5 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 5 / 5
Yayın Driver recognition using gaussian mixture models and decision fusion techniques(Springer-Verlag Berlin, 2008) Benli, Kristin Surpuhi; Düzağaç, Remzi; Eskil, Mustafa TanerIn this paper we present our research in driver recognition. The goal of this study is to investigate the performance of different classifier fusion techniques in a driver recognition scenario. We are using solely driving behavior signals such as break and accelerator pedal pressure, engine RPM, vehicle speed; steering wheel angle for identifying the driver identities. We modeled each driver using Gaussian Mixture Models, obtained posterior probabilities of identities and combined these scores using different fixed mid trainable (adaptive) fusion methods. We observed error rates is low as 0.35% in recognition of 100 drivers using trainable combiners. We conclude that the fusion of multi-modal classifier results is very successful in biometric recognition of a person in a car setting.Yayın Automatic modulation classification for mimo systems using fourth-order cumulants(IEEE, 2012) Mühlhaus, Michael S.; Öner, Mustafa Mengüç; Dobre, Octavia Adina; Jkel, Holger U.; Jondral, Friedrich K.Automatic classification of the modulation type of an unknown communication signal is a challenging task, with applications in both commercial and military contexts, such as spectrum surveillance, cognitive radio, and electronic warfare systems. Most of the automatic modulation classification (AMC) algorithms found in the literature assume that the signal of interest has been transmitted using a single antenna. In this paper, a novel AMC algorithm for multiple input multiple output (MIMO) signals is proposed, which employs fourth-order cumulants as features for classification. First, perfect channel state information (CSI) is assumed. Subsequently, a case of more practical relevance is considered, where the channel matrix is unknown and has to be estimated blindly by employing independent component analysis (ICA). The performance of the proposed classification algorithm is investigated through simulations and compared with an average likelihood ratio test (ALRT) which can be considered as optimum in the Bayesian sense, but has a very high computational complexity.Yayın A novel algorithm for MIMO signal classification using higher-order cumulants(IEEE, 2013) Muehlhaus, Michael S.; Öner, Mustafa Mengüç; Dobre, Octavia Adina; Jaekel, Holger U.; Jondral, Friedrich K.Automatic modulation classification (AMC) of unknown communications signals is employed in both commercial and military applications, such as cognitive radio, spectrum surveillance, and electronic warfare. Most of the AMC methods proposed in the literature are developed for systems with a single transmit antenna. In this paper, an AMC algorithm for multiple-input multiple-output (MIMO) signals is proposed, which is based on higher-order cumulants. The use of cumulants with different orders, as well as their combinations as feature vectors are investigated. The ideal case of a priori knowledge of the channel state information (CSI) is considered, along with a setting of practical relevance, where the channel matrix is blindly estimated through independent component analysis. The performance of the proposed algorithm with different features is evaluated through simulations and compared with that of the average likelihood ratio test (ALRT).Yayın Space time block code classification for MIMO signals exploiting cyclostationarity(Institute of Electrical and Electronics Engineers Inc, 2015) Turan, Merve; Öner, Mustafa Mengüç; Çırpan, Hakan AliBlind and noncooperative identification of the transmission parameters of unknown communication signals has been employed both in military and civilian applications. Multiple-Input-Multiple-Output (MIMO) transmission systems emerging in the last decade pose new challenges to the signal identification systems, one of which is the identification of the Space-Time Block Code (STBC) used in the transmission. In this work, we present a novel STBC classification algorithm that exploits the joint wide sense cyclostationary characteristics of the coded transmit signals as discriminating features. Compared to existing algorithms, the proposed method can discriminate between a large number of different STBCs.Yayın Cyclostationarity based blind block timing estimation for alamouti coded MIMO signals(IEEE, 2017-06) Gül, Serhat; Öner, Mustafa Mengüç; Çırpan, Hakan AliBlind parameter estimation algorithms provide a powerful tool for application scenarios where the use of training or pilot sequences is not desirable, e.g., in order to improve the bandwidth efficiency of the transmission, or in noncooperative scenarios where such sequences are not available to the receiver. This letter proposes a blind block timing estimation algorithm for Alamouti space-time block coded signals exploiting the second order joint cyclostationary characteristics of the received signal vector, which is induced by the space time block coding operation performed by the transmitter. The proposed algorithm outperforms the existing algorithms by a wide margin.
