Mühendislik ve Doğa Bilimleri Fakültesi

Permanent URI for this communityhttps://gcris.khas.edu.tr/handle/20.500.12469/36

Browse

Now showing 1 - 20 of 163

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
An Analysis for the Use of Compressed Sensing Method in Microwave Imaging
(IEEE, 2017) Çalışkan, Cafer; 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
An analysis for the use of compressed sensing method in microwave imaging [Mikrodalga Görüntülemede Sıkıştırılmış Algılama Yönteminin Kullanımına Yönelik Bir Analiz]
(Institute of Electrical and Electronics Engineers Inc., 2017) Çalışkan, Cafer; Tekbaş, Mustafa; Ünal, İlhami; Erdogan, 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. © 2017 IEEE.
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: 0
Büyük Patlama – Büyük Çöküş Optimizasyon Yöntemi Kullanılarak Bluetooth Tabanlı İç Mekan Konum Belirleme Sisteminin Doğruluğunun İyileştirilmesi
(Süleyman Demirel Üniversitesi, 2018) Arsan, Taner
Düşük enerjili Bluetooth işaretçi (Bluetooth low energy - BLE beacon) teknolojisi, iç mekan konum belirleme sistemlerinde başarılı ve düşük maliyetli çözümler sunan gelişmekte olan bir teknolojidir. Bu çalışmada, BLE işaretçileri (beacons) kullanan bir iç mekan konum belirleme sistemi geliştirilmiş, kullanılan ilave algoritmalarla standart sensörlerden elde edilen konum değerlerinin doğruluğunun artırılması amaçlanmıştır. Bunun için, deneysel iç mekan konum algılama sisteminden elde edilen konum bilgilerine Büyük Patlama – Büyük Çöküş (Big Bang – Big Crunch (BB-BC)) optimizasyon yöntemi uygulanmış ve konum doğruluğunun geliştirildiği yapılan testlerle kanıtlanmıştır. Test alanı olarak, 9,60 m × 3,90 m boyutundaki 37,44 m2'lik alan seçilmiş ve 2,40 m × 1,30 m boyutundaki oniki tane ızgara alanına ayak izi (fingerprinting) algoritması uygulanmıştır. Test alanına dört tane BLE işaretçi (beacon) yerleştirilmiş, on iki test alanından 150 saniye boyunca toplam 9.000 ölçüm yapılmıştır. Ölçüm sonuçları Büyük Patlama – Büyük Çöküş optimizasyon yöntemi ile Öklid uzaklık eşleştirme yöntemi ve Kalman Filtresi kullanılarak iyileştirilmiş, bu sayede konum doğruluğu %26,62'den %75,69'a arttırılmıştır.
Citation Count: 0
Büyük patlama büyük çöküş optimizasyon yöntemi ile ultra geniş band sensörlerinin iç mekân konum belirleme doğruluklarının iyileştirilmesi
(Pamukkale Üniversitesi, 2018) Arsan, Taner
Ultra geniş band teknolojisi, birçok iç mekân konum belirleme sisteminde başarılı çözümler sunan, diğer yöntemlere kıyasla daha iyi performans gösteren, gelişmekte olan bir teknolojidir. Bu çalışmada, ultra geniş band (Ultra Wide Band-UWB) sensörler kullanılarak bir iç mekân konum belirleme sistemi geliştirilmiş ve kullanılan ek algoritmalarla, standart donanımların sağladığı doğruluk düzeyi arttırılırken aynı zamanda ortalama hatayı azaltmak hedeflenmiştir. Bu amaçla Büyük Patlama - Büyük Çöküş (Big Bang-Big Crunch veya BB-BC) optimizasyon yöntemi deneysel iç mekân konumlandırma sistemine uygulanmış ve ölçüm doğruluğu üzerindeki olumlu etkisi yapılan testlerle kanıtlanmıştır. Test alanı olarak 7.35 m × 5.41 m boyutlarında 39.76 m2 'lik bir alan seçilmiş ve özel olarak tasarlanmış bir tavan sistemine yerden 2.85 m yüksekliğe üç farklı UWB alıcı yerleştirilmiş ve 182 adet test noktasından 60 sn.süreyle toplam 10.920 ölçüm alınmıştır. Ölçüm sonuçları Büyük Patlama - Büyük Çöküş optimizasyon algoritması ile düzeltilerek, ortalama hatası önceki 20.72 cm değerinden 15.02 cm’ye düşürülmüş, böylelikle ölçüm sonuçlarının doğruluğu arttırılmıştır.
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.

Browse

Browsing Mühendislik ve Doğa Bilimleri Fakültesi by Department "Fakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü"