Bilgisayar Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://gcris.khas.edu.tr/handle/20.500.12469/45

Browse

Now showing 1 - 20 of 42

Citation Count: 11
Accurate Refinement of Docked Protein Complexes Using Evolutionary Information and Deep Learning
(Imperıal College Press, 2016) Akbal-Delibas, Bahar; Farhoodi, Roshanak; Pomplun, Marc; Haspel, Nurit
One of the major challenges for protein docking methods is to accurately discriminate native-like structures from false positives. Docking methods are often inaccurate and the results have to be refined and re-ranked to obtain native-like complexes and remove outliers. In a previous work we introduced AccuRefiner a machine learning based tool for refining protein-protein complexes. Given a docked complex the refinement tool produces a small set of refined versions of the input complex with lower root-mean-square-deviation (RMSD) of atomic positions with respect to the native structure. The method employs a unique ranking tool that accurately predicts the RMSD of docked complexes with respect to the native structure. In this work we use a deep learning network with a similar set of features and five layers. We show that a properly trained deep learning network can accurately predict the RMSD of a docked complex with 1.40 angstrom error margin on average by approximating the complex relationship between a wide set of scoring function terms and the RMSD of a docked structure. The network was trained on 35000 unbound docking complexes generated by RosettaDock. We tested our method on 25 different putative docked complexes produced also by RosettaDock for five proteins that were not included in the training data. The results demonstrate that the high accuracy of the ranking tool enables AccuRefiner to consistently choose the refinement candidates with lower RMSD values compared to the coarsely docked input structures.
Citation Count: 1
An Analysis for the Use of Compressed Sensing Method in Microwave Imaging
(IEEE, 2017) Yiğit, Enes; Tekbaş, Mustafa; Ünal, İlhami; Erdoğan, Sercan; Çalışkan, Cafer
One of the most important problems encountered in microwave imaging methods is intensive data processing traffic that occurs when high resolution and real time tracking is desired. Radar signals can be recovered without loss of data with a randomly selected subset of the measurement data by compression sensing (CS) method which has been popular in recent years. For this reason, in this study, the use and capabilities of the CS method were investigated for tracking moving human, and the target information was correctly determined for the data obtained much below the Nyquist sampling criterion. In this study, it was revealed that the CS method can be developed for target detection and tracking
Citation Count: 1
Ask me: A Question Answering System via Dynamic Memory Networks
(Institute of Electrical and Electronics Engineers Inc., 2019) Yiğit, Gülsüm; Amasyalı, Mehmet Fatih
Most of the natural language processing problems can be reduced into a question answering problem. Dynamic Memory Networks (DMNs) are one of the solution approaches for question answering problems. Based on the analysis of a question answering system built by DMNs described in [1], this study proposes a model named DMN∗ which contains several improvements on its input and attention modules. DMN∗ architecture is distinguished by a multi-layer bidirectional LSTM (Long Short Term Memory) architecture on input module and several changes in computation of attention score in attention module. Experiments are conducted on Facebook bAbi dataset [2]. We also introduce Turkish bAbi dataset, and produce increased vocabulary sized tasks for each dataset. The experiments are performed on English and Turkish datasets and the accuracy performance results are compared by the work described in [1]. Our evaluation shows that the proposed model DMN∗ obtains improved accuracy performance results on various tasks for both Turkish and English.
Citation Count: 5
Biclustering Expression Data Based on Expanding Localized Substructures
(Springer-Verlag Berlin, 2009) Erten, Cesim; Sözdinler, Melih
Biclustering gene expression data is the problem of extracting submatrices of genes and conditions exhibiting significant correlation across both the rows and the columns of a data matrix of expression values. We provide a method LEB (Localize-and-Extract Biclusters) which reduces the search space into local neighborhoods within the matrix by first localizing correlated structures. The localization procedure takes its roots from effective use of graph-theoretical methods applied to problems exhibiting a similar structure to that of biclustering. Once interesting structures are localized the search space reduces to small neighborhoods and the biclusters are extracted from these localities. We evaluate the effectiveness of our method with extensive experiments both using artificial and real datasets.
Citation Count: 4
Channel Estimation for Realistic Indoor Optical Wireless Communication in Aco-Ofdm Systems
(Springer, 2018) Özmen, Atilla; Şenol, Habib
In this paper channel estimation problem in a visible light communication system is considered. The information data is transmitted using asymmetrical clipped optical orthogonal frequency division multiplexing. Channel estimation and symbol detection are performed by the Maximum Likelihood and the Linear Minimum Mean Square Error detection techniques respectively. The system performance is investigated in realistic environment that is simulated using an indoor channel model. Two different channels are produced using the indoor channel model. Symbol error rate (SER) performance of the system with estimated channels is presented for QPSK and 16-QAM digital modulation types and compared with the perfect channel state information. As a mean square error (MSE) performance benchmark for the channel estimator Cramer-Rao lower bound is also derived. MSE and SER performances of the simulation results are presented.
Citation Count: 11
Channel Estimation for Tds-Ofdm Systems in Rapidly Time-Varying Mobile Channels
(IEEE-Inst Electrical Electronics Engineers Inc, 2018) Başaran, Mehmet; Şenol, Habib; Erküçük, Serhat; Çırpan, Hakan Ali
This paper explores the performance of time-domain synchronous orthogonal frequency-division multiplexing (TDS-OFDM) systems operated under rapidly time-varying mobile channels. Since a rapidly time-varying channel contains more unknown channel coefficients than the number of observations, the mobile channel can conveniently be modeled with the discrete Legendre polynomial basis expansion model to reduce the number of unknowns. The linear minimum mean square error (LMMSE) estimate can be exploited for channel estimation on inter-block-interference-free received signal samples owing to transmitting pseudo-noise (PN) sequences. In conventional TDS-OFDM systems, the channel estimation performance is limited due to estimating channel responses only from the beginning part of the channel. Therefore, a new system model named "partitioned TDS-OFDM system" is proposed to improve the system performance by inserting multiple PN sequences to the middle and end parts of the channel as well. In addition to providing the reconstruction error performance, Bayesian Cramer-Rao lower hound is derived analytically. Also, the LMMSE-based symbol detection is employed. To alleviate the negative effects of inter-carrier-interference (ICI) occuring in mobile channels, ICI cancellation is applied to enhance the detection performance. The simulation results demonstrate that the proposed TDS-OFDM system is superior to the conventional system and its corresponding performance is able to approach the achievable lower performance bound.
Citation Count: 1
Dark Patches in Clustering
(IEEE, 2017) Ishaq, Waqar; Büyükkaya, Eliya
This survey highlights issues in clustering which hinder in achieving optimal solution or generates inconsistent outputs. We called such malignancies as dark patches. We focus on the issues relating to clustering rather than concepts and techniques of clustering. For better insight into the issues of clustering we categorize dark patches into three classes and then compare various clustering methods to analyze distributed datasets with respect to classes of dark patches rather than conventional way of comparison by performance and accuracy criteria because performance and accuracy may provide misleading conclusions due to lack of labeled data in unsupervised learning. To the best of our knowledge this prime feature makes our survey paper unique from other clustering survey papers.
Citation Count: 1
Data-Aided Autoregressive Sparse Channel Tracking for Ofdm Systems
(IEEE, 2016) Buyuksar, Ayse Betul; Şenol, Habib; Erküçük, Serhat; Cirpan, Hakan Ali
In order to meet future communication system requirements channel estimation over fast fading and frequency selective channels is crucial. In this paper Space Alternated Generalized Expectation Maximization Maximum a Posteriori (SAGE-MAP) based channel estimation algorithm is proposed for Orthogonal Frequency Division Multiplexing (OFDM) systems for Autoregressive (AR) modeled time-varying sparse channels. Also an initialization algorithm has been developed from the widely used sparse approximation algorithm Orthogonal Matching Pursuit (OMP) since the performance of SAGE algorithm strictly depends on initialization. The results show that multipath delay positions can be tracked successfully for every time instant using the proposed SAGE-MAP based approach.
Citation Count: 1
Effect of Inter-Block Region on Compressed Sensing Based Channel Estimation in Tds-Ofdm Systems
(Institute of Electrical and Electronics Engineers Inc., 2016) Başaran, Mehmet; Erküçük, Serhat; Şenol, Habib; Çırpan, Hakan Ali
Time domain synchronous orthogonal frequency division multiplexing (TDS-OFDM) is the basis technology for digital television standard (DTV) employed in some countries thanks to its high spectral efficiency when compared to traditional cyclic prefix OFDM. Moreover, it does not require pilot usage in frequency domain channel estimation. Instead of data usage as cyclic prefix, pseudo-noise (PN) sequences are transmitted in guard intervals. Due to interference from the previous OFDM data symbol, the received signal in guard interval can be decomposed into a small-sized signal that contains only PN sequences utilizing the inter-block-interference (IBI)-free region in the convolution matrix. Due to sparsity, multipath fading channel can be obtained by the application of compressed sensing (CS) technique to reconstruct the high-dimensional sparse channel from the decreased-size of received signal through the known PN sequence matrix. In this study, the effect of the size of IBI-free region on CS and Bayesian CS (BCS) based channel estimation is investigated. Accordingly, reconstruction error performances of basis pursuit (BP) and BCS are compared. Simulation results show that the channel estimation can be improved by trading-off the length of the IBI-free region. However, an increase in IBI-free region leads to decreased energy efficiency at both the transmitter and receiver side.
Citation Count: 0
Effect of the Channel Estimation Error on the Performance of the Source Estimator in a Wireless Sensor Network With Orthogonal Channels
(IEEE, 2008) Şenol, Habib; Tepedelenlioğlu, Cihan
In this work effect of the channel estimation error on the MSE performance of the source estimator in a wireless sensor network with orthogonal flat fading channels is studied. A two-phase approach was employed where in the first phase the orthogonal fading channel coefficients are estimated and in the second phase channel estimates and sensor observations transmitted to fusion center are used for the source estimation. We consider a sensor network in which the channel estimates are fed-back to the sensors for optimal power allocation which leads to switch off the sensors with bad channels in the second phase. We also show that training power should be at least half of the total power. Our analytical findings are corroborated by simulation results.
Citation Count: 0
An Energy Efficient Routing Algorithm (x-Centric Routing) for Sensor Networks
(INT INST Informatics & Systemics, 2011) Ataç, Göktuğ; Dağ, Tamer
Recent developments in wireless communications and electronics technologies have enabled the progress in low cost sensor networks. Sensor networks differ from traditional networks in several ways such as the severe energy constraints redundant low-rate date and many-to-one flows that the sensor networks require. One of the major challenges facing the design of a routing protocol for Wireless Sensor Networks (WSNs) is to find the most reliable path between the sources and the sink node by considering the energy awareness as an essential design parameter. This paper introduces a new routing protocol called as X-Centric routing by considering the above parameters. Under the X-Centric routing the decision making mechanism depends on the capacity of the sink node by switching between address-centric routing (AC-Routing) and data-centric routing (DC-Routing). The design tradeoffs between energy and communication overhead savings in these routing algorithms have been considered by considering the advantages and performance issues of each routing algorithm.
Citation Count: 2
First Impressions on Social Network Sites: Impact of Self-Disclosure Breadth on Attraction
(Academic Conferences and Publishing International Limited, 2017) Baruh, Lemi; Cemacılar, Zeynep; Bisson, Christophe; Chisik, Yoram I.
This paper reports the results of two experiments that investigate the relationship between the quantity of information disclosed on an SNS profile and profile viewers' first impressions of the profile owner. Both experiments utilized a 2 (low quantity of information vs. high quantity of information) by 2 (male vs. female profile) design. In the first experiment (n = 1059), the respondents were randomly assigned to the experimental conditions. The results showed that profile viewers were more favorable to profiles of women. Also, both for female and male SNS profiles, higher quantity of information led to more positive ratings of the profile owner. The second experiment expanded the findings from the first experiment in two ways. First, in the second experiment (n = 320), rather than being randomly assigned to the profile gender condition, the respondents could pick the gender of the profile they would review. Second, informed by previous research on face to face interactions which indicate that quantity of self-disclosure can increase interpersonal attraction by reducing the level of uncertainty about relational outcomes, we tested whether uncertainty reduction mediated the relationship between quantity of information presented in an SNS profile and interpersonal attraction. Female profiles were selected more often than male profiles by both female and male respondents; however, there was no difference in interpersonal attraction ratings that male and female profiles received. Higher quantity of information presented in an SNS profile had a significant impact on interpersonal attraction. The results from the second experiment also indicated that while quantity of information positively influenced profile viewers' perceptions regarding the agreeableness of the profile owner, it did not have an impact on viewers' perceptions regarding the dependability of the profile owner. As predicted, the impact of quantity of information on interpersonal attraction was mediated by a reduction in uncertainty levels.
Citation Count: 1
Flex: a Modular Software Architecture for Flight License Exam
(Springer-Verlag Berlin, 2010) Arsan, Taner; Saka, Hamit Emre; Şahin, Ceyhun
This paper is about the design and implementation of an examination system based on World Wide Web. It is called FLEX-Flight License Exam Software. We designed and implemented flexible and modular software architecture. The implemented system has basic specifications such as appending questions in system building exams with these appended questions and making students to take these exams. There are three different types of users with different authorizations. These are system administrator operators and students. System administrator operates and maintains the system and also audits the system integrity. The system administrator can not be able to change the result of exams and can not take an exam. Operator module includes instructors. Operators have some privileges such as preparing exams entering questions changing the existing questions and etc. Students can log on the system and can be accessed to exams by a certain URL. The other characteristic of our system is that operators and system administrator are not able to delete questions due to the security problems. Exam questions can be inserted on their topics and lectures in the database. Thus
Citation Count: 1
A Framework for Combined Recognition of Actions and Objects
(Springer-Verlag Berlin, 2012) Ar, İlktan; Akgül, Yusuf Sinan
This paper proposes a novel approach to recognize actions and objects within the context of each other. Assuming that the different actions involve different objects in image sequences and there is one-to-one relation between object and action type we present a Bayesian network based framework which combines motion patterns and object usage information to recognize actions/objects. More specifically our approach recognizes high-level actions and the related objects without any body-part segmentation hand tracking and temporal segmentation methods. Additionally we present a novel motion representation based on 3D Haar-like features which can be formed by depth color or both images. Our approach is also appropriate for object and action recognition where the involved object is partially or fully occluded. Finally experiments show that our approach improves the accuracy of both action and object recognition significantly.
Citation Count: 0
Fully Decentralized, Collaborative Multilateration Primitives for Uniquely Localizing Wsns
(Springer, 2009) Cakiroglu, Arda; Erten, Cesim
We provide primitives for uniquely localizing WSN nodes. The goal is to maximize the number of uniquely localized nodes assuming a fully decentralized model of computation. Each node constructs a cluster of its own and applies unique localization primitives on it. These primitives are based on constructing a special order for multilaterating the nodes within the cluster. The proposed primitives are fully collaborative and thus the number of iterations required to compute the localization is fewer than that of the conventional iterative multilateration approaches. This further limits the messaging requirements. With relatively small clusters and iteration counts we can localize almost all the uniquely localizable nodes. © 2009 Springer Berlin Heidelberg.
Citation Count: 1
Hybrid Mpi Plus Upc Parallel Programming Paradigm on an Smp Cluster
(TUBITAK Scientific & Technical Research Council Turkey, 2012) Bozkuş, Zeki
The symmetric multiprocessing (SMP) cluster system which consists of shared memory nodes with several multicore central processing units connected to a high-speed network to form a distributed memory system is the most widely available hardware architecture for the high-performance computing community. Today the Message Passing Interface (MPI) is the most widely used parallel programming paradigm for SMP clusters in which the MPI provides programming both for an SMP node and among nodes simultaneously. However Unified Parallel C (UPC) is an emerging alternative that supports the partitioned global address space model that can be again employed within and across the nodes of a cluster. In this paper we describe a hybrid parallel programming paradigm that was designed to combine MPI and UPC programming models. This paradigm's objective is to mix the MPI's data locality control and scalability strengths with UPC's fine-grain parallelism and ease of programming to achieve multiple-level parallelism at the SMP cluster which itself has multilevel parallel architecture. Utilizing a proposed hybrid model and comparing MPI-only to UPC-only implementations this paper presents a detailed description of Cannon's algorithm benchmark application with performance results of a random-access benchmark and the Barnes-Hut N-Body simulation. Experiments indicate that the hybrid MPI+UPC model can significantly provide performance increases of up to double in comparison with UPC-only implementation and up to 20% increases in comparison to MPI-only implementation. Furthermore an optimization was achieved that improved the hybrid performance by an additional 20%.
Citation Count: 0
Implementation of a Sdn (software Defined Network)
(International Institute of Informatics and Systemics IIIS, 2014) Ergen, Mithat Sinan; Kutlan, Sarp; Dağ, Tamer; Dağ, Hasan
Improving resource efficiency enhancing network security and achieving simpler network management have become the main goals for networking in the previous years. To accomplish these ideas an efficient routing traffic monitoring access control and server load balancing systems need to be designed. However these objectives make the optimization and management of networks rather difficult. In this paper Software Defined Networks (SDN) an alternative way for creating an optimized network by taking into account the difficulties met today is introduced. Software Defined Networks provide the separation of control and data planes for the switches which allows programming for a customized control plane. With simplified network management through SDN it can be possible to dynamically adjust the behavior of the network equipment independently from equipment manufacturers. New mechanisms with new potential benefits can easily be explored and used. Quality of Service and network security problems can be solved rapidly. In this paper it is described how to build a virtualized SDN in order to show the benefits of SDN over a distributed network. Virtualization can provide deployment and delivery flexibility cost savings and improved user experience.
Citation Count: 0
Importance of Regional Differences in Brain Throughout Aging for Down Syndrome
(Association for Computing Machinery, 2018) Kulan, Handan; Dağ, Tamer
Down syndrome (DS) which affects approximately one in 700 live births is caused by an extra copy of the long arm of human chromosome 21 (HSA21). Statistical analysis has been done for understanding the protein expression profiles based on age and sex differences in DS. In addition there are ongoing research efforts for comprehending expression patterns based on different brain regions. However little is known about the mechanisms of expression differences in brain regions throughout aging. Insights into these mechanisms are required to understand the susceptibility of distinct brain regions to neuronal insults with aging. Dissection of this selective vulnerability will be critical to our understanding of DS. By extracting information from the critical proteins which take part in the mechanism of the molecular pathways the diagnosis of DS can become easier. Also understanding the molecular pathways can contribute to develop effective drugs for the treatment of DS. In this work forward feature selection technique is applied for determining the protein subsets for old and young mice datasets which consist of the expression profiles across different brain regions. When these subsets are analyzed it is observed that selected proteins play important roles in the processes such as mTOR signaling pathway AD MAPK signaling pathway and apoptosis. We believe that the subsets of protein selected in our work can be utilized to understand the process of DS and can be used to develop age-related effective drugs.
Citation Count: 1
Joint Channel Estimation and Equalization for Ofdm Based Broadband Communications in Rapidly Varying Mobile Channels
(IEEE, 2010) Şenol, Habib; Poor, H. Vincent
This paper is concerned with the challenging and timely problem of channel estimation for orthogonal frequency division multiplexing (OFDM) systems in the presence of frequency selective and very rapidly time varying channels. In OFDM systems operating over rapidly time-varying channels the orthogonality between subcarriers is destroyed leading to inter-carrier interference (ICI) and resulting in an irreducible error floor. The band-limited discrete cosine serial expansion of low-dimensionality is employed to represent the time-varying channel. In this way the resulting reduced dimensional channel coefficients are estimated iteratively with tractable complexity and independently of the channel statistics. The algorithm is based on the expectation maximization-maximum a posteriori probability (EM-MAP) technique leading to a receiver structure that also yields the equalized output using the channel estimates. The pilot symbols are employed to estimate the initial coefficients effectively and unknown data symbols are averaged out in the algorithm in a non-data-aided fashion. It is shown that the computational complexity of the proposed algorithm to estimate the channel coefficients and to generate the equalized output as a by-product is similar to O(N) per detected symbol N being the number of OFDM subcarriers. Computational complexity as well as computer simulations carried out for the systems described in WiMAX and LTE standards indicate that it has significant performance and complexity advantages over existing suboptimal channel estimation and equalization algorithms proposed earlier in the literature.
Citation Count: 0
Joint Phase Noise Estimation And Source Detection [ortak Faz Gürültüsü Kestirimi ve Kaynak Sezimlemesi]
(2010) Kaleli, Burç Arslan; Şenol, Habib; Panayırcı, Erdal
Rapidly time-varying and random disturbing effects on the phase of a signal waveform are known as phase noise. In this paper we consider the problem of joint detection of continuous-valued information source output and estimation of a phase noise by using expectation maximization (EM) algorithm. In order to estimate phase noise initial phase noise values are determined by cubic interpolation that utilizes pilot symbols. Computer simulations are performed for the proposed algorithm and the average mean square error (MSE) - signal to noise ratio (SNR) performance of source detector and phase noise estimator is presented for each iteration of the algorithm. Moreover average MSE - pilot spacing performance curves of phase noise estimator are given for various SNR values. ©2010 IEEE.

Browse

Browsing Bilgisayar Mühendisliği Bölümü Koleksiyonu by Access Right "info:eu-repo/semantics/closedAccess"