Browsing by Author "Yilmaz, Derya"

Now showing 1 - 5 of 5

Effect Of Singular Value Decomposition Based Preconditioning On Compressive Classification
(2022) Orman, Ozgur Devrim; Yilmaz, Derya
Due to the rapid increase in the amount of data being stored and processed in the world, innovative solutions in the fields of data storage and data processing are increasingly needed; Compressive Sampling (CS) and Compressive Classification (CC) are two approaches that provide solutions for both areas, respectively. The use of CC to obtain information from the data through classification reduces the processing load as it enables the classification to be performed directly in the measurement domain obtained by CS. CS makes possible a lossless reconstruction with a high probability of less samples than the amount required by the Shannon sampling theorem, and by applying Preconditioning (PC) to the measurement matrix used, the amount of data required for reconstruction can be further reduced due to the number of samples required for reconstruction. The contribution of the use of the matrix derived from the measurement matrix by Singular Value Decomposition (SVD) as the measurement matrix in the CS, on the reconstruction performance has been studied only experimentally in the literature. In this study, as a first, it has been shown analytically that this approach based on SVD is a PC (SVD-PC) and will reduce the number of samples required for reconstruction in CS, meanwhile two different Monte Carlo (MC) simulations were carried out regarding to this finding. The SVD-PC performance supported by simulations is evaluated experimentally with SS applications performed on two different data sets and using three different classifiers, moreover the effect of SVD-PC on CC performance is investigated for the first time in the literature in this study.
Increasing the Efficiency of Missile Telemetry Tests by Using Data Compression Techniques
(2018) Saglam, Asli; Yilmaz, Derya
Telemetry tests conducted for a missile aim to improve ongoing design work in order to better meet the performance requirements. These tests can be performed before/during the qualification stage and the design team can observe the missile's performance via the data collected in these tests. These data packages are transmitted by wireless (radio frequency-RF) communication to a ground station for post-processing. Considering the importance of telemetry tests in affecting the project's work in the design phase, it is important to accomplish them by gathering as much data as possible. This study proposes compressing telemetry data before the transmission process in order to reduce the bandwidth requirement. Thus, the study investigates this practice's effects on the RF communication range and the increase in link margin via link budget calculations. Considering the characteristics of missile telemetry data (rate of change, different frame formats, etc.), synthetic telemetry data were generated in accordance with the real-life data structures, then this data were compressed using lossless data compression methods. While investigating the effects of transmitting a data train of decreased bandwidth on RF communication parameters, link budget analysis was conducted while keeping the unrelated RF parameters such as the type of modulation, transmitter/receiver characteristics, antenna properties constant. Results show that different compression algorithms provide variable amounts of improvement in downsizing the telemetry data; thus helping to increase a telemetry flight tests' efficiency for missiles.
A New Motion Model Selection Approach for Multi-Model Particle Filters
(2019) Ucar, Barkan; Yilmaz, Derya
One of the important factors in real-time tracking of the moving radar targets is the speed of the algorithm. In the multi-model particle filters (WPFs) which is frequently preferred tracking of such targets, the numbers of particles and motion models are important parameters determining the speed of the filter. Reducing the number of particles and/or the model transitions processes as much as possible will facilitate real-time tracking of moving targets by accelerating the algorithm. In this study, for reducing the time cost of the MMPF, a new approach called weighted statistical model selection (WSMS) which reduces the number of model estimation calculations is proposed. A new basic MMPF algorithm that allows the use of the WSMS approach is also constituted. In order to evaluate the success of the WSMS; the WPFs integrated with the WSMS, are simulated for different noise variances, particle numbers, and scenarios. The simulation results are compared based on processing time and prediction error criterions. The results demonstrate that the WSMS approach increases the speed of the algorithm by reducing the processing time at high rates without any change in the prediction error and, thus it can be used in real-time tracking of the moving targets.
A Preliminary Study on OSA Severity Levels Detection by Evaluating Speech Signals Nonlinearities With Multi-Class Classification
(2023) Ugur, Tugce Kantar; Yilmaz, Derya; Yildiz, Metin; Yetkin, Sinan
Diagnosis of obstructive sleep apnea (OSA) from speech has become a popular research area in recent years, which can be an alternative way to the application difficulties in polysomnography (PSG). The promising results obtained in our previous study, in which we tried to detect apnea using nonlinear analysis of speech, gave rise to the thought that it is possible to detect OSA and OSA severity by diversifying speech samples and nonlinear features. The principal aim of this study, for the first time in the literature, is to detect the OSA severity levels as mild, moderate, and severe as in the clinic use (multi-class classification) using nonlinear analyses of speech while the patient is awake. In addition, healthy/OSA classification (binary classification) was also carried out. The feature selection method of ANOVA was applied to 336 features (28 voices x 12 features) for each subject, 14 and 5 features were used in multi-class and binary classifications, respectively. As a result of the classifications made with various KNN and SVMs models, the best results were obtained by SVMs in both classifications for OSA severities (with one-vs-all classification scheme and the Gaussian kernel) and OSA detection (with the quadratic kernel) as 82% and 95.1% accuracies, respectively. The proposed study showed that OSA and OSA severity can be determined with the small number of nonlinear features calculated from a few different speech samples, in nearly 15 minutes, consistent with PSG results (simple snorer, mild, moderate, and severe OSA). In conclusion, the highest OSA/healthy classification accuracy rate in the literature was achieved. Furthermore, OSA severity detection in four-class performed quite well as a preliminary study.
Quantitative Data for Transcutaneous Electrical Nerve Stimulation and Acupuncture Effectiveness in Treatment of Fibromyalgia Syndrome
(2019) Yueksel, Merve; Ayas, Sehri; Cabioglu, Mehmet Tugrul; Yilmaz, Derya; Cabioglu, Cagri; 0000-0002-1903-7132; 0000-0002-5078-6529; 30949223
Aim. To evaluate the effects of acupuncture and transcutaneous electric nerve stimulation (TENS) applications on the quantitative electroencephalography (qEEG) changes and to evaluate their therapeutic effects in patients with fibromyalgia syndrome (FMS). The study included 42 patients with FMS and 21 healthy volunteers. The patients were randomly assigned to two groups (n=21 in each) to undergo either TENS or acupuncture application. In both acupuncture and TENS groups, baseline electroencephalography (EEG) recording was performed for 10min and, then, TENS or acupuncture was performed for 20min, followed by another 10min EEG recording. Baseline qEEG findings of FMS patients in the TENS and acupuncture groups were similar. Delta and theta powers over the frontal region of FMS patients were lower than controls. Theta powers of right posterior region were also lower than controls. In the TENS group, after the treatment, an increase was observed in the alpha power of the left anterior region as well as a decrease in pain scores. In the acupuncture group, an increase was determined in the alpha power of the right and left posterior regions as well as a decrease in pain score after the treatment. The power of low- and moderate-frequency waves on resting EEG was decreased in the patients with FMS. Decreased pain and increased inhibitor activity were found on qEEG after TENS and acupuncture applications. In conclusion, both TENS and acupuncture applications seem to be beneficial in FMS patients.