基于深度学习的WLAN个体识别实践

该项目主要来源于实际的工程实践中，通过传感器采集到的WIFI信号来完成对个体的识别分析，数据集来源于真实环境采集，这里就暂时不放出来了，拿一个数据样本来举例说明，单个数据样本结构如下所示：

<type 'dict'>
['dmrsdata_opt', '__version__', '__header__', '__globals__']

本文中采集到的数据样例均为mat文件，需要解析处理，下面是解析代码：

#!usr/bin/env python
#encoding:utf-8
from __future__ import division'''
__Author__:沂水寒城
功能： 数据处理
'''import os
import json
import scipy.io as scio
from matplotlib import pyplot as pltdataFile = 'data/0.mat'
data = scio.loadmat(dataFile)
print(type(data))
print(data.keys())

从上面的结果可以看到单个数据样本是dict对象，里面共有4个键，数据对象存储在 dmrsdata_opt 中，接下来看下数据样例，代码实现如下：

value=data['dmrsdata_opt']
value=value.tolist()
for one in value:print one

结果如下：

[(-0.0007918778302306839+0.0015635690783301378j)]
[(-0.015343566502675158-0.012903878441803485j)]
[(0.004304750816005688-0.013818757363005748j)]
[(0.06706575930695897+0.015753424905311557j)]
[(0.05143436042568576-0.001965315624892796j)]
[(0.030319509251495635+0.011913896784290796j)]
[(0.005323942467451941-0.005878895393572519j)]
[(-0.0031591241566389892-0.03601726188808278j)]
[(0.031178331410580844-0.023614992946031706j)]
[(0.04350371116492135-0.06855920008022003j)]
[(0.004873764157005724-0.004945619801736011j)]
[(-0.0446833945850634+0.06014792435290728j)]
[(-0.012592437533106293+0.0170575582373121j)]
[(0.014632968921309403+0.06651300495372531j)]
[(-0.047964254378443136+0.015851999653825777j)]
[(-0.024351787497722276-0.08043393578274803j)]
[(-0.0026803630325430124-0.017765371156057874j)]
[(-0.07317035312002901-0.03061157718787506j)]
[(-0.015645396773547125-0.03688770865785794j)]
[(0.06936572090373899+0.020457666912395225j)]
[(0.053158424189278755-0.0007020257678296005j)]
[(0.03201730466866248+0.011617040895429928j)]
[(0.006898673233212326-0.005888967422528565j)]
[(-0.0016027273419863541-0.03832786709368796j)]
[(0.029334104590367425-0.026119250175436228j)]
[(0.04022325068513619-0.06751188661041577j)]
[(0.006557497280555391-0.0029127754893026273j)]
[(-0.044237207577107654+0.0631190815576329j)]
[(-0.009786288746971721+0.017698489844108448j)]
[(0.01510438000877306+0.06635251021923222j)]
[(-0.04966366405904105+0.01617963955040894j)]
[(-0.024387083409265268-0.07887701836676515j)]
[(-0.007033883640168763-0.01921276556369099j)]
[(-0.07475463224915743-0.02983033935668482j)]
[(-0.014702048262615942-0.03486279859305224j)]
[(0.07326801873707933+0.018146542984197524j)]
[(0.05224082124932434-0.0035126856661067164j)]
[(0.03203297830914367+0.009256558417460398j)]
[(0.003315231093153608-0.004950132249086503j)]
[(-0.0022279853083015076-0.03788220078552292j)]
[(0.028867203527986756-0.02751728721881755j)]
[(0.03650453541859455-0.0701761122383095j)]
[(0.0037816071055080964-0.005897992317229548j)]
[(-0.044077235519603464+0.06124459518696333j)]
[(-0.012301706279368316+0.020344667067038386j)]
[(0.015129604978419583+0.0632208592686126j)]
[(-0.04953846256567508+0.018207971019652755j)]
[(-0.025929418771209124-0.07889611529042219j)]
[(-0.0059260524538904-0.0206208759712363j)]
[(-0.07505148833493924-0.03152813101637623j)]
[(-0.017784343826181957-0.0387746413276666j)]
[(0.07358848463893797+0.01674346671239252j)]
[(0.0537736090395783-0.002722420072878675j)]
[(0.033596548326842675+0.010048436296921317j)]
[(0.005795878061411984-0.0036934916321030636j)]
[(-0.0037910317588729786-0.036328180218251536j)]
[(0.026042481385322686-0.024269985016937744j)]
[(0.03601906010954576-0.06768591646161376j)]
[(0.004552774786480018-0.005888443855401033j)]
[(-0.04581032220069925+0.06309836967732711j)]
[(-0.014145935076779935+0.017840411617911115j)]
[(0.015250288931751666+0.06680772212188896j)]
[(-0.05031917771987643+0.018969589348657542j)]
[(-0.02764340961570743-0.0785846733931259j)]
[(-0.004687461626308926-0.016867390684086214j)]
[(-0.07600225024601669-0.03046676004825956j)]
[(-0.019345014127832648-0.041094270537834134j)]
[(0.07359964360672211+0.015941514826777355j)]
[(0.05458909584497742-0.00738685901067318j)]
[(0.029382811365082386+0.010645570467680266j)]
[(0.004998964216703277-0.0029172879366531185j)]
[(-0.007333576673242154-0.0408814790169284j)]
[(0.02870219787827206-0.02643016751700589j)]
[(0.038379020800665006-0.07001613929066669j)]
[(0.005955849179547304-0.005567978052002861j)]
[(-0.04194227690212228+0.06703595986165596j)]
[(-0.012436454800894382+0.019087502882927414j)]
[(0.016818370853271373+0.06604106832193593j)]
[(-0.04827464914148436+0.018829805702792073j)]
[(-0.028270802545244375-0.08045412231564902j)]
[(-0.0037557988150048374-0.016386429701125638j)]
[(-0.07196016975540998-0.030733354507926566j)]
[(-0.01719727970718086-0.03613563691194395j)]
[(0.07235093956117339+0.017681777775177262j)]
[(0.05269765028274896-0.0036893793884857813j)]
[(0.03342489106401095+0.010378973140676437j)]
[(0.005835685134327775-0.006808944534205562j)]
[(-0.0051895941496590825-0.03820717957980137j)]
[(0.026388170279629666-0.02880471045908511j)]
[(0.03463456292894389-0.07189461775550487j)]
[(0.006432297220857839-0.00494110735438552j)]
[(-0.041761072067600664+0.06593425434832982j)]
[(-0.013238404165781564+0.019076340750427856j)]
[(0.0184010387832265+0.06529060994931438j)]
[(-0.04767352653557176+0.019139110659668387j)]
[(-0.03028906564454711-0.07875419213218135j)]
[(-0.00640701249748211-0.019689213110701976j)]
[(-0.07727004943494518-0.027184159760717613j)]
[(-0.018901723474288836-0.03659536323914937j)]
[(0.06972998493485272+0.012034709638769903j)]
[(0.05287220528443079-0.005547665782670276j)]
[(0.0322030223956039+0.008956802812551219j)]
[(0.0037654094035998254-0.00588340784092301j)]
[(-0.0062700650072300725-0.037615603458519095j)]
[(0.024492973710471107-0.02739156403706178j)]
[(0.03260675028075306-0.06942351712218892j)]
[(0.006422748759029324-0.0041699396734135976j)]
[(-0.035700211338454996+0.0663136249892092j)]
[(-0.010882958245819842+0.018304650392467026j)]
[(0.018105792313261683+0.06356203309638064j)]
[(-0.0470623270561681+0.021023143810349684j)]
[(-0.036231376493443844-0.07786181416187346j)]
[(-0.00814461404819589-0.016276904270508374j)]
[(-0.07651242320010904-0.022499014677290964j)]
[(-0.022800030202059656-0.03818866835003835j)]
[(0.07506110006182123+0.009258298714701664j)]
[(0.05369724144179707-0.010983271412837604j)]
[(0.034075372022774435+0.006801657662169043j)]
[(0.0047082334572648476-0.006204397211448715j)]
[(-0.005654355601203901-0.03729010020697449j)]
[(0.023747029120407985-0.03053276354797037j)]
[(0.027946828189774744-0.0717975400576951j)]
[(0.006091121268200903-0.0019649154211595823j)]
[(-0.03711069448405448+0.06907944140425344j)]
[(-0.012146247114283939+0.020028713265921393j)]
[(0.0240268732524778+0.06189687347705117j)]
[(-0.047701648353929774+0.023798512149316463j)]
[(-0.03594568135264436-0.07536206883628964j)]
[(-0.007809563323421866-0.017663780467367843j)]
[(-0.07870124663496958-0.02284522318432908j)]
[(-0.022824728341402756-0.032711118310696174j)]
[(0.07330730061028104+0.012685186840057948j)]
[(0.05243105186868556-0.007731456318537996j)]
[(0.03360557233140503+0.006931369180617989j)]
[(0.004722817933571385-0.006188199509540445j)]
[(-0.007368348225979473-0.036978660286876394j)]
[(0.02235350220057012-0.03162439614220185j)]
[(0.027976564074642885-0.07648772179759003j)]
[(0.005033735275141045-0.006820106221635808j)]
[(-0.03587927942947758+0.06973044771042171j)]
[(-0.011839843208663867+0.020955340507816767j)]
[(0.0240268732524778+0.06189687347705117j)]
[(-0.04848397579436398+0.024590912705766285j)]
[(-0.03780848162784775-0.07397809037828029j)]
[(-0.008762459406042932-0.018917521862602524j)]
[(-0.08103997365893277-0.019742218509333644j)]
[(-0.024693088643281014-0.034460404176598874j)]
[(0.07303514394982003+0.00550984756329187j)]
[(0.05294013521353393-0.013322522003928333j)]
[(0.03437674001237695+0.0069409176424465036j)]
[(0.003800704029165125-0.007440327679173393j)]
[(-0.00922716095616784-0.039499114822350107j)]
[(0.02310609751361164-0.027726614761835806j)]
[(0.027956377541741885-0.07256870675006794j)]
[(0.007688937837841276-0.007421754322643895j)]
[(-0.03416979771992362+0.07097753857959893j)]
[(-0.006694444721577197+0.02083916489775088j)]
[(0.02370136911079457+0.06251258189447825j)]
[(-0.04663020051232205+0.026324002254198883j)]
[(-0.0405939228859092-0.07619214343040144j)]
[(-0.007981219696114962-0.01733324263501362j)]
[(-0.059532278310395044-0.022859224834078432j)]
[(-0.0006206217105010313-0.044110206972140076j)]
[(0.00865543294421098-0.03234228247434184j)]
[(0.034251203754450385-0.06192932314273751j)]
[(0.05412427182159682+0.015028889728930881j)]
[(-0.04455309781778976+0.04146495213563271j)]
[(-0.06654053954606043+0.00013959672203625595j)]
[(-0.049213023863164465+0.03909093276068102j)]
[(-0.021189489553572433+0.04239615355580598j)]
[(-0.013208083922227363-0.004766613886710134j)]
[(-0.0014916513068333756-0.012471163732565677j)]
[(0.012253520204444063-0.05476358847174442j)]
[(-0.05387161021087018-0.0516544489581015j)]
[(-0.05843063536890469-0.0011793506327796438j)]
[(-0.008437419918666422-0.04337780016919775j)]
[(0.04100436559800144-0.022930266276235234j)]
[(0.0696530900124685+0.0014279596551577262j)]
[(0.022669054809354806-0.0768121752444637j)]
[(0.016281477856026242-0.031201816082986104j)]
[(-0.01667426123881531-0.0010590613454280664j)]
[(-0.021110275611474064-0.009177991405883879j)]
[(0.02703181517294466+0.03135739994667274j)]
[(0.022193532565333438-0.029749911057509983j)]
[(0.03289226146352063-0.0024277634993526195j)]
[(-0.04442737320236558+0.04583918155730929j)]
[(-0.044158977208829456-0.01464553055443738j)]
[(0.02921786631000528-0.009765977417007994j)]
[(-0.019062217714482375-0.03706677477168233j)]
[(0.00854822099221823-0.019106076239456912j)]
[(-0.004777899778443093+0.05700737256419869j)]
[(-0.014518068954178068+0.00550508517520708j)]
[(0.04498806437318516-0.016193176447391103j)]
[(-0.0173684138971846-0.033459201176387204j)]
[(0.02823239907704128-0.026300455009957844j)]
[(0.0404592352051719+0.053436306962946226j)]
[(-0.02199079253146755+0.0017335505437243437j)]
[(0.0012538656487676228-0.04395023580477453j)]
[(-0.04906751247350318-0.0057970915283498195j)]
[(-0.007349312984019602-0.017022325293443965j)]
[(0.028566862674252888-0.00853455939663381j)]
[(0.0004759866501797116-0.023217698549560552j)]
[(0.014703973703409163-0.07266133610449188j)]
[(-0.05967200116470197-0.046402424756445876j)]
[(-0.039620199869554035-0.03970294204319246j)]
[(0.031561165040748615-0.03592618422525412j)]
[(0.03424083787610273+0.029559102906530046j)]
[(0.06469341211966007-0.0011161036093332646j)]
[(0.03403285220686978-0.05305115001205907j)]
[(0.008130091253586512-0.005237963786776174j)]
[(-0.0014604076882575104+0.01137501780084509j)]
[(-0.023326585359621965+0.034289671178927436j)]
[(0.006295749983569243+0.05832852121154759j)]
[(0.05010863730268036+0.03216553518331067j)]
[(0.018009804224695895+0.05449761867163325j)]
[(-0.055945476051756295-0.0014812412009105914j)]
[(-0.022498013995957578-0.07870084821151363j)]
[(-0.004631741556720435-0.02853209211011467j)]
[(-0.0513909627975425-0.050397807846818514j)]
[(0.027679706208583815-0.07818551543447963j)]
[(0.0510116560144766+0.03496000163145451j)]
[(-0.03774711517562922+0.0703270594011127j)]
[(-0.009500131177212087+0.04404280258736268j)]
[(0.008795430760119072+0.07954149721780254j)]
[(-0.06720836811323513+0.027606847261334506j)]
[(-0.017648380898349192-0.0828914979357255j)]
[(0.06347404197496902-0.049409263535511325j)]
[(0.004863755243415245-0.02801902131871175j)]
[(0.02849009576287707-0.0621386489054785j)]
[(0.05510476625390884+0.009277329309047459j)]
[(-0.04098029280943466+0.04367396437797106j)]
[(-0.0669260336837757+0.007789776104115451j)]
[(-0.0430131366275685+0.045357697056451415j)]
[(-0.016204063123989945+0.04415446431640965j)]
[(-0.012160769958123551-0.001486153851994296j)]
[(-0.0017672740228377353-0.013396176858720698j)]
[(0.006141167246285304-0.0535714566768046j)]
[(-0.0590562917586758-0.046076921504901266j)]
[(-0.05940609334166938+0.005359575664283522j)]
[(-0.01327137561831818-0.04154763272603445j)]
[(0.04008172862076719-0.0265282933376698j)]
[(0.0706431375542231-0.005094767260177588j)]
[(0.013330633316472287-0.07767198374624544j)]
[(0.011616517328302397-0.034363203115394786j)]
[(-0.014009510659355875-0.0024318776217076227j)]
[(-0.020223455887563795-0.006368942903701002j)]
[(0.030483932025422912+0.029979548644514256j)]
[(0.01813021910078835-0.03025609369771095j)]
[(0.030902647507178874-0.0030413361618797635j)]
[(-0.039782035587693804+0.048197006790907215j)]
[(-0.04572705735007192-0.013878874777286165j)]
[(0.031552604008676204-0.008964551075718563j)]
[(-0.02297406133923536-0.03398448019671541j)]
[(0.009925549715848282-0.017999858723849592j)]
[(0.0016453715098844295+0.05518333316702488j)]
[(-0.012053620182127512+0.006776310713566371j)]
[(0.047988952913625316-0.021329548259499544j)]
[(-0.024843511744657133-0.033357085931970544j)]
[(0.024023174909240327-0.027261851530013734j)]
[(0.047978655243326604+0.048660208718372254j)]
[(-0.019349650383646774+0.003461602742470981j)]
[(-0.00360132371804019-0.04289285020755374j)]
[(-0.049241022318128144+0.0007529935395765366j)]
[(-0.0087972304644807-0.015014703577619831j)]
[(0.028611705267347156-0.010862646470786802j)]
[(-0.0010920953698004675-0.022451042870869815j)]
[(0.009242621119824088-0.0727006140232972j)]
[(-0.06282835173756332-0.04095009835154229j)]
[(-0.044178011560650696-0.034601864559270716j)]
[(0.02597912909459428-0.03955233626976213j)]
[(0.033144170602601164+0.03016526592638636j)]
[(0.06377367441340483-0.006241882495773992j)]
[(0.027835101714772843-0.0570027970999431j)]
[(0.006295411906602506-0.008513387807013991j)]
[(-0.002873030543153309+0.01182571967841884j)]
[(-0.02161710607233551+0.03553676333408236j)]
[(0.012377321899803007+0.057134772482760846j)]
[(0.05262856817256607+0.027960825885127716j)]
[(0.022056920383171787+0.05501838722180915j)]
[(-0.056755926200687146+0.003970559856588209j)]
[(-0.028935345748394795-0.07454710757521624j)]
[(-0.007270745972443085-0.02794502799111357j)]
[(-0.05654752292282918-0.04947968331693477j)]
[(0.019412203255507864-0.07886573069475494j)]
[(0.051857400491594145+0.027951277423299198j)]
[(-0.029990834091177903+0.07428322116169378j)]
[(-0.0043295105878157075+0.04079497681835534j)]
[(0.015832277676771037+0.07572784119387112j)]
[(-0.06523680305615673+0.03445455316786921j)]
[(-0.025309199241639487-0.0801291456954897j)]
[(0.0552458273229861-0.05555083177720799j)]
[(-0.0011689865347092251-0.03305779265756106j)]
[(0.02027194918545381-0.06670548282086028j)]
[(0.054361196725706926+0.0022624827895762825j)]
[(-0.03710612188713571+0.046022240259601846j)]
[(-0.0672695876148609+0.01463961677695098j)]
[(-0.03758655589210215+0.04929979934152191j)]
[(-0.011709144705528137+0.04761560517345026j)]
[(-0.014490470702947587-0.0015002147611733003j)]
[(-0.0011706619363076702-0.011528339678900656j)]
[(0.003685741836806842-0.057959746068291323j)]
[(-0.06377568601323227-0.03907057344566672j)]
[(-0.05697931420781509+0.012061367110086915j)]
[(-0.01639295463844221-0.039998125051182866j)]
[(0.03871845981771706-0.02996421070796254j)]
[(0.07191545141584865-0.009935898140073906j)]
[(0.00864044959937918-0.07770171785083632j)]
[(0.00866897073133177-0.037017881171598634j)]
[(-0.014829509862875258+0.0037910934405701374j)]
[(-0.01914084729789468-0.004645402707235543j)]
[(0.03160634635279987+0.028587634455978575j)]
[(0.016271405827070193-0.032776546848746486j)]
[(0.03168735109653386-0.007707386495768511j)]
[(-0.03931009851083512+0.05038240921716873j)]
[(-0.04529492971916629-0.00857801910231331j)]
[(0.03158737457281442-0.012867368915631939j)]
[(-0.02798974771511306-0.033398507219087166j)]
[(0.007800662682253829-0.022216493127081384j)]
[(0.006154352172733177+0.056314774762140106j)]
[(-0.010660094250888742+0.007867944197936466j)]

完整项目目录如下：

文件说明如下表所示：

文件名称	文件说明
data/	数据集目录
result/	结果数据目录
dataHandle.py	数据解析模块
ploter.py	数据可视化模块
test.py	模型测试分析模块
tools.py	工具模块
trainModel.py	模型建模训练模块

模型结构如下所示：

默认设置100次迭代计算，训练输出如下：

模型摘要如下：

_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
input_1 (InputLayer)         (None, 128, 160, 2)       0
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 128, 160, 16)      304
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 64, 80, 16)        0
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 64, 80, 24)        3480
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 32, 40, 24)        0
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 32, 40, 32)        6944
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 16, 20, 32)        0
_________________________________________________________________
flatten_1 (Flatten)          (None, 10240)             0
_________________________________________________________________
dvector (Dense)              (None, 128)               1310848
_________________________________________________________________
activation_1 (Activation)    (None, 128)               0
_________________________________________________________________
dense_1 (Dense)              (None, 2)                 258
=================================================================
Total params: 1,321,834
Trainable params: 1,321,834
Non-trainable params: 0
_________________________________________________________________

模型测试准确度如下所示：

训练集-测试集损失函数曲线如下所示：

训练集-测试集准度率曲线如下所示：

模型分类混淆矩阵如下所示：

后续有时间再来填坑，详细介绍了。

基于深度学习的WLAN个体识别实践相关推荐

蚂蚁金服张洁：基于深度学习的支付宝人脸识别技术解秘-1
蚂蚁金服张洁:基于深度学习的支付宝人脸识别技术解秘(1) 2015-08-13 10:22 于雪 51CTO 字号:T | T 用户身份认证是互联网金融发展的基石.今年三月,在德国汉诺威举办的IT展览 ...
DeepEye：一个基于深度学习的程序化交易识别与分类方法
DeepEye:一个基于深度学习的程序化交易识别与分类方法徐广斌,张伟上海证券交易所资本市场研究所,上海 200120 上海证券交易所产品创新中心,上海 200120 摘要:基于沪市A股交 ...
一种基于深度学习的增值税发票影像识别系统
一种基于深度学习的增值税发票影像识别系统-专利技术交底书缩略语和关键术语定义 1.卷积神经网络(Convolutional Neural Networks, CNN)是一类包含卷积计算且具有深度结构 ...
基于深度学习的人脸性别识别系统（含UI界面，Python代码）
摘要:人脸性别识别是人脸识别领域的一个热门方向,本文详细介绍基于深度学习的人脸性别识别系统,在介绍算法原理的同时,给出Python的实现代码以及PyQt的UI界面.在界面中可以选择人脸图片.视频进行检 ...
基于深度学习的轴承故障识别-构建基础的CNN模型
上回书说到,处理序列的基本深度学习算法分别是循环神经网络(recurrent neural network)和一维卷积神经网络(1D convnet).上篇构建了基础的LSTM模型,这一篇自然轮到CN ...
基于深度学习的轴承故障识别
毕设题目:基于深度学习的轴承故障识别.这个博客用来记录和整理毕设过程中遇到的一些问题,看的一些参考资料等. 目录轴承故障识别_实验过程深度学习相关笔记 Tensorflow学习笔记无归类杂项一 ...
基于深度学习的声纹识别
一.选题 1.1 题目: 基于深度学习的声纹识别 1.2 研究内容: ① 研究用于声纹识别的语音参数以及这些参数对声纹识别性能的影响. ② 研究声纹识别的传统方法及性能. ③ 在研究声纹识别的传统方法 ...
基于深度学习的轴承故障识别-总结及常见问题
新年快乐. 把猪年的事结束在猪年,这篇写一下最后的总结展望,顺便归纳一下常被问到的问题. 总结前面做的简单概括就是:选择神经网络模型→测试CNN和LSTM→选择CNN→优化. 我认为的几个主要的缺陷 ...
opencv交通标志识别_教你从零开始做一个基于深度学习的交通标志识别系统
教你从零开始做一个基于深度学习的交通标志识别系统基于Yolo v3的交通标志识别系统及源码自动驾驶之--交通标志识别在本文章你可以学习到如何训练自己采集的数据集,生成模型,并用yolo v3算法 ...
《基于深度学习的加密流量识别研究》-2022毕设笔记
参考文献: 基于深度学习的网络流量分类及异常检测方法研究_王伟基于深度学习的加密流量分类技术研究与实现_马梦叠基于深度学习的加密流量识别研究综述及展望_郭宇斌基于深度学习的加密流量算法识别研究_ ...

基于深度学习的WLAN个体识别实践

基于深度学习的WLAN个体识别实践相关推荐

最新文章

热门文章