izpis_h1_title_alt

Ločevanje skupin elektromiografskih materničnih posnetkov s terminskim in prezgodnjim porodom z uporabo vzorčne entropije.
Semenova, Vlada (Author), Jager, Franc (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (1,00 MB)

Abstract
Napovedovanje prezgodnjega poroda je pereč in nerešen problem. V magistrskem delu sem se osredotočila na reševanje problema ločevanja in klasifikacije skupin elektromiografskih materničnih posnetkov s terminskim in prezgodnjim porodom, snemanih tako pred 26. kot po 26. tednu nosečnosti. Do sedaj so bile narejene raziskave v katerih so ločevali ti dve skupini na frekvenčnem področju s spodnjo mejo od 0,08 Hz do 0,3 Hz ter zgornjimi mejami do 3Hz ali 4Hz. V magistrskem delu sem se osredotočila na področji med 0,08 Hz ter 5 Hz, saj ti predeli niso dobro raziskani. Uporabila sem vzorčno entropijo, kot eno od trenutno najbolj obetavnih tehnik in mednarodno referenčno podatkovno bazo TPEHG DB materničnih elektromiografskih posnetkov. Za klasifikacijo posnetkov sem testirala klasifikator k najbljižjih sosedov(k-NN), klasifikatorja z linearno in kvadratično diskriminantno analizo (LDA,QDA), Naivni Bayes, metodo podpornih vektorjev ter odločitvena drevesa. Za oceno stopnje ločevanja skupin posnetkov sem uporabila statistično analizo variance (ANOVA). Zaradi neenakomerne porazdelitve med številom posnetkov, ki so bili prezgodji ter terminski, sem uporabila metodo sintetičnega prevzorčevanja minoritetne množice (SMOTE), da bi s tem zagotovila bolj resnične rezultate. Rezultat magistrskega dela je, da smo potrdili, da je za klasifikacijo med prezgodnjimi in terminskimi porodi na posnetkih, ki so bili posneti zgodaj, najboljše področje od 1 Hz - 5 Hz. Ugotovili smo tudi, da z višanjem frekvence ali širjenjem frekvenčnega območja, postanejo pre- zgodnji posnetki manj regularni in manj napovedljivi; terminski posnetki pa nasprotno postanejo bolj regularni ter bolj napovedljivi. Doseženi rezultati klasifikacije posnetkov s terminskim in prezgodnjim porodom so ob uporabi frekvenčnega področja od 1 Hz do 2,2 Hz in samo značilk vzorčne entropije (občutljivost 88,8 %, specifičnost 81,8 %, klasifikacijska točnost 85,3%) povsem primerljivi doseženim rezultatom klasifikacije drugih obstoječih študij (občutljivost 89 %, specifičnost 91 %, klasifikacijska točnost 90 %), ki pa so poleg značilk vzorčne entropije vključevale še druge značilke signalov, značilke spektrov signalov, prav tako pa tudi dodatno klinično informacijo o nosečnostih.

Language:Slovenian
Keywords:terminski porod, prezgodnji porod, podatkovna baza TPEHG DB, klasifikacija med posnetki s prezgodnjim in terminskim porodom, Butterworth-ov filter, vzorčna entropija
Work type:Master's thesis/paper (mb22)
Organization:FRI - Faculty of computer and information science
Year:2016
Views:519
Downloads:244
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share: Bookmark and Share

Secondary language

Language:English
Title:Separating sets of term and pre-term uterine electromyogram records using sample entropy
Abstract:
Predicting preterm labour is a serious and unresolved problem. In this master thesis I focused on resolving the problem of separation and classifi- cation of groups of uterine electromyographic recordings with the term and pre-term birth, which were recorded before 26th week and after 26th week of gestation. Until now, studies have been made where they separated the two groups in the frequency range with a lower limit of 0.08 Hz to 0.3 Hz and highest limit of 3 Hz or 4 Hz. In this master thesis, I focused on the area between 0.08 Hz and 5 Hz, since these areas are not well researched. I used the sample entropy as one of the currently most promising techniques and international reference database TPEHG DB of uterine electromyographic recordings. For the classification of recordings I tested the K nearest neighbors (K-NN) classifier, linear and quadratic discriminant analysis (LDA, QDA) classifiers, Naive Bayes, support vector machine method and decision trees. To assess the degree of separation of groups of recordings I used a statistical analysis of variance (ANOVA). Because of the uneven distribution of the number of recordings that were preterm and term, I used Synthetic Minority Over-sampling Technique (SMOTE), in order to ensure more real results. The result of the master’s thesis is that it was confirmed that the classification between preterm and term births on the recordings that were recorded early the best area was from 1 Hz - 5 Hz. We have also found that by increasing of the frequency or by widening of the frequency area, preterm recordings become less regular and less predictable; term recordings on the contrary, become more regular and more predictable. The achieved results of classification of recordings with term and preterm delivery using frequency band from 1 Hz and 2.2 Hz, and sample entropy features only, (Sensitivity 88.8 %, Specificity 81.8 %, Classification accuracy 85.3 %) are quite comparable to achieved results of classification of other existing studies (Sensitivity 89 %, Specificity 91 %, Classification accuracy 90 %) which, besides sample entropy features, also involved other signal features, signal spectra features, as well as additional clinical information about pregnancies.

Keywords:Term labour, Pre-term labour, TPEHG DB data base, Classification between sets of term and pre-term records, Butterworth filter, Sample entropy

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back