) method, that guarantees the online solution quality under uncertain future inputs, and (2) the novel combination of spatial, temporal and topological information using machine learning. We evaluated the accuracy of our algorithm using field test data collected on bus routes covering urban and rural areas. Furthermore, we also investigated the relationships between accuracy and output delays in processing live input streams.In our tests on field test data, VSW outperformed the traditional localizing method in terms of both accuracy and output delay. Our results suggest that it is viable for lowlatency applications such as traffic sensing.

Abstract-The ability to accurately predict traffic speed in a large and heterogeneous road network has many useful applications, such as route guidance and congestion avoidance. In principle, data driven methods such as Support Vector Regression (SVR) can predict traffic with high accuracy, because traffic tends to exhibit regular patterns over time. However, in practice, the prediction performance can vary significantly across the network and during different time periods. Insight into those spatial and temporal trends can improve the performance of Intelligent Transportation Systems (ITS). Traditional prediction error measures such as Mean Absolute Percentage Error (MAPE) provide information about individual links in the network, but do not capture global trends. We propose unsupervised learning methods, such as k-means clustering, Principal Component Analysis (PCA), and Self Organizing Maps (SOM) to mine spatial and temporal performance trends at both network level and for individual links. We perform prediction for a large, interconnected road network, for multiple prediction horizons, with SVR based algorithm. We show the effectiveness of the proposed performance analysis methods by applying them to the prediction data of SVR.Index Terms-Large-scale network prediction, spatial and temporal error trends.

The conventional shape-from-focus (SFF) methods have inaccuracies because of piecewise constant approximation of the focused image surface (FIS). We propose a scheme for SFF based on representation of three-dimensional (3-D) FIS in terms of neural network weights. The neural networks are trained to learn the shape of the FIS that maximizes the focus measure.

No abstract

Abstract-With the development of inexpensive sensors such as GPS probes, Data Driven Intelligent Transport Systems (D 2 ITS) can acquire traffic data with high spatial and temporal resolution. The large amount of collected information can help improve the performance of ITS applications like traffic management and prediction. The huge volume of data, however, puts serious strain on the resources of these systems. Traffic networks exhibit strong spatial and temporal relationships. We propose to exploit these relationships to find low-dimensional representations of large urban networks for data compression. In this paper, we study different techniques for compressing traffic data, obtained from large urban road networks. We use Discrete Cosine Transform (DCT) and Principal Component Analysis (PCA) for 2-way network representation and Tensor Decomposition for 3-way network representation. We apply these techniques to find low-dimensional structures of large networks, and use these low-dimensional structures for data compression.