%PDF-1.5
%
2 0 obj
<<
/Type /Catalog
/Names 4 0 R
/Pages 5 0 R
/Metadata 6 0 R
/Outlines 7 0 R
/PageMode /UseNone
/OpenAction 8 0 R
/ViewerPreferences <<
/FitWindow true
>>
>>
endobj
6 0 obj
<<
/Type /Metadata
/Length 4437
/Subtype /XML
>>
stream
2019-09-11T07:49:50+01:00
2020-01-16T09:23:23+01:00
LaTeX with hyperref package
pdfTeX-1.40.18
application/pdf
A support vector machine (SVM) based detection is applied to different equalization schemes for a data center interconnect link using coherent 64 GBd 64-QAM over 100 km standard single mode fiber (SSMF). Without any prior knowledge or heuristic assumptions, the SVM is able to learn and capture the transmission characteristics from only a short training data set. We show that, with the use of suitable kernel functions, the SVM can create nonlinear decision thresholds and reduce the errors caused by nonlinear phase noise (NLPN), laser phase noise, I/Q imbalances and so forth. In order to apply the SVM to 64-QAM we introduce a binary coding SVM, which provides a binary multiclass classification with reduced complexity. We investigate the performance of this SVM and show how it can improve the bit-error rate (BER) of the entire system. After 100 km the fiber-induced nonlinear penalty is reduced by 2 dB at a BER of 3.7 10-3. Furthermore, we apply a nonlinear Volterra equalizer (NLVE), which is based on the nonlinear Volterra theory, as another method for mitigating nonlinear effects. The combination of SVM and NLVE reduces the large computational complexity of the NLVE and allows more accurate compensation of nonlinear transmission impairments.
[0.95]Mitigation of Nonlinear Impairments by Using Support Vector Machine and Nonlinear Volterra Equalizer
endstream
endobj
46 0 obj
<<
/Filter [/FlateDecode]
/Length 3871
>>
stream
xڵZ[w6~ϯqG/}$urlIm4Z#Mt.cO"A A4z<B%T
g"8Z0|b7
WbAUAUYKc#5ݐG{~10/iHbej`EI6:Df&OϞN&B$
Vom_=ghM@ĊY5OglȕHdWu/:˦>(\7WYKol;箬y9M]5QRcb3!},pL/Y]<*jmF]_*e[d<PWi8Og"Z[[7?\Sg1R"JqJ,yZEA,*u MvQd*SI&G3)H`,FI?
I3桒wPvO
)0hïڐ2aTBO#'㙈)L "חLn?H~;.PnӫѶJsmdl&SrèlԝN>'x6Oxԫtke*FXǁ\2*j.s0s
uח%EιڊkpĶWMOgFknޕW.omە7B"d!ee4}{upQ"\K^Ijմ(K}?FII8M0\"4 iޥkun%6wkonΖoU 7A
v蔃-^Jx1\]
|ynH9\c~kmUviyqr݇8 x(Ѐn:!u밉6Ȅo>
hlN%$3Ҷ`?Y;, X&"q
t16r/ZTd{Zp0
/yA۬i%qtZSvDUIdoBde5om ]C> bfwvo1lx}堖Nʁ"빕,]HyS2Q#Q;q<| Xo>xOͭF!
쩣dN&ԑlZilGei){ʭx"uzuE_lxMU5vv@qK9ka@x+՟m)Qx̔fd+@55ՂƳC?IPm6}u셁v[ⷣ+7{ށY9-fe>TGWCЦ{wJ>H0 vY)YA@+T$6
eTnl[cP^ڸS=6,뙢
|-l^v*#B(p[N&: 8dYh2KQilpl3AM?Mhtsbodco* ֝8*mBs뮡'~gaLnힻȐfF},=Hn-zl:kyͼ)eƮw#cFD`x$PaJh۲p1RtԸ C=r|k,#QlؚN*AI }Qtkշs9)|`[NPD4N w_b ;XEڎ
#+Zc쉆
vj_ɶ7XK7*'}A?һ.Vb@w/zJQPLgEa SCR b