http://ieeexplore.ieee.org TOC Alert for Publication# 5326 2013 February 26 42 6 C1 4 92 42 6 C2 C2 135 42 6 790 808 516 42 6 809 824 1683 42 6 825 836 584 42 6 837 853 743 42 6 854 864 607 42 6 865 878 693 42 6 879 888 1035 42 6 889 898 1079 42 6 899 912 3498 42 6 913 925 790 42 6 926 933 506 42 6 934 946 1000 42 6 947 956 822 42 6 957 969 855 42 6 970 982 1329 42 6 983 993 808 42 6 994 1002 746 42 6 1003 1010 372 42 6 1011 1020 386 42 6 1021 1030 888 42 6 1031 1041 1259 42 6 1042 1053 676 42 6 1054 1070 1386 42 6 1071 1080 889 42 6 1081 1092 2545 42 6 1093 1102 902 42 6 1103 1119 2424 42 6 1120 1127 596 42 6 1128 1134 722 42 6 1135 1139 638 42 6 1140 1141 131 42 6 1142 1151 877 42 6 1152 1158 664 42 6 1159 1168 1038 42 6 1169 1179 1496 42 6 1180 1189 1417 42 6 1190 1203 1084 42 6 1204 1218 937 42 6 1219 1230 605 42 6 1231 1242 497 42 6 1243 1256 307 42 6 1257 1272 615 42 6 1273 1290 386 42 6 1291 1307 955 42 6 1308 1317 1090 42 6 1318 1325 723 42 6 1326 1340 1504 42 6 1341 1353 849 42 6 1354 1364 548 42 6 1365 1373 950 42 6 1374 1383 709 42 6 1384 1399 938 42 6 1400 1411 691 42 6 1412 1423 1353 42 6 1424 1438 1155 42 6 1439 1453 1979 42 6 1454 1464 771 42 6 1465 1477 927 42 6 1478 1490 822 42 6 1491 1499 1033 42 6 1500 1509 1286 42 6 1510 1518 723 42 6 1519 1530 1113 42 6 1531 1542 1334 42 6 1543 1554 2172 42 6 1555 1565 1176 42 6 1566 1578 993 42 6 1579 1589 690 42 6 1590 1599 748 42 6 1600 1612 1097 42 6 1613 1623 668 42 6 1624 1632 2228 42 6 1633 1643 1030 42 6 1644 1655 2218 42 6 1656 1668 662 42 6 1669 1678 963 k-nearest neighbors, respectively, for phase identification of microdrill bits. The experimental results demonstrate that using low enlargement and resolution microdrill bit images the proposed method can measure up to high inspection accuracy, and provide a conclusion that the highest identification rates are obtained by PCA-SVMs, which are higher than that of the conventional method.]]> 42 6 1679 1689 771 k -means. Our experimental results establish that our method is able to spot the execution of an exploit, with a cumulative detection rate of over 90%. In addition, we propose an entropy-based approach that speeds up the construction of a profile for ordinary system behavior.]]> 42 6 1690 1704 3078 42 6 1705 1715 1126 42 6 1716 1729 1305 42 6 1730 1741 879 Q-learning algorithm is implemented to minimize the active power loss while satisfying operational constraints. The proposed method does not require accurate system model and can learn from scratch. Simulation studies with power systems of different sizes show that the method is very computationally efficient and able to provide near-optimal solutions. It can be observed that prior knowledge can significantly speed up the learning process and decrease the occurrences of undesirable disturbances. The proposed method has good potential for online implementation.]]> 42 6 1742 1751 686 42 6 1752 1762 868 42 6 1763 1771 1315 42 6 1772 1783 890 42 6 1784 1796 6698 42 6 1797 1805 446 42 6 1806 1817 1451 42 6 1818 1827 698 42 6 1828 1841 1059 42 6 1842 1853 1889 42 6 1854 1859 510 42 6 1860 1860 262 42 6 1861 1861 205 42 6 1862 1862 1156 42 6 1863 1884 427 42 6 C3 C3 28 42 6 C4 C4 36