3 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 3 / 3
Öğe A novel approach for extracting ideal exemplars by clustering for massive time-ordered datasets(TÜBİTAK, 2017-07-30) Ertuğrul, Ömer FarukThe number and length of massive datasets have increased day by day and this yields more complex machine learning stages due to the high computational costs. To decrease the computational cost many methods were proposed in the literature such as data condensing, feature selection, and filtering. Although clustering methods are generally employed to divide samples into groups, another way of data condensing is by determining ideal exemplars (or prototypes), which can be used instead of the whole dataset. In this study, first the efficiency of traditional data condensing by clustering approach was confirmed according to obtained accuracies and condensing ratios in 9 different synthetic or real batch datasets. This approach was then improved to be employed in time-ordered datasets. In order to validate the proposed approach, 23 different real time-ordered datasets were used in experiments. Achieved mean RMSEs were 0.27 and 0.29 by employing the condensed (mean condensed ratio was 97.17%) and the whole datasets, respectively. Obtained results showed that higher accuracy rates and condensing ratios were achieved by the proposed approach.Öğe A noninvasive time-frequency-based approach to estimate cuffless arterial blood pressure(TÜBİTAK, 2018-09-28) Ertuğrul, Ömer Faruk; Sezgin, NecmettinArterial blood pressure (ABP) is one of the most vital signs in the prophylaxis and treatment of blood pressure-related diseases because raised blood pressure is the most significant cause of death and the second major cause of disability in the world. Higher ABP yields greater strain on arteries and these extra strains turn arteries into thicker, less flexible, and more narrow structures. This increases the possibility of having an artery busting or artery occlusion, which are the primary reasons for heart attacks, kidney disease, or strokes. In addition to its importance in monitoring cardiovascular homeostasis, measurement of ABP is imperative in surgical operations. In this study, a simple and effective approach was proposed to estimate ABP from electrocardiogram (ECG) and photoplethysmograph (PPG) signals by an extreme learning machine (ELM) and statistical properties of the ECG and/or PPG signals in the time-frequency domain. To evaluate and apply the proposed approach, the Cuffless Blood Pressure Estimation Dataset, which was published and shared by UCI, was employed. First, the statistical properties were extracted from ECG and PPG signals that were in the time-frequency domain. Later, extracted features were employed to estimate cuffless ABP for each subject by the ELM and some popular machine learning methods. Achieved results and reported results in the literature showed that the proposed approach can be successfully employed for estimating cuffless blood pressure (BP) from ECGs and/or PPGs. Additionally, with the proposed approach, the systolic BP, mean BP, and diastolic BP can be calculated simultaneously.Öğe A fast feature selection approach based on extreme learning machine and coefficient of variation(TÜBİTAK, 2017-07-30) Ertuğrul, Ömer Faruk; Tağluk, Mehmet EminFeature selection is the method of reducing the size of data without degrading their accuracy. In this study, we propose a novel feature selection approach, based on extreme learning machines (ELMs) and the coefficient of variation (CV). In the proposed approach, the most relevant features are identified by ranking each feature with the coefficient obtained through ELM divided by CV. The achieved accuracies and computational costs, obtained with the use of features selected via the proposed approach in 9 classification and 26 regression benchmark data sets, were compared to those obtained with all features, as well as those obtained with the features selected by a wrapper and a filtering method. The achieved accuracy values obtained with the proposed approach were generally higher than when using all features. Furthermore, high feature reduction ratios were obtained with the proposed approach, including the achieved feature reduction ratios in epilepsy, liver, EMG, shuttle, and abalone. Stock data sets were 90.48%, 90%, 70.59%, 66.67%, 75%, and 77.78%, respectively. This approach is an extremely fast process that is independent of the employed machine-learning methods.
