Recent Submissions

  • ShakeMe: Key generation from shared motion 

    Y�zug�zel H.; Niemi J.; Kiranyaz, Mustafa Serkan; Gabbouj M.; Heinz T. ( Institute of Electrical and Electronics Engineers Inc. , 2015 , Conference Paper)
    Devices equipped with accelerometer sensors such as today's mobile devices can make use of motion to exchange information. A typical example for shared motion is shaking of two devices which are held together in one hand. ...
  • Long-term epileptic EEG classification via 2D mapping and textural features 

    Samiee K.; Kiranyaz, Mustafa Serkan; Gabbouj M.; Saramaki T. ( Elsevier Ltd , 2015 , Article)
    Interpretation of long-term Electroencephalography (EEG) records is a tiresome task for clinicians. This paper presents an efficient, low cost and novel approach for patient-specific classification of long-term epileptic ...
  • Structural damage detection in real time: Implementation of 1D convolutional neural networks for SHM applications 

    Avci O.; Abdeljaber O.; Kiranyaz, Mustafa Serkan; Inman D. ( Springer , 2017 , Conference Paper)
    Most of the classical structural damage detection systems involve two processes, feature extraction and feature classification. Usually, the feature extraction process requires large computational effort which prevent the ...
  • Learned vs. hand-designed features for ECG beat classification: A comprehensive study 

    Ince T.; Zabihi M.; Kiranyaz, Mustafa Serkan; Gabbouj M. ( Springer Verlag , 2017 , Conference Paper)
    In this study, in order to find out the best ECG classification performance we realized comparative evaluations among the state-of-the-art classifiers such as Convolutional Neural Networks (CNNs), multi-layer perceptrons ...
  • Sleep stage classification using sparse rational decomposition of single channel EEG records 

    Samiee K.; Kovacs P.; Kiranyaz, Mustafa Serkan; Gabbouj M.; Saramaki T. ( Institute of Electrical and Electronics Engineers Inc. , 2015 , Conference Paper)
    A sparse representation of ID signals is proposed based on time-frequency analysis using Generalized Rational Discrete Short Time Fourier Transform (RDSTFT). First, the signal is decomposed into a set of frequency sub-bands ...
  • Face segmentation in thumbnail images by data-adaptive convolutional segmentation networks 

    Kiranyaz, Mustafa Serkan; Waris M.-A.; Ahmad I.; Hamila R.; Gabbouj M. ( IEEE Computer Society , 2016 , Conference Paper)
    In this study we address the problem of face segmentation in thumbnail images. While there have been several approaches for face detection, none performs detection in such low resolution and segmentation with pixel accuracy. ...
  • Vibration suppression in metastructures using zigzag inserts optimized by genetic algorithms 

    Avci O.; Abdeljaber O.; Kiranyaz, Mustafa Serkan; Inman D. ( Springer New York LLC , 2017 , Conference Paper)
    Metastructures are known to provide considerable vibration attenuation for mechanical systems. With the optimization of the internal geometry of metastructures, the suppression performance of the host structure increases. ...
  • K-Subspaces Quantization for Approximate Nearest Neighbor Search 

    Ozan E.C.; Kiranyaz, Mustafa Serkan; Gabbouj M. ( IEEE Computer Society , 2016 , Article)
    Approximate Nearest Neighbor (ANN) search has become a popular approach for performing fast and efficient retrieval on very large-scale datasets in recent years, as the size and dimension of data grow continuously. In this ...
  • Particle swarm clustering fitness evaluation with computational centroids 

    Raitoharju J.; Samiee K.; Kiranyaz, Mustafa Serkan; Gabbouj M. ( Elsevier B.V. , 2017 , Article)
    In this paper, we propose a new way to carry out fitness evaluation in dynamic Particle Swarm Clustering (PSC) with centroid-based encoding. Generally, the PSC fitness function is selected among the clustering validity ...
  • Efficiency validation of one dimensional convolutional neural networks for structural damage detection using a SHM benchmark data 

    Avci O.; Abdeljaber O.; Kiranyaz M.S.; Boashash B.; Sodano H.; ... more authors ( International Institute of Acoustics and Vibration, IIAV , 2018 , Conference Paper)
    In this paper, a novel one dimensional convolution neural network (1D-CNN) based structural damage assessment technique is validated with a benchmark study published by IASC-ASCE Structural Health Monitoring Task Group in ...
  • Optimization on ports activation towards energy efficient data center networks 

    Chkirbene Z.; Hamila R.; Foufou S.; Kiranyaz, Mustafa Serkan; Gabbouj M. ( Springer Verlag , 2018 , Conference Paper)
    Nowadays, Internet of thing including network support (i.e. checking social media, sending emails, video conferencing) requires smart and efficient data centers to support these services. Hence, data centers become more ...
  • Progressive Operational Perceptrons 

    Kiranyaz, Mustafa Serkan; Ince T.; Iosifidis A.; Gabbouj M. ( Elsevier B.V. , 2017 , Article)
    There are well-known limitations and drawbacks on the performance and robustness of the feed-forward, fully-connected Artificial Neural Networks (ANNs), or the so-called Multi-Layer Perceptrons (MLPs). In this study we ...
  • 1-D Convolutional Neural Networks for Signal Processing Applications 

    Kiranyaz, Mustafa Serkan; Ince T.; Abdeljaber O.; Avci O.; Gabbouj M. ( Institute of Electrical and Electronics Engineers Inc. , 2019 , Conference Paper)
    1D Convolutional Neural Networks (CNNs) have recently become the state-of-the-art technique for crucial signal processing applications such as patient-specific ECG classification, structural health monitoring, anomaly ...
  • A k-nearest neighbor multilabel ranking algorithm with application to content-based image retrieval 

    Zhang H.; Kiranyaz, Mustafa Serkan; Gabbouj M. ( Institute of Electrical and Electronics Engineers Inc. , 2017 , Conference Paper)
    Multilabel ranking is an important machine learning task with many applications, such as content-based image retrieval (CBIR). However, when the number of labels is large, traditional algorithms are either infeasible or ...
  • Spatiotemporal saliency estimation by spectral foreground detection 

    Aytekin C.; Possegger H.; Mauthner T.; Kiranyaz, Mustafa Serkan; Bischof H.; ... more authors ( Institute of Electrical and Electronics Engineers Inc. , 2018 , Article)
    We present a novel approach for spatiotemporal saliency detection by optimizing a unified criterion of color contrast, motion contrast, appearance, and background cues. To this end, we first abstract the video by temporal ...
  • Matlab/Simulink Modeling and Simulation of Electric Appliances Based on their Actual Current Waveforms 

    Gastli A.; Kiranyaz, Mustafa Serkan; Hamila R.; Ellabban O. ( Institute of Electrical and Electronics Engineers Inc. , 2019 , Conference Paper)
    This paper presents a novel modeling technique of electric appliances using Matlab/Simulink based on their actual measured current waveforms. Home appliances were used as the study case, but the proposed approach can be ...
  • Performance Comparison of Learned vs. Engineered Features for Polarimetric SAR Terrain Classification 

    Ahishali M.; Ince T.; Kiranyaz, Mustafa Serkan; Gabbouj M. ( Institute of Electrical and Electronics Engineers Inc. , 2019 , Conference Paper)
    In this work, we propose to use learned features for terrain classification of Polarimetric Synthetic Aperture Radar (PolSAR) images. In the proposed classification framework, the learned features are extracted from sliding ...
  • Sepsis Prediction in Intensive Care Unit Using Ensemble of XGboost Models 

    Zabihi M.; Kiranyaz, Mustafa Serkan; Gabbouj M. ( IEEE Computer Society , 2019 , Conference Paper)
    Sepsis is caused by the dysregulated host response to infection and potentially is the main cause of 6 million death annually. It is a highly dynamic syndrome and therefore the early prediction of sepsis plays a key role ...
  • Convolutional neural networks for real-time and wireless damage detection 

    Avci O.; Abdeljaber O.; Kiranyaz, Mustafa Serkan; Inman D. ( Springer New York LLC , 2020 , Conference Paper)
    Structural damage detection methods available for structural health monitoring applications are based on data preprocessing, feature extraction, and feature classification. The feature classification task requires considerable ...
  • 1D Convolutional Neural Networks Versus Automatic Classifiers for Known LPI Radar Signals under White Gaussian Noise 

    Yildirim A.; Kiranyaz, Mustafa Serkan ( Institute of Electrical and Electronics Engineers Inc. , 2020 , Article)
    In this study we analyze the signal classification performances of various classifiers for deterministic signals under the additive White Gaussian Noise (WGN) in a wide range of signal to noise ratio (SNR) levels (-40dB ...

View more