Ender Ayanoglu

Ender Ayanoglu

Auto-generated profile, based on publicly available information

Ender Ayanoglu

Department of Electrical Engineering and Computer Science, University of California at Irvine, Irvine, CA, USA

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2022 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
EAEnder Ayanoglu
Ender Ayanoglu
KDKemal Davaslioglu
Kemal Davaslioglu
YSYalin E. Sagduyu
Yalin E. Sagduyu
Generative Adversarial Networks (GANs) are Machine Learning (ML) algorithms that have the ability to address competitive resource allocation problems together with detection and mitigation of anomalous behavior. In this paper, we investigate their use in next-generation (NextG) communications within the context of cognitive networks to address i) spectrum sharing, ii) detecting anomalies, and iii) mitigating security attacks. GANs have the following advantages. First, they can learn and synthesize field data, which can be costly, time consuming, and nonrepeatable. Second, they enable pre-training classifiers by using semi-supervised data. Third, they facilitate increased resolution. Fourth, they enable the recovery of corrupted bits in the spectrum. The paper provides the basics of GANs, a comparative discussion on different kinds of GANs, performance measures for GANs in computer vision and image processing as well as wireless applications, a number of datasets for wireless applications, performance measures for general classifiers, a survey of the literature on GANs for i)-iii) above, and future research directions. As a use case of GAN for nextG communications, we show that a GAN can be effectively applied for anomaly detection in signal classification (e.g., user authentication) outperforming another state-of-the-art ML technique such as an autoencoder.

26 October 2022 in IEEE Wireless Communications Letters
Verified
Journal Article
Closed access
KDKemal Davaslioglu
Kemal Davaslioglu
SBSerdar Boztas
Serdar Boztas
MEMehmet Can Ertem
Mehmet Can Ertem
YSYalin E. Sagduyu
Yalin E. Sagduyu
EAEnder Ayanoglu
Ender Ayanoglu
Deep learning (DL) finds rich applications in the wireless domain to improve spectrum awareness. Typically, DL models are either randomly initialized following a statistical distribution or pretrained on tasks from other domains in the form of transfer learning without accounting for the unique characteristics of wireless signals. Self-supervised learning (SSL) enables the learning of useful representations from Radio Frequency (RF) signals themselves even when only limited training data samples with labels are available. We present a self-supervised RF signal representation learning method and apply it to the automatic modulation recognition (AMR) task by specifically formulating a set of transformations to capture the wireless signal characteristics. We show that the sample efficiency (the number of labeled samples needed to achieve a certain performance) of AMR can be significantly increased (almost an order of magnitude) by learning signal representations with SSL. This translates to substantial time and cost savings. Furthermore, SSL increases the model accuracy compared to the state-of-the-art DL methods and maintains high accuracy when limited training data is available.

12 August 2019 in IEEE Transactions on Green Communications and Networking
Verified
Journal Article
Open access
SZShunqing Zhang
Shunqing Zhang
SXShugong Xu
Shugong Xu
GLGeoffrey Ye Li
Geoffrey Ye Li
EAEnder Ayanoglu
Ender Ayanoglu
Green radios jointly consider the spectrum efficiency and the energy efficiency in wireless networks in order to provide sustainable development. In the past two decades, various green radio solutions for different types of terminals and radio access networks have been developed, some of which have been used in the designs of wireless products. In this paper, we provide a historical view on some fundamental works and practical issues. In addition to providing a comprehensive overview on theoretical achievements, we also discuss several important power saving solutions with notable engineering impacts, such as Doherty power amplifier and separated baseband unit -remote radio unit architecture, which might be overlooked in previous publications. Moreover, with the huge growth of wireless traffic in the near future, green radio design for future wireless networks shall involve an end-to-end energy efficiency investigation of mobile terminals, radio access and core networks, and different applications. By introducing green radio schemes for advanced terminals and future wireless networks, this article will not only be beneficial for readers with only preliminary background in communications and signal processing but also have reference and historical values for researchers and practical engineers in the area.

23 June 2009 in IEEE Transactions on Communications
Verified
Journal Article
Closed access
IIInanc Inan
Inanc Inan
FKFeyza Keceli
Feyza Keceli
EAEnder Ayanoglu
Ender Ayanoglu
We propose an analytical model for the performance analysis of the enhanced distributed channel access (EDCA) function of the IEEE 802.11e standard. The proposed discrete-time Markov chain (DTMC) model incorporates the main quality-of-service (QoS) features of 802.11e, namely, contention window (CW), arbitration interframe space (AIFS), and transmit opportunity (TXOP) differentiation. Due to its specific design, the proposed DTMC model jointly considers the state of the medium access control (MAC) layer buffer and the MAC differentiation mechanisms which facilitates a novel performance analysis framework at an arbitrary traffic load. Analytical and simulation results are compared to demonstrate the accuracy of the proposed approach for varying traffic load, EDCA parameters, and MAC layer buffer space.

1 January 2006
Verified
Conference Paper
Closed access
IIInanc Inan
Inanc Inan
FKFeyza Keceli
Feyza Keceli
EAEnder Ayanoglu
Ender Ayanoglu
The IEEE 802.11e standard defines the Hybrid Coordination Function (HCF) which specifies the QoS algorithms in the MAC layer of the next generation 802.11 wireless LAN (WLAN). The HCF is composed of two access functions: A distributed contention-based channel access function (EDCA) providing prioritized QoS and a centralized polling-based channel access function (HCCA) providing parameterized QoS. In this paper, we address the efficient medium access control (MAC) of the mostly variable bit rate (VBR) and bursty multimedia traffic in HCCA and propose a novel application-aware adaptive 802.11e QoS scheduler. The proposed scheduler coordinates the resource allocation of the associated flows using adaptive service intervals, transmit opportunities, and polling order. The service schedule is based not only on the traffic classification done according to the packet size, interval distribution, and the direction but also on the instantaneous buffered traffic conditions. The proposed scheduler is shown to have significant performance gains in terms of multimedia traffic channel utilization, packet loss ratio, delay, and jitter when compared with the other schemes.

23 August 2017 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Open access
CCCemil Can Coskun
Cemil Can Coskun
EAEnder Ayanoglu
Ender Ayanoglu
In this paper, the tradeoff between energy efficiency and spectral efficiency in multicell heterogeneous networks is investigated. Our objective is to maximize both energy efficiency and spectral efficiency of the network, while satisfying the minimum rate requirements of the users. We define our objective function as the weighted summation of energy efficiency and spectral efficiency functions. The fractional frequency reuse (FFR) scheme is employed to suppress intercell interference. We formulate the problem as cell-center boundary selection for FFR, frequency assignment to users, and power allocation. The optimal solution of this problem requires exhaustive search over all cell-center radii, frequency assignments, and power levels. We propose a three-stage algorithm and apply it consecutively until convergence. First, we select the cell-center radius for the FFR method. Second, we assign the frequency resources to users to satisfy their rate requirements and also maximize the objective function. Third, we solve the power allocation subproblem by using the Levenberg-Marquardt method. Minimum rate requirements of users are also included in the solution by using dual decomposition techniques. Our numerical results show a Pareto-optimal solution for energy efficiency and spectral efficiency. We present energy efficiency, spectral efficiency, outage probability, and average transmit power results for different minimum rate constraints. Among other results, we show that, in a particular setting, 13% energy efficiency increase can be obtained in a multicell heterogeneous wireless network by sacrificing 7% spectral efficiency.