English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

An Extreme Learning Machine (ELM)-based novel channel estimation algorithm is proposed for orthogonal frequency division multiplexing (OFDM) communication system with multi-path propagation characteristics. In addition, a low-pass filter is utilized to filter the noise components which are separated from the information component of the channel characteristics. The simulation results show that the proposed novel algorithm significantly outdo the traditional least squares (LS) algorithm, linear minimum mean square error (LMMSE) estimation algorithm sometime even better than the Maximum Likelihood (ML) algorithm. Introduction Broadband frequency-selective channel is divided into several narrowband flat fading channels by employing OFDM, which has a strong ability of anti-interference and anti-pulse from wireless multi-path fading channel in high-speed wireless data transmission. For the next generation wireless communication system, OFDM technology is one of the key technologies of the train control system based on wireless communication WLAN. In the future communication system LTE-R for a railway based on the long-term evolution (LTE), OFDMA (OFDM Access) is the downlink transmission technology [1]. In the OFDM wireless communication, the channel estimation is very critical aspect. The methods of channel estimation include the blind estimation, semi-blind estimation and non-blind estimation method [2-4]. The channel impulse response at the pilot of [5] is utilizing the least squares (LS) algorithm, which does not take the noise impact. The channel estimation algorithm utilizes the SVM algorithm, which has heightened computation complexity [6-7]. In addition, the optimal channel estimation for OFDM system is using MMSE criterion [8].While following the guidelines of the estimation algorithm, the biggest drawback is the heightened computation complexity, so the low rank estimation attracts much attention because it can obtain higher performance in the case of reduced computation complexity. Through the determination of the signal subspace dimension and then obtaining the compromise between the computational complexity and estimated performance, that in the case of the estimation performance unchanged, the computational complexity has effectively reducing by reducing the rank of the matrix. Literature [9] has proposed a rank value and adaptive tracking method. The remainder of this paper is organized as follows. Section 2 gives the OFDM system model. Section 3 describes the novel channel estimation algorithm, whose LS operator is utilizing the ELM forecast strategies to increase the transmission efficiency of the system. Section 4 discusses the channel response transform domain characteristics obtained in section 3, and then through a low-pass filter the noise component is removed. Section 5 the performance between novel channel estimation algorithm in this paper and the classic channel estimation are compared by simulation. Section 6 the conclusion is given. System Model OFDM system model is shown in Figure 1. After the fast Fourier inverse transform (Inverse Fast Fourier Transform, IFFT), each OFDM input symbol is modulated to the mutually orthogonal on International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2015) © 2015. The authors Published by Atlantis Press 933 the N sub-carriers. The modulated signal is expressed as k X , where k denotes the number of OFDM symbols transmitted. Each symbol contains N sub-carriers. In order to overcome the inter-symbol interference (ISI) due to multi-path effects of the channel, the OFDM symbols are required the guard interval in the front and rear inter-symbol, whose length is greater than the maximum channel delay. In order to ensure the orthogonality between sub-carriers, the cyclic prefix (CP) usually adds the guard interval in the OFDM system. D/A I F F T . . . x1

The Novel Channel Estimation Algorithm Relying on ELM