第 15 回 月例発表会 - 医療情報システム研究室
Contents
1. Fig 1 2 2 2 12. Genetic Algorithm GA 2 2 1 GA GA
3. Federation 7H 7 9 717 y Fiz AP Federation 1 Sian eee qup Va aa OptorSim ae ENU 2 Hier achical Federation Fig 1 Hybrid Bottom Up Sensor 4
4. Fig 1 2 2 2
5. watershed seeded watershed Ne PTY Virion Eig 1 RAIRA AA D l 7 ROUGE EZMCISVY CHEST CLCHPEICLOTU
6. GA 2 2 2 RAMA gt z 0 0 Vf ai k oy an k 0 d k V f ai k tn k 73 Vf FL PA 3 a k x k 1 z k a k d k k k 1 2 3 3 1 GA
7. watershed Fig 6 seeded watershed seeded watershed 3 2 watershed seed seed seeded watershed watershed seed seed 0 255 BE 1
8. 2 8VM 2 MULT Lk 0 breast cancer 3 2 3 1 Vladimir Vapnik The support vector method H of function es
9. Fig 3 Hig 3 R Genetic Algorithm GA 7 GA 2 3 2 Step 1
10. 5 UT watershed seeded watershed seeded watershed
11. C 3 2 AAD CSS DICT GLCP YE CHS Ae Cis 2 4 4 1 MRI 4 1 1 MRI MRI 4 1 2 MRI Echelon Vega 1 5T 1
12. SD 2H 1 Kazuo TSUBOTA and Shin HATO Corneal dis ease and regenerative medicine TRENDS IN THE SCIENCES Vol 15 No 7 pp 8 13 2010 2 2 Vol 1297 pp 125 135 2002 3 Vol 34 No 7 pp 871 883 1993 4 Doron BLATT Alfred HERO and Hillel GAUCH MAN A convergent incremental gradient method with a constant step size SIAM Journal on Opti mization Vol 18 No 1 pp 29 51 2007 5 Ya xiang YUAN A new stepsize for the steepest descent method Journal of Computational Mathe matics Vol 24 No 2 pp 149 56 2006 15 2012 08 24 B Sakito NUNOKAWA
13. Sequential Gaussian random walk ID e Unitary random walk ID 1 ID ID ID Random Sequen tial Random Gaussian random walk Unitary ran dom walk 4 3 ENU Za
14. ENU 5 RemoteFile Replication RemoteFile Local Repli cation Caching B kU Economic Model ENU Sequential Random 10 r o o IO r o NEN HEN V o bs o M 4r o M 4 2 o 2 o O 1 j O L 1 1 1 4 J 0 2 4 6 8 10 O 2 4 6 8 10 Gaussian Random walk Unitary Random walk lO r 10 8 o 8 TT e C o o Q o o o o 6 e o o 6 e o
15. 023 v Bd e Fig 2 GE GR GP GP Quen GP CH Fie 2
16. 10 9 569 455 269 A 186 Fig 5 2 breast cancer Table 1 Table 2 radius texture perimeter area smoothness compactness concavity concave points CO CO NE GD Ot HB WW N re symmetry fractal dimension 10 Concave points rate 15 25 30 35 40 45 texture gray scale value Fig 5 4 3 4 3 1 2 2 Texture Concave Points Fig 6 SVM Fig 7 ee grein RIEORIIC 13 FRMERRIC ROTE MN 20 0 57 130 Table 3 2
17. 2 LL L SL 2 2 2 SVM
18. 002 Eig 2 Table 1 AWA AE mm T US 17 Lmsec 3500 msec 99 T2 axial plane 4 1 3 42cm FOR 7 Fig 3 Fatiei eF TOSI 1 N Patients AgeD22Y Patients SexF Fig 3 MRI Tika amp 17 EARE fS MRI S4 4 2 4 2 1 MRI 4 2 2 Fat
19. NIRS Near Infrared Spectroscopy EEG Electroencephalograph NIRS EEG NIRS EEG EC D 2 2 2 1 DY 2 2 2 22 0 8 5
20. 10 70 75 45 36 75 x y y Fig 2 Fig 3 BLX a Standard Deviation SD SD 3 2 Fig 2 GA Table 1 Table 2 x y CHS koc Fig 2 X X BLX als Fig 3 HA di w di 0
21. Tl T2 e 2 3 2 4 MRI S N Obst UL
22. T Step 2 SVM Step3 015 Step 4 X Step 5 Step2 Step4 Am o RTE m e Hit Fig 2 o ott 1 Fig 3 3 3 n xay i Laun 2 Re yi E 1 1 5 BRT 1 0 2
23. Af 2 Caching Economic Model NoReplication 5 3 1 INo Replication No replication lk 3 2 Caching 46 Least Recently Used LRU
24. 3 3 025 S gt d V Fig 7 MIN ERASER earn BR NY SEY EY f qo Pc dE OCA EC Mia Mic YA 45295 ae fea qu AH Y F ROE AE Anni Fig 8 e P AH LO R CN mage Fig 7 4 AMOER 200 CHO GP 4 2 4 2 1 watershed seeded watershed Fig 8 Fig 8 old V seed seeded watershed merge watershed seed merge
25. O z T x y 1 0 1 Wy neus NET 1 A 1 W Wy FAK nate 255 2 3 EK step 1 3 3 1 23s CLEA CH Bs 2
26. SD Fig 5 0 80 80 80 Fig 4 40 SD Fig 7 A
27. 4 0 9 a BIZ alk 8 13Hz lk w Z vw Davidson cv 2 TAPS 9 EEG cv 4 4 1 EEG F3 F4 FFT Fast Fourier Transform cv 8 13 Hz BOW SN4ZKO Fig 2 5 F3 F4 gw Fig 2 vw
28. Federation OptroSim IBERIA YP IHF
29. in vitro BX E
30. Table 1 100 x 100 50 1 A Fig 4 SD 40 80 120 SD 160 200 3 3 SD 40 80 120 160 200 10 Fig 4 GA Fig 5 0 7 40 10 Fig 6 GA 10 3 4 3 4 1 Fig 5
31. 3 3 Economic Model Economic Model Carman 9 Economic Model EE BIA E f r Dn Economic Model f f
32. FA f f E fr n 1 E V f k n r 5 Pi f 1 1 random walk random walk MID ID 2 028 Qo CE and SE SE Fig 2 Tu TD f random walk i 2 bar_f ID S 1
33. 3 4 3 v cw AF y Wiha f a Zzz g d a f a a dk a gt 0 1 mini 6 a a gt 0 2 w 9 10 AT v Vio kot 022 ET Bin Or A
34. He Kiyofumi UEHORI GA GA 1 D 5
35. coronal plane Bone 2 H A axial plane
36. 13 29 Table 4 2 fH 4 3 2 3 3 Texture Concave Points Radius SVM 6 v CRURA 45 0 DIVA Un 31 5 017 points rate o Concave 0 006 15 20 25 30 35 45 50 texture gray scale mum Fig 6 o o o Concave points rate 0 005 15 20 25 30 40 45 50 texture gray scale value Fig 7 Table 5 3
37. Fig 9 Fig 10 5 Fig 10 Fig 9 Table 1 Table 1 Table 1 Average Table 1 image2
38. z 2 2 2 3 BXONS GP NC 4 Fig 2 LAL GP 2 Fig 2 OA
39. Table 1 image old seed merge Imagel 15 10 20 Image2 13 Image3 7 Image4 9 Average 7 12 026 merge seed seeded watershed BE CR ALBA IVS 4 GP 5 100 X 100 pixel
40. step 1 step 2 0 255 step 3 step 4 Fig 5 3 2 watershed wa tershed watershed seed seed A i i No watershed seed EA e watershed um m watershed watershed TOH SAMO Ib 7
41. 3 NoReplication LRU Economic Model Caching EconomicModel Sequential 5000 4000 3000 s 2000 1000 Unitary Sequential Random Gaussian Fig 4 Economic Model Hierachical NoRepli cation Caching Economic Model fe 4 5 2 ENU ENU Fig 5 0 9 0 8 0 7 0 6 0 5 0 4 0 3 0 2 0 1 Caching EcoModel ENU Random Gaussian Sequential Unitary Fig 5 4000 No
42. MRI MRI 1 Fat Biz Calc 1 2 MRI Magnetic Resonance Imaging 2 1 PSA OK SSR FR OO 2 i OAK B8 MRI MRI 001 Fig 1 MRI 2 2 MRI
43. coronal plane E 1 MR Echelon Vega 2008 2 http www pip club com enjoy bikyaku 2012 5 3 Scott A Huettel Functional Magnetic Resonance Imaging Sinauer Associaes Inc 2009 15 2012 08 24 l XR ZR Ayumi OHMURA aE AR MRI
44. 1 E E MRI magnetic resonance imaging MRI Ne Hts Ll 2 2 1 Pleas ant Unpleasant Neutral fMRI functional magnetic resonance imaging 2 2 Pleas
45. n 3 r 4 S r f 215 f f is 1 Pf zais 2 T MS 3 S gt fO 4L 4 4 OptorSim Effective Network Usage ENU 41 Fig 2 Table 1 rc Table 1
46. Z XY CUT Z T1 XY T2 UE D 3 3 1 REL MRI TI T2
47. 3 1 Fig 2 se T TA 014 ez 2 1 Fig 1 2 SVM 3 gt X
48. 12 3 1 5 07 10 1 1 2 Table 1 2 5 MRI RE X Fig 3 MRI ECHELON Vega 1 5 T 23 Table 2 2 6 SPM89 1 Realign 004 s Pleasant Unpleasant 3 Neutral Fig 3 MRI ECHELON Vega 1 5T 4S Fig 5 Unpleasant Slice timing Unpleasant ORLA Neutral Smoothing
49. Eo ee 45 Table 6 3 31 0 83 2 3 3 3 6
50. MRI MRI Magnetic Resonance Imaging MRI CT Computed Tomography cu 990 68
51. GA SD 5 GA GA
52. merge LPL old vA weal Sa Seed AE AX b LTY merge Aw pq ATQ SS S Se Feta Pate Paso Fig 9 GP old 4 2 2
53. 82 x nem PU c NY RI NN mY A amp lt EY Hil RES Fig 4 Fig 3 O eL mo aiu ope 1 Fig 5 Fig 4 2 us 1 watershed 2 024 seeded watershed watershed
54. 2 Hierachical 027 T J g uU Fig 1 Federation Federation Peer to Peer P2P Federation 3 ON 8 3
55. Capacity 30 GB 172 100 GB 95 300MB s Table 2 JobA 58 50 JobB 14 30 JobC 12 10 JobD 5 4906 JobE 3 3 JobF 6 3 2 Table 2 Ek 3D 1 GB Table 3
56. 24 2 10 15 18 NIRS ETG 7100 Hitachi medical Co Japan 22CH cL 10 20 EEG Polymate AP 100 TEAC Corporation NIRS 10 20 Cz F3 F4 2 3 1IAPS International Affec tive Picture System 18 1710 4599 4660 5202 5621 5700 8030 8200 8470 1300 3000 3060 3102 3150 3170 3180 6313 6570 Fig 1 18 17 145 65 145 1 Fei
57. 1 N Koizumi and et al Cultivated corneal endothelialtransplanta tion in a primate The Journal of Cornea and External Disease Vol 27 pp 48 55 2011 2 Carpenter AE and et al image analysis software for identifying and quantifying cell phenotypes Genome Biol 7 10 R100 Oct 31 2006 3 M D Abramoff and et al Image processing with imagej Biopho tonics international Volume 11 Issue 7 pp 36 42 2004 4 26 2012 SY 5 SS J Koza Genetic programming on the programming of computers by means of natural selection MIT Press 1992 6 D Hagyard and et al Analysis of watershed algorithms for greyscale images Image Processing 1996 Proceedings Inter national Conference on volume 3 41 44 1996 15 2012 08 24 H Federation RIF 56H Ryosuke FUJII
58. CH A 14 1 5 14 B 14 1 9 C 1 5 9 14 D 1 5 9 E 14 5 WRA 5 3 Fig 4 Fig 4 VLPFC ventrolateral prefrontal cortex RERESET CH Fig 4 CH5 valence valence 9 Ec IAPS Fig 5 5
59. Random Random Sequeitial Random Gaussian random walk Unitary random walk 4 Fig 3 e Sequential ID ID 1 4 2 029 Table 3 3 200 10 ms Random e Random
60. 3 1 ER oo 2 JR n 2 1 ERDRE LT ABER E CO T8 LC S eee NE L DU M Lice De eo DED LO 9 1 g
61. 3 5c SVM Support Vector Machine 2 SVM KTI 5 SVM 1 ECD ODER SVM CI 2 aes 3 4 5 3
62. 14 ee ARRAN 6 1 14 3 3 1 NIRS Oxy Hb Oxy hemoglobin Oxy Hb 9 HL CH1 5 6 10 CH4 9 8 13 3 2 EEG ORR 2 Davidson Cerebral Asymmetry 95 v2
63. Sequential Random Gaussian Unitary 6 NoRepcaliton 031 4000 NoReplication 3500 8 Caching EcoModel mp 3000 2500 c 2000 N 1500 O E 1000 oc 500 0 Sequential Random Gaussian Unitary Fig 7 Remote 4000 NoReplication m i 3500 Caching S EcoModel Di 3000 zi 2500 c 2000 D 1500 O a 1000 500 0 Sequential Random Gaussian Unitary Fig 8 Local Fig 6 Replication Fig 7 Remote
64. 107 49 17 51 Fig 5 Fig 6 120 3 4 2 Fig 5 GA 40 40 Table 3 40 GA BLX w BLX alk Table 3 100 SD mean SD 161 13 107 49 17 51 O RRRA Fig 7 Qo
65. 9 6 IAPS 5 CH NIRS EEG 1 Yoko Hoshi Jinghua Huang Shunji Kohri Yoshinobu Iguchi Masayuki Naya Takahiro Okamoto and Shuji Ono Recognition of human emotions from cerebral blood flow changes in the frontal region a study with event related near infrared spectroscopy J Neuroimag ing Vol 21 No 2 pp e94 e101 2011 2 SCHMIDT L A Frontal brain electrical activity eeg distinguishes valence and intensity of
66. Fig 2 F4 F3 gw F3 F4 Davidson 4 2 NIRS 5 Dunnett n 6 X n 9 1 OD Oxy Hb REA 2 3 4 5 6 Fig 3 C CH5 0 12 2 3 4 5 6 7 8 9 Oxy Hb mM mm eo eo A s Fig 3 Oxy Hb C Fig 3 2 Table 1 Table 1 Dunnett
67. ENU Random Gussian Economic Model Caching Replication 7 Federation Caching Economic Model NoReplication ENU 2 Caching Economic Model 23 NoRepli cation ENU Th Sequential T Caching Economic Model
68. 120 80 160 200 Fig 6 SD Table 2 GA 50 600 1 0 100 BLX a a DE 0 5 2 021 1000 800 800 700 600 500 400 300 200 100 a H 80 120 160 200 SD 40 Fig 5 GA 25000 20000 M zi 15000 10000 A 5000 0 80 120 160 200 SD 40 Fig 6 SD SD 100 Table 3
69. Economic Model Caching Federation 1 J Ferguson A P Millar C Nicholson K Stockinger F Zini D G Cameron R Schiaffino OptorSim v2 1 Installation and User Guide 2006 2 Srikumar Venugopal Rajkumar Buyya and Kota giri Ramamohanarao A Taxonomy of Data Grids for Distributed Data Sharing Management and Pro cessing ACM Computing Surveys CSUR Vol 38 2006 3 M Carman F Zini L Serafini and K Stockinger Towards an Economy Based Optimisation of File Access and Replication on a Data Grid Cluster Computing and the Grid 2002 2nd IEEE ACM In ternational Symposium on p 340 2002 032 4 A Paul Millar Luigi Capozza Kurt Stockinger William H Bell David G Cameron and Floriano Zini Optorsim A Grid Simulator for Studying Dy namic Data Replication Strategies International Journal of High Performance Computing Applica tions Vol 17 pp 403 416 2003
70. 4 4 1 3 GP RL GP 2 4 346 X 260 pixel L 100 x 100 pixell 100 x 100 pixel
71. Fig 8 Local NoReplication Replication 0 Remote 3000 Local 500 Caching Economic Model Sequential Random Replication Local ENU Economic Model Caching
72. Fig 4 0 PA gt SVM Confidence Margin na 1 0 if yf a lt 0 otherwise vts fien 1 AMA JE ZX AM k Err 3 1 k CHS 2 x Pg k D Y Flei im yis F 0 3 k maximize O k f zi myi f 2i 1 4 subject to E
73. valance rate 1 69 valance rate 2 59 valence rating 2 59 valence rating 1 69 z Oxy Hb mM mm Pr 0 01 s Fig 5 valence Fig 5 I 5 VLPFC VLPFC VLPFC Fig 5 PET
74. 1019 1050 1052 1090 Unpleasant 1110 1111 1113 1114 1120 3000 3051 1060 3068 3069 RU 3071 3100 3101 3266 3400 Table 3 REGIE FUR 2191 2214 2215 2372 2383 1 BE Neutral 2393 2394 2480 2595 7550 2 5740 7036 7041 7050 7100 7130 7161 7224 7234 7500 3 MARKA 005 Fig 6 Neutral Pleasant Unpleasant 1 Dean Sabatinelli Lang PJ Andreas Keil Bradley MM Emotional perception Correlation of func tional mri and event related potentials Technical report 2006 Fletcher PC Frith CD Baker SC et al The mind S eye precuneus activation in memory related ima gency Technical report 1995 Lang PJ Bradley MM Cuthbert BN International affective picture system iaps technical manual and affective ratings Technical report 1999 Friston KJ Ashburner JT Stefan Kiebel Thomas Nichols Penny WD Statistical Parametric Map ping The Analysis of Functional Brain Images Academic Press Inc 2006 Table 4 Pleasant EREB HRIH MRTE Unple
75. Biz Calc 4 1 4 2 3 4 2cm FOR 7 Fig 4 Fig 5 Fig 4 Fat Biz Calc 1 Eig 5 Fat Biz Calc 2 Table 2 Eat Biz Calc Fat Biz Calc 2 axial plane 003 Table 2 cm 2 0 0 10 tem 2 31 5 29 5 30 6 110 5 116 3 41 5 0 0 0 0 Uk eo o N QOQ oOo CO r2
76. musical emotions Cognition and Emotion Vol 15 No 4 pp 487 500 2001 3 P J Lang M M Bradley and B N Cuthbert Inter national affective picture system iaps Technical man ual and affective ratings Technical report University of Florida 1999 4 Fox PT and Raichle ME Focal physiological uncoupling of cerebral blood flow and oxidative metabolism during somatosensory stimulation in human subjects Proc Natl Acad Sci USA Vol 83 pp 1140 1144 1986 5 Richard J Davidson Paul Ekman Clifford D Saron Joseph A Senulis and Wallace V Friesen Approach Withdrawal and cerebral asymmetry Emotional expres sion and brain physiology i Journal of Personality and Social Psychology Vol 58 No 2 pp 330 341 1990 6 Rene J Huster Stephan Stevens Alexander L Gerlach and Fred Rist A spectralanalytic approach to emotional responses evoked through picture presentation nterna tional Journal of Psychophysiology Vol 72 No 2 pp 212 216 May 2009 7 Hampshire Adam Owen and M Adrian Fractionating attentional control using Event Related fMRI Cerebral Cortez Vol 16 No 12 pp 1679 1689 December 2006 8 Parkekh PI George MS Ketter TA Brain activity during transient sadness and happiness in healthy women Am J Psychiatry pp 341 351 1995 O0 150 HHHUHH 2012 08 2400 OU OEE OEE BRE te smith Waterman 1 D EU U LI U EE UO LEO L Ut UO UBL Arika FUKUSHIMA IIHHUHHHHHH
77. 0D0 Symbolic Aggregation approXimation SAX 9 0000 LU D Step 2 Smith Waterman L H E B E E EL LE 0 Smith 0000000 Smith Waterman HHHHHHHHHHHHHHHHHHHHHL HHHHHHHHHHHHHHHHHHHHHLH HIHHHHHHHHHHHHHHHHHHH smith Waterman HHHHHHHHHHHHH FAST All FASTA Basic Local Alignment Search Tool BLAST OOOO0000000000000 HOUOUUUD2000000 Co BU CUUU BL BO CO H EU E E E Smith Waterman HHHHHHHHHLH ae ENE ee Be Smith Waterman 2t 000000000 HHEig 1HHHHHHHHHHHHHHHHHL Fig 10 10 1000000000 oor tr HHHHHHHHHHHHH 00O mismatch HHHHHHHHHHHgaplHHHHHHHHL HHHHHHHHHHHHHHHHHHHHHL AOE Ey EEE CE OE EE CE Bi CD BHBHCHHHHHHHHHHHHHHHHL match 1 mismatch 1 Fig 2 HHHHHHLH gap t i UUUUU SW y 1 z 1 match SW y 10x gap SW y x 1 gap 0 SW ye max 1 SW y 10z 1 mismatch SW y 10x gap SW y x 1 gap 0 SW yi max 2 2 JU HL BEL D LI LI HHHHHHHHHHHHHHUHHUHHUHHHL HHHHHHHHHHHUHHHHHHUHHL HHHHHHHUHHHHHHUHHUHHHHL ODO Figs 20000000000000 200 L HHHHHH1IHHHHHHHHHHHHHHL HHHUHHHHHHHHOHHHHHHHHHH HHUHHHHHUHHHHHH2 HHHU1HHHHL HHHHHHHHHHHHHBH CHUD BU cu LU UD 3 OU EN NTETE 3 1 HHHH HHHHHHHHHHHHHH Smith Waterman HHHHHHHHHHHHHHUHHHHHHHHHHLH HHHHHHHHHHHHHHHHHHHHHHHHLH HHHHHHL Probe2 CH24 CH23 CH22 E ES CH21 0 CH20 0 CH19 0 CH18 E E 0 CH17 0 CH1
78. 6 0 CH15 0 E RE CH14 0 CH13 0 CH12 0 CH11 Em E 0 CH10 0 CH9 0 CH8 0 2 2 2 CH7 0 CH6 0 CH5 0 CH4 EE E CH3 0 CH2 0 CH1 E amp 0 0 0 L 0 H H 0 K 4 0 a Fig 3 fNIRS I 3 2 HHHHLH HHHHHHHHHHHHHHHHHHHHH GO NOGO ITask IfNIRSHHHHHHHHHHHHHHH Fig 3 0000000 AD BI CO 300000000 HHHHHHHHHH ETG 7100 D D U U DU U CE L DU DD DU Table 1 00L Table 1 fNIRS I I LH LU uuu Uu Ug HHHH ull 24 IIHHHHH is 30 0 IIHHHH s 120 0 O00000 fs 30 0 5 0 10 0 IIHHHHHHHHHH is HHHHHHHHH Rz 3 3 DL Smith Waterman JOU 0000000000000 HHHHHHHHHHHHHHHHH 3 3 1 000 HHHHHHHHHHHHHHHHHHHHH 5H 10 HHHHHHHHHH HHHH 3 HHHHHH 3H HHHHHHHHHHHHHHzHHHHHHHHH UD HHHHHHHHHHHHHHHHHHHHHHHH HHHHHHHHHHHHHHHHHHHHHHHH HHHHHHHHHHHHHHHHHHHHHHHH HHHHHHHHHHHHHHHHHHH logon 1 3 3 3 2 Smith Waterman match 1 mismatch 1 gap 1HHHHHHHHHHHHHHHHHHHHHHHL fNIRS 5 1O0 16 o P mM mm o o o o A N e N oo 0 50 100 150 200 s Fig 4 HHHL HHHHHHHHHHHHH matchi 100 mismatch lggHHHHHUHHHHHHHHHHHUHHLH 3 3 3 HHHHHHHHHHHHHHHHHHHHHHH HHHHHHH HHHHHHHHHHH1HHHH 24HHHHHHUHHHHHHHHHHUHHH OHHLH HHHHHUHHHHHHHHHHHHL RETE vao us BR 3 4 DL HHHHHHHHINIRS
79. HHHHHHHHHHHHHHHHLH HHHHHHHHHHHHUHHHUHHHHHHHHHL EL Bm a a es E e e e EN a EDD EIE EE HHHHHHHHHHHHHHUHHHUHHHHHHHLH HHHHUHHHUHHHHHHHUHHHHHHUHHHHL 4 ul U EH E Smith Waterman O O O NIRS OO OOOOOOUOOOUUOOOOUOUOOUOUUUUUL EDEDEEEBRSEEBIEE ELDER ER ERES DEESSET SE DEPPRERS ERE E ES a ae i a EE EJ o PAPE DEBES E EO EI HHHHHHHHHHHHHHHHHHHHHHHHL HHHHHHHHHHHHHHHHHHHHHHHHHL LIE EER ETE ENE ESE EM EE SEM EME Ctl EERE Ei HHHHHHHHHHHHHHHHHHHHHHHHL HHHHHHHHHHHHHH UU 1 Scott C Bunce Meltem Izzetoglu Kurtulus Izze toglu Banu Onaral and Kambiz Pourrezaei Func IEEE ENGI NEERING IN MEDICINE AND BIOLOGY MAG AZINE Vol 25 No 4 pp 54 62 2006 tional near infrared spectroscopy 2 Takuma Nishii Masato Yoshimi Mitsunori Miki and Hisatake Yokouchi Similar subsequence retrieval from two time series Tomoyuki Hiroyasu data using homology search Systems Man and Cy bernetics 2010 IEEE International Conference on pp 1062 1067 2010 3 T F Smith and M S Waterman Identification of common molecular subsequences J Mol Biol Vol 147 pp 195 197 1981 gt Abdullah Mueen Zhu Sydney Cash Brandonwestover exact discov ery of time series motifs SDM pp 473 484 2009 Eamonn Keogh and Qiang 5 Eugene G Shpaer Max Robinson David Yee D Candlin Robert Mines Hunkapiller Sensitivity and selectivity in protein James and Tim similarity searches A comparison of smith wat
80. HHHHHHHHHHHHI HHHHHHHHHHHHHHHHHHHHHHH Table 100 4202400000000 HHHHHHH 160 HHHHHUHUHHUHHH 5H10H16HHUHHHHHHL HHHHH SH10H16HHHHHHHHHHHHH AL 1HHHHHHH INIRSHHHHHHH Fig 400000 4 3 4 1 IL IL I pg 50109 161 00000 U Smith Waterman HHHHHHHHHHHHHUHHHUHHHHHHHHL HHHHHHHHHHHHHHHHHHISmith Waterman HHHHHHHHHHHHUHHHHHHHHHHHHLH HHHHHHHHHHHHHHHHHHLH NIRS LU HHHHHHHHHHHHHHHHHHH NIRS L LU HHHHHHHHHHHUHHHUHHHHHHHHHHLH HHHHHHUHHHHHHHHHHHH Fe 50000 HHHHHUHHOHHHHHHHHHU Fig 7L UL C UI HHHHHHHHHHHHHHHHH AD BI UU LU HOU sr 100 16 DEO DL UL UO EL UL OL EE OL O DE OL BE D LU IIHHHHHHHHCHHHHHHHH 1000000 HHHHUHHHUHHHHHHHUHHHHHHHHHHL HHHHHHHHHHHHHHHHHHHHHL HHHHHHHHHHHHHHHHHHHHHHHH HHHHHHHHHHHHHHHHHHHHHH AUB HHHHHHHH5HH95HH1IHHHHHHHHLH 0 8 0 7 R 0 6 0 5 25 20 4 m10 0 3 m16 0 2 0 1 0 A B C Fig 5 HHHHHHLH Fig 6 HHHHHUHHHHHL n5 m10 E16 B C 0 025 4 o 20 015 0 005 E 0 A e S Fig 7 OHHHHHHLH HHHHHHHHHHHHHHHHH Fig 60 UU HHHHHHHHHHHHHH ADBILULULULUSLU 37 HHHHHHHUHHHHHHHHH95SH7HHHHHHLH HHHHFjg 6HHHHHHHHHHHHHHHHHH HHHHHHO9HH1HUHHHHHHHHHHHL OHHUHHHUHHHUHHHHHHUHHUHHHHL HHHHHUHHHHHHHH 5H10H16HHHHHHLH HHOHHHHHHHHHHHHHHHHHUHHHHHLH HUUUU 3 9 UU HHHHHHUHHHHHHHHHHHHHHHHHH HHHHHHHHHUHHHUHHUHUHHUHHHHHHLH HHHHHO9HH1HHHHHHHHHHHHHHLH HHHHHHHHHHHHHHHHHHHHHHHHLH TERE wg N E pE aC E HHHHUHHUHHHHHHHHHHHHHOHHHHHLH HHHHHHHHU
81. HHHHHUHHHHUHHHHHHHHHHHUHHHHHHHHHHHUHHHHHHHHH HHHUHHHHHHHHHHHHHHHUHHHHHHHHHHHHHHHHHHHHHHHHHHLH IIHHHHHHUHHHHHHHHHHHUHHHHUHHHHUHHHHHHHUHHHHHHHHHHL D U U Smith Waterman 0 000 IfNIRSHHHHHHHHHHHHHHHHHH EL a a i a H3 OE ELEUEE EL EE EL EE HE 1 HHHL HHHHHHHHHHHHHHHHHHHHHHHHL fanctional Near infrared Spectroscopy fNIRS HHHHHHHHHHH nfNIRSUDU 10 000 ETG 71000000000000 0 120000 BOVE Ey EE i0 EO SARE EGE Ey EE El EIEN ENE HHHHHHHHHHHHHHHHHHHHHHHHLH HHHHHHHHHHHHHHHHHHHHHHHHHL HHHHHHHHHHHHHHHHHHHHHHHHHH HHH 2 DNAHHHHHHHHHHHHHHHH HHHHHHHHHH Smith WatermanD 1 D D DU INIRSHHHHHHHHHHHHHHHHHHHHHH Smith Waterman O DNA I OO OHOOUUAGOO0 U0 TOO0 00 e U D UL JD DI OTOOO O0 400000000000000000 OE Ee EE ESE PEE Ta UTIs EP Eres Te HHHHHHHHHHHHHHHH Smith Waterman J INIRSHHHHHHHHHHHHHH NIRS 1 EI D O opp LDO HHHHHHHHS5HHH1O0HHHHHHHHHHHLH HHHHHHHHHHHHHHHHHHHHHHHHHL WREROHERSRERERBESRDEERHEUEEEPEEEESUENRBESNEREHER O O Smith Waterman OO 1 B HE HEU HEU HU BE U ET UDB UL LL 2 Smith Waterman 000 ETT EJERCER EE HHH 2HHHHHHHHHHHHHHHHHHH E EP BED Step 1 fNIRSHHHHHHHH 0 U D U Waterman D UL UO DH BL O U D D U EE OI L HHHHHHHHHH tNIRSD DU U U U U U U HHHHHHHHHHHHHHHHHHH INIRS 010 HIHHHHHHHHHUHHHHHHHHHHHHHL Be EVE EE DEBERE BD ET T ELEN SCIRET E lt 6 CI EIo PR EDDIE EE EP d BE EEEn EET ER ER E e EISE DESE SH SE o Doe eo EET UUUUUOOOO000000000
82. HWHM 8 mm m VP o 4 BR Coresister Table 4 Pleasant Neutral f BENIN 3 Unpleasant Normalize MNI t 0 000001 Pleasant Unpleasant Neutral Fig 4 Fig 6 17 3 Table 3 Pleasant BEATS Table 2 Coronal GE EPI T2 Table 1 FOY at 9 _ TR ms 50 4611 4641 4658 4659 4666 TE ms 40 Pleasant 4676 4677 4680 4681 4690 A24 XE mm 5 1440 1460 1463 1530 1540 50 1590 1610 1710 1750 1920 1010
83. Replication 8 Caching 3500 EcoModel 3000 2500 2000 1500 Replication 1000 500 Sequential Random Gaussian Unitary Fig 6 Replication Sequential NoReplication Caching Economic Model ENU Se quential EconomicModel Caching NoReplication ENU P seem Uc NoReplicaton ENU Caching EconomicModel sequential Unitary ENU
84. S MTAL arci 2 2 1 FB CORO OE CHAO HNO REGEDIT CODY ARNAR Fig 1 LS NVA 3 IB tres opes de TN TRIS eS S dis AMAA n megia pix 2173 Wy DS i flr E 2 n P WE j CS ChLONROS7A AcolP step 1 AUTER ZARAR X SEJUTA bd TABORA mage VON TONS step 2
85. Vol 1 No 15 24 August 2012 The Monthly Lecture Meeting zs 15 1 e155 Published by the Medical Information System Laboratory OF Doshisha University Kyotanabe Japan Medical Information System Laboratory The Monthly Lecture Meeting Contents MRIHHHUHHHUHHHHHHHHHHLH HHHHHHHUHHHHHHHHHHHHHL NIRS EEGHHHHHHHHHHHHHHHHHI Smith WatermanlHHHHHHHHHHHHHHHHHHHHHHHL SVMHHHHHHHUHHHHHHHHHHHHHHHHHHHHHHHLH HHUHHHHHUHHHHHUHHHHHHHHHHHHL EEE E TE ee a ee Federation HHHHHHHHHHHHHHHHHHHHHHHHHHHLH 00 UD BI IE sess RN A EE EE WEEE s 3 UO U0 HO UU MM s es 23 2f 15 2012 08 24 MR1 AR Usui TOMOMI dt EB Fd MEE
86. ant Unpleasant D Neutral Pleasant Unpleasant T Fei L CHAE L IER OVT Fig 1 10 cm 1 HAT nea Fig 1 2 3 1 24 Lt 2 4 IAPS International Affective Picture System 3 Fig 2 30 COR 6 Pleasant Unpleasant Neutral TO
87. er man in hardware to blast and fasta GENOMICS Vol 38 pp 179 191 1996 c Herbert A Sturges val Journal of the American Statistical Association Vol 21 No 153 pp 65 66 1926 The choice of a class inter 013 7 OOO0 0000 G00000000000000 The 26th Annual Conference of the Japanese Society for Artificial Intelligence 2012 15 2012 08 24 B SVM Yuichi OHBORI 3
88. o o v by o M 4r o M 4r b Zt D 2L O O j O 2 4 6 8 10 O 2 4 6 8 10 Fig 3 Replication 1 Remote 7000 NoRepcaliton FIle 0 LocalFile 1 Bond Caching EcoModel RemoteFile Local File Local C Replication ENU 5 5 1 Fig 4
89. rr 0 5 0 MIO TT HTOTITOTTTH E 0 di d2 d3 o RTE Hy e ET Fig 4 4 4 1 016 amp OTM LE 3 ET 2 SVM 3 3 2 GA Table 2 SVM 2 Table 1 GA 500 500 NO sce A 4 0 9 0 01 1 4 2 UCI Machine Learning Repository breast cancer
90. sant Beni BARBIE Neutral TRE 15 2012 08 24 H NIRS EEG HG Takayuki HAYASHI Em ALS NIRS EEG NIRS EEG 1 ALS ALS
91. timation in J A K Suykens and J Vandewalle Nonlinear Modeling Advanced Black Box Techniques Kluwer Academic Publishers Boston pp 55 85 1998 Vladimir Vapnik Statistical learning theory John Wiley New York 1998 Terrence Furey Nello Cristianini Nigel Duffy David Bednarski sler Support vector machine classification and Michel Schummer and David Haus validation of cancer tissue samples using microar ray expression data Bioinformatics vol 16 no 10 pp 906 914 2000 018 4 Sujun Hua and Zhirong Sun Support vector ma chine approach for protein subcellular localization prediction Bioinformatics vol 17 no 8 pp 721 728 2001 Nello Cristianini John Taylor An Introduction to Support Vector Machines And Other Kernel Based Learning Methods Cambridge University Press 2000 David Goldberg Genetic algorithms in search op timization and machine learning Addison Wesley 1989 Darrel Whitley A genetic algorithm tutorial Statistics and computing vol 4 no 2 pp 65 85 1994 UCI Machine Online Available http archive ics uci edu ml datasets html Learning Repository Nick Street William Wolberg Olvi Mangasarian Nuclear Feature Extraction For Breast Tumor Di agnosis International Symposium on Electronic Imaging Science and Technology vol 1905 pp 861 870 1993 15 2012 08 24 H
Download Pdf Manuals
Related Search