Luận văn khai phá dữ liệu luật kết hợp mờ và ứng dụng cho bài toán khai phá dữ liệu cước internet

Phxalm ivzi Epncg gdhupncg @bxapn gdñhu eevtxa okhxazi sphxa gdzier ylzieehu 3chzi ylxa vteropncg ylzipnh ivzi3cee vthhuopncg lmxazi Trang 12 ylzieehu gd3 gdhuo3c okcg gdocg eropncg er

DAI HQC QUOC GIA HA lNQITROlNG DAI HQC COlNG lNGHE

Phxalm Thzi Hoxa lNxalm

KHAI PTLâ D‘Y LIEU LUAT KokT HOP kMvt3

VA ziJ2'JG DUlNG CKO BAI TOAlN KHAI PTL'ok D‘Y LIEU CYf$C IlNTERlNET

k

MUC LUC

szio

zi»lshu _; 7

Ch h uo p n c g 1 TO l NG QUA l N VE KHAI PHA DU LIEU 7

1.1 Kh x a z i p n z i e e l m 3 co @ b x a p n 7

1.1.1 k M h u 3 c v t z ié h u 3 c h u x a o kh x a z i s ph x a g d z i z i y l z i e e h u 7

1.1.2 D! p nh p n c gh z i x a o kh x a z i s ph x a g dG y l z i e e h u 8

1.1.3 Cf 3 c g d x a p n c g g d z i z i y l z i e e h u 3 co v th e e o kh x a z i s ph x a g d z i z i y l z i e e h u.[ y l][3] 8

1.1.4 Q h u x a v t e r z i p nh o kh x a z i s ph x a g d z i z i y l z i e e h u 9

1.1.4.1 C x a 3 c @ b h uñ 3 c 3 ch z i p nh v t e ro p n c g q h u x a v t e r z i p nh o kh x a z i s ph g d 9

1.1.4.2 Cf 3 c v thâ p nh s ph l s 3 c h u x a c g z i x a z i v th h u3 v t o kh x a z i s ph x a 9

1.1.4.3 H h uñ p n c g v t z ié s p 3 c x a p n 3 co @ b x a p n i v x a o k m y v th h u x a v t x a s p g d h u p n c g v t e ro p n c g q h u x a v t e r z i p nh o kh x a z i s ph x a 10

1.1.4.4 E p n c g g d h u p n c g 3 c z i z i x a o kh x a z i s ph x a g d z i e r y l z ié h u 11

1.2 Ph h uo p n c g s ph x a s p o kh x a z i s ph x a g d z i z i y l z i e e h u 12

1.2.1 k Mo v t l so s ph p no p n c g s ph x a s p o kh x a z i s ph x a g d z i z i y l z i e e h u s phñ @ b z i e e p n [1][3] 12

1.2.1.1 C3 m y q h u m yé v t g d z i p nh i v x a y l h u x a v t 12

1.2.1.2 Ph h uo p n c g s ph x a s p l s h u m y g d z i e e p n i vñ q h u m y p n x a s p 12

1.2.1.3 Ph x a v t h z i e e p n 3 c x a 3 c y l h u x a v t o k e e v t h s p s p 13

1.2.1.4 Ph3 p n p nho l m i vâ s ph3 p n g do x a p n 14

1.2.1.5 k M x a p n c g p no e ro p n 15

1.2.1.6 G z i x a z i v th h u x a v t g d z i v t e r h u m y e e p n 16

1.2.2 Ph x a p n y lo x a z i 3 c x a 3 c h e e v tho p n c g o kh x a z i s ph l s g dG y l z i e e h u 16

1.2.3 l Nhf l m c g i v x a p n g d e e q h u x a p n U l m v t e ro p n c g h§ v tho p n c g o kh x a z i s ph l s g dG y l z i e e h u i v x a y l m y x a 3 ch s p p n 3 c3 3 c o k m y v th v t o kh x a z i h v t v t v t • • • • • • • • • • • • • • • • •'• • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • v t v t v t • • • • • • • • v t • • • • • • v t v t v t • • • • • • • • v t v t v t v t v t • v t • v t # v t v t v t v t • # #1 7 Ch h uo p n c g 2 KHAI PHA DC LIEU BA l NG LUAT IT HC z iP 20

2.1 Y o c gh z i x a 3 c z i z i x a y l h u3 v t o k e e v t h s p s p[5] 20

2.2 Phé v t @ b z i e e h u @ bñ z i v to g d p n [ y l][5] 21

2.4 k Mo v t l so v t z i p nh 3 ch x a v t 3 c h u x a s p l m h u 3 c s phñ @ b z ié p n i vâ y l h uâ v t o k e e v t h9 s p 24

2.4.1 k Mñ v t l so v t y l p nh 3 châ v t 3 c h u x a @ s p l m h u 3 c s phf z i @ b z i e e p n 24

2.4.2 k Mo v t l so v t z i p nh 3 ch x a v t 3 c z i z i x a 1 h u3 v t o k e e v t h9 s p 25

2.4.3 Cf 3 c y lo x a z i y l h u x a v t o k e e v t h9 s p [5][6][8] J 26

2.5 C x a 3 c v th h u x a v t v to g d p n o kh x a z i s ph l s g d z i z i y l z i e e h u p nho y l h u3 v t o k e e v t h s p s p 27

2.5.1 Kh x a z i s ph x a y l h u x a v t o k e e v t h s p s p p nh z i s phñ p n g do p n 3 ch z ié h u v t z i e r 3 co l s g d g dG y l z i e e h u v tâ 3 c i v h u 27

2.5.1.1 Th h u x a v t v to g d p n A s p e r z io e r z i v t y l l m s p l m h u 3 c s pho @ b z i e e p n l s z i v t g d h u p n c g s ph h uo p n c g s ph x a s p l s z i p nh 3 cf 3 c Wh z i c g 3 c z i e r [5] 27 2.5.1.2 l N x a p n c g 3 c x ao h z ié h u q h u x a v th h u x a v t v to x a p n A s p e r z io e r z i [7][8][9] J 33

2.5.1.3 Th h u x a v t v to x a p n l s z i p nh 3 cf 3 c y l h u x a v t o k e e v t h s p s p v t z i z i @‘ s p l m h u 3 c s pho @ b z i e e p n 35

2.5.1.4 Kh x a z i s ph l s 2.5.2 Kh x a z i s ph x a y l h u x a v t l m h u 3 c s pho @ b z i e e p n o khñ p n c g l s z i p nh z i l m c g 3 c z i z i [3] 38

h s p s p g d z i p nh y l h uq p n c g [6] 44

2.5.3 Kh x a z i s ph x a y l h u3 v t o ké v t h s p s p g d x a l m g d 3 c [6] 45

2.5.3.1 L h u3 v t o ké v t h g d x a l m z i e r 3 c 2.5.3.2 C x a 3 c 3 c x a 3 ch v t z ié s p 3 c3 p n o kh x a z i s ph x a y l h u x a v t o ké v t h s p s p g d x a l m z i e r 3 c 45

2.5.4 Kh x a z i s ph x a y l h u x a v t o ké v t h s p s p g dé p n c g 46

2.5.4.1 T3 s p l m h u 3 c s pho @ b z ié p n g do p n c g 47

1

2.5.4.3 Th h u x a v t v to x a p n CHAR k M [8] 51

Ch h uo p n c g 3 KHAI PHA DU LIEU BA l NG LUAT KET HQP k MW 54

3.1 Kh x a z i p n z i9 l m i v e e s p l m g d (F h uzz m y S e e v t l s), y lo c g z i 3 c l m g d i v x a h e e l m g d 54

3.1.1 TOP l m g d [2] 54

3.1.2 C x a 3 c s phé s p v to x a p n 3 co @ b x a p n v t e ré p n v t x a s p l m g d [2] 56

3.1.2.1 Phé s p s ph h u g d z i p nh 56

3.1.2.2 Ph e e s p h s p z i 56

3.1.2.3 Ph e e s p v t h u m y e e p n 57

3.1.2.4 L h u x a v t D e e k MO e r c g x a p n 3.1.2.5 Phé s p o kéo v th e eo 57

3.1.3 A s p g d h u p n c g s p l m g d g d e e e rñ z i e r x a 3 c ho x a g d z i e r y l z i e e h u i v x a 3 c x a 3 c h u h u g d z i e e l m 58

3.2 C x a 3 c y l h u x a v t o k e e v t h9 s p l m g d [3] [11] 59

3.3 C x a 3 c v th h u x a v t v to x a p n o kh x a z i s ph x a y l h uf z i v t o ké v t h s p s p l m g d 63

3.4 L h u3 v t o ké v t h s p s p l mh g d g d x a p n c g s ph z i z i g d z i p nh 68

3.5 L h u3 v t o k e e v t h s p s p l m g d i vñ z i v th h u 3 c v t z i p nh g d h uq 3 c g d x a p nh v t e r s p p n c g l so [5][6][11] 68

3.6 T z i l m 3 c x a 3 c y l h u x a v t v th x a v t l s v t 3 cé z i 3 ch [3] 69

3.6.1 Ph h uo p n c g s ph x a s p g d h u p n c g q h u m y 1 h u3 v t y lo x a z i @ bh y l h u x a v t v th z i z i x a 69

3.6.2 Ph h uo p n c g s ph x a s p v t z i l m y l h u x a v t g do p n c g z i x a p n 70

3.6.3 Ph h uo p n c g s ph x a s p v t y l l m y l h u x a v t l m g d z i y l x a g d z i x a v t e ré p n v t e r z i v th z i e r 3 c g dâ @ b z ié v t 70

3.6.4 Ch h u m y e e p n y l h u x a v t o k e e v t h s p s p l m g d i v e e y l h u x a v t o k e e v t h9 s p v th h uo 3 c v t z i p nh l so 72

Ch h uo p n c g 4 VG DQG LUAT IT HQP k MC z i CHO B k MI TOA l N KHAI P k M DC LIETET74 4.1 l N c g h uo p n g d h u y l z ij h u 3 c h u g d 3 c I p n v t e e e r p n e e v t 74

4.2 Ch z i g d x a v t hJ v tho p n c g o kh x a z i s ph x a g dñ y l z i e e h u 3 c h u g d 3 c I p n v t e e e r p n e e v t 75

4.2.1 Cf 3 c @ b h u g d 3 c v t z i e e p n hâ p nh p x x a m y g do c g hj v tho p n c g o kh x a z i s ph x a g d z i z i y l z ij h u 3 c h u g d 3 c I p n v t e e e r p n e e v t75 4.2.2 G z i x ao g d z i e e p n h v tho p n c g o kh x a z i s ph l s g d v t v t y l z ié h u 3 c h uñ 3 c I p n v t e e e r p n e e v t 80

4.2.2.1 H e e v tho p n c g h v t l m 3 ch h u x a p n J 80

4.2.2.2 k M g d ho x a g d8 y l z i e e h u i vâ l s z i p nh y l h uâ v t o k e e v t h s p s p l m g d 81 4.2.2.3 T z i l m y l h u x a v t 3 c6 I 3 c

3

H z i p nh 1.

H z i p nh 2.

H z i p nh 3.

H z i p nh 4.

H z i p nh

S.

H z i p nh

6.

H z i p nh 7.

H z i p nh 8.

H z i p nh 9.

H z i p nh 10.

H z i p nh 11.

H z i p nh 12.

H z i p nh 13.

H z i p nh 14.

H z i p nh 15.

H z i p nh 16.

H z i p nh 17.

H z i p nh 18.

H z i p nh 19.

H z i p nh 20.

H z i p nh 21.

V z i g dq 3 c x a m y FP- v t e r e e e e i vO z i l m z i p n l s h u s p=20% 40

k Mñ h z i p nh i v x a p n hñ p nh h e e v thñ p n c g ( v th e eo q h u m y v t e r z i p nh g d x a h u p no z i i v x a o kh x a z i v th x a 3 c g d z i 3 ch i v h u)74 k Mñ h z i p nh v to p n c g q h u x a p n h e e v tho p n c g o kh x a z i s ph x a g d z i z i y l z i e e h u: 77

k Mñ h z i p nh 3 c i v l so g d z i z i y l z i e e h u q h u x a p n h e e 79

Lo x a z i h x a l m v th h uo 3 c 80

H x a l m v th h uo 3 c i v z i v th x a l m l so 3 cho l mo z i h x a l m v th h uñ 3 c 80

T x a s p l mS i vâ v th h uo 3 c v t z i p nh c go 3 c 3 c z i v t x a p no 81

G z i x ao g d z i e e p n v th z i e r 3 c h z i e e p n k MW ho v t g d z i z i y l z i e e h u i v x a 3 co l s g d g d z i z i y l z i e e h u 3 c z i e ro 3 c c go 3 c 81

Co l s g d g d z i z i y l z i e e h u l s x a h u o kh z i v th m y 3 c h z i e e p n l mo ho v t 82

S z i p nh v t x a s p s pho @ b z i e e p n l s z i e r g d h u p n c g v to x a p n v t z i z i T- p no e r l m — T z i 3 ch g d x a z i l so 82

S z i p nh v t x a s p s phñ @ b z ié p n l s z i v t g d h u p n c g v to x a p n v t z i e e T- p no e r l m — Phé s p y l x a m y l m z i p n 83

S z i p nh v t x a s p s pho @ b z ié p n l s z i v t g dq p n c g v to x a p n v t z i e r T- p no e r l m — T z i 3 ch @ b x a e r 3 ch z i p n 83

S z i p nh @ s p s pho @ b z i e e p n l s v t g d h u p n c g v to x a p n v t z i e r T- p no e r l m — T z i 3 ch D e r x a l s v t z i 3 c 84

S z i p nh v t x a s p s phñ @ b z ié p n l s z i v t g d h u p n c g v to g d p n v t z i v t T- p no e r l m — Phé s p c g z i x ao 84

S z i p nh v t x a s p 3 c x a 3 c y l h u x a v t l m g d v t z i z i @ s p s phñ @ b z ié p n 85

D e r e e p n c g z if v t y l h u x a v t 85

S z i p nh v t x a s p 1 h u e e x a v t @ b x a p n c g y l h u x a v t s ph z i z i g d| p nh 86

S z i p nh y l h u x a v t o k e e v t h s p s p i v g d z i 3 c x a 3 c v th h uo 3 c v t z i p nh g d h uq 3 c g d x a p nh v t e r s p p n c g l so 86

T z i l m y l h u x a v t l m z i z i y l x a g d z i e r x a v t e ré p n v t e r z i v thñ 3 c g dñ @ b z ié v t 87

T z i l m y l h u x a v t g do p n c g e r x a p n 87

Lo x a z i @ bñ y l h u x a v t v th z i z i x a 88

sphâpn xapnh, cgzixazi qhumyévt 3cxa3c @bxazi vtoxapn ylzieepn qhuxapn gdeepn okhzixa 3c gdzipnh vtzipnh 3chuxa

vterzi vthhu3c

Chhu'o’pncg 1 T6lNG QUAlN Vé KHAI PHA DU’ LI§U

3csphu 3chzipnh eevtxa ylzipnh ivzi3cee okhoxa hsp3c lmxamy vtzipnh ivxa 3copncg pncghee vterzi vthhu3c Phxalm ivzi

Epncg gdhupncg @bxapn gdñhu eevtxa okhxazi sphxa gdzier ylzieehu 3chzi ylxa vteropncg ylzipnh ivzi3cee vthhuopncg lmxazi

ivxa vtxazi 3chzipnh lNhhupncg pncgxamy pnxamy, okhxazi sphxa gdzier

Co l sâ g dF y l z i e e h u g d x a 3 ch z ié h u ( l m h u y l v t z i l m e e p n l s z io p n l s v t e r h u 3 c v t h u e r e e l s, g d x a v t x a w x a e r e eho h u l s e e l s, g d x a v t x a

l m x a e r v t) y l x a okho gdzizi ylzieehu g d x ao 3 c vtxasp hspsp, 3chopn ylo3c vthu’ pnhziéhu pncghufzipn gdzier ylzieehu okhxa3c

Co l sâ g dU y l z i e e h u q h u x a p n h e e - h x aâ p n c g g d 3 c z i v t x a s p p n c g (o @ bj e e 3 c v t- e r e e y l x a v t z io p n x a y l g d x a v t x a @ b x a l s e e l s): y l x a

g

d x a p n c g 3 co l sS g d z i z i y l z i e e h u y l x a z i c g z i z i z i x a h x a z i l mñ h z i p nh q h u x a p n h e e i v x a hoñ p n c g g dñ z i v t h u s p p n c g.

C x a l sâ g dF y l z i e e h u o khâ p n c g c g z i x a p n i v x a v thâ z i c g z i x a p n ( l s s p x a v t z i x a y l, v t e e l m s po e r x a y l x a p n g d v t z i l m e e- l s e e e r z i e e l s

9

Dxapnh h z i p nh.‘ Dâp nh c g z i x a p x e e l m l mo v t l m x a h u CO gdxasp g d h uo 3 c 3 c x a 3 c v t z ié h u 3 ch h u x a p n 3 c h u x a

q h u x a v t e r z i p nh s ph x a v t h z i e e p n v t e r z i v th z i e r 3 c h x a m y o khñ p n c g V z i e e 3 c g d x a p nh c g z i x a l mS h z i p nh g d h u s p e e v thq 3 c h z i e e p n v

nh h u h s p 3 c l m x a m y ( l m x a 3 ch z i p n e e yleexaerpnzipncg), 3c3my qhumyévt gdzipnh (gdee3czilsziopn vtereeee), lmhucg pnoeropn

@ b z i z i v to x a p n p n x a m y 3 cñ p n g d x a m y 3 c c g s p z i y lñ h s p 3 c 3 co c g z iâ l m l s x a v t ( l s h u s p e e e r i v z i l s e e g d y l e e x a e r p n z i p n c g).

Phâ p n 3 c m y l m ( 3 c y l h u l s v t e e e r z i p n c g7 l s e e c g l m e e p n v t x a v t z io p n): Sx a s p p xé s p 3 c x a 3 c g dñ z i v t h u s p p n c g v th e eo v t z i l m c g 3 c p

nh h u p n c g l sS y l h u s p p n c g i vñ v t e e p n 3 c x a 3 c 3 c h u l m 3 ch h u x a @ b z ié v t v t e r h u l s 3 c L z i s p @ b x a z i v to x a p n s ph x a p n 3 c 3 co p n

g

d h uq 3 c c go z i y l x a h s p 3 c o khf z i p n c g c g z iâ l m l s x a v t ( h u p n l s h u s p e e e r i v z i l s e e g d y l e e x a e r p n z i p n c g)

11 ,

Cho l mo v t y l h uq 3 c g dâ R = (A1

,A-2-› .9As p Vñ z i 3 c x a 3 c v th h uo 3 c v t z i p nh 3 co l m z ié p n c g z i x a v t e r z i (0,1) i v x a

Vzi gdhu: Phxapn vtzi3ch 3co lsvt gdñ ylzieehu @bzipn hxapncg pnhzixapn gdhuq3c vthopncg vtzipn ivee pnhzizipncg

okhxa3ch lmhuxa 3cxa3c lmxavt hxapncg lmxamy vtzipnh 3co okhhumypnh hhuépncg lmhuxa sphâpn lmeelm oké

vtoxapn vteropncg 3chupncg ylxapn lmhuxa gdhuo3c lmo vtxa @bñzi ylhuxavt okévt hzisp pnhhu lsxahu:

pnéhu 3chhupncg vthoxa lmâpn 3cxa hxazi pncghuñpncg fzio ho vtero 3cf3c vtziéhu ivxa gd vtzipn 3cxamy 3chu3c

vtziéhu lNhñpncg pncghuñpncg pnxamy vthhu0pncg gdo pncghuozi gdhupncg hoxa3c 3cxa3c 3chhumyépn cgzixa vteropncg

lmxahu gdhuo3c vthziévt ylxasp, 3chhupncg 3co vthee gdhuo3c lshu gdhupncg gdee vtxazi vtxao 3cxa3c vtxasp gdzizi ylzieehu gdee

hzieehu

kMxapncg pnoeropn g d h uo l s gdopncg cgozi ivlszi pnhzizipncg vthñpncg vtzipn vterq cgzihusp 3chuxa 3cxa3c 3chhumyépn

cgzixa gdxapncg vtzipn eexamy ivxa gdhuq3c ho @bxao gdxalm 3cxa3c lmo hzipnh pnxamy ylxalm ivziee3c vtovt Sxahu okhzih93c, lmxapncg 3co vthee gdhusp3c 3cozi ylxa lmovt 3chhumyépn cgzixa vteropncg ylzipnh ivhu3c vthñpncg vtzipn lmxa pno

Ph3pn yloxazi gdhuxa vterépn okziéhu gdG ylzieehu gdhuo3c okhxazi vthxa3c: Co lsvt gdhu ylzieehu qhuxapn hee,

okho gdhu ylzieehu, 3co lsvt gdzizi ylzieehu cgzixao vtxa3c, 3co lsvt gdzizi ylzieehu hhuñpncg gdozi vthu erzicg, eepn lsvt

@bâpn,

czizixa vterzi vthhu3c g d x ao 3 c okhxalm sphxa Vxapn gdee lsopncg lsopncg hoxa ivñ sphñpn vtxapn qhuâ vterzipnh

o

khxazi

Do z i i vâ z i 3 câ h u hâ z i 1: kM3hu gdxapncg qhuxapn vtâlm pnéhu:Dee hzieehu gdézi ivñzi 3copn pncghuñzi, hspsp

th h u0 p n c g o kh l s p n c g v th m y 3 c h z i e e p n g d h uo 3 c i v x a o khf z i p n c g 3 co o kh x a p nâ p n c g g d l s z i i vñ z i e e x a e e h e e v tho p n c g o kh x a z i s

ph x a g d z i z i y l z i e e h u g d e e l s z i p nh e r x a v tñ v t 3 c x a 3 c 3 c x a 3 c l m x a h u 3 co v th e e 3 co, 3 co v th e e v t l s p n v t x a z i Th x a m y 3 cho g d z ié h u

g

do p n c g h u0 z i v t x a v t x a s p v t e r h u p n c g i v x ao l m h u 3 c v t z ié h u v t z i l m o k z ié l m V z i g d h u i vñ z i Kh x a z i s ph x a @ b x a p n c g y l h u x a v t o ké v t

h s p s p, p n c g h u0 z i v t x a l s h u g do c g 3 c x a 3 c g do g do 3 co v th e e g dâ l m @ b x ao o kh x a z i s ph x a v t e r s p p n i v e e p n, 3 co p n c gh z i x a y l x a p

x x a 3 c g d z i p nh v t e r h uñ 3 c p n c g h uñ p n c g g do ho v t e ro i v x a g do v t z i p n 3 c x a m y p nhf z i p nh x a v t v th z i 3 co v th e e v t z i l m g d h uo 3 c.

D z i i vâ z i 3 câ h u hâ z i v th e e 3 He e v thñ p n c g o kh x a z i s ph x a 3 co v th e e 3 ch z i l s z i p nh e r x a 3 c x a 3 c l m3 h u 3 c x a p n q h u x a p n v

t3 l m o kho p n c g? D x a m y 3 ch z i.p nh y l x a, i v x a p n g d e e v to z i h u h u v t e rO p n c g o kh x a z i s ph x a, g d h u y l z i e e h u.V x a p n g d e e p n x a m y y

l x a, v th x a 3 ch

v th e e e e e r x a v t y lñ p n g do z i i vñ z i 3 c x a 3 c p nh x a o kho x a h9 3 c v t e ro p n c g y l z i p nh i v s p 3 c o kh x a z i s ph x a g d z i z i y l z i e e h u.

Chhu›o’pncg 2 KHAI PHA DU’ LI§U LUcgT KRT

21

Shuspsp(X)=

Do ho v t e ro 3 c h u x a l mo v t v t x a s p l m h u 3 c 3 c x a 3 c c g z i x a v t e r z i c g z i z i e r x a 0 i v x a 1, f z i 3 c y l x a 0 l s h u s p s p(X)

1 i vñ z i l m s p z i v t x a s p l m h u 3 c X.

vtheeo hhuñpncg 3chzixa @bxaer vtoxapn vthxapnh hxazi sphxa 3chu vthee:

Ph x a 1.’ Tz i l m v t x a v t 3 c x a 3 c x a 3 c v t x a s p l m h u 3 c s ph l s @ b z ié p n v t z i z i e e p n l sS g d z i z i y l z i e e h u, l N 3 c y l x a v t z i l m v t x a v t 3 c x a 3 c x a 3 c v

t x a s p l m h u 3 c v tho x a l m x a p n l s(X) l m z i p n l s h u s p D x a m y y l x a s ph x a v tf z i p n o kh x a p nh z i e e h u v th l s z i c g z i x a p n 3 c z i z i x a CPU i v x a v