Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
9 results
Search Results
Publication Metadata only Coupled Shape Priors for Dynamic Segmentation of Dendritic Spines(IEEE, 2017) Atabakilachini, Naeimeh; Erdil, Ertunc; Argunsah, A. Ozgur; Rada, Lavdie; Unay, Devrim; Cetin, Mujdat; Sabanci University; University of Zurich; Bahcesehir University; Izmir Ekonomi UniversitesiSegmentation of biomedical images is a challenging task, especially when there is low quality or missing data. The use of prior information can provide significant assistance for obtaining more accurate results. In this paper we propose a new approach for dendritic spine segmentation from microscopic images over time, which is motivated by incorporating shape information from previous time points to segment a spine in the current time point. In particular, using a training set consisting of spines in two consecutive time points to construct coupled shape priors, and given the segmentation in the previous time point, we can improve the segmentation process of the spine in the current time point. Our approach has been evaluated on 2-photon microscopy images of dendritic spines and its effectiveness has been demonstrated by both visual and quantitative results.Publication Metadata only Energy and Spectral Efficiency for Heterogeneous Cellular Networks with Stochastic Deployment(IEEE, 2017) Demirtas, Mahmut; Saginda, Cagatay; Soysal, Alkan; Bahcesehir UniversityIn this paper, we investigate the energy efficiency and spectral efficiency of heterogeneous networks, where macro cell and microcell base stations are deployed according to two separate stochastic geometry based processes. Here, micro base stations are placed over the regions for which the received signal strength is below a certain limit. By employing the deployment model we propose, we investigate the effects of certain parameters like macro and micro base station densities, and user density on energy efficiency of heterogeneous networks. The results show that deploying micro base stations considerably improves both energy efficiency and spectral efficiency in a dense user scenario.Publication Metadata only Classification of Band-Specific Regional Hemispheric Connectivity in Obsessive Compulsive Disorder(IEEE, 2017) Aydin, Serap; Tan, Oguz; Bahcesehir University; Uskudar UniversityIn the present study, inter-electrode hemispheric dependency has been estimated by using frequency, time and phase domain methods (Fourier Correlation, Wavelet Correlation (WC), Hilbert Correlation) for eight individual brain lobes (pre-frontal, anterio-frontal, central, occipital, parietal, posterio-frontal, anterio-temporal, posterio-temporal) in five frequency band activities (Delta (0.5 - 4 Hz), Theta (4 - 8 Hz), Alpha (8-16 Hz), Beta (16-32 Hz) and, Gamma (32-64 Hz)) for detection of obsessive compulsive disorder (OCD). For this purpose, patients and controls are classified by using non-linear Least-Squares Support-Vector-Machine with 10-fold cross validation for both eight features in each sub-band and single ban-specific feature at each lobe. The best classification performance (87, 15% and 96, 65% in Beta and Gamma) is obtained for eight features estimated by using WC. In particular, single feature through WC has provided the relatively lower but useful classification performance in Beta (72, 34% at prefrontal, (72, 59% at occipital, 76, 39% at posterio-frontal, 70, 89% at anterio-temporal, 71, 14% at posterio-temporal) and Gamma (71, 84% at prefrontal, 76, 39% at occipital, 76, 39% at posterio-frontal, 70, 89% at anterio-temporal, 71, 77% at posterio-temporal). In detail, OCD is found to be characterized by low hemispheric dependency in Gamma over cortex. In conclusion, OCD causes abnormalities at almost every hemispheric lobe. WC provides the best estimations to compute band specific asymmetry levels due to non-linear and non-stationary nature of EEG.Publication Metadata only Open Distributed System to Provide Real-Time Communication Service over Web(IEEE, 2017) Armagan, Ozgur; Guner, Huseyin; Keskin, Selcuk; Kocak, Taskin; Netas; Bahcesehir UniversityNowadays, corporate companies use different applications and service providers to take advantage of services such as instant messaging, e-mail, social networks and company-wide calls. These service providers are demanding higher licensing fees for additional features needed by the institutions. For example, the ability to call landlines as well as in-house calls can greatly increase the costs of the corporate companies. Moreover, there is no application in the market that provides ease of use by collecting all these services under one roof. In this work, a system has been designed to ensure that all these shortcomings are eliminated and landlines can be called. ThePublication Metadata only Facial Emotion Classification Using Deep Embedding with Triplet Loss Function(IEEE, 2017) Bircanoglu, Cenk; Arica, Nafiz; Bahcesehir UniversityIn this paper, a deep embedding method using triplet loss function is proposed for classification of the emotions in face images. The originality of proposed method lies in the loss function, different from the other deep learning-based facial emotion classification approaches. The input face images are embedded into a lower dimensional feature space using a multi layer convolutional neural network. In this embedding process the loss function is calculated by taking triple samples in the training dataset. For each sample in batches, two samples are selected in such a way that one of them is from the same class and the other one from the different class. The loss function aims to close the samples belonging to the same class to each other in the Euclidean space and to move away from the samples in the different class. In the performance analysis of proposed method, two popular deep architectures, namely AlexNet and VGG are used on two datasets called CIFE and GaMo. The experiments show that the proposed method outperforms the other popular loss functions and the available studies on this particular datasets.Publication Metadata only Face Frontalization Enhanced by Deep Learning(IEEE, 2017) Celik, Anil; Arica, Nafiz; Bahcesehir UniversityIn this study, a new approach based on 3-D models and deep learning to frontalize face images is proposed. Specifically designed for facial expression analysis, the proposed approach aims to reduce possible negative effects that a posed face image can generate, by normalizing the face region. In the first phase, the face image is semi-frontalized, with a pre-established 3-D reference model based approach. Then, missing regions on semi-frontalized images due to geometric transformation are reconstructed with the help of a denoising stacked autoencoder network. In this phase, missing regions created by line of sight are learned, with a deep architecture, using numerous images. When examined, it can be said that, faces acquired with the proposed approach, are objectively better than the faces acquired with a deep learning or 3-D based method alone. Therefore, it is assumed that the proposed approach can be used in face based computer vision methods as a beneficial pre-processing step.Publication Metadata only Modal Beamforming for Circular Acoustic Vector Sensor Arrays(IEEE, 2017) Gur, Berke; Bahcesehir UniversityIn this paper, modal beamformers for circular vector sensor arrays are investigated. As an alternative to existing methods for pressure and 2-dimensional (2D) particle velocity sensor arrays, a modal beamformer for circular arrays of 1D acoustic vector sensors is presented. Directivity performance of these modal beamformers are analyzed and the proposed method is shown to perform better compared to pressure arrays due to improved white noise gain. Furthermore, it is aslo shown that the proposed method can achieve a directivity performance similar to that of the 2D vector sensor array using only half the number of sensors.Publication Metadata only Multiple Visual Object Recognition For Poster Detection(TURGUT OZAL UNIV, 2012) Kuzhan, Abdullah; Ozden, Kemal Egemen; Kiray, V; Ozcan, R; Malas, T; Bahcesehir UniversityWe are aiming at an Augmented Reality application where multiple instances of a movie poster can be detected and localized. In that regard, we studied the problem of detecting and localizing multiple instances of planar objects, or objects which have repetitive patterns on it. Local image features, such as SIFT or SURF features are popular methods for image search and localization tasks. However classical methods which depend on initial feature matching, fail when there are multiple instances of the same object or when the objects have repetitive patterns on them. We extended and modified those methods in various ways to handle such situations. First of all, instead of an initial putative feature matching phase, we consider all possible meaningful matches in a Hough voting schema. Considering the nature of the target application which requires efficiency due to limited mobile platform CPU power and where the posters are distinctly apart, we do Hough transform only in translation space. Various subtle issues are also clarified, including an explicit formulation of the transformations. Techniques are verified with actual experiments.Publication Metadata only Ensemble Clustering Selection by Optimization of Accuracy-Diversity Trade off(IEEE, 2017) Akyuz, Sureyya; Otar, Buse Cisil; Bahcesehir University; Bahcesehir UniversityThe aim of clustering is to group objects which have common features within the group but have dissimilarities with other groups. Clustering algorithms involve finding a common structure without using any label, similarly like other unsupervised methods. Recent studies show that the decision of the ensemble clusters gives more accurate results than any single clustering solution. Besides that, the accuracy and diversity of the ensemble are one of the important factors which effect the overall success of the algorithm. There is a trade off between accuracy and diversity, in other words, you sacrifice one while you increase the performance of the other. On the other hand, the optimum number of clustering solutions is one of the parameters that effect the final result. Recently, finding the best subset of the ensemble clustering solutions by eliminating the redundant solutions has become one of the most challenging problems in the literature. The proposed study here aims to find a best model which optimizes the accuracy and diversity trade off by selecting the best subset of cluster ensemble.