Research Outputs
Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2
Browse
85 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Metadata only 3D shape correspondence by isometry-driven greedy optimization(IEEE Computer Soc, 2010) N/A; Department of Computer Engineering; Sahillioğlu, Yusuf; Yemez, Yücel; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; 215195; 107907We present an automatic method that establishes 3D correspondence between isometric shapes. Our goal is to find an optimal correspondence between two given (nearly) isometric shapes, that minimizes the amount of deviation from isometry. We cast the problem as a complete surface correspondence problem. Our method first divides the given shapes to be matched into surface patches of equal area and then seeks for a mapping between the patch centers which we refer to as base vertices. Hence the correspondence is established in a fast and robust manner at a relatively coarse level as imposed by the patch radius. We optimize the isometry cost in two steps. in the first step, the base vertices are transformed into spectral domain based on geodesic affinity, where the isometry errors are minimized in polynomial time by complete bipartite graph matching. the resulting correspondence serves as a good initialization for the second step of optimization in which we explicitly minimize the isometry cost via an iterative greedy algorithm in the original 3D Euclidean space. We demonstrate the performance of our method on various isometric (or nearly isometric) pairs of shapes for some of which the ground-truth correspondence is available.Publication Metadata only A classification of concurrency bugs in java benchmarks by developer intent(Association for Computing Machinery (ACM), 2006) Department of Computer Engineering; Department of Computer Engineering; N/A; Keremoğlu, M. Erkan; Taşıran, Serdar; Elmas, Tayfun; Researcher; Faculty Member; PhD Student; Department of Computer Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; N/A; N/A; N/AThis work addresses the issue of selecting the formal correctness criterion for a concurrent Java program that best corresponds to the developer's intent. We study a set of concurrency-related bugs detected in Java benchmarks reported in the literature. On these programs, we determine whether race-freedom, atomicity or refinement is the simplest and most appropriate criterion for program correctness. Our purpose is to demonstrate empirically the fact that the appropriate fix for a concurrency error and the selection of a program analysis tool for detecting such an error must be based on the proper expression of the designer's intent using a formal correctness criterion.Publication Open Access A deep learning approach for data driven vocal tract area function estimation(Institute of Electrical and Electronics Engineers (IEEE), 2018) Department of Computer Engineering; Department of Electrical and Electronics Engineering; Erzin, Engin; Asadiabadi, Sasan; Faculty Member; Department of Computer Engineering; Department of Electrical and Electronics Engineering; College of Sciences; Graduate School of Sciences and Engineering; 34503; N/AIn this paper we present a data driven vocal tract area function (VTAF) estimation using Deep Neural Networks (DNN). We approach the VTAF estimation problem based on sequence to sequence learning neural networks, where regression over a sliding window is used to learn arbitrary non-linear one-to-many mapping from the input feature sequence to the target articulatory sequence. We propose two schemes for efficient estimation of the VTAF; (1) a direct estimation of the area function values and (2) an indirect estimation via predicting the vocal tract boundaries. We consider acoustic speech and phone sequence as two possible input modalities for the DNN estimators. Experimental evaluations are performed over a large data comprising acoustic and phonetic features with parallel articulatory information from the USC-TIMIT database. Our results show that the proposed direct and indirect schemes perform the VTAF estimation with mean absolute error (MAE) rates lower than 1.65 mm, where the direct estimation scheme is observed to perform better than the indirect scheme.Publication Metadata only A moving window approach for blind equalization using subgradient projections(IEEE, 2004) N/A; N/A; Department of Electrical and Electronics Engineering; Kızılkale, Can; Erdoğan, Alper Tunga; PhD Student; Faculty Member; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 41624A novel blind equalization method based on a subgradient search over a convex cost surface is examined under a noisy channel and a modification is proposed. This is an alternative to the existing iterative blind equalization approaches such as Constant Modulus Algorithm (CMA) which mostly suffer from the convergence problems caused by their non-convex cost functions. The proposed method is an iterative algorithm, for both real and complex constellations, with a very simple update rule that minimizes the l(infinity) norm of the equalizer output under a linear constraint on the equalizer coefficients. The subgradient based algorithm has a fast convergence behavior attributed to the convex l(infinity) cost surface. A moving window based approach is used in this algorithm to both decrease algorithm's complexity and increase its immunity to noise. / Bu makalede alt-bayır izdüşümleri kullanılarak yapılan kör eşitleme metodunun gürültülü bir kanal için performansı incelenmiş ve bu performansın arttırılması için bir öneride bulunulmuştur. Bu algoritma daha önce önerilen sabit genlik algoritmasi(CMA) gibi özyineli yöntemlere bir alternatif olarak sunulmaktadır. Bilindiği gibi daha once sunulan algoritmalar dışbükey olmayan maliyet işlevlerinden dolayı yakınsallık problemi yaşamaktadırlar. Önerilen yöntem, hem gerçek hem de karmaşık burçlar (constellation) için, denkleştirici katsayıları üzerindeki doğrusal bir kısıt altında denkleştiricinin çıktısını l(infinity), normunu enküçültme esasına dayalı, basit bi güncelleme yapısına sahip özyinelemeli bir algoritmadır. Bu algoritma l(infinity) maliyet yüzeyinin karakterinden dolayı hızlı yakınsama davranışına sahiptir. Algoritmanin hem karmaşıklığını azaltacak hem de gürültüye karşı bağışıklığını yükseltecek hareketli pencereye dayalı bir yapı kullanılmıştır.Publication Metadata only A multitask multiple kernel learning algorithm for survival analysis with application to cancer biology(JMLR-Journal Machine Learning Research, 2019) N/A; Department of Industrial Engineering; Department of Industrial Engineering; Dereli, Onur; Oğuz, Ceyda; Gönen, Mehmet; PhD Student; Faculty Member; Faculty Member; Department of Industrial Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; N/A; 6033; 237468Predictive performance of machine learning algorithms on related problems can be improved using multitask learning approaches. Rather than performing survival analysis on each data set to predict survival times of cancer patients, we developed a novel multitask approach based on multiple kernel learning (MKL). Our multitask MKL algorithm both works on multiple cancer data sets and integrates cancer-related pathways/gene sets into survival analysis. We tested our algorithm, which is named as Path2MSurv, on the Cancer Genome Atlas data sets analyzing gene expression profiles of 7,655 patients from 20 cancer types together with cancer-specific pathway/gene set collections. Path2MSury obtained better or comparable predictive performance when benchmarked against random survival forest, survival support vector machine, and single-task variant of our algorithm. Path2MSury has the ability to identify key pathways/gene sets in predicting survival times of patients from different cancer types.Publication Metadata only A new scalable multi-view video coding configuration for robust selective streaming of free-viewpoint TV(IEEE, 2007) Özbek, Nükhet; Tunalı, E. Turhan; Department of Electrical and Electronics Engineering; Tekalp, Ahmet Murat; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; 26207Free viewpoint TV (FTV) is a new media format that allows a user to change his/her viewpoint freely. To this effect, multi-view video must be coded to sAtışfy two conflicting requirements: i) achieve high compression efficiency, and ii) allow view switching with low delay. This paper proposes a new encoding configuration for scalable multi-view video coding, which achieves a compromise between the two requirements. In the new scalable multi-view configuration, the base layer is encoded with inter-view prediction at a minimum acceptable quality, while enhancement layers for each view only depend on their respective base layers (with no interview prediction). Thus, the base layer shall be served to all users, while enhancement layers shall be served selectively to users depending on their channel bandwidth and viewing direction. We compare the compression efficiency of the proposed method with those of non-scalable multi-view coding (MVC) and simulcast (H.264/AVC of each view independently) solutions.Publication Metadata only Abalone life phase classification with deep learning(IEEE, 2018) Ozsarfati, Eran; Yılmaz, Alper; N/A; N/A; Şahin, Egemen; Saul, Can Jozef; Researcher; Researcher; N/A; N/A; N/A; N/AIn this paper, we present algorithmic and architectural comparison of deep learning models for predicting abalone age range. While abalone age can be determined through very detailed steps in a laboratory, we present an efficient method for determining its age through machine learning models. We present a precise and an efficient method for converting data to a computable version through binary encoding and normalization. We experiment with various topological variances in neural network architectures, convolutional approach to the task at hand and recently succeeding residual neural network architecture for finding the optimal prediction accuracy and efficiency. Although the conventional machine learning methods showed success in this field, our deep learning model tests yield an accuracy of 79.09% accuracy, surpassing the conventional machine learning algorithms as we incorporated methods for preventing over-fitting and methods for normalizing the output throughout the network.Publication Metadata only Adaptive peer-to-peer video streaming with optimized flexible multiple description coding(IEEE, 2006) Akyol, Emrah; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Tekalp, Ahmet Murat; Civanlar, Mehmet Reha; Faculty Member; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; College of Engineering; 26207; 16372Efficient peer-to-peer (P2P) video streaming is a challenging task due to time-varying nature of both the number of available peers and network/channel conditions. To this effect, we propose a receiver driven P2P streaming system which utilizes a flexible scalable multiple description coding method [1], where the number of base and enhancement descriptions, and the rate and redundancy level of each description can be adapted on the fly. The optimization of the parameters of the proposed MDC scheme according to network conditions is discussed within the context of the proposed adaptive P2P streaming framework, where the number and quality of available streaming peers/paths are a priori unknown and vary in time. Experimental results, by means of NS-2 network simulation of a P2P video streaming system, show that adaptation of the number, type, and rate of descriptions and the redundancy level of each description according to network conditions yields significantly superior performance when compared to MDC schemes using a fixed number of descriptions/layers with fixed rate and redundancy level.Publication Open Access AfriKI: machine-in-the-loop Afrikaans poetry generation(Association for Computational Linguistics (ACL), 2021) Baş, Anıl; Department of Comparative Literature; van Heerden, Imke; Other; Department of Comparative Literature; College of Social Sciences and Humanities; 318142This paper proposes a generative language model called AfriKI. Our approach is based on an LSTM architecture trained on a small corpus of contemporary fiction. With the aim of promoting human creativity, we use the model as an authoring tool to explore machine-in-the-loop Afrikaans poetry generation. To our knowledge, this is the first study to attempt creative text generation in Afrikaans.Publication Metadata only An adaptive paraunitary approach for blind equalization of all equalizable MIMO channels(IEEE, 2006) Department of Electrical and Electronics Engineering; Erdoğan, Alper Tunga; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; 41624We introduce a novel adaptive paraunitary approach to be used for the blind deconvolution of all deconvolvable MIMO mixing systems with memory. The proposed adaptive approach is based on the use of alternating projections technique for the enforcement of the paraunitary constraint. The use of this approach enables extension of various instantaneous Blind Source Separation (BSS) approaches to handle the convolutive BSS case. Three such methods, namely FastICA, Multi User Kurtosis and BSS for Bounded Magnitude signals are provided to illustrate the use of this approach.