Observation, parametric modelling and classification of respiratory sounds
Başlık çevirisi mevcut değil.
- Tez No: 364445
- Danışmanlar: YRD. DOÇ. DR. YASEMİN P. KAHYA
- Tez Türü: Yüksek Lisans
- Konular: Biyomühendislik, Göğüs Hastalıkları, Bioengineering, Chest Diseases
- Anahtar Kelimeler: Belirtilmemiş.
- Yıl: 1992
- Dil: İngilizce
- Üniversite: Boğaziçi Üniversitesi
- Enstitü: Biyo-Medikal Mühendislik Enstitüsü
- Ana Bilim Dalı: Biyomedikal Mühendisliği Ana Bilim Dalı
- Bilim Dalı: Belirtilmemiş.
- Sayfa Sayısı: 160
Özet
Özet yok.
Özet (Çeviri)
Auscultation is a widely used method in the diagnosis of pulmonary diseases and in the analysis of respiratory sounds. The characteristics of respiratory sounds show differences in pathological cases from normal cases. The object of this study is, to observe the characteristics of respiratory sounds in both cases, to analyse them in time and frequency domain and to distinguish a normal case from a pathological case. To achieve mentioned goals, respiratory sounds heard over the chest waH from the specific locations were recorded. The flow signal was also recorded by a flowmeter to synchronize on the inspiration and expiration phases, because the characteristics of respiratory sounds may change from phase to phase. An AR modeling was applied to obtain a parametric representation of the sounds. The analysis of respiratory sounds was performed after they were distinguished to inspiration and expiration phases. Mahalanobis distance measure, and minimum distance classification method is used to classify respiratory sounds into appropriate classes. Experiments showed that the suggested classifier can distinguish the normal case from a pathological case if and only if a large database of lung sounds is available. The classification method was also compared with Itakura distance measure and k-nearest neighbor classification method which was performed in a previous study. The abrupt changes (crackles) in the respiratory sound waveforms of pathological cases were observed and a new method is suggested to detect them because they have a special importance in the diagnosis of some pulmonary diseases.
Benzer Tezler
- Recognition and monitoring of human motions using RF signals
İnsan hareketlerinin RF sinyalleri kullanarak tanımlanması ve izlenmesi
CAN UYSAL
Doktora
İngilizce
2020
Elektrik ve Elektronik MühendisliğiEskişehir Teknik ÜniversitesiElektrik-Elektronik Mühendisliği Ana Bilim Dalı
DOÇ. DR. TANSU FİLİK
- İnvolüsyonel sinir ağları ile hiperspektral verilerin analizi
Analysis of hyperspectral data with involutional neural networks
MÜCAHİT CİHAN
Doktora
Türkçe
2024
Elektrik ve Elektronik MühendisliğiKonya Teknik ÜniversitesiElektrik ve Elektronik Mühendisliği Ana Bilim Dalı
PROF. DR. MURAT CEYLAN
- Mimari tasarımda biçim grameri:metro istasyon tasarımı
Shape grammer in architectural design: subway station design
NURBİN PAKER
- Mezo ölçek model rüzgar şiddeti öngörü sonuçlarının yapay sinir ağları ve k en yakın komşu algoritması ile iyileştirilmesi
Artificial neural networks and k nearest neighborhood algorithm approach to improving wind speed prediction of the mesoscale forecast model results
DUYGU AKYIL
Yüksek Lisans
Türkçe
2019
Meteorolojiİstanbul Teknik ÜniversitesiMeteoroloji Mühendisliği Ana Bilim Dalı
PROF. DR. ŞÜKRAN SİBEL MENTEŞ
- Fuzzy clustering based ensemble learning approach: Applications in digital advertising
Bulanık kümeleme tabanlı topluluk öğrenmesi yaklaşımı: Dijital reklam alanında uygulamalar
AHMET TEZCAN TEKİN
Doktora
İngilizce
2021
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİstanbul Teknik Üniversitesiİşletme Mühendisliği Ana Bilim Dalı
PROF. DR. FERHAN ÇEBİ
PROF. DR. TOLGA KAYA