Bilgisayar Mühendisliği Bölümü Koleksiyonu

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

Browse

Now showing 1 - 20 of 154

Citation Count: 1
Accelerating Brain Simulations on Graphical Processing Units
(IEEE, 2015) Bozkuş, Zeki; El-Ghazawi, Tarek A.; Bozkuş, Zeki
NEural Simulation Tool(NEST) is a large scale spiking neuronal network simulator of the brain. In this work we present a CUDA(R) implementation of NEST. We were able to gain a speedup of factor 20 for the computational parts of NEST execution using a different data structure than NEST's default. Our partial implementation shows the potential gains and limitations of such possible port. We discuss possible novel approaches to be able to adapt generic spiking neural network simulators such as NEST to run on commodity or high-end GPGPUs.
Citation Count: 4
Accurate indoor positioning with ultra-wide band sensors
(Tubitak, 2020) Arsan, Taner
Ultra-wide band is one of the emerging indoor positioning technologies. In the application phase, accuracy and interference are important criteria of indoor positioning systems. Not only the method used in positioning, but also the algorithms used in improving the accuracy is a key factor. In this paper, we tried to eliminate the effects of off-set and noise in the data of the ultra-wide band sensor-based indoor positioning system. For this purpose, optimization algorithms and filters have been applied to the raw data, and the accuracy has been improved. A test bed with the dimensions of 7.35 m x 5.41 m and 50 cm x 50 cm grids has been selected, and a total of 27,000 measurements have been collected from 180 test points. The average positioning error of this test bed is calculated as 16.34 cm. Then, several combinations of algorithms are applied to raw data. The combination of Big Bang-Big Crunch algorithm for optimization, and then the Kalman Filter have yielded the most accurate results. Briefly, the average positioning error has been reduced from 16.34 cm to 7.43 cm.
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: 4
Action Recognition Using Random Forest Prediction with Combined Pose-based and Motion-based Features
(IEEE, 2013) Ar, İlktan; Akgül, Yusuf Sinan
In this paper we propose a novel human action recognition system that uses random forest prediction with statistically combined pose-based and motion-based features. Given a set of training and test image sequences (videos) we first adopt recent techniques that extract low-level features: motion and pose features. Motion-based features which represent motion patterns in the consecutive images are formed by 3D Haar-like features. Pose-based features are obtained by the calculation of scale invariant contour-based features. Then using statistical methods we combine these low-level features to a novel compact representation which describes the global motion and the global pose information in the whole image sequence. Finally Random Forest classification is employed to recognize actions in the test sequences by using this novel representation. Our experimental results on KTH and Weizmann datasets have shown that the combination of pose-based and motion-based features increased the system recognition accuracy. The proposed system also achieved classification rates comparable to the state-of-the-art approaches.
Citation Count: 2
Active reconfigurable control of a submarine with indirect adaptive control
(2003) Kerestecioğlu, Feza; Kerestecioğlu, Feza
An indirect adaptive controller is designed for submersibles. The design is developed using a linearized MIMO model of a submarine. Standard recursive least squares estimation method is used to estimate the parameters. Depth and pitch angle of the submarine is controlled by means of the well-known indirect self-tuning method. In case of a system fault estimated parameters of the submarine model have been used to update the controller coefficients.
Citation Count: 0
Amplitude and Frequency Modulations with Cellular Neural Networks
(Springer, 2015) Tander, Baran; Özmen, Atilla
Amplitude and frequency modulations are still the most popular modulation techniques in data transmission at telecommunication systems such as radio and television broadcasting gsm etc. However the architectures of these individual systems are totally different. In this paper it is shown that a cellular neural network with an opposite-sign template can behave either as an amplitude or a frequency modulator. Firstly a brief information about these networks is given and then the amplitude and frequency surfaces of the generated quasi-sine oscillations are sketched with respect to various values of their cloning templates. Secondly it is proved that any of these types of modulations can be performed by only varying the template components without ever changing their structure. Finally a circuit is designed simulations are presented and performance of the proposed system is evaluated. The main contribution of this work is to show that both amplitude and frequency modulations can be realized under the same architecture with a simple technique specifically by treating the input signals as template components.
Citation Count: 1
Analytical Expense Management System
(IEEE, 2009) Arsan, Taner; Bozkuş, Zeki; Arsan, Taner
Although the development of communication technologies (e.g: UMTS ADSL) allowed the elaboration of multiple users' web applications (e.g. information storage) there are still many improvements on many applications to be done and uncovered areas. Expense management systems on web application area are still in their infancy. Expense management software is widely spread in companies and most of time supported by their intranet. These solutions are quite simple as they mainly collect the information related to the expenses and may propose a simple aggregation of these figures. The result is close to what an excel sheet provides.
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: 0
Audience Tracking and Cheering Content Control in Sports Events
(IEEE, 2020) Arsan, Taner; Dursun, Sefa; Kumas, Osman; Çakir, Nagehan; Arsan, Taner
Swearing cheers encountered in sports competitions do not comply with sports ethics and morals. Even if this kind of cheering is a group, the entire tribune block is penalized in accordance with the current rules. This method is not preventive and individual punishment should be used. The aim of this study is to determine the individuals who cheer with swearing content. In this study, the person detection is made with the multi-task cascaded convolutional neural network. Moreover, facial landmarks representing the facial regions and the regions related to them are determined as a result of this process. The mouth region is also determined by means of these important points removed, and finally the mouth is determined according to the equation. The face recognition is carried out because the person would be in a state of yelling if the mouth opening ratio exceeds the threshold value by determining the rate of opening. Landmarks extracted from the facial regions for the face recognition are transformed into feature vectors by FaceNet, and the model is created by classifying these vectors with classifiers to use in recognition process. When evaluated in terms of industry, face recognition and detection systems find a wide field of study.
Citation Count: 1
A Bayesian approach to developing a strategic early warning system for the French milk market
(Halmstad University, 2017) Bisson, Christophe; Gürpınar, Furkan
A new approach is provided in our paper for creating a strategic early warning system allowing the estimation of the future state of the milk market as scenarios. This is in line with the recent call from the EU commission for tools that help to better address such a highly volatile market. We applied different multivariate time series regression and Bayesian networks on a pre-determined map of relations between macro-economic indicators. The evaluation of our findings with root mean square error (RMSE) performance score enhances the robustness of the prediction model constructed. Our model could be used by competitive intelligence teams to obtain sharper scenarios, leading companies and public organisations to better anticipate market changes and make more robust decisions.
Citation Count: 1
Bayesian estimation of discrete-time cellular neural network coefficients
(TUBITAK Scientific & Technical Research Council Turkey, 2017) Şenol, Habib; Özmen, Atilla; Şenol, Habib
A new method for finding the network coefficients of a discrete-time cellular neural network (DTCNN) is proposed. This new method uses a probabilistic approach that itself uses Bayesian learning to estimate the network coefficients. A posterior probability density function (PDF) is composed using the likelihood and prior PDFs derived from the system model and prior information respectively. This posterior PDF is used to draw samples with the help of the Metropolis algorithm a special case of the Metropolis--Hastings algorithm where the proposal distribution function is symmetric and resulting samples are then averaged to find the minimum mean square error (MMSE) estimate of the network coefficients. A couple of image processing applications are performed using these estimated parameters and the results are compared with those of some well-known methods.
Citation Count: 54
BEAMS: backbone extraction and merge strategy for the global many-to-many alignment of multiple PPI networks
(Oxford University Press, 2014) Erten, Cesim; Erten, Cesim
Motivation: Global many-to-many alignment of biological networks has been a central problem in comparative biological network studies. Given a set of biological interaction networks the informal goal is to group together related nodes. For the case of protein-protein interaction networks such groups are expected to form clusters of functionally orthologous proteins. Construction of such clusters for networks from different species may prove useful in determining evolutionary relationships in predicting the functions of proteins with unknown functions and in verifying those with estimated functions. Results: A central informal objective in constructing clusters of orthologous proteins is to guarantee that each cluster is composed of members with high homological similarity usually determined via sequence similarities and that the interactions of the proteins involved in the same cluster are conserved across the input networks. We provide a formal definition of the global many-to-many alignment of multiple protein-protein interaction networks that captures this informal objective. We show the computational intractability of the suggested definition. We provide a heuristic method based on backbone extraction and merge strategy (BEAMS) for the problem. We finally show through experiments based on biological significance tests that the proposed BEAMS algorithm performs better than the state-of-the-art approaches. Furthermore the computational burden of the BEAMS algorithm in terms of execution speed and memory requirements is more reasonable than the competing algorithms.
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: 7
Big Data Platform Development with a Domain Specific Language for Telecom Industries
(IEEE, 2013) Arsan, Taner; Bozkuş, Zeki; Bozkuş, Zeki; Arsan, Taner
This paper introduces a system that offer a special big data analysis platform with Domain Specific Language for telecom industries. This platform has three main parts that suggests a new kind of domain specific system for processing and visualization of large data files for telecom organizations. These parts are Domain Specific Language (DSL) Parallel Processing/Analyzing Platform for Big Data and an Integrated Result Viewer. hi addition to these main parts Distributed File Descriptor (DFD) is designed for passing information between these modules and organizing communication. To find out benefits of this domain specific solution standard framework of big data concept is examined carefully. Big data concept has special infrastructure and tools to perform for data storing processing analyzing operations. This infrastructure can be grouped as four different parts these are infrastructure programming models high performance schema free databases and processing-analyzing. Although there are lots of advantages of Big Data concept it is still very difficult to manage these systems for many enterprises. Therefore this study suggest a new higher level language called as DSL which helps enterprises to process big data without writing any complex low level traditional parallel processing codes a new kind of result viewer and this paper also presents a Big Data solution system that is called Petaminer.
Citation Count: 14
CAMPways: constrained alignment framework for the comparative analysis of a pair of metabolic pathways
(Oxford University Press, 2013) Erten, Cesim; Biyikoglu, Turker; Erten, Cesim
Motivation: Given a pair of metabolic pathways an alignment of the pathways corresponds to a mapping between similar substructures of the pair. Successful alignments may provide useful applications in phylogenetic tree reconstruction drug design and overall may enhance our understanding of cellular metabolism. Results: We consider the problem of providing one-to-many alignments of reactions in a pair of metabolic pathways. We first provide a constrained alignment framework applicable to the problem. We show that the constrained alignment problem even in a primitive setting is computationally intractable which justifies efforts for designing efficient heuristics. We present our Constrained Alignment of Metabolic Pathways (CAMPways) algorithm designed for this purpose. Through extensive experiments involving a large pathway database we demonstrate that when compared with a state-of-the-art alternative the CAMPways algorithm provides better alignment results on metabolic networks as far as measures based on same-pathway inclusion and biochemical significance are concerned. The execution speed of our algorithm constitutes yet another important improvement over alternative algorithms.
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: 35
Channel Estimation for Residual Self-Interference in Full-Duplex Amplify-and-Forward Two-Way Relays
(IEEE-INST Electrical Electronics Engineers Inc, 2017) Şenol, Habib; Tepedelenlioglu, Cihan; Şenol, Habib
Training schemes for full duplex two-way relays are investigated. We propose a novel one-block training scheme with a maximum likelihood estimator to estimate the channels between the nodes as well as the residual self-interference (RSI) channel simultaneously. A quasi-Newton algorithm is used to solve the estimator. As a baseline a multi-block training scheme is also considered. The Cramer-Rao bounds of the one-block and multi-block training schemes are derived. By using the Szego's theorem about Toeplitz matrices we analyze how the channel parameters and transmit powers affect the Fisher information. We show analytically that exploiting the structure arising from the RSI channel increases its Fisher information. Numerical results show the benefits of estimating the RSI channel.
Citation Count: 11
Channel Estimation for TDS-OFDM Systems in Rapidly Time-Varying Mobile Channels
(IEEE-Inst Electrical Electronics Engineers Inc, 2018) Şenol, Habib; Erküçük, Serhat; 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
Channel estimation in underwater cooperative OFDM system with amplify-and-forward relaying
(IEEE, 2012) Şenol, Habib; Panayırcı, Erdal; Erdoğan, Mustafa; Uysal, Murat
This paper is concerned with a challenging problem of channel estimation for amplify-and-forward cooperative relay based orthogonal frequency division multiplexing (OFDM) systems in the presence of sparse underwater acoustic channels and of the correlative non-Gaussian noise. We exploit the sparse structure of the channel impulse response to improve the performance of the channel estimation algorithm due to the reduced number of taps to be estimated. The resulting novel algorithm initially estimates the overall sparse channel taps from the source to the destination as well as their locations using the matching pursuit (MP) approach. The correlated non-Gaussian effective noise is modeled as a Gaussian mixture. Based on the Gaussian mixture model an efficient and low complexity algorithm is developed based on the combinations of the MP and the space-alternating generalized expectation-maximization (SAGE) technique to improve the estimates of the channel taps and their location as well as the noise distribution parameters in an iterative way. The proposed SAGE algorithm is designed in such a way that by choosing the admissible hidden data properly on which the SAGE algorithm relies a subset of parameters is updated for analytical tractability and the remaining parameters for faster convergence Computer simulations show that underwater acoustic (UWA) channel is estimated very effectively and the proposed algorithm has excellent symbol error rate and channel estimation performance.
Citation Count: 13
Characterization Of Mps Capped Cds Quantum Dots And Formation Self-Assembled Quantum Dots Thin Films On A Glass Substrate
(Natl Inst R&D Materials Physics, 2011) Koç, Kenan; Tepehan, Fatma Zehra; Tepehan, Galip Gültekin
Colloidal powdered and thin film forms of MPS capped CdS quantum dots have been produced by combination of colloidal chemistry and sol-gel method. Nanoparticles were self-assembled directly on a glass substrate using spin coating method without introducing any matrix. Colloidal powdered and thin film forms were characterised by absorbance photolimunescence XRD FT-IR HRTEM and AFM measurements. The HRTEM images give a grain size of 2.5-3.0 nm and this is in agreement with the values found in the absorbance and XRD measurement. Average size of the quantum dots increase with increasing of heat treatment temperature due to Oswald ripening.

Browse

Browsing Bilgisayar Mühendisliği Bölümü Koleksiyonu by Language "en"