Huseyin Ozkan

Bilkent University, Engüri, Ankara, Turkey

Are you Huseyin Ozkan?

Claim your profile

Publications (10)11.24 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We introduce a comprehensive and statistical framework in a model free setting for a complete treatment of localized data corruptions due to severe noise sources, e.g., an occluder in the case of a visual recording. Within this framework, we propose i) a novel algorithm to efficiently separate, i.e., detect and localize, possible corruptions from a given suspicious data instance and ii) a Maximum A Posteriori (MAP) estimator to impute the corrupted data. As a generalization to Euclidean distance, we also propose a novel distance measure, which is based on the ranked deviations among the data attributes and empirically shown to be superior in separating the corruptions. Our algorithm first splits the suspicious instance into parts through a binary partitioning tree in the space of data attributes and iteratively tests those parts to detect local anomalies using the nominal statistics extracted from an uncorrupted (clean) reference data set. Once each part is labeled as anomalous vs normal, the corresponding binary patterns over this tree that characterize corruptions are identified and the affected attributes are imputed. Under a certain conditional independency structure assumed for the binary patterns, we analytically show that the false alarm rate of the introduced algorithm in detecting the corruptions is independent of the data and can be directly set without any parameter tuning. The proposed framework is tested over several well-known machine learning data sets with synthetically generated corruptions; and experimentally shown to produce remarkable improvements in terms of classification purposes with strong corruption separation capabilities. Our experiments also indicate that the proposed algorithms outperform the typical approaches and are robust to varying training phase conditions.
    IEEE transactions on neural networks and learning systems 09/2014; DOI:10.1109/TNNLS.2014.2382606 · 4.37 Impact Factor
  • Huseyin Ozkan, Arda Akman, Suleyman S. Kozat
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a new estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have partial and noisy access to the hidden state sequence as side information. This access can be seen as ''partial labeling'' of the hidden states. Furthermore, we model possible mislabeling in the side information in a joint framework and derive the corresponding EM updates accordingly. In our simulations, we observe that using this side information, we considerably improve the state recognition performance, up to 70%, with respect to the ''achievable margin'' defined by the baseline algorithms. Moreover, our algorithm is shown to be robust to the training conditions.
    Signal Processing 01/2014; 94:490-497. DOI:10.1016/j.sigpro.2013.07.015 · 2.24 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we study the binary classification problem in machine learning and introduce a novel classification algorithm based on the “Context Tree Weighting Method”. The introduced algorithm incrementally learns a classification model through sequential updates in the course of a given data stream, i.e., each data point is processed only once and forgotten after the classifier is updated, and asymptotically achieves the performance of the best piecewise linear classifiers defined by the “context tree”. Since the computational complexity is only linear in the depth of the context tree, our algorithm is highly scalable and appropriate for real time processing. We present experimental results on several benchmark data sets and demonstrate that our method provides significant computational improvement both in the test (5 ~ 35×) and training phases (40 ~ 1000×), while achieving high classification accuracy in comparison to the SVM with RBF kernel.
    Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on; 01/2013
  • Source
    Huseyin Ozkan, Arda Akman, Suleyman S. Kozat
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a new estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have \emph{partial} and \emph{noisy} access to the hidden state sequence as side information. This access can be seen as "partial labeling" of the hidden states. Furthermore, we model possible mislabeling in the side information in a joint framework and derive the corresponding EM updates accordingly. In our simulations, we observe that using this side information, we considerably improve the state recognition performance, up to 70%, with respect to the "achievable margin" defined by the baseline algorithms. Moreover, our algorithm is shown to be robust to the training conditions.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, using “context tree weighting method”, a novel classification algorithm is proposed for real time machine learning applications, which is mathematically shown to be “competitive” with respect to a certain class of algorithms. The computational complexity of our algorithm is independent with the amount of data to be processed and linearly controllable. The proposed algorithm, hence, is highly scalable. In our experiments, our algorithm is observed to provide a comparable classification performance to the Support Vector Machines with Gaussian kernel with 40∼1000× computational efficiency in the training phase and 5∼35× in the test phase.
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a novel estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have partial and noisy access to the hidden state sequence as side information. This access can be seen as “partial labeling” of the hidden states. Furthermore, we model possible mislabeling in the side information in a joint framework and derive the corresponding EM updates accordingly. In our simulations, we observe that using this side information, we considerably improve the state recognition performance, up to 70%, with respect to the “achievable margin” defined by the baseline algorithms. Moreover, our algorithm is shown to be robust to different training conditions.
    Cognitive Information Processing (CIP), 2012 3rd International Workshop on; 01/2012
  • H. Ozkan, A. Akman, S.S. Kozat
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, the iterative Expectation-Maximization equations are mathematically derived for Hidden Markov Models (HMM), when there is partial and noisy access to the hidden states. Since the standard HMM is recovered when this partial and noisy access is turned off, our study provides a generalized observation model; and proposes a new model training algorithm within this model. According to the simulation results, our algorithm can improve the performance of the state recognition up to 70% with respect to the “achievable margin”, and also, is robust to different training conditions.
    Signal Processing and Communications Applications Conference (SIU), 2012 20th; 01/2012
  • M.A. Donmez, H. Ozkan, S.S. Kozat
    [Show abstract] [Hide abstract]
    ABSTRACT: We study the transient performances of three convexly constrained adaptive combination methods that combine outputs of two adaptive filters running in parallel to model a desired unknown system. We propose a theoretical model for the mean and mean-square convergence behaviors of each algorithm. Specifically, we provide expressions for the time evolution of the mean and the variance of the combination parameters, as well as for the mean square errors. The accuracy of the theoretical models are illustrated through simulations in the case of a mixture of two LMS filters with different step sizes.
    Machine Learning for Signal Processing (MLSP), 2012 IEEE International Workshop on; 01/2012
  • Source
    F. Porikli, H. Ozkan
    [Show abstract] [Hide abstract]
    ABSTRACT: Nonlinear kernel Support Vector Machines achieve better generalizations, yet their training and evaluation speeds are prohibitively slow for real-time object detection tasks where the number of data points in training and the number of hypotheses to be tested in evaluation are in the order of millions. To accelerate the training and particularly testing of such nonlinear kernel machines, we map the input data onto a low-dimensional spectral (Fourier) feature space using a cosine transform, design a kernel that approximates the classification objective in a supervised setting, and apply a fast linear classifier instead of the conventional radial basis functions. We present a data driven hypotheses generation technique and a LogistBoost feature selection. Our experimental results demonstrate the computational improvements 20~100× while maintaining a high classification accuracy in comparison to SVM linear and radial kernel basis function classifiers.
    Advanced Video and Signal-Based Surveillance (AVSS), 2011 8th IEEE International Conference on; 10/2011
  • Huseyin Ozkan