Fingertip ECG signal based biometric recognition system
dc.contributor.advisor | Gürkan, Hakan | en_US |
dc.contributor.advisor | Güz, Ümit | en_US |
dc.contributor.author | Güven, Gökhan | en_US |
dc.contributor.other | Işık Üniversitesi, Fen Bilimleri Enstitüsü, Elektronik Mühendisliği Yüksek Lisans Programı | en_US |
dc.date.accessioned | 2016-08-02T10:29:57Z | |
dc.date.available | 2016-08-02T10:29:57Z | |
dc.date.issued | 2016-05-10 | |
dc.department | Işık Üniversitesi, Fen Bilimleri Enstitüsü, Elektronik Mühendisliği Yüksek Lisans Programı | en_US |
dc.description | Text in English ; Abstract: English and Turkish | en_US |
dc.description | Includes bibliographical references (leaves 94-98) | en_US |
dc.description | xviii, 115 leaves | en_US |
dc.description.abstract | The idea is the; realize biometric recognition system by using ECG signal which was began to use in the last 10 years. Until now, ECG based biometric systems have been developed by using the database which ECG signals are taken from the subjects’ chest by using patient monitor or high speed data acquisition systems. For constructing database, most researchers have used three disposable ECG electrodes on subjects’ chest to extract the ECG signal. Because of that, ECG based biometric systems were being considered hard to use. For this reason, we want to make a system that is easy to carry, and easy to apply on subjects. In most of biometric systems, ECG database have constructed by using ECG signal of the subjects that were taken by using electrodes which were located in left and right side of the heart with a reference electrode on right leg. However, in our system, the database consisted of the ECG signals which were taken by using patient’s right and left thumb. The difference of our system with the others is; there is EMG noise which is in the same frequency range with ECG signal. Because of frequencies are the same, it is very hard to eliminate with filters. For this reason, database was enhanced by applying the different filters on ECG signal to reduce the noises for higher recognition rate. First week of the dataset -which was obtained by using ECG signals of 30 people in two separate weeks- is extracted the personality information by performing AC/DCT and MFCC methods and is reserved as training dataset. ECG signals which obtained by AC/DCT methods in second week are called as test dataset. First candidate is determined by putting the AC/DCT features of an unknown person into the LDA classifier. In the meantime, same person’s MFCC features put into the LDA classifier and the second candidate is determined. If these two candidates are the same, they are labeled as A and B person. If they are not the same person, then QRS frames of the proximate two candidates obtained from AC/DCT features and QRS frames of the proximate two candidates obtained from MFCC features are sent to K-NN algorithm. QRS frames of these 4 candidates are sorted ascending according to the proximity to the QRS frame of unknown person, and nearest candidate to unknown QRS segment is labeled as A and B person. Proposed method was reached to success at rate of %96 average frame recognition. | en_US |
dc.description.abstract | Projenin başlıca amacı, 10 yıldan beri süre gelen EKG sinyali ile yapılan biyometrik sistemlerini, farklı bir ölçüm yöntemiyle gerçekleştirmektir. Şu ana kadar yapılan EKG tabanlı biometrik sistemlerin çoğu, hastanelerde kullanılan hasta başı monitör veya yüksek hızlı veri analiz kartları yardımıyla EKG ölçümlerinin alınarak veri kümelerinin oluşturulmasına dayanmaktadır. Bu kapsamda her bir deneğin göğsüne tek kullanımlık 3 adet elektrot takılarak kanal 1 ölçüm uçlarından EKG sinyali alınmıştır. Her bir denek için kullanılan elektrotlar hem maliyeti arttırmakta, hem de zahmetli bir iş olmaktadır. Bu cihazların pahalı olmasının yanı sıra kullanılabilirlikleri de bir hayli zordur. Bu yüzden amacımız; kolaylıkla taşınabilir, kullanımı kolay, elektrot tak çıkar derdinden kurtaracak bir sistem yaparak biyometrik tanıma sistemini gerçekleştirmek istememizdir. Diğer biyometrik tanıma sistemlerinde, kalbin sağ ve sol tarafına yerleştirilen elektrotlar ve sağ bacağa takılan referans elektrotu ile alınan EKG sinyallerinden oluşan veri kümeleri kullanılmıştır. Sistemimizde ise sağ ve sol kol başparmaklardan alınan EKG sinyallerinin diğer parmakları da referans alarak veri kümesini oluşturmaktayız. Diğer sistemlerden farklı olarak sistemimizde, EKG sinyallerinin üstüne binen EMG gürültüsü daha fazla olmaktadır. EKG ve EMG sinyallerin frekans aralıkları iç içe olduklarından dolayı birbirinden filtreler yardımıyla ayrılması bir hayli zordur. Bu nedenle farklı filtreler uygulayarak EKG sinyallerinin gürültü oranını azaltmaya yönelik yöntemler kullandık ve EKG veri tabanlarımızı geliştirdik. Otuz kişiden iki farklı haftada aldığımız EKG sinyalleriyle oluşturulan veri kümesinin ilk haftası AC/DCT ve MFCC metotlarına uygulanarak kişilik bilgileri çıkartılır ve eğitim veri seti olacak şekilde ayrılır. İkinci hafta aldığımız EKG sinyalleri ise AC/DCT ve MFCC metotlarından geçirilerek test veri seti olarak isimlendirilir. AC/DCT öznitelikleri çıkarılan kişi LDA sınıflandırıcıya sokularak bir aday belirlenir. Eş zamanlı olarak aynı kişinin MFCC öznitelikleri de LDA sınıflandırıcıya sokularak bir aday daha belirlenir. Eğer bu iki aday aynı ise, A veya B kişisi diye etiketlenir. Eğer birbirinden farklı iseler AC/DCT özniteliklerinden çıkarılan en yakın iki adayın QRS bölütleri ve MFCC özniteliklerinden çıkarılan en yakın iki adayın QRS bölütleri K-NN algoritmasına gönderilir. Bu dört adayın QRS bölütleri, bilinmeyen kişinin QRS bölüdüne yakınlığına göre küçükten büyüğe sıralanır ve en yakın aday, A veya B kişisi olarak etiketler. Önerdiğimiz yöntemle ortalama bölüt tanıma oranı %96 ‘ya ulaşmıştır | en_US |
dc.description.tableofcontents | Introduction to Biometric Recognition System | en_US |
dc.description.tableofcontents | Biosignals | en_US |
dc.description.tableofcontents | Measurement Techniques | en_US |
dc.description.tableofcontents | 12-Lead Measurement Setup and Einthoven’s triangle | en_US |
dc.description.tableofcontents | Common Monitoring Problems | en_US |
dc.description.tableofcontents | Baseline Wandering | en_US |
dc.description.tableofcontents | Powerline Noise | en_US |
dc.description.tableofcontents | Muscle Tremor | en_US |
dc.description.tableofcontents | Misleaded Electrodes | en_US |
dc.description.tableofcontents | ECG Waveform Components | en_US |
dc.description.tableofcontents | P wave | en_US |
dc.description.tableofcontents | PR interval | en_US |
dc.description.tableofcontents | QRS complex | en_US |
dc.description.tableofcontents | ST segment | en_US |
dc.description.tableofcontents | T wave | en_US |
dc.description.tableofcontents | QT interval | en_US |
dc.description.tableofcontents | Analog Filters | en_US |
dc.description.tableofcontents | Fundamentals of Analog Filters | en_US |
dc.description.tableofcontents | Lowpass Filter Design | en_US |
dc.description.tableofcontents | First-order lowpass filter design | en_US |
dc.description.tableofcontents | Second order unity gain lowpass filter design | en_US |
dc.description.tableofcontents | Highpass Filter Design | en_US |
dc.description.tableofcontents | First-order inverting highpass filter design | en_US |
dc.description.tableofcontents | Second-order unity gain highpass filter design | en_US |
dc.description.tableofcontents | Designing 5th order Lowpass Filter | en_US |
dc.description.tableofcontents | Digital Filters | en_US |
dc.description.tableofcontents | Fundamental of Digital Filters | en_US |
dc.description.tableofcontents | FIR Lowpass Filter | en_US |
dc.description.tableofcontents | FIR Highpass Filter | en_US |
dc.description.tableofcontents | FIR Bandpass Filter | en_US |
dc.description.tableofcontents | FIR Bandstop Filter | en_US |
dc.description.tableofcontents | FIR and IIR Notch Filter Design | en_US |
dc.description.tableofcontents | IIR and FIR Notch Filter Application on Matlab | en_US |
dc.description.tableofcontents | IIR Notch Filter Application on dsPICs | en_US |
dc.description.tableofcontents | Design of Fingertip ECG Measurement System | en_US |
dc.description.tableofcontents | Block Diagram of Fingertip ECG Measurement System | en_US |
dc.description.tableofcontents | Power Supply of ECG circuit | en_US |
dc.description.tableofcontents | Instrumentation Amplifier | en_US |
dc.description.tableofcontents | Right Leg Drive Circuit | en_US |
dc.description.tableofcontents | 5ᵗʰ order Lowpass Filter | en_US |
dc.description.tableofcontents | Opto-coupler | en_US |
dc.description.tableofcontents | Schematic of Fingertip ECG Circuit | en_US |
dc.description.tableofcontents | dsPIC microC Program | en_US |
dc.description.tableofcontents | Matlab Program | en_US |
dc.description.tableofcontents | Matlab Outputs of the ECG circuit | en_US |
dc.description.tableofcontents | Basics for designing PCB of Fingertip ECG | en_US |
dc.description.tableofcontents | Introductions to Feature Extraction and Classification | en_US |
dc.description.tableofcontents | Features related to ECG Based Biometric Systems and Features Extraction Methods | en_US |
dc.description.tableofcontents | AC/DCT Based Features | en_US |
dc.description.tableofcontents | Mel-Frequency Cepstral Coefficient Based Features | en_US |
dc.description.tableofcontents | Methods for Classification | en_US |
dc.description.tableofcontents | Linear Discriminant Analysis based Classification Method | en_US |
dc.description.tableofcontents | K-Nearest Neighbors (K-NN) Classification Method | en_US |
dc.description.tableofcontents | Proposed Method | en_US |
dc.description.tableofcontents | Preprocessing Stage | en_US |
dc.description.tableofcontents | Feature Extraction and Classification Process | en_US |
dc.description.tableofcontents | Experimental Work | en_US |
dc.description.tableofcontents | ECG Dataset | en_US |
dc.description.tableofcontents | Assessment Creteria | en_US |
dc.description.tableofcontents | Assessment Result | en_US |
dc.description.tableofcontents | Discussion and Conclusions | en_US |
dc.description.tableofcontents | Selection of Microcontroller | en_US |
dc.description.tableofcontents | Basic configuration of dsPIC30F3011 | en_US |
dc.description.tableofcontents | Amplifier | en_US |
dc.description.tableofcontents | Operational Amplifier | en_US |
dc.description.tableofcontents | Op-amp Selection | en_US |
dc.description.tableofcontents | Instrumentation Amplifier | en_US |
dc.description.tableofcontents | Instrumentation Amplifier Selection | en_US |
dc.description.tableofcontents | Other Circuit Components | en_US |
dc.description.tableofcontents | DC-DC Isolated Voltage Regulator | en_US |
dc.description.tableofcontents | FT232RL USB Serial Adapter | en_US |
dc.description.tableofcontents | Crystal Oscillator | en_US |
dc.description.tableofcontents | SMD LED | en_US |
dc.description.tableofcontents | SMD Capacitor | en_US |
dc.description.tableofcontents | Opto-coupler | en_US |
dc.description.tableofcontents | Normalized Denominator Polynomials in Factored Form | en_US |
dc.description.tableofcontents | EPIC Ultra High Impedance ECG Sensor | en_US |
dc.identifier.citation | Güven, G. (2016). Fingertip ECG signal based biometric recognition system. İstanbul: Işık Üniversitesi Fen Bilimleri Enstitüsü. | en_US |
dc.identifier.uri | https://hdl.handle.net/11729/1063 | |
dc.institutionauthor | Güven, Gökhan | en_US |
dc.language.iso | en | en_US |
dc.publisher | Işık Üniversitesi | en_US |
dc.relation.publicationcategory | Tez | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 United States | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/us/ | * |
dc.subject.lcc | TK7882.B56 G88 2016 | |
dc.subject.lcsh | Biometric identification. | en_US |
dc.subject.lcsh | Electrocardiography -- Data processing. | en_US |
dc.subject.lcsh | Electrocardiography -- methods. | en_US |
dc.subject.lcsh | Fingerprints. | en_US |
dc.subject.lcsh | Anthropometry -- Methodology. | en_US |
dc.title | Fingertip ECG signal based biometric recognition system | en_US |
dc.title.alternative | Parmak ucu EKG tabanlı biyometrik tanıma sistemi | en_US |
dc.type | Master Thesis | en_US |
dspace.entity.type | Publication |