Mühendislik Fakültesi

Permanent URI for this communityhttps://hdl.handle.net/20.500.12416/2

Browse

Now showing 1 - 12 of 12

Alternative Enhancement of Associativity Based Routing (Aeabr) for Mobile Networks
(Springer, 2010) Preveze, Barbaros; Safak, Aysel; 17573; Elektrik-Elektronik Mühendisliği
This study proposes an alternative enhancement for the Enhanced Associativity Based Routing (EABR) method which is a derivation of ABR (Associativity Based Routing) by relative speed and relative distance estimation using the received power strength (RPS) of the nodes. In this study, it is shown that EABR outperforms some other well known protocols. The performance of EABR is improved in terms of number of route reconstructions (RRC) and connected status percentage (CSP). Message overhead and bandwidth utilization is also investigated.
Artificial Neural Networks Modeling of Uniform Temperature Effects of Symmetric Linear Haunched Beams
(2019) İnan, Tolga; 60368; Elektrik-Elektronik Mühendisliği
Ataletsel ve EMG Sensörlerin Kaynaşımını Kullanan Akıllı Eldiven Sistemi Tasarımı
(2019) Akan, Erhan; 251470; Elektrik-Elektronik Mühendisliği
Comparison of Single Channel Indices for U-Net Based Segmentation of Vegetation in Satellite Images
(SPIE, 2020) Ülkü, İrem; Barmpoutis, P.; Stathaki, T.; Akagündüz, Erdem; 233834
Hyper-spectral satellite imagery, consisting of multiple visible or infrared bands, is extremely dense and weighty for deep operations. Regarding problems related to vegetation as, more specifically, tree segmentation, it is difficult to train deep architectures due to lack of large-scale satellite imagery. In this paper, we compare the success of different single channel indices, which are constructed from multiple bands, for the purpose of tree segmentation in a deep convolutional neural network (CNN) architecture. The utilized indices are either hand-crafted such as excess green index (ExG) and normalized difference vegetation index (NDVI) or reconstructed from the visible bands using feature space transformation methods such as principle component analysis (PCA). For comparison, these features are fed to an identical CNN architecture, which is a standard U-Net-based symmetric encoder-decoder design with hierarchical skip connections and the segmentation success for each single index is recorded. Experimental results show that single bands, which are constructed from the vegetation indices and space transformations, can achieve similar segmentation performances as compared to that of the original multi-channel case
Defining Image Memorability Using the Visual Memory Schema
(2020) Akagündüz, Erdem; Bors, Adrian G.; Evans, Karla K.; 233834
Memorability of an image is a characteristic determined by the human observers' ability to remember images they have seen. Yet recent work on image memorability defines it as an intrinsic property that can be obtained independent of the observer. The current study aims to enhance our understanding and prediction of image memorability, improving upon existing approaches by incorporating the properties of cumulative human annotations. We propose a new concept called the Visual Memory Schema (VMS) referring to an organization of image components human observers share when encoding and recognizing images. The concept of VMS is operationalised by asking human observers to define memorable regions of images they were asked to remember during an episodic memory test. We then statistically assess the consistency of VMSs across observers for either correctly or incorrectly recognised images. The associations of the VMSs with eye fixations and saliency are analysed separately as well. Lastly, we adapt various deep learning architectures for the reconstruction and prediction of memorable regions in images and analyse the results when using transfer learning at the outputs of different convolutional network layers.
Genişbant Erişim Telekomünikasyon Sistemlerinin Kullanım Kriterleri
(1) Küçükoğlu, Afşin; Baykal, Yahya; 7812
Hızla artan bilgisayar ağı ihtiyacını gidermek ve yüksek hızı son kullanıcı noktalarına ulaştırabilmek amacıyla geliştirilmiş olan genişbant erişim sistemlerinin (access systems) teknolojik son durumu incelendi. Herhangi bir erişim uygulamasında kullanılması gereken tercih nedenleri karşılaştırıldı. Bu karşılaştırmayı sistematik olarak yapan internet tabanlı bir yazılım geliştirildi. Yazılımda, sistem kullanıcısının ihtiyacı ve mevcut altyapı faktörleri doğrultusunda hangi erişim sisteminin kullanıcı tarafından tercih edilmesi gerektiği kararına optimum olarak varılabilmesi hedeflendi. Çalışmamız, xDSL (x Digital Subscriber Line) ile Fiber Optic erişimlerini kapsayan kablolu ve LMDS (Local Multipoint Distribution Services) ile FSO (Free Space Optics) erişimlerini kapsayan kablosuz sistemleri içermektedir. Yazılım tarafından istenilen sorular ihtiyaç doğrultusunda cevaplandırıldığında, tüm sistemler bir ana karşılaştırma tablosunda toplanmakta, sistem maliyetleri de göz önüne alınarak bir karşılaştırma yapılmakta, sonuçta ise teknik ve ekonomik olarak uygulanabilir çözümler ve optimum çözüm önerilmektedir.
Hand Gesture Classification Using Inertial Based Sensors via a Neural Network
(IEEE, 2017) Akan, Erhan; Tora, Hakan; Uslu, Baran; 251470; Elektrik-Elektronik Mühendisliği
In this study, a mobile phone equipped with four types of sensors namely, accelerometer, gyroscope, magnetometer and orientation, is used for gesture classification. Without feature selection, the raw data from the sensor outputs are processed and fed into a Multi-Layer Perceptron classifier for recognition. The user independent, single user dependent and multiple user dependent cases are all examined. Accuracy values of 91.66% for single user dependent case, 87.48% for multiple user dependent case and 60% for the user independent case are obtained. In addition, performance of each sensor is assessed separately and the highest performance is achieved with the orientation sensor.
IEEE
(2013 Ieee 52Nd Annual Conference On Decision and Control (Cdc), 2013) Schmidt, Klaus Werner; 271229
Reconfigurable manufacturing systems (RMSs) are designed to quickly adapt to new products and production requirements. To this end, RMSs need to be able to perform fast changes between different configurations. This paper investigates the reconfiguration of RMSs in a supervisory control framework. Different from previous work, we formulate and solve a reconfiguration problem that allows to start a newly requested configuration before the previously active configuration has been completed. Our solution is optimal in the sense that there is no other solution that enables an earlier start of the new configuration. The practicability of the proposed solution is demonstrated by a small RMS example.
Işık hüzmesi profili ölçme sistemi
(2011) Çil, Celal Zaim; Baykal, Yahya Kemal; Çil, Celal Zaim; Cambaz, Göknur; Baykal, Yahya Kemal; Erseven, S.; Karabulut, S.; Ertuğ, A. Mithat; 7812; Elektronik ve Haberleşme Mühendisliği; Elektrik-Elektronik Mühendisliği
Online adaptive decision fusion framework based on projections onto convex sets with application to wildfire detection in video
(2011) Günay, Osman; Töreyin, Behçer Uğur; Çetin, Ahmet Enis; 19325
t. In this paper, an online adaptive decision fusion framework is developed for image analysis and computer vision applications. In this framework, it is assumed that the compound algorithm consists of several sub-algorithms, each of which yields its own decision as a real number centered around zero, representing the confidence level of that particular sub-algorithm. Decision values are linearly combined with weights that are updated online according to an active fusion method based on performing orthogonal projections onto convex sets describing sub-algorithms. It is assumed that there is an oracle, who is usually a human operator, providing feedback to the decision fusion method. A video-based wildfire detection system is developed to evaluate the performance of the algorithm in handling the problems where data arrives sequentially. In this case, the oracle is the security guard of the forest lookout tower verifying the decision of the combined algorithm. Simulation results are presented.
Using wavelet transform self-similarity for effective multiple description video coding
(IEEE, 2016) Choupani, Roya; Wong, Stephan; Tolun, Mehmet
Video streaming over unreliable networks requires preventive measures to avoid quality deterioration in the presence of packet losses. However, these measures result in redundancy in the transmitted data which is utilized to estimate the missing packets lost in the delivered portions. In this paper, we have used the self-similarity property if the discrete wavelet transform (DWT) to minimize the redundancy and improve the fidelity of the delivered video streams in presence of data loss. Our proposed method decomposes the video into multiple descriptions after applying the DWT. The descriptions are organized in such a way that when one of them is lost during transmission, it is estimated using the delivered portions by means of self-similarity between the DWT coefficients. In our experiments, we compare video reconstruction in the presence of data loss in one or two descriptions. Based on the experimental results, we have ascertained that our estimation method for missing coefficients by means of self-similarity is able to improve the video quality by 2.14dB and 7.26dB in case of one description and two descriptions, respectively. Moreover, our proposed method outperforms the state-of-the-art Forward Error Correction (FEC) method in case of higher bit-rates.
Yeni Rotalama Algoritmalarının 802.16j AĞI Etkin Çıktı Oranı Artırımına Düşük Araç Hızları Altındaki Etkileri
(2011) Preveze, Barbaros; 17573; Elektrik-Elektronik Mühendisliği
Çoklu ortam verileri içeren kablosuz gezgin ağlarda, yeni bilişsel yöntemler ve rotalama algoritmaları kullanılarak, sistemdeki rota ömrü, bağlantı kesinti miktarı, ortalama sekme sayısı ve paket kaybı gibi performans parametrelerinin iyileştirilmesiyle, IEEE 802.16j ağ yapısının etkin çıktı oranının arttırılması sağlanmıştır. Bu amaçla, mevcut IEEE 802.16j ağında kullanılmakta olan OFDMA ve TDMA erişim tekniklerine ek olarak kullanılmak üzere önerilen, En Çok Sıkışan İlk Erişir (MCAF), Spektrumsal Yardımlaşma (SA) ve Arabellek Yönetimi (BM) metotları ile 802.16j ağında etkin çıktı oranı artırımı için elde edilen simülasyon sonuçları, elde edilen teorik sonuçlarla ve literatürde elde edilmiş olan diğer çalışmaların sonuçlarıyla kıyaslanarak doğrulanmıştır. Bu çalışmada ayrıca, önerilen AEABR (Erişebilirlik Tabanlı Rotalama Alternatif Geliştirimi) ve ATAABR (Erişilebilirlik Tik Ortalamalı Erişebilirlik Tabanlı Rotalama) isimli yeni uzun ömürlü rotalama algoritmalarının, geliştirilen etkin çıktı oranı yükseltimi metotlarıyla birlikte uygulanmasıyla, diğer rotalama algoritmalarına göre, daha da yüksek etkin çıktı oranları elde ettikleri gösterilmiştir. Önerilen yeni metotlar, dağınık ağ yapılarının, gezgin düğümler tarafından, anlık plansız sinyalleşme ile yönetimine dayanarak çalışmaktadır.

Browse

Browsing Mühendislik Fakültesi by Department "Çankaya Üniversitesi, Mühendislik Fakültesi, Elektrik Elektronik Mühendisliği Bölümü"