Teknik Bilimler Meslek Yüksekokulu / Vocational School of Technical Sciences

Permanent URI for this collectionhttps://hdl.handle.net/11727/2031

Browse

Now showing 1 - 15 of 15

Blood pressure prediction from speech recordings
(2020) Ankishan, Haydar
The aim of this study is to extract new features to show the relationship between speech recordings and blood pressure (BP). For this purpose, a database consisting of / a / vowels with different BP values under the same room and environment conditions is presented to the literature. Convolutional Neural Networks- Regression (CNN-R), Support Vector Machines- Regression (SVMs-R) and Multi Linear Regression (MLR) are used in this study to predict BP with extracted features. From the experiments, the highest accuracy rates of BP prediction from / a / vowel have been obtained based on Systolic BP values with CNNR. In the study, 89.43 % for MLR, 92.15 % for SVM-R and 93.65 % for CNN-R are obtained when ReliefF has been used. When the root mean square errors (RMSE) are considered, the lowest error value is obtained with CNN-R as RMSE = 0.2355. In conclusion, it can be observed that the proposed feature vector (FVx) shows a relationship between BP and the human voices, and in this direction, it can be used as an FVx in a system that will be developed in order to follow the tension of individuals. (C) 2020 Elsevier Ltd. All rights reserved.
Classification of acoustic signals with new feature: Fibonacci space (FSp)
(2019) Ankishan, Haydar; 0000-0002-6240-2545; AAH-4421-2019
In this study, a new feature and feature space (FSp) are introduced by using the approach of Fibonacci series formation. The results are presented as two experimental studies. The nine groups of acoustic signals and pathological human voices are investigated in the first and second experiments, respectively. Convolutional Neural Network (CNN) and Multi-Class Support Vector Machines (M-SVMs) are used to figure out the effect of the proposed feature and its FSp on the classification accuracy. It is observed that the proposed feature and its formed space yield significant results for the discrimination of those signals. Experimental studies show that the classification accuracy of test data is increased by 5.3% when the proposed feature is used with CNN and M-SVMs. In addition, each acoustic group is significantly discriminated in both experimental studies. It is concluded that the proposed feature and its space can be used as a temporal feature for different purposes such as automatic speech recognition, pattern recognition, and emotional voice discrimination etc. (C) 2018 Elsevier Ltd. All rights reserved.
Discovery of a glitch in the accretion- powered pulsar SXP 1062
(2017) Imam, Sıtkı Cagdas; Serim, M.M.; Sahiner, S.; Cerri-Serim, D.; Baykal, A.; 0000-0003-0820-9186
We present timing analysis of the accretion-powered pulsar SXP 1062, based on the observations of Swift, XMM-Newton and Chandra satellites covering a time span of about 2 yr. We obtain a phase coherent timing solution that shows that SXP 1062 has been steadily spinning down with a rate-4.29(7) x10(-14) Hz s(-1) leading to a surface magnetic field estimate of about 1.5 x 10(14) G. We also resolve the binary orbital motion of the system from X-ray data that confirms an orbital period of 656(2) d. On MJD 56834.5, a sudden change in pulse frequency occurs with Delta v = 1.28(5) x 10(-6) Hz, which indicates a glitch event. The fractional size of the glitch is Delta v/v similar to 1.37(6) x 10(-3) and SXP 1062 continues to spin-down with a steady rate after the glitch. A short X-ray outburst 25 d prior to the glitch does not alter the spin-down of the source; therefore, the glitch should be associated with the internal structure of the neutron star. While glitch events are common for isolated pulsars, the glitch of SXP 1062 is the first confirmation of the observability of this type of events among accretion-powered pulsars. Furthermore, the value of the fractional change of pulse frequency ensures that we discover the largest glitch reported up to now.
The Effects of Illumination on the Current Conduction Mechanisms of the Au/C20H12/N-Si Schottky Barrier Diode (SBD)
(2023) Bengi, Seda; 0000-0002-3348-0712; HPH-9613-2023
Using the I-V characteristics both in the dark and under varied illumination-intensities (50-250 mW.cm(-2)) by 50 mW.cm(-2) steps in the wide range bias-voltage (+/- 5 V), specific fundamental electrical and photo effects parameters of the Au/C20H12/n-Si SBD were examined. Due to the creation of electron-hole pairs and their drift in opposite directions under the influence of an electric field, the value of photocurrent in the reverse bias (I-ph) increases when illumination density is increased. The barrier height (Phi(B0)) tended to decrease due to the increase in photocurrent, while the diode's ideality factor (n) increased with increasing illumination intensity. Also, the Schottky structure's open-circuit voltage (V-oc), short circuit current (I-sc), filling factor (FF), and efficiency (eta) were determined to be 0.358 V, 95.5 mu A, 33%, and 0.028% under 50 mW.cm(-2), respectively. The R-s and R-sh values found using Ohm's law are a vital function of illumination and voltage which decrease with increasing illumination intensity. Additionally, using the forward bias I-V data and accounting for the bias dependent of the effective barrier height (Phi(e)) and ideality factor n(V) for different illumination intensities, the energy density distribution profile of surface states (N-ss) was obtained. According to these results, the organic interlayer consisting of C20H12 is light-sensitive and suitable for optoelectronic devices such as photodetectors and photodiodes.
Estimation of heartbeat rate from speech recording with hybrid feature vector (HFV)
(2019) Ankishan, Haydar; 0000-0002-6240-2545; AAH-4421-2019
This paper introduces a new hybrid feature vector for revealing the relationship between human voice and heartbeat rate (HBR). Various samples of the sustained vowel /a/ for different HBR have been extracted from a database which is created for this study. A convolutional neural network (CNN)-Regression (R), support vector machines (SVMs)-Regression (R), and multiple linear regression (MLR) are used as regression models. The experimental results show that the percentage of predictions within an acceptable error margin has been obtained as 98.92% for CNN-R, 98.70% for SVMs-R and 96.88% for MLR when Forward Sequential is used as a feature selection algorithm. The results also reveal that the CNN-R (root mean square error (RMSE) =0.3909) has produced better prediction values in estimating HBR than those produced by SVMs-R (RMSE=0.4277) and MLR (RMSE =0.4449). As a result, it is seen that the extracted hybrid feature vector provides a novel relationship between human voice and HBR. (C) 2019 Elsevier Ltd. All rights reserved.
A hybrid measure for the discrimination of the acoustic signals: Feature matrix (FMx)
(2019) Anskishan, Haydar; Inam, Sitki Cagdas; 0000-0002-6240-2545; 0000-0003-0820-9186; AAH-4421-2019
We introduce a new feature matrix (FMx) to discriminate the acoustic signals with the help of their hybrid characteristics. The FMx has hybrid domain characteristics consisting of feature values such as distributional area (polygonal area), maximum values of the histogram and fundamental frequency of the difference-difference (d2d) vector. To show the performance of the FMx, three different datasets are used together with quadratic discriminant analysis (QDA), multiclass support vector machines (M-SVMs) and convolutional neural networks (CNN). The simulation results show that FMx provides effective and useful information for the discrimination of the signals into subclasses with the help of ReliefF and forward sequential algorithms. In simulations, the test accuracies with QDA, M-SVMs and CNN were obtained as 94.20%, 100% and 100% respectively. So, the results of the simulations support the effectiveness of the FMx for the acoustic signal classification with three different datasets compared to the previous studies. (C) 2019 Elsevier Ltd. All rights reserved.
A model for the visualization and analysis of elevator traffic
(2019) Ciflikli, Cebrail; Tartan, Emre Oner
Analysis of elevator traffic in high rise buildings is critical to the performance evaluation of elevator group control systems (EGCS). Elevator dispatching methods or parking algorithms in an EGCS can be designed or modified according to analyses of traffic flow. However, interpretation of traffic flow based solely on numerical data may not be explicit and transparent for EGCS experts as well as for other non-expert building administration. In this study, we present a model for visualization and analysis of elevator traffic. First, we present an alternative approach for traffic analysis which we call route visualization. In the proposed approach, we initially decompose elevator traffic into its component parts and investigate each component independently. Then, using superposition of components we obtain a reconstructed model of overall traffic. This modeling approach provides component-based traffic analysis and representation of routes with intensities through data visualization. In the second part we introduce a multi-dimensional analysis of time parameters in ECGS. This approach provides a comparative analysis of several control algorithms such as dispatch or park algorithms for different combinations of traffic components.
A Novel Approach for Estimating Heat Transfer Coefficients of Ethylene Glycol-Water Mixtures
(2014) Bulut, Murat; Ankishan, Haydar; Demircioglu, Erdem; Ari, Seckin; Sengul, Orhan; https://orcid.org/0000-0002-6240-2545; AAH-4421-2019
Ethylene glycol-water mixtures (EGWM) are vital for cooling engines in automotive industry. Scarce information is available in the literature for estimating the heat transfer coefficients (HTC) of EGWM using knowledge-based estimation techniques such as adaptive neuro-fuzzy inference systems (ANFIS) and artificial neural networks (ANN) which offer nonlinear input-output mapping. In this paper, the supervised learning methods of ANFIS and ANN are exploited for estimating the experimentally determined HTC. This original research fulfills the preceding modeling efforts on thermal properties of EGWM and HTC applications in the literature. An experimental test setup is designed to compute HTC of mixture over a small circular aluminum heater surface, 9.5 mm in diameter, placed at the bottom 40-mm-wide wall of a rectangular channel 3 mm x 40 mm in cross section. Measurement data are utilized as the train and test data sets of the estimation process. Prediction results have shown that ANFIS provide more accurate and reliable approximations compared to ANN. ANFIS present correlation factor of 98.81 %, whereas ANN estimate 87.83 % accuracy for test samples.
An OFDM throughput analysis for cognitive radio application in contiguous or noncontiguous TV white spaces
(2015) Ciftlikli, Cebrail; Tuncer, Ahmet Turgut; Ozturk, Yusuf
Radio frequency spectrum is a finite and scarce resource. Efficient use of the radio frequency spectrum is a fundamental research issue. Since a large portion of the assigned radio frequency spectrum is used only sporadically, the bands currently allocated to TV services can be opportunistically reassigned to support broadband networking services while continuing to provide broadcast TV. The fragmented and unused TV channels named white spaces have a considerable amount of bandwidth potential and long transmission ranges. Bandwidth scalability can be supported by bonding multiple contiguous or noncontiguous consecutive channels using orthogonal frequency division multiplexing (OFDM)-based cognitive radio. In this paper, an in-depth throughput analysis of OFDM fixed carrier spacing and fixed carrier number approaches has been done for various modulation schemes in TV white spaces. Signal propagation delay is studied under various channel conditions. An analytical model-based estimation of the throughput by taking into account channel bonding is presented.
Reduced Graphene Oxide-GelMA Hybrid Hydrogels as Scaffolds for Cardiac Tissue Engineering
(2016) Shin, Su Ryon; Zihlmann, Claudio; Akbari, Mohsen; Assawes, Pribpandao; Cheung, Louis; Zhang, Kaizhen; Manoharan, Vijayan; Zhang, Yu Shrike; Yuksekkaya, Mehmet; Wan, Kai-tak; Nikkhah, Mehdi; Dokmeci, Mehmet R.; Tang, Xiaowu (Shirley); Khademhosseini, Ali; 0000-0002-2665-5799; 27254107; P-1760-2016
Biomaterials currently used in cardiac tissue engineering have certain limitations, such as lack of electrical conductivity and appropriate mechanical properties, which are two parameters playing a key role in regulating cardiac cell behavior. Here, the myocardial tissue constructs are engineered based on reduced graphene oxide (rGO)-incorporated gelatin methacryloyl (GelMA) hybrid hydrogels. The incorporation of rGO into the GelMA matrix significantly enhances the electrical conductivity and mechanical properties of the material. Moreover, cells cultured on composite rGO-GelMA scaffolds exhibit better biological activities such as cell viability, proliferation, and maturation compared to ones cultured on GelMA hydrogels. Cardiomyocytes show stronger contractility and faster spontaneous beating rate on rGO-GelMA hydrogel sheets compared to those on pristine GelMA hydrogels, as well as GO-GelMA hydrogel sheets with similar mechanical property and particle concentration. Our strategy of integrating rGO within a biocompatible hydrogel is expected to be broadly applicable for future biomaterial designs to improve tissue engineering outcomes. The engineered cardiac tissue constructs using rGO incorporated hybrid hydrogels can potentially provide high-fidelity tissue models for drug studies and the investigations of cardiac tissue development and/or disease processes in vitro.
Security and Privacy in Medical Internet of Things and Cluster-Based Wireless Sensor Networks for Health Care
(2020) Hammoodi, Asmaa Salih; Ozdemir, Suat; Tuncer, A. Turgut; Celebi, Fatih V
Advances in sensing, networking, and the ambient intelligence of wireless sensor networks (WSNs) have been taking place in many applications recently. Growing health-care systems need wireless-based sensor networks to provide data on the health status and living environment of patients during periods of illness. Mainly WSNs use the mechanism of clustering to reduce the energy consumption required with hierarchical structures to enhance network performance. The second prevalent challenge concerns the security of WSN cluster nodes because of the big attacks and security investigations come in WSN-health care applications as a challenging and motivating problem. This paper focuses on two essential platforms adopted within WSN applications. The hardware platform characterizes the WSN cluster nodes specifying automatically encrypted nodes during routing. The software platform is a simulation performed with two features: one identical to the hardware platform to enhance the results and compare between them, a second structure implementing three encryption algorithms as a reasonable technique to secure cluster nodes: Caesar cipher, RC4, and advanced encryption standard (AES). The first goal achieved by our plan is our private and secure medical protocol, which depends on identity-based cryptography, accomplished via the hardware platform. The second goal derived from the simulation is increasing the number of PEGASIS chains when the time needed to perform the task is limited particularly in cases of emergency to preview history and data of patients, but more chains get many frames of data aggregation, which causes overlap. Eventually, the system provides a rapid, efficient, flexible, secure, and authoritative infrastructure where our results showed that data retention in the node and by using the appropriate cryptographic algorithms in the group achieved privacy and security in the health care centers.
Sequential Decision Making for Elevator Control
(2023) Tartan, Emre Oner; Ciflikli, Cebrail; 0000-0002-5688-4226; JVD-9650-2023
In the last decade Reinforcement Learning (RL) has significantly changed the conventional control paradigm in many fields. RL approach is spreading with many applications such as autonomous driving and industry automation. Markov Decision Process (MDP) forms a mathematical idealized basis for RL if the explicit model is available. Dynamic programming allows to find an optimal policy for sequential decision making in a MDP. In this study we consider the elevator control as a sequential decision making problem, describe it as a MDP with finite state space and solve it using dynamic programming. At each decision making time step we aim to take the optimal action to minimize the total of hall call waiting times in the episodic task. We consider a sample 6-floor building and simulate the proposed method in comparison with the conventional Nearest Car Method (NCM).
Slot Parameter Optimization for Multiband Antenna Performance Improvement Using Intelligent Systems
(2015) Demircioglu, Erdem; Yagli, Ahmet Fazil; Gulgonul, Senol; Ankishan, Haydar; Tartan, Emre Oner; Sazli, Murat H.; Imeci, Taha
This paper discusses bandwidth enhancement for multiband microstrip patch antennas (MMPAs) using symmetrical rectangular/square slots etched on the patch and the substrate properties. The slot parameters on MMPA are modeled using soft computing technique of artificial neural networks (ANN). To achieve the best ANN performance, Particle Swarm Optimization (PSO) and Differential Evolution (DE) are applied with ANN's conventional training algorithm in optimization of the modeling performance. In this study, the slot parameters are assumed as slot distance to the radiating patch edge, slot width, and length. Bandwidth enhancement is applied to a formerly designed MMPA fed by a microstrip transmission line attached to the center pin of 50 ohm SMA connecter. The simulated antennas are fabricated and measured. Measurement results are utilized for training the artificial intelligence models. The ANN provides 98% model accuracy for rectangular slots and 97% for square slots; however, ANFIS offer 90% accuracy with lack of resonance frequency tracking.
Timing studies of X Persei and the discovery of its transient quasi-periodic oscillation feature
(2014) Acuner, Z.; Inam, S.C.; Sahiner, S.; Serim, M.M.; Baykal, A.; Swank, J.
We present a timing analysis of X Persei (X Per) using observations made between 1998 and 2010 with the Proportional Counter Array (PCA) onboard the Rossi X-ray Timing Explorer (RXTE) and with the INTEGRAL Soft Gamma-Ray Imager (ISGRI). All pulse arrival times obtained from the RXTE-PCA observations are phase-connected and a timing solution is obtained using these arrival times. We update the long-term pulse frequency history of the source by measuring its pulse frequencies using RXTE-PCA and ISGRI data. From the RXTE-PCA data, the relation between the frequency derivative and X-ray flux suggests accretion via the companion's stellar wind. However, the detection of a transient quasi-periodic oscillation feature, peaking at similar to 0.2 Hz, suggests the existence of an accretion disc. We find that double-break models fit the average power spectra well, which suggests that the source has at least two different accretion flow components dominating the overall flow. From the power spectrum of frequency derivatives, we measure a power-law index of similar to-1, which implies that, on short time-scales, disc accretion dominates over noise, while on time-scales longer than the viscous time-scales, the noise dominates. From pulse profiles, we find a correlation between the pulse fraction and the count rate of the source.
A viable snore detection system: hardware and software implementations
(2020) Tuncer, Ahmet Turgut; Bilgen, Mehmet
A stand-alone, custom-made biomedical system was introduced for long-term monitoring of sleep and detection of snoring events. Commercially available electronic components were assembled for recording audio, pulse, and respiration signals. Its software was implemented for off-line processing of the acquired signals in C++ and MATLAB environments. The linear and nonlinear features of the signals were extracted and characterized using spectral energy distribution, entropy, and largest Lyapunov exponent (LLE). The performance of the system was evaluated with real physiological data gathered from 14 chronic snorers. Analysis of the cases indicated that the system identified the snoring events with an accuracy of 88.22%, sensitivity of 94.91%, and positive predictive value of 90.95%. This high level of validation confirmed the reliability and utility of the system in detecting snoring.