API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Jul 14th, 2017
530
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 15.20 KB | None | 0 0
raw download clone embed print report
  1. "relations": [
  2.  
  3. {
  4.  
  5. "type": "memberOf",
  6.  
  7. "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
  8.  
  9. "score": 0.353495,
  10.  
  11. "arguments": [
  12.  
  13. {
  14.  
  15. "text": "Patients",
  16.  
  17. "entities": [
  18.  
  19. {
  20.  
  21. "type": "Person",
  22.  
  23. "text": "Patients"
  24.  
  25. }
  26.  
  27. ]
  28.  
  29. },
  30.  
  31. {
  32.  
  33. "text": "Classify Liver Cancer",
  34.  
  35. "entities": [
  36.  
  37. {
  38.  
  39. "type": "Organization",
  40.  
  41. "text": "Classify Liver Cancer"
  42.  
  43. }
  44.  
  45. ]
  46.  
  47. }
  48.  
  49. ]
  50.  
  51. },
  52.  
  53. {
  54.  
  55. "type": "educatedAt",
  56.  
  57. "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
  58.  
  59. "score": 0.284405,
  60.  
  61. "arguments": [
  62.  
  63. {
  64.  
  65. "text": "Tom Wenska",
  66.  
  67. "entities": [
  68.  
  69. {
  70.  
  71. "type": "Person",
  72.  
  73. "text": "Tom Wenska2"
  74.  
  75. }
  76.  
  77. ]
  78.  
  79. },
  80.  
  81. {
  82.  
  83. "text": "University of Hawaii",
  84.  
  85. "entities": [
  86.  
  87. {
  88.  
  89. "type": "Organization",
  90.  
  91. "text": "University of Hawaii"
  92.  
  93. }
  94.  
  95. ]
  96.  
  97. }
  98.  
  99. ]
  100.  
  101. },
  102.  
  103. {
  104.  
  105. "type": "partOf",
  106.  
  107. "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
  108.  
  109. "score": 0.463644,
  110.  
  111. "arguments": [
  112.  
  113. {
  114.  
  115. "text": "University of Hawaii",
  116.  
  117. "entities": [
  118.  
  119. {
  120.  
  121. "type": "Organization",
  122.  
  123. "text": "University of Hawaii"
  124.  
  125. }
  126.  
  127. ]
  128.  
  129. },
  130.  
  131. {
  132.  
  133. "text": "Cancer Research Center",
  134.  
  135. "entities": [
  136.  
  137. {
  138.  
  139. "type": "Organization",
  140.  
  141. "text": "Cancer Research Center"
  142.  
  143. }
  144.  
  145. ]
  146.  
  147. }
  148.  
  149. ]
  150.  
  151. },
  152.  
  153. {
  154.  
  155. "type": "basedIn",
  156.  
  157. "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
  158.  
  159. "score": 0.695919,
  160.  
  161. "arguments": [
  162.  
  163. {
  164.  
  165. "text": "University of Hawaii",
  166.  
  167. "entities": [
  168.  
  169. {
  170.  
  171. "type": "Organization",
  172.  
  173. "text": "University of Hawaii"
  174.  
  175. }
  176.  
  177. ]
  178.  
  179. },
  180.  
  181. {
  182.  
  183. "text": "Manoa",
  184.  
  185. "entities": [
  186.  
  187. {
  188.  
  189. "type": "GeopoliticalEntity",
  190.  
  191. "text": "Manoa"
  192.  
  193. }
  194.  
  195. ]
  196.  
  197. }
  198.  
  199. ]
  200.  
  201. },
  202.  
  203. {
  204.  
  205. "type": "locatedAt",
  206.  
  207. "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
  208.  
  209. "score": 0.539062,
  210.  
  211. "arguments": [
  212.  
  213. {
  214.  
  215. "text": "Manoa",
  216.  
  217. "entities": [
  218.  
  219. {
  220.  
  221. "type": "GeopoliticalEntity",
  222.  
  223. "text": "Manoa"
  224.  
  225. }
  226.  
  227. ]
  228.  
  229. },
  230.  
  231. {
  232.  
  233. "text": "USA",
  234.  
  235. "entities": [
  236.  
  237. {
  238.  
  239. "type": "GeopoliticalEntity",
  240.  
  241. "text": "USA"
  242.  
  243. }
  244.  
  245. ]
  246.  
  247. }
  248.  
  249. ]
  250.  
  251. },
  252.  
  253. {
  254.  
  255. "type": "agentOf",
  256.  
  257. "sentence": "We vectorize the output of the wavelet and construct a new matrix by replacing each column of the original data matrix with the vectorized form of the wavelet coefficients.",
  258.  
  259. "score": 0.55659,
  260.  
  261. "arguments": [
  262.  
  263. {
  264.  
  265. "text": "We",
  266.  
  267. "entities": [
  268.  
  269. {
  270.  
  271. "type": "Organization",
  272.  
  273. "text": "We"
  274.  
  275. }
  276.  
  277. ]
  278.  
  279. },
  280.  
  281. {
  282.  
  283. "text": "replacing",
  284.  
  285. "entities": [
  286.  
  287. {
  288.  
  289. "type": "EventPersonnel",
  290.  
  291. "text": "replacing"
  292.  
  293. }
  294.  
  295. ]
  296.  
  297. }
  298.  
  299. ]
  300.  
  301. },
  302.  
  303. {
  304.  
  305. "type": "agentOf",
  306.  
  307. "sentence": "We vectorize the output of the wavelet and construct a new matrix by replacing each column of the original data matrix with the vectorized form of the wavelet coefficients.",
  308.  
  309. "score": 0.581557,
  310.  
  311. "arguments": [
  312.  
  313. {
  314.  
  315. "text": "matrix",
  316.  
  317. "entities": [
  318.  
  319. {
  320.  
  321. "type": "Person",
  322.  
  323. "text": "matrix"
  324.  
  325. }
  326.  
  327. ]
  328.  
  329. },
  330.  
  331. {
  332.  
  333. "text": "replacing",
  334.  
  335. "entities": [
  336.  
  337. {
  338.  
  339. "type": "EventPersonnel",
  340.  
  341. "text": "replacing"
  342.  
  343. }
  344.  
  345. ]
  346.  
  347. }
  348.  
  349. ]
  350.  
  351. },
  352.  
  353. {
  354.  
  355. "type": "hasAttribute",
  356.  
  357. "sentence": "It is shown that the expansion and compression of data leads to a better neural network model to classify the liver cancer patients.",
  358.  
  359. "score": 0.90168,
  360.  
  361. "arguments": [
  362.  
  363. {
  364.  
  365. "text": "patients",
  366.  
  367. "entities": [
  368.  
  369. {
  370.  
  371. "type": "Person",
  372.  
  373. "text": "patients"
  374.  
  375. }
  376.  
  377. ]
  378.  
  379. },
  380.  
  381. {
  382.  
  383. "text": "liver cancer",
  384.  
  385. "entities": [
  386.  
  387. {
  388.  
  389. "type": "HealthCondition",
  390.  
  391. "text": "liver cancer"
  392.  
  393. }
  394.  
  395. ]
  396.  
  397. }
  398.  
  399. ]
  400.  
  401. },
  402.  
  403. {
  404.  
  405. "type": "residesIn",
  406.  
  407. "sentence": "In Section IIA, the survival time analysis is used to classify the patients.",
  408.  
  409. "score": 0.378734,
  410.  
  411. "arguments": [
  412.  
  413. {
  414.  
  415. "text": "patients",
  416.  
  417. "entities": [
  418.  
  419. {
  420.  
  421. "type": "Person",
  422.  
  423. "text": "patients"
  424.  
  425. }
  426.  
  427. ]
  428.  
  429. },
  430.  
  431. {
  432.  
  433. "text": "Section IIA",
  434.  
  435. "entities": [
  436.  
  437. {
  438.  
  439. "type": "GeopoliticalEntity",
  440.  
  441. "text": "Section IIA"
  442.  
  443. }
  444.  
  445. ]
  446.  
  447. }
  448.  
  449. ]
  450.  
  451. },
  452.  
  453. {
  454.  
  455. "type": "residesIn",
  456.  
  457. "sentence": "In Section IIC, a neural network model is trained to classify the patients.",
  458.  
  459. "score": 0.355952,
  460.  
  461. "arguments": [
  462.  
  463. {
  464.  
  465. "text": "patients",
  466.  
  467. "entities": [
  468.  
  469. {
  470.  
  471. "type": "Person",
  472.  
  473. "text": "patients"
  474.  
  475. }
  476.  
  477. ]
  478.  
  479. },
  480.  
  481. {
  482.  
  483. "text": "Section IIC",
  484.  
  485. "entities": [
  486.  
  487. {
  488.  
  489. "type": "GeopoliticalEntity",
  490.  
  491. "text": "Section IIC"
  492.  
  493. }
  494.  
  495. ]
  496.  
  497. }
  498.  
  499. ]
  500.  
  501. },
  502.  
  503. {
  504.  
  505. "type": "agentOf",
  506.  
  507. "sentence": "We describe how the parameters of the neural network model are optimized.",
  508.  
  509. "score": 0.964451,
  510.  
  511. "arguments": [
  512.  
  513. {
  514.  
  515. "text": "We",
  516.  
  517. "entities": [
  518.  
  519. {
  520.  
  521. "type": "Organization",
  522.  
  523. "text": "We"
  524.  
  525. }
  526.  
  527. ]
  528.  
  529. },
  530.  
  531. {
  532.  
  533. "text": "describe",
  534.  
  535. "entities": [
  536.  
  537. {
  538.  
  539. "type": "EventCommunication",
  540.  
  541. "text": "describe"
  542.  
  543. }
  544.  
  545. ]
  546.  
  547. }
  548.  
  549. ]
  550.  
  551. },
  552.  
  553. {
  554.  
  555. "type": "productOf",
  556.  
  557. "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
  558.  
  559. "score": 0.717205,
  560.  
  561. "arguments": [
  562.  
  563. {
  564.  
  565. "text": "Data\nExpansion",
  566.  
  567. "entities": [
  568.  
  569. {
  570.  
  571. "type": "Product",
  572.  
  573. "text": "Data\nExpansion"
  574.  
  575. }
  576.  
  577. ]
  578.  
  579. },
  580.  
  581. {
  582.  
  583. "text": "Classify Liver Cancer",
  584.  
  585. "entities": [
  586.  
  587. {
  588.  
  589. "type": "Organization",
  590.  
  591. "text": "Classify Liver Cancer"
  592.  
  593. }
  594.  
  595. ]
  596.  
  597. }
  598.  
  599. ]
  600.  
  601. },
  602.  
  603. {
  604.  
  605. "type": "basedIn",
  606.  
  607. "sentence": "In Section II-D, we show the numerical results obtained through simulation evaluations.",
  608.  
  609. "score": 0.55049,
  610.  
  611. "arguments": [
  612.  
  613. {
  614.  
  615. "text": "we",
  616.  
  617. "entities": [
  618.  
  619. {
  620.  
  621. "type": "Organization",
  622.  
  623. "text": "We"
  624.  
  625. }
  626.  
  627. ]
  628.  
  629. },
  630.  
  631. {
  632.  
  633. "text": "Section II-D",
  634.  
  635. "entities": [
  636.  
  637. {
  638.  
  639. "type": "GeopoliticalEntity",
  640.  
  641. "text": "Section II-D"
  642.  
  643. }
  644.  
  645. ]
  646.  
  647. }
  648.  
  649. ]
  650.  
  651. },
  652.  
  653. {
  654.  
  655. "type": "hasAttribute",
  656.  
  657. "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
  658.  
  659. "score": 0.605721,
  660.  
  661. "arguments": [
  662.  
  663. {
  664.  
  665. "text": "We",
  666.  
  667. "entities": [
  668.  
  669. {
  670.  
  671. "type": "Person",
  672.  
  673. "text": "We"
  674.  
  675. }
  676.  
  677. ]
  678.  
  679. },
  680.  
  681. {
  682.  
  683. "text": "liver cancer",
  684.  
  685. "entities": [
  686.  
  687. {
  688.  
  689. "type": "HealthCondition",
  690.  
  691. "text": "liver cancer"
  692.  
  693. }
  694.  
  695. ]
  696.  
  697. }
  698.  
  699. ]
  700.  
  701. },
  702.  
  703. {
  704.  
  705. "type": "hasAttribute",
  706.  
  707. "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
  708.  
  709. "score": 0.898158,
  710.  
  711. "arguments": [
  712.  
  713. {
  714.  
  715. "text": "patients",
  716.  
  717. "entities": [
  718.  
  719. {
  720.  
  721. "type": "Person",
  722.  
  723. "text": "patients"
  724.  
  725. }
  726.  
  727. ]
  728.  
  729. },
  730.  
  731. {
  732.  
  733. "text": "liver cancer",
  734.  
  735. "entities": [
  736.  
  737. {
  738.  
  739. "type": "HealthCondition",
  740.  
  741. "text": "liver cancer"
  742.  
  743. }
  744.  
  745. ]
  746.  
  747. }
  748.  
  749. ]
  750.  
  751. },
  752.  
  753. {
  754.  
  755. "type": "memberOf",
  756.  
  757. "sentence": "A Neural Network Model to Classify Liver Cancer Patients Using Data Expansion and Compression Ashkan Zeinalzadeh1 , Tom Wenska2 , Gordon Okimoto2 Abstract— We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data.",
  758.  
  759. "score": 0.25856,
  760.  
  761. "arguments": [
  762.  
  763. {
  764.  
  765. "text": "patients",
  766.  
  767. "entities": [
  768.  
  769. {
  770.  
  771. "type": "Person",
  772.  
  773. "text": "patients"
  774.  
  775. }
  776.  
  777. ]
  778.  
  779. },
  780.  
  781. {
  782.  
  783. "text": "groups",
  784.  
  785. "entities": [
  786.  
  787. {
  788.  
  789. "type": "Organization",
  790.  
  791. "text": "groups"
  792.  
  793. }
  794.  
  795. ]
  796.  
  797. }
  798.  
  799. ]
  800.  
  801. },
  802.  
  803. {
  804.  
  805. "type": "hasAttribute",
  806.  
  807. "sentence": "Then the data is used to train a neural network model that enables us to classify cancer patients into two different classes of high-risk and low-risk patients.",
  808.  
  809. "score": 0.922835,
  810.  
  811. "arguments": [
  812.  
  813. {
  814.  
  815. "text": "patients",
  816.  
  817. "entities": [
  818.  
  819. {
  820.  
  821. "type": "Person",
  822.  
  823. "text": "patients"
  824.  
  825. }
  826.  
  827. ]
  828.  
  829. },
  830.  
  831. {
  832.  
  833. "text": "cancer",
  834.  
  835. "entities": [
  836.  
  837. {
  838.  
  839. "type": "HealthCondition",
  840.  
  841. "text": "liver cancer"
  842.  
  843. }
  844.  
  845. ]
  846.  
  847. }
  848.  
  849. ]
  850.  
  851. },
  852.  
  853. {
  854.  
  855. "type": "employedBy",
  856.  
  857. "sentence": "Neural network models are not computationally effective for big data sets.",
  858.  
  859. "score": 0.533977,
  860.  
  861. "arguments": [
  862.  
  863. {
  864.  
  865. "text": "models",
  866.  
  867. "entities": [
  868.  
  869. {
  870.  
  871. "type": "Person",
  872.  
  873. "text": "authors"
  874.  
  875. }
  876.  
  877. ]
  878.  
  879. },
  880.  
  881. {
  882.  
  883. "text": "network",
  884.  
  885. "entities": [
  886.  
  887. {
  888.  
  889. "type": "Organization",
  890.  
  891. "text": "Neural Network Model"
  892.  
  893. }
  894.  
  895. ]
  896.  
  897. }
  898.  
  899. ]
  900.  
  901. },
  902.  
  903. {
  904.  
  905. "type": "employedBy",
  906.  
  907. "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
  908.  
  909. "score": 0.738014,
  910.  
  911. "arguments": [
  912.  
  913. {
  914.  
  915. "text": "Gordon Okimoto",
  916.  
  917. "entities": [
  918.  
  919. {
  920.  
  921. "type": "Person",
  922.  
  923. "text": "Gordon Okimoto2\nAbstract"
  924.  
  925. }
  926.  
  927. ]
  928.  
  929. },
  930.  
  931. {
  932.  
  933. "text": "USA azeinalz@nd.edu\n2",
  934.  
  935. "entities": [
  936.  
  937. {
  938.  
  939. "type": "Organization",
  940.  
  941. "text": "USA azeinalz@nd.edu\n2"
  942.  
  943. }
  944.  
  945. ]
  946.  
  947. }
  948.  
  949. ]
  950.  
  951. },
  952.  
  953. {
  954.  
  955. "type": "employedBy",
  956.  
  957. "sentence": "The techniques for resampling from data 1Ashkan Zeinalzadeh is with the Department of Electrical Engineering, University of Notre Dame, IN, USA azeinalz@nd.edu 2 Gordon Okimoto and Tom Wenska are with the Cancer Research Center, University of Hawaii at Manoa, HI, USA gordono@hawaii.edu are data dependent.",
  958.  
  959. "score": 0.528551,
  960.  
  961. "arguments": [
  962.  
  963. {
  964.  
  965. "text": "Tom Wenska",
  966.  
  967. "entities": [
  968.  
  969. {
  970.  
  971. "type": "Person",
  972.  
  973. "text": "Tom Wenska2"
  974.  
  975. }
  976.  
  977. ]
  978.  
  979. },
  980.  
  981. {
  982.  
  983. "text": "Cancer Research Center",
  984.  
  985. "entities": [
  986.  
  987. {
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!