KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 5 of 5

Some of the metrics are blocked by your
consent settings
Optimized CNN-based channel estimation for zero-padded uplink OFDMA in 5G new radio over fast-fading channels
(2026-07-01)
Mata, Tanairat
;
Boonsrimuang, Pisit
This paper addresses a pilot-assisted channel estimation applicable to the uplink orthogonal frequency-division multiple-access with zero-padding in a 5G new radio. The adjacent uplink subchannels in the frequency domain are allocated separately for each user, and each subchannel assigns the pilot signal independently. This paper proposes a convolutional neural network-based channel estimation, including one-dimensional and two-dimensional architectures, designed to optimize the handling of rapid fading channel variations encountered in high-mobility scenarios. The estimation process leverages the subchannels of each user to enhance accuracy. Simulation results demonstrate the effectiveness of the proposed method in offering a better bit-error rate and a higher transmission data rate than the conventional channel estimation methods under challenging conditions. Finally, this paper discusses the considerable computational complexity of aspects of the lightweight two convolutional neural network architectures.
Some of the metrics are blocked by your
consent settings
Robust Channel Estimation for MIMO-OFDM-IM Full-Duplex Relaying under Residual Self-Interference in Time-Varying Fading
(2026-01-01)
Mata, Tanairat
;
Boonsrimuang, Pisit
Full-duplex relaying can significantly improve spectral efficiency in vehicular communications, but its practical performance is constrained by residual self-interference (SI) and rapidly time-varying channels. This work proposes a Walsh–Hadamard and null (WHN) pilot with maximum likelihood (ML)–based channel estimation (CE) for MIMO OFDM-IM full-duplex relays. Unlike prior designs that prioritize either low complexity or estimation accuracy, the proposed WHN scheme improves the performance–complexity trade-off by leveraging asymmetric pilot intervals and structured orthogo nalization. Two widely recognized baselines are considered for comparison: (i) cyclic-shifted Zadoff–Chu (CS-ZC) preamble pilots representing the low-complexity DFT-domain benchmark, and (ii) scattered pilot-and-null (PN) patterns with ML refinement representing the high-accuracy benchmark used in LTE/5G systems. Results reveal a consistent carrier-to-noise power ratio (CNR)-dependent crossover: WHN outperforms CS-ZC when CNR≥28dBandsurpassesPNundermoderate-to-high mobility. At 35 dB CNR, WHN provides up to 35% BER reduction with only 29% complexity overhead. A standard-compliant link budget analysis further indicates non-trivial coverage gains under the evaluated Doppler regimes and considered residual SI model. All simulation assumptions, Doppler profiles, and SI models follow V2X guidelines, and results are validated across multiple random seeds. Overall, WHN offers a complexity-aware CE solution for full-duplex V2X systems.
Some of the metrics are blocked by your
consent settings
Deep Learning-Based Channel Estimation With 1D CNN for OFDM Systems Under High-Speed Railway Environments
(2025-01-01)
Siriwanitpong, Aphitchaya
;
Sanada, Kosuke
;
Hatano, Hiroyuki
;
Mori, Kazuo
;
Boonsrimuang, Pisit
In OFDM wireless communications, channel estimation performance is compromised in high-speed railway environments owing to extremely fast multipath fading and severe Doppler effect. Recently, a deep learning approach has been employed to improve the channel estimation performance, however it encounters significant challenges due to its high computational complexity. In order to deal with these challenges, this paper proposes channel estimation employing deep learning with one-dimensional convolutional neural network (1D CNN) schemes to enhance conventional least squares (LS) estimation. The first scheme provides better performance compared to conventional LS estimation. However, it is only suitable for OFDM systems with full pilot symbols, leading to decreased transmission efficiency and high complexity. In order to address those problems, the second scheme develops 1D CNN-based channel estimation employing scattered pilot symbols to enhance transmission efficiency and reduce computational complexity. In comparison to conventional LS estimation and deep learning-based channel estimation with bi-gated recurrent unit (bi-GRU), the performance evaluation demonstrates that the proposed 1D CNN-based schemes simultaneously improve channel estimation performance, transmission efficiency, and reduce computational complexity.
Some of the metrics are blocked by your
consent settings
Pilot-Assisted Channel Estimation for SFBC MIMO-OFDM with Index Modulation in Higher Time-Varying Fading Channel
(2024-01-01)
Mata, Tanairat
;
Boonsrimuang, Pisit
Orthogonal frequency division multiplexing (OFDM) with Index modulation can provide higher spectral and energy efficiencies. For multiple-input, multiple-output OFDM with space-frequency block coding (SFBC MIMO-OFDM), the transmitter can send the information signal with high transmit diversity gain to the receiver, improving system performance. In this paper, we propose a pilot-assisted channel estimation by using SFBC MIMO-OFDM with index modulation. The proposed system can perform a better bit-error-rate (BER) performance and higher transmission data rate than the conventional system in a higher time-varying fading channel.
Some of the metrics are blocked by your
consent settings
An Effective Channel Estimation for Massive MIMO–OFDM System
(2020-09-01)
Mata, Tanairat
;
Boonsrimuang, Pisit
The massive Multiple-Input and Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO–OFDM) system provides a high data transmission for the next generation mobile communication i.e. 4G, 5G, etc. In the practical MIMO–OFDM system, N points of IFFT/FFT is larger than M data subcarriers (N> M) in each OFDM symbol to reject the aliasing after D/A converter. To demodulate information data, the channel responses for all MIMO channel links need to be estimated so as to employ in MIMO data detection for demodulation at the receiver. The discrete Fourier transform estimator (DFE) was proposed for the system which can estimate the MIMO channels accurately when N= M. However, its accuracy will be hugely degraded when N> M because of the oversampling of data transmission. To improve the estimation accuracy when N> M, the maximum likelihood estimator (MLE) was proposed for the system which can achieve higher estimation accuracy than that of the DFE. However, its accuracy will be degraded a lot in the massive MIMO–OFDM system when N> M, due to the estimation error increased in proportion to the increasing of N<inf>T</inf> transmit antennas. To solve these problems, this paper proposes a direct time-domain estimator (DTE) with preamble symbol with scattered-pilot (preamble-SCP) for the massive MIMO–OFDM system when N> M. In the proposed method, it is presented with three salient features; achieving higher estimation accuracy with keeping almost the same computational complexity as the conventional estimators, improving Bit- Error- Rate (BER) with low-complexity MIMO data detection, and providing higher transmission data rate compared with the MLE. Using the normalizedMSE, BER and throughput evaluated by computer simulations, it can be verified that the proposed DTE with preamble-SCP obviously provides higher estimation accuracy, better BER with low-complexity MIMO data detection, and much higher transmission data rate which is approximately 32.5 Mbps gain over the MLE at 5 MHz-BW respectively.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results