Browsing by Author "Ozaydin, Selma"

Now showing 1 - 4 of 4

Citation - WoS: 0
Citation - Scopus: 2
Comparative Performance Analysis of Filtering Methods for Removing Baseline Wander Noise from an ECG Signal
(World Scientific Publ Co Pte Ltd, 2024) Ozaydin, Selma; Özaydın, Selma; Ahmad, Imteyaz; 253019; Çankaya Meslek Yüksekokulu
ECG signals play a vital role in the diagnosis of cardiovascular conditions. However, they often suffer from the effects of various noise sources, including baseline wandering, respiratory artifact noise, power line interference and electrode motion artifacts. To overcome these challenges, it is imperative to implement low-frequency signal noise reduction strategies. Such strategies aim to significantly improve the quality of ECG signals, thus promoting more accurate and reliable diagnosis of cardiovascular disorders. This paper conducts a comparative analysis to assess the effectiveness of commonly used filtering and wavelet techniques in reducing Baseline Wander (BW) noise within ECG signals generated by the influence of breathing or electrode movements. It is common to observe the selection and evaluation of only one particular technique in the existing literature. In contrast, this study aims to provide a comprehensive comparative analysis, providing insight into the performance and relative merits of different techniques. Our research uses both filtering and Discrete Wavelet Transform (DWT) techniques in baseline noise removal. In this context, a reference point is established utilizing noise-free signals and a meticulous investigation of the wavelet-based approach that most effectively eliminates the resulting noise is provided. Subsequently, we assess the reference input and output signal via Signal-to-Noise Ratio (SNR) and Kolmogorov-Smirnov statistical test measurements. The most important contribution of this work to the scientific community resides in the comprehensive examination of IIR/FIR-based and wavelet method-based filtering methods capable of yielding the highest SNR levels across various ECG signals with various types of BW noise. Additionally, the effectiveness of the Chebychev-II filter in BW noise removal is highlighted. Our study was conducted using the MATLAB platform and code command lines were shared to facilitate the reproduction of our study by other researchers. It is considered that this study will be an important reference in the selection of effective techniques for removing BW noise within ECG signals.
Citation - WoS: 4
Citation - Scopus: 11
Design of a text ındependent speaker recognition system
(Ieee, 2017) Ozaydin, Selma; Özaydın, Selma; Ozaydin, Selma; 253019; Çankaya Meslek Yüksekokulu
This paper presents the design of a text independent speaker recognition system based on Mel-Frequency Cepstrum Coefficients and Gaussian Mixture Models. HTK speech recognition toolkit is used in the design of speaker models. The system is aimed to use it as a biometric authentication system. The experiments were performed on speech data consist of 134 speakers from YOHO database for different training conditions. The increase of the proposed system performance is observed with the decrease of Equal Error Rate. Experiment results show that the system gives the best recognition performance for Gaussian mixture model with 64 mixtures.
Examination of Energy Based Voice Activity Detection Algorithms for Noisy Speech Signals
(2019) Özaydın, Selma; Ozaydin, Selma; 253019; Çankaya Meslek Yüksekokulu
Bu çalışmada, iki farklı enerji tabanlı konuşma bölgesi aktivasyonu detektör (KAD) algoritmasının gürültülü giriş sinyallerine karşı davranışları incelenmektedir. İncelenen KAD detektörleri, konuşma sınırlarını etkin bir şekilde belirlemek için zaman düzlemindeki metotları kullanmaktadır. Zaman düzlemi kısa zaman aralığında enerji hesabı ve/veya sıfır geçiş oranı, metotların performansını değerlendirmede kullanılmaktadır. Her iki algoritmanın ilk aşamasında, zaman düzleminde her bir konuşma alt kesitinde enerji değerleri hesaplanmaktadır. Enerji oranları ve eşik değerler, konuşma sinyalinin aktif bölgelerini belirlemede kullanılmaktadır. Karar eşik değeri, konuşma sinyalinin başında sessiz bir bölge aralığında hesaplanmaktadır. Seçilen metotların etkinliği temiz ve gürültülü konuşma sinyal örnekleri için test edilmiştir. Metotlar, değişik SNR seviyelerinde gürültülü konuşma sinyalleri kullanarak test edilmiştir. Sonuçlar göstermiştir ki, 0dB SNR seviyesine kadar yavaşca azalan performansla her iki metot etkinliklerini koruyabilmekte, ancak 0dB SNR seviyesi altında her iki metot etkinliğini kaybetmektedir.
Citation - WoS: 0
Citation - Scopus: 0
Investigation of factors affecting noise robustness in voice activity detectors
(Gazi Univ, Fac Engineering Architecture, 2023) Ozaydin, Selma; Özaydın, Selma; 253019; Çankaya Meslek Yüksekokulu
In this manuscript, some voice activity detectors (VADs) in the literature were examined in terms of factors affecting their robustness under different acoustic noise conditions and in this context, the changes in detection accuracy rates according to changing noise conditions were tested. In this scope, the effect of situations such as whether the threshold value used in the decision phase in VAD methods is fixed or adaptive, the analysis window is short or long, the use of more than one feature vector together has been evaluated and analyzed comparatively. While three of the four different VAD detectors examined in this manuscript use feature vectors within the short-term analysis window while generating the decision result, one decides according to the measurement result of long-term spectral vectors. The VAD detectors in the article have been tested using the NOIZEUS noisy speech database. Thus, the performance of the analyzed VADs has been evaluated under different acoustic conditions using an extensive database that has already taken place in the literature. During the testing of the analyzed VADs, different input noise speech signals with environmental background noises between [15-0dB] such as restaurant, car, street, or station were tested. Tests were carried out using objective test measurement methods and the detection accuracy rate of each VAD method was measured. The results showed that each method gave different endurance performance in adverse environmental conditions.