Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/11
Browse
14 results
Search Results
Article Citation - WoS: 5Citation - Scopus: 6A Comparative Study of Metaheuristic Feature Selection Algorithms for Respiratory Disease Classification(MDPI, 2024) Gürkan Kuntalp, D.; Özcan, N.; Düzyel, Okan; Kababulut, F.Y.; Kuntalp, M.The correct diagnosis and early treatment of respiratory diseases can significantly improve the health status of patients, reduce healthcare expenses, and enhance quality of life. Therefore, there has been extensive interest in developing automatic respiratory disease detection systems. Most recent methods for detecting respiratory disease use machine and deep learning algorithms. The success of these machine learning methods depends heavily on the selection of proper features to be used in the classifier. Although metaheuristic-based feature selection methods have been successful in addressing difficulties presented by high-dimensional medical data in various biomedical classification tasks, there is not much research on the utilization of metaheuristic methods in respiratory disease classification. This paper aims to conduct a detailed and comparative analysis of six widely used metaheuristic optimization methods using eight different transfer functions in respiratory disease classification. For this purpose, two different classification cases were examined: binary and multi-class. The findings demonstrate that metaheuristic algorithms using correct transfer functions could effectively reduce data dimensionality while enhancing classification accuracy. © 2024 by the authors.Article Citation - WoS: 4Citation - Scopus: 4A New Shapley-Based Feature Selection Method in a Clinical Decision Support System for the Identification of Lung Diseases(MDPI, 2023) Kababulut, Fevzi Yasin; Kuntalp, Damla Gurkan; Düzyel, Okan; Özcan, Nermin; Kuntalp, MehmetThe aim of this study is to propose a new feature selection method based on the class-based contribution of Shapley values. For this purpose, a clinical decision support system was developed to assist doctors in their diagnosis of lung diseases from lung sounds. The developed systems, which are based on the Decision Tree Algorithm (DTA), create a classification for five different cases: healthy and disease (URTI, COPD, Pneumonia, and Bronchiolitis) states. The most important reason for using a Decision Tree Classifier instead of other high-performance classifiers such as CNN and RNN is that the class contributions of Shapley values can be seen with this classifier. The systems developed consist of either a single DTA classifier or five parallel DTA classifiers each of which is optimized to make a binary classification such as healthy vs. others, COPD vs. Others, etc. Feature sets based on Power Spectral Density (PSD), Mel Frequency Cepstral Coefficients (MFCC), and statistical characteristics extracted from lung sound recordings were used in these classifications. The results indicate that employing features selected based on the class-based contribution of Shapley values, along with utilizing an ensemble (parallel) system, leads to improved classification performance compared to performances using either raw features alone or traditional use of Shapley values.Article Enhancing Thickness Determination of Nanoscale Dielectric Films in Phase Diffraction-Based Optical Characterization Systems With Radial Basis Function Neural Networks(IOP Publishing, 2023) Ataç, Enes; Karatay, Anıl; Dinleyici, Mehmet SalihAccurate determination of the optical properties of ultra-thin dielectric films is an essential and challenging task in optical fiber sensor systems. However, nanoscale thickness identification of these films may be laborious due to insufficient and protracted classical curve matching algorithms. Therefore, this experimental study presents an application of a radial basis function neural network in phase diffraction-based optical characterization systems to determine the thickness of nanoscale polymer films. The non-stationary measurement data with environmental and detector noise were subjected to a detailed analysis. The outcomes of this investigation are benchmarked against the linear discriminant analysis method and further verified by means of scanning electron microscopy. The results show that the neural network has reached a remarkable accuracy of 98% and 82.5%, respectively, in tests with simulation and experimental data. In this way, rapid and precise thickness estimation may be realized within the tolerance range of 25 nm, offering a significant improvement over conventional measurement techniques.Article Citation - WoS: 3Citation - Scopus: 4Cost-Effective Experiments With Additively Manufactured Waveguide and Cavities in the S-Band(Iop Publishing Ltd, 2023) Karatay, Anıl; Yilmaz, Hasan Önder; Özkal, Ceren; Yaman, FatihThis study demonstrates the applicability of additively manufactured components that are metalized with conductive tape for two different microwave experiments. We focus on dielectric measurements and prototyping elliptical accelerator cavities at a low power regime for 2.45 GHz. To illustrate the accuracy of our results for the commonly used solid/liquid materials in engineering and to compare the fundamental accelerator cavity parameters with previous research rectangular and elliptic 3D-printed cavities coated with aluminum-type tape were employed in the experiments. Results reported for the complex-valued permittivities and specific design parameters for the cavity prototype are consistent with the literature. Various approaches to obtain the conductivity value of the tape and the effect of the roughness/thickness of the coating on the reflection parameter are discussed in detail. We confirm the effectiveness of the proposed approach, which reduces costs and provides a high degree of accuracy for investigated applications.Article Citation - WoS: 3Citation - Scopus: 4Quasi-Supervised Strategies for Compound-Protein Interaction Prediction [article](Wiley-VCH Verlag, 2021) Çakı, Onur; Karaçalı, BilgeIn-silico compound-protein interaction prediction addresses prioritization of drug candidates for experimental biochemical validation because the wet-lab experiments are time-consuming, laborious and costly. Most machine learning methods proposed to that end approach this problem with supervised learning strategies in which known interactions are labeled as positive and the rest are labeled as negative. However, treating all unknown interactions as negative instances may lead to inaccuracies in real practice since some of the unknown interactions are bound to be positive interactions waiting to be identified as such. In this study, we propose to address this problem using the Quasi-Supervised Learning (QSL) algorithm. In this framework, potential interactions are predicted by estimating the overlap between a true positive dataset of compound-protein pairs with known interactions and an unknown dataset of all the remaining compound-protein pairs. The potential interactions are then identified as those in the unknown dataset that overlap with the interacting pairs in the true positive dataset in terms of the associated similarity structure. We also address the class-imbalance problem by modifying the conventional cost function of the QSL algorithm. Experimental results on GPCR and Nuclear Receptor datasets show that the proposed method can identify actual interactions from all possible combinations.Article Citation - WoS: 18Citation - Scopus: 31Applied Mel-Frequency Discrete Wavelet Coefficients and Parallel Model Compensation for Noise-Robust Speech Recognition(Elsevier, 2006) Tüfekçi, Zekeriya; Gowdy, John N.; Gürbüz, Sabri; Patterson, EricInterfering noise severely degrades the performance of a speech recognition system. The Parallel Model Compensation (PMC) technique is one of the most efficient techniques for dealing with such noise. Another approach is to use features local in the frequency domain, such as Mel-Frequency Discrete Wavelet Coefficients (MFDWCs). In this paper, we investigate the use of PMC and MFDWC features to take advantage of both noise compensation and local features (MFDWCs) to decrease the effect of noise on recognition performance. We also introduce a practical weighting technique based on the noise level of each coefficient. We evaluate the performance of several wavelet-schemes using the NOISEX-92 database for various noise types and noise levels. Finally, we compare the performance of these versus Mel-Frequency Cepstral Coefficients (MFCCs), both using PMC. Experimental results show significant performance improvements for MFDWCs versus MFCCs, particularly after compensating the HMMs using the PMC technique. The best feature vector among the six MFDWCs we tried gave 13.72 and 5.29 points performance improvement, on the average, over MFCCs for -6 and 0 dB SNR, respectively. This corresponds to 39.9% and 62.8% error reductions, respectively. Weighting the partial score of each coefficient based on the noise level further improves the performance. The average error rates for the best MFDWCs dropped from 19.57% to 16.71% and from 3.14% to 2.14% for -6 dB and 0 dB noise levels, respectively, using the weighting scheme. These improvements correspond to 14.6% and 31.8% error reductions for -6 dB and 0 dB noise levels, respectively. (c) 2006 Elsevier B.V. All rights reserved.Article Citation - WoS: 67Citation - Scopus: 78Chirp Group Delay Analysis of Speech Signals(Elsevier, 2007) Bozkurt, Barış; Couvreur, Laurent; Dutoit, ThierryThis study proposes new group delay estimation techniques that can be used for analyzing resonance patterns of short-term discrete-time signals and more specifically speech signals. Phase processing or equivalently group delay processing of speech signals are known to be difficult due to large spikes in the phase/group delay functions that mask the formant structure. In this study, we first analyze in detail the z-transform zero patterns of short-term speech signals in the z-plane and discuss the sources of spikes on group delay functions, namely the zeros closely located to the unit circle. We show that windowing largely influences these patterns, therefore short-term phase processing. Through a systematic study, we then show that reliable phase/group delay estimation for speech signals can be achieved by appropriate windowing and group delay functions can reveal formant information as well as some of the characteristics of the glottal flow component in speech signals. However, such phase estimation is highly sensitive to noise and robust extraction of group delay based parameters remains difficult in real acoustic conditions even with appropriate windowing. As an alternative, we propose processing of chirp group delay functions, i.e. group delay functions computed on a circle other than the unit circle in z-plane, which can be guaranteed to be spike-free. We finally present one application in feature extraction for automatic speech recognition (ASR). We show that chirp group delay representations are potentially useful for improving ASR performance. (c) 2007 Elsevier B.V. All rights reserved.Article Citation - WoS: 3Citation - Scopus: 3Manipulating the Frequency Response of Small High-Frequency Atomic Force Microscope Cantilevers(IOP Publishing, 2020) Brar, Harpreet Singh; Balantekin, MüjdatWe study small (less than 10 mu m-long) high-frequency (greater than 1 MHz) cantilevers specially designed for visualization of biomolecular processes in high-speed atomic force microscopes. The frequency responses of the first three flexural eigenmodes are investigated for the modified geometries. It is found that the Q-factors can be significantly altered in the desired way by reengineering the cantilever geometry without affecting its main operational parameters, such as the spring constant and the resonance frequency of the first flexural eigenmode in an air environment. In addition, higher-order flexural resonances can be moved away from the fundamental resonance with these geometrical modifications. The Q-factors in liquid, on the other hand, do not show a significant difference due to high viscous damping of the medium. Regular cantilevers modified by a focused ion beam are used to demonstrate the validity of the finite element simulation model.Article Citation - WoS: 62Citation - Scopus: 70Railway Monitoring System Using Optical Fiber Grating Accelerometers(IOP Publishing Ltd., 2018) Yüksel, Kıvılcım; Kinet, Damien; Moeyaert, Veronique; Kouroussis, Georges; Caucheteur, ChristopheOptimal operation, reduced energy consumption, longer service availability, and high safety level are the major concerns in today's railway transport systems. Smart monitoring systems should address these issues without interrupting railway operability. Many successful works have been carried out to provide railway monitoring functions using fiber Bragg grating (FBG) sensors on rail. Most of them are based on strain measurement due to the train passage. This paper presents a highly sensitive means for railway monitoring based on vibration measurement. FBG accelerometers placed on sleeper have been employed as sensor heads, which significantly facilitated the field sensor installation work compared to the positioning on the foot of the rail. An optimized signal demodulation algorithm has been effectively used to extract from the accelerometer traces both the axle number and the average speed information. Excellent capability of the developed system to obtain both parameters has been demonstrated by the way of field trials carried out on a Belgian railway line, during its normal operation. Easy installation, multi-function diagnosis, good data integrity, and compatibility with fiber optic sensors make the proposed sensor a good candidate for railway monitoring applications.Article Citation - WoS: 3Citation - Scopus: 4Hierarchical Motif Vectors for Prediction of Functional Sites in Amino Acid Sequences Using Quasi-Supervised Learning(Institute of Electrical and Electronics Engineers Inc., 2012) Karaçalı, BilgeWe propose hierarchical motif vectors to represent local amino acid sequence configurations for predicting the functional attributes of amino acid sites on a global scale in a quasi-supervised learning framework. The motif vectors are constructed via wavelet decomposition on the variations of physico-chemical amino acid properties along the sequences. We then formulate a prediction scheme for the functional attributes of amino acid sites in terms of the respective motif vectors using the quasi-supervised learning algorithm that carries out predictions for all sites in consideration using only the experimentally verified sites. We have carried out comparative performance evaluation of the proposed method on the prediction of N-glycosylation of 55,184 sites possessing the consensus N-glycosylation sequon identified over 15,104 human proteins, out of which only 1,939 were experimentally verified N-glycosylation sites. In the experiments, the proposed method achieved better predictive performance than the alternative strategies from the literature. In addition, the predicted N-glycosylation sites showed good agreement with existing potential annotations, while the novel predictions belonged to proteins known to be modified by glycosylation.