Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
4 results
Search Results
Article Citation - WoS: 8Citation - Scopus: 14An End-To Trainable Feature Selection-Forecasting Architecture Targeted at the Internet of Things(IEEE, 2021) Nakıp, Mert; Karakayalı, Kubilay; Güzeliş, Cüneyt; Rodoplu, VolkanWe develop a novel end-to-end trainable feature selection-forecasting (FSF) architecture for predictive networks targeted at the Internet of Things (IoT). In contrast with the existing filter-based, wrapper-based and embedded feature selection methods, our architecture enables the automatic selection of features dynamically based on feature importance score calculation and gamma-gated feature selection units that are trained jointly and end-to-end with the forecaster. We compare the performance of our FSF architecture on the problem of forecasting IoT device traffic against the following existing (feature selection, forecasting) technique pairs: Autocorrelation Function (ACF), Analysis of Variance (ANOVA), Recurrent Feature Elimination (RFE) and Ridge Regression methods for feature selection, and Linear Regression, Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM), 1 Dimensional Convolutional Neural Network (1D CNN), Autoregressive Integrated Moving Average (ARIMA), and Logistic Regression for forecasting. We show that our FSF architecture achieves either the best or close to the best performance among all of the competing techniques by virtue of its dynamic, automatic feature selection capability. In addition, we demonstrate that both the training time and the execution time of FSF are reasonable for IoT applications. This work represents a milestone for the development of predictive networks for IoT in smart cities of the near future.Conference Object Citation - WoS: 2Citation - Scopus: 4A Comparison of Feature Selection Algorithms for Cancer Classification Through Gene Expression Data: Leukemia Case(Institute of Electrical and Electronics Engineers Inc., 2018) Taşçı, Aslı; İnce, Türker; Güzeliş, CüneytIn this study, three different feature selection algorithms are compared using Support Vector Machines as classifier for cancer classification through gene expression data. The ability of feature selection algorithms to select an optimal gene subset for a cancer type is evaluated by the classification ability of selected genes. A publicly available micro array dataset is employed for gene expression values. Selected gene subsets were able to classify subtypes of the considered cancer type with high accuracies and showed that these feature selection methods were applicable for bio-marker gene selection.Article Citation - WoS: 5Citation - Scopus: 5Steady-State Analysis of Nonlinearly Coupled Chua's Circuits With Periodic Input(World Scientific Publishing Co. Pte Ltd, 2003) Savacı, Ferit Acar; Yalçın, M. E.; Güzeliş, CüneytIn this paper, nonlinearly coupled identical Chua's circuits, when driven by sinusoidal signal have been analyzed in the time-domain by using the steady-state analysis techniques of piecewise-linear dynamic systems. With such techniques, it has become possible to obtain analytical expressions for the transfer functions in terms of the circuit parameters. The proposed system under consideration has also been studied by analog simulations of the overall system on a hardware realization using off-the-shelf components as well as by a time-domain analysis of the synchronization error.Conference Object Citation - WoS: 42Citation - Scopus: 43An Automatic Level Set Based Liver Segmentation From Mri Data Sets(Institute of Electrical and Electronics Engineers Inc., 2012) Göçeri, Evgin; Ünlü, Mehmet Zübeyir; Güzeliş, Cüneyt; Dicle, OğuzA fast and accurate liver segmentation method is a challenging work in medical image analysis area. Liver segmentation is an important process for computer-assisted diagnosis, pre-evaluation of liver transplantation and therapy planning of liver tumors. There are several advantages of magnetic resonance imaging such as free form ionizing radiation and good contrast visualization of soft tissue. Also, innovations in recent technology and image acquisition techniques have made magnetic resonance imaging a major tool in modern medicine. However, the use of magnetic resonance images for liver segmentation has been slow when we compare applications with the central nervous systems and musculoskeletal. The reasons are irregular shape, size and position of the liver, contrast agent effects and similarities of the gray values of neighbor organs. Therefore, in this study, we present a fully automatic liver segmentation method by using an approximation of the level set based contour evolution from T2 weighted magnetic resonance data sets. The method avoids solving partial differential equations and applies only integer operations with a two-cycle segmentation algorithm. The efficiency of the proposed approach is achieved by applying the algorithm to all slices with a constant number of iteration and performing the contour evolution without any user defined initial contour. The obtained results are evaluated with four different similarity measures and they show that the automatic segmentation approach gives successful results. © 2012 IEEE.