http://ieeexplore.ieee.org TOC Alert for Publication# 6979 2013 May 21 14 1 C1 C4 52 14 1 C2 C2 137 14 1 1 12 1340 14 1 13 21 832 14 1 22 33 1660 $khbox{NN}$ and extended Kalman filter (EKF)-trained ANN positioning algorithms. Moreover, the presented ANN structures replace not only the positioning algorithms but the overloaded map-matching process as well.]]> 14 1 34 46 1796 14 1 47 55 1535 14 1 56 68 1065 14 1 69 81 1364 14 1 82 97 1672 14 1 98 112 2474 14 1 113 123 1060 14 1 124 135 801 14 1 136 145 484 14 1 146 154 719 14 1 155 168 1607 14 1 169 179 310 14 1 180 188 543 14 1 189 198 1163 14 1 199 213 1145 14 1 214 224 1426 14 1 225 235 1088 14 1 236 248 1666 14 1 249 261 1672 14 1 262 273 2158 14 1 274 283 1278 14 1 284 294 817 14 1 295 302 967 $^{circ}$ in day and night driving.]]> 14 1 303 312 886 14 1 313 321 983 $k$-nearest neighbors (kNNs), multiple-layer perceptrons (MLPs), support vector machines (SVMs), and random forest. The classification reliability is further enhanced by a second classifier ensemble, which is composed of a set of base MLPs coordinated by an ensemble metalearning method called rotation forest (RF). For both of the ensembles, rejection option is accomplished by relating the consensus degree from majority voting to a confidence measure and by abstaining to classify ambiguous samples if the consensus degree is lower than a threshold. The final class label is assigned by dual majority voting from the two ensembles. Experimental results using more than 600 images from a variety of 21 makes of cars and vans demonstrated the effectiveness of the proposed approach. The cascade ensembles produce consistently reliable results. With a moderate ensemble size of 25 in the second ensemble, the two-stage classification scheme offers 98.65% accuracy with a rejection rate of 2.5%, exhibiting promising potential for real-world applications.]]> 14 1 322 332 744 14 1 333 347 1465 14 1 348 359 2066 $i$ and $j$ a probability of a successful transfer from $i$ to $j$. If a transfer between two legs is unsuccessful, the customer needs to reconsider the remaining path to the destination. The problem is modeled as a Markov decision process, and the main contribution is a backward induction algorithm that generates an optimal policy for traversing the public transport network in terms of a given objective, e.g., reliability, ride time, waiting time, walking time, or the number of transfers. A straightforward method for maximizing reliability is also suggested, and the algorithms are tested on real-life Helsinki area public transport data. Computational examples show that, with a given input, the proposed algorithms rapidly solve the journeying problem.]]> 14 1 360 369 270 14 1 370 379 713 14 1 380 387 397 14 1 388 397 1398 14 1 398 407 1118 14 1 408 418 2534 14 1 419 427 1148 14 1 428 437 771 14 1 438 447 770 14 1 448 458 1094 $pm$ 13.1, clearly outperforming other state-of-the-art methods. Including road shape information improves road detection results over existing appearance-based methods. Finally, it is shown that invariant features and temporal information provide robustness against disturbing imaging conditions.]]> 14 1 459 468 2341 $hbox{CO}_{2}$ emissions using intelligent transportation system (ITS) technologies. In the proposed model, traffic data that were collected by ITS are fully utilized to estimate detailed vehicle technology data (e.g., vehicle type) and driving pattern data (e.g., speed, acceleration, and road slope) in the road network. The road network is divided into a set of small road segments to consider the effects of heterogeneous speeds within a road link. A real-world case study in Beijing, China, is carried out to demonstrate the applicability of the proposed model. The spatiotemporal distributions of $ hbox{CO}_{2}$ emissions in Beijing are analyzed and discussed. The results of the case study indicate that ITS technologies can be a useful tool for real-time estimations of $hbox{CO}_{2}$ emissions with a high spatiotemporal resolution.]]> 14 1 469 479 953 14 1 480 485 166 14 1 485 491 1231 14 1 492 498 750 14 1 499 499 592 14 1 500 500 678 14 1 C3 C3 120