Search

Your search keyword '"Tepe, Kemal"' showing total 2 results
Start Over Author "Tepe, Kemal" Topic algorithms
2 results on '"Tepe, Kemal"'

1. QAM equalization and symbol detection in OFDM systems using extreme learning machine.

Author

Muhammad, Ishaq, Tepe, Kemal, and Abdel-Raheem, Esam

Subjects
*ORTHOGONAL frequency division multiplexing, *AMPLITUDE modulation, *MACHINE learning, *OBJECT recognition (Computer vision), *ALGORITHMS, *BOTTLENECKS (Manufacturing), *SIMULATION methods & models, *LEAST squares
Abstract

This paper presents a new learning-based framework to jointly solve equalization and symbol detection problems in orthogonal frequency division multiplexing systems with quadrature amplitude modulation. The framework utilizes extreme learning machine (ELM), a recent addition to the class of supervised learning algorithms, to achieve fast training, high performance, and low error rates. The proposed ELM scheme employs infinitely differentiable nonlinear activation functions in least-square solution to learn the channel response, which is the equalization part. In addition to equalization, ELM performs symbol detection. Existing learning-based schemes require an additional symbol slicer for the symbol detection. The proposed framework does not experience training bottleneck imposed by gradient descent-based approaches. Simulation results show that the proposed framework outperforms other learning-based equalizers in terms of symbol error rate and training speeds. [ABSTRACT FROM AUTHOR]

Published
2013
Full Text
View/download PDF

2. Blind adaptive low-complexity time-domain equalizer algorithm for ADSL systems by adjacent lag autocorrelation minimization (ALAM).

Author

Gul Muhammad, Ishaq, Abdel-Raheem, Esam, and Tepe, Kemal E.

Subjects
*EQUALIZERS (Electronics), *TIME-domain analysis, *COMPUTATIONAL complexity, *AUTOCORRELATION (Statistics), *ALGORITHMS, *ASYMMETRIC digital subscriber lines, *PERFORMANCE evaluation
Abstract

Abstract: This paper presents new algorithms that exploit uncorrelation between adjacent data samples produced by IFFT in ADSL systems. These algorithms update time-domain equalizer (TEQ) coefficients by adjacent lag autocorrelation minimization (ALAM) to shorten the channel. ALAM is an addition to the family of several existing autocorrelation-based algorithms that can achieve similar or better performance at lower complexity compared to other algorithms. The complexity reduction is achieved by designing a cost function without the sum-square, and further utilizing symmetrical TEQ property to reduce the complexity of the adaptation of TEQ to half of other existing algorithms. Furthermore, to avoid the limitations of lower bitrate after reaching the maximum bitrate and high complexity, an adaptive TEQ using equal-taps constraint (ETC) is introduced to maximize the bitrate along with achieving the lowest complexity. In addition, a simplified approach is used to calculate the expectation to reduce the computational complexity for ALAM and the other existing autocorrelation-based algorithms. Simulation results demonstrate that the proposed algorithms and modified existing algorithms achieve similar or better performance figures with reduced complexities. [Copyright &y& Elsevier]

Published
2013
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results