Preprocessing and parameter extraction algorithms for diagnostic analysis of EMCG
Başlık çevirisi mevcut değil.
- Tez No: 400549
- Danışmanlar: PROF. JAAKKO MALMIVUO, YRD. DOÇ. DR. JUHA NOUSIAINEN
- Tez Türü: Yüksek Lisans
- Konular: Elektrik ve Elektronik Mühendisliği, Electrical and Electronics Engineering
- Anahtar Kelimeler: Belirtilmemiş.
- Yıl: 1998
- Dil: İngilizce
- Üniversite: Tampereen Teknillinen Yliopisto (Tampere University of Technology)
- Enstitü: Yurtdışı Enstitü
- Ana Bilim Dalı: Elektrik Mühendisliği Ana Bilim Dalı
- Bilim Dalı: Belirtilmemiş.
- Sayfa Sayısı: 96
Özet
Özet yok.
Özet (Çeviri)
The electrocardiography (ECG) and the magnet ocardiograpliy (MCG) are fully non-invasive, totally harmless, safe and quick methods for measuring the electrical activity of the heart. However, diagnostic information conveyed by the non-invasive ECG and MCG signals is limited. Also, differences in the ECG and MCG waveforms induced by a diagnostic event may overlap with normal inter individual variability. Furthermore, especially the MCG signals may be highly distorted by the environmental noise. This study concerns the preprocessing and parameter extraction algorithms for use in the diagnostic analysis of the MCG together with ECG. This combined analysis of the simultaneous ECG and MCG is called electromag-netocardiography (EMCG). Preprocessing of EMCG signals needs several steps. Adaptive filtering, transform domain non-linear filtering and template averaging were implemented in this study. Adaptive noise cancellation is based on local optimization of "filtering parameters and it is a proven method for improving signal to noise ratio (SNR) at first stage. An adaptive noise canceller is designed for primary attenuation of the expected high level noise in MCG measurements. Adaptive noise cancelling, designed filter and its results with the expected noise are introduced. However, high noise level and the variability in the MCG signals bring the necessity of further denoising. Local optimization of the balance between detail preservation and noise attenuation in transform domain, is discussed. The transform domain filter designed for EMCG signals and results of the filter are introduced. QRS-complex detection with Haar-wavelet, stationary reference point evaluation in filtered signal, noise level detection for each beat, rejection of noisiest heart beats, baseline correction and template averaging algorithms are introduced.
Benzer Tezler
- Condition monitoring and fault detection for electrical power systems using signal processing and machine learning techniques
Sı̇nyal ı̇şleme ve makı̇ne öğrenme teknı̇klerı̇ kullanılarak elektrı̇k güç sı̇stemleri ı̇çı̇n durum ı̇zleme ve arıza belirleme
YASMIN NASSER MOHAMED
Doktora
İngilizce
2024
Elektrik ve Elektronik Mühendisliğiİstanbul Teknik ÜniversitesiElektrik Mühendisliği Ana Bilim Dalı
PROF. DR. ŞAHİN SERHAT ŞEKER
- Bulanık (Fuzzy) sınıflayıcılarla EKG şekil bozukluklarının belirlenmesi
Detection of ECG shape changes by using fuzzy classifiers
ZÜMRAY DOKUR
- Derin öğrenme ile histopatolojik görüntü analizi
Histopathological image analysis using deep learning
ŞABAN ÖZTÜRK
Doktora
Türkçe
2019
Elektrik ve Elektronik MühendisliğiKonya Teknik ÜniversitesiElektrik-Elektronik Mühendisliği Ana Bilim Dalı
DOÇ. DR. BAYRAM AKDEMİR
- Prediction of COVID 19 disease using chest X-ray images based on deep learning
Derin öğrenmeye dayalı göğüs röntgen görüntüleri kullanarak COVID 19 hastalığının tahmini
ISMAEL ABDULLAH MOHAMMED AL-RAWE
Yüksek Lisans
İngilizce
2024
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolGazi ÜniversitesiBilgisayar Mühendisliği Ana Bilim Dalı
PROF. DR. ADEM TEKEREK
- EMG işaretlerinin tanı destek amaçlı sınıflandırılması
Classification of EMG signals for the purpose of diagnosis support
HANİFE KÜÇÜK
Doktora
Türkçe
2015
BiyomühendislikOndokuz Mayıs ÜniversitesiElektrik-Elektronik Mühendisliği Ana Bilim Dalı
YRD. DOÇ. İLYAS EMİNOĞLU