In semantic communication systems, deep learning-based joint source-channel coding (DeepJSCC) has demonstrated superior performance, particularly in low signal-to-noise ratio (SNR) scenarios and under limited bandwidth conditions, compared to traditional communication technologies. However, most existing studies rely on communication models based on autoencoders (AE), where the distribution of transmission symbols is treated as a complete black box, causing inefficient use of limited transmission symbols. Moreover, many existing methods for image transmission focus on optimizing pixel-wise metrics, without considering the semantic information of the images. This pixel-level optimization often compromises the semantic fidelity and perceptual quality of the reconstructed images. To address these problems, we propose a novel semantic communication system that combines a variational autoencoder (VAE) and a generative adversarial network (GAN). Specifically, a VAE is used to arbitrarily control the distribution of transmission symbols according to channel conditions, while a GAN is used to maximize the similarity of semantic information. Simulation results demonstrate that the proposed method improves the perceptual quality of the reconstructed images compared to conventional approaches.

Doppler shifts are a common occurrence in high mobility environments as a result of the relative motion of the transmitter and receiver. Inter-carrier interference (ICI) is a result of this, which affects communication quality and emphasizes the need for adaptive communication systems beyond 5G and 6G. The most extreme of estimation method, which inserts pilot signals at the leading and last portion of the communication packets, enables highly precise estimation. However, this method has serious latency problem because of the pilot signals inserted at the last portion of the communication packet. In this paper, we proposes a novel estimation method for the maximum Doppler shift identification using decision feedback channel estimation (DFCE). Our proposed method can identify the channel and compensate the faded signal. In this case, we can use the defeated signal as a reference signal. Therefore, our proposed method can estimate the Doppler shift without any additional pilot signal at the last portion of the communication packet.

This paper proposes a novel hybrid beamforming (HBF) structure that groups transmit antennas and users in multiuser multiple-input single-output (MUMISO) systems. In the conventional HBF structure, all transmit antennas are utilized to make radio waves directional in the direction of each user. In this case, radio frequency (RF) signals after digital-to-analog conversion are joined with the antenna with the smallest channel gain due to the variation in channel gain of each antenna based on the base station (BS) location and users, and the transmit antenna used is not optimized. Small channel gain antennas transmit signals that can be affected by interference and noise, degrading communication performance. Therefore, we propose a HBF structure that optimizes the transmit antennas used to make radio waves directional in the direction of each user by grouping users and antennas with a focus on the channel gain of each transmit antenna obtained from channel estimation. Phase shifters can be reduced in the analog precoder by the proposed method in comparison with the conventional method while still keeping performance of sum rate, as shown through simulations.

Lately, the advanced television systems committee (ATSC) 3.0 standard has been established, enabling the rollout of 4 K ultra-high-definition and simultaneous multichannel high-definition broadcasting services. A unique transmitter identification (TxID) sequence is assigned with long spread coding to mitigate interference of the broadcasting signal. In this scenario, the maximum achievable data transmission rate is limited. Currently, to increase the transmission rate of the data signal as a TxID, various researches are being carried out. This paper introduces a new method to reduce interference in data communications using the cross-polarization discrimination (XPD) property. The proposed system can reduce the inference from both of the broadcasting signal and TxID signal using polarization property. Therefore, the proposed system can enhance the data transmission rates without causing the interference to the broadcasting signal.

Internet of Vehicles (IoV) is an emerging technology that has been rapidly developing in recent years, which combines the internet, wireless communication technology, and vehicle electronics to realize the intelligence of interaction between vehicles and greatly improve the efficiency and safety of the transportation system. However, high-frequency and cyclical communications between vehicles and the limited system capacity in the region have led to serious conflicts in the allocation of wireless resources for vehicle networking. To solve this problem, this paper models resource allocation as a multi-agent deep reinforcement learning problem and proposes a Multi-Agent Actor-Critic (MAAC) algorithm based on distributed execution. The multi-agent algorithm can achieve distributed computing by modeling the training mechanism and reward function, thus improving resource utilization. Experimental results show that the proposed algorithm improves the total Vehicle-to-Infrastructure (V2I) link capacity and Vehicle-to-Vehicle (V2V) link transmission success rate.

This paper introduces a novel robust signal-to-noise ratio (SNR) estimation against Doppler shift using a convolutional neural network (CNN)-based multimodal network. SNR estimation is valuable for Beyond 5G (B5G) and 6G since it helps to evaluate the channel state information (CSI) reliability that is fed back from users and schedule radio resources. The proposed scheme increases feature diversity by converting the same received signal into multiple modalities, enabling accurate and robust SNR estimation against Doppler shifts. Simulation results show that the proposed scheme provides the most accurate estimation compared to conventional schemes in the presence of Doppler shifts.

In order to meet the ever-growing demand for data traffic, highly efficient multiple access schemes, such as OFDMA, are widely used in modern communication standards. In such multiple access schemes, adaptive modulation and coding (AMC) are used to optimize the transmission rate of each user. However, feedback information, such as SNR and Doppler shift, characterizing the communication environment of each user is indispensable of key importance for AMC. In the past, these information and parameters were often estimated using reference signals. However, the reference signal becomes overhead, resulting in throughput degradation and processing delay. Furthermore, the computation burden can be large as it is necessary to perform channel parameter estimation individually for each user. Previously, over the single-user channel, we have proposed a joint SNR and Doppler shift detection method via a spectrogram-based data-driven method, without the reference signal. This paper extends this framework to multiuser OFDM multiple access channels. In the newly proposed method, SNR and Doppler shift for all users can be detected simultaneously via deep learning-guided object detection algorithms from each spectrogram image. Simulation results are provided to validate the effectiveness of the proposed method.

Recently, vehicle to everything (V2X) communications is paid attention in order to realize a smart transportation such as safety driving and automated cruise. It necessitates an ultra-reliable and low-latency communications (URLLC) even at fast fading environment involved by moving vehicles. Generally, forward error correction (FEC) code such as polar code requires long block code length to raise error correction capability while it deteriorates the channel tracking accuracy in pilot-aided estimation. In our previous work, to meet these trade-off demands, we proposed a frame splitting method. It splits information data in half and estimate channel state information (CSI) of the former part. That of latter is simply extrapolated using the former CSI. In this paper, we expand the previous work into multiple-input and multiple-output (MIMO) eigenbeam-space division multiplexing (E-SDM) system, which can improve communication accuracy significantly. To keep the benefit of E-SDM for fast fading, we propose two data assignment methods based on the eigenbeams. The computer simulation results clarified that these two methods could improve the BER performance in the V2X communication.

With the increase in demand for wireless data traffic, high-speed communication systems are required in many environment. Adaptive modulation and coding is an important technique to realize this, but it requires feedback of communication environment information represented by SNR. Conventional SNR estimation methods have a problem of degrading estimation accuracy in fast-moving environments and the presence of carrier frequency offset (CFO). Convolutional neural network (CNN) is capable of estimating the SNR from the trained received signal dataset accurately. This paper investigates an input signal representation to further improve the SNR classification accuracy by CNN. We then propose to combine respective spectrogram data of IQ domains. It can extract the features related to SNR from the received signal to the maximum extent possible and thus achieve highly accurate SNR estimation. Simulation results show that the proposed approach outperforms the other existing candidates.

This paper proposes a novel convolutional neural network (CNN) based joint classification method to characterize the signal-to-noise power ratio (SNR) and Doppler shift using spectrogram images, in order to enable efficient adaptive modulation and coding (AMC) designs. It is necessary to maintain high communication performances even in stringent environments where transceivers move at high speed due to the diversification of wireless applications. To optimize the transmission rate in such dynamic environments, AMC scheme is known to be effective. AMC is generally designed based on feedback information (FBI) such as the SNR and Doppler shift acquired on the receiving side. Here, the challenge is an increase in calculation burden, processing delay and estimation accuracy of the FBI. We focused on the spectrogram which is composed of power values in the time and frequency domains. Its two-dimensional fluctuation represents the Doppler shift as well as noise values. In the proposed method, such key information for AMC can be simultaneously extracted from a single spectrogram via a trained CNN. Therefore it is expected to contribute to reducing the computational burden and speeding up the signal processing. Simulation results are presented to demonstrate that the proposed method achieves better performance than traditional methods.

This paper proposes a highly accurate signal to noise ratio (SNR) estimation method for adaptive modulation and coding (AMC) by learning power spectral density (PSD) images with a convolutional neural network (CNN). Accurate SNR estimation is indispensable for adaptive control schemes such as AMC. Proposed method trains the CNN using PSD images and the corresponding SNR value as a teacher signal, and outputs the SNR in response to an input of unknown PSD image. Once trained, the SNR can be estimated with high speed and high accuracy, so AMC performance can be improved. Furthermore, since PSD is hardly affected by the Doppler shift, proposed method is resistant to high-speed environment. Compared with the previously proposed method which estimates SNR from a PSD data using a neural network, the proposed method can improve the estimation accuracy, bit error rate (BER) and throughput performance when AMC is applied.

This paper proposes the blind interference power estimation via deep learning approach exploiting the visualized wireless signal information. Blind adaptive array (BAA) signal processing is the powerful solution to suppress various kinds of interference such as inter-cell interference (ICI) and intersystem interference (ISysI) for which receivers cannot obtain a priori information represented as channel state information (CSI). However, BAAs cannot always suppress interference due to its blind nature. Depending on signal-to-interference power ration (SIR), adequate BAA algorithms should be switched. In order to estimate SIR in a blind manner, we propose to apply a convolutional neural network (CNN) trained by IQ constellation images where contains the desired and interference signals. This paper presents its methodology and fundamental possibility.

This paper expands the analytic formulation of single-cell multi-user massive multiple-input-multiple-output (MIMO) systems with matched-filter (MF) precoding into multiantenna user environments. Massive MIMO technologies are now remarkably evolving such as pre/post coding including beamforming strategies. Not only a base station (BS) having hundreds of antenna elements, but also user terminals (UTs) are also capable of array signal processing. It is enabled by implementation of array antennas in practical scale due to widespread millimeter wave band. Evaluating performance on massive MIMO systems where both BS and UTs have array antennas could impose impractical computation complexity. As an introduction of this challenge, this paper newly derives mathematical formulation of outage probability performance on MF precoded massive MIMO systems with multi-antenna user circumstance. Its consistency is confirmed by comparing the derived analytical model to the simulation results.

Massive Multiple-Input-Multiple-Output (MIMO) systems, where the base station (BS) is equipped with hundred antennas, is expected to be one of the key technologies for the next generation wireless systems. Pilot contamination is one of performance degradation factor for massive MIMO. This paper presents an approach which aims to eliminate this pilot contamination impact. High Time Resolution Carrier Interferometry (HTRCI) was previously proposed which can perform channel estimation with the reduced number of pilot signals. It utilizes a comb-type pilot allocation and realizes highly accurate channel state information (CSI) estimation and interpolation by time-domain signal processing. Unused pilot subcarriers are available to obtain the more number of CSI. This paper expands the concept of HTRCI to estimate more channels and these CSIs can be separated by time-domain signal processing in the same manner. It is applied to the pilot de-contamination on downlink multi-cell MIMO transmission. Computer simulation results confirms that the BER performance can be improved as compared with the conventional method.

Orthogonal Freaquency Division Multiplexing (OFDM) is one of the transmission techniques that is widely used for high speed data transmission. The orthogonality allows signal spectrum to be separated without any interference or power loss due to leakage to other subcarriers. However, time varying channel with high Doppler shift could destroy the orthogonality, resulting in severe Inter Carrier Interference (ICI) and degrading BER performance. Accurate channel estimation is required to compensate for ICI effects. Decision Directed Channel Estimation (DDCE) is known as the effective time varying channel estimation method using demodulated data. In this paper, we propose a novel DDCE method by frame splitting and channel extrapolation. Under the fast fading environment, the estimated channel state information (CSI) is different from real channel state especially in the latter part of the data packet. In order to mitigate this impact, we halved the information data and performed channel estimation only in the former half part where the influence of fading is small. In the latter half part, we attempted to predict the channel state using quadratic extrapolation. Computer simulation results indicate that the proposed scheme can improve the BER performance even under the fast fading environment.

This paper proposes a novel weight derivation method to improve adaptive array interference suppression performance based on our previously conceived Sample Matrix Inversion algorithm using Common Correlation Matrix (CCM-SMI), by data-aided approach. In recent wireless communication system which possesses lots of subcarriers, the computation complexity is serious problem when using SMI algorithm. To mitigate this problem, CCM based SMI algorithm has been proposed. It computes the correlation matrix by the received time domain signals before fast Fourier transform (FFT). However, due to the limited number of pilot symbols, the estimated channel state information (CSI) is often incorrect. Therefore, it leads limited interference suppression performance. In this paper, we newly employ a data-aided channel state estimation. Decision results of received symbols are obtained by CCM-SMI and then fed-back to the channel estimator. It assists improving CSI estimation accuracy. Computer simulation result reveals that our method accomplishes better Bit Error Rate (BER) performance in spite of the minimum pilot symbols with only a little additional computation complexity.

This paper proposes a novel code length optimization for improving the throughput performance on Orthogonal Frequency Division Multiple - Interleave Division Multiple Access (OFDM-IDMA) based Visible Light Communication (VLC). VLC is under the global spotlight, since Light Emitting Diode (LED) has recently become a part of building infrastructure and VLC functionality is fairly easy by adding communication components to LED lighting. To enhance the VLC capability, OFDM-IDMA has been proposed as a connection method in a multiuser environment. By applying an interleave pattern peculiar to the transmission signal of each user, signals are well separated and multiple access becomes possible in VLC-OFDM-IDMA. However, VLC-OFDM-IDMA necessitates a low coding rate error correction code as well as a long length spreading code which limits the throughput performance. To resolve this problem, we newly introduce a channel ranking and allocates the short length spreading code to a user in good channel state. Overall throughput performance can be improved while the compatible BER performance.

This paper proposes an improved puncturing scheme exploiting the feature of systematic polar codes. Puncturing is the process of removing part of the encoded bits and can realize various coding rates to adopt to the channel condition. However, the puncturing deteriorates BER performance because the removed bits are generally unknown at the receiving side. Polar codes support systematic encoding which generate the codeword that has the same value of information bits. Using this characteristic, the transmitting side punctures known bits shared between transmitter and receiver in the codeword. The receiving side then decodes the received signal by setting punctured bits to the known value to assist the decoding capability. Computer simulation verifies the effectiveness of the proposed puncturing scheme.

This paper expands our previously proposed semi-blind uplink interference suppression scheme on multicell multiuser massive MIMO systems to support multi modulus signals. The original proposal applies channel state information (CSI) aided blind adaptive array (BAA) interference suppression after the beamspace preprocessing and decision feedback channel estimation (DFCE). It employed the constant modulus algorithm (CMA) as the BAA scheme which can fully exploit the degree of freedom (DoF) of massive antenna arrays to suppress both inter-user interference (IUI) and inter- cell interference (ICI). Its effectiveness has been verified under the extensive pilot contamination constraint. Unfortunately, CMA basically works well only for the constant envelope signal such as QPSK and thus the proposed scheme should be expanded to cover QAM signals for more general use. This paper newly proposes to apply multi modulus algorithm (MMA) and data-aided sample matrix inversion based minimum mean square error (MMSE-SMI) weight derivation. It can successfully realize interference suppression under the use of multi-level envelope signals such as 16QAM with satisfactorily outage probability performance.

Vehicle-installed access points (VAPs) based mobile network emerges as a flexible and efficient wireless access means for 5G and beyond. This paper reports analytical results on vehicle-to-pedestrian (V2P) connectivity on higher frequency band. Introducing 5G new radio (NR) numerology can expand applicability of orthogonal frequency division multiplexing (OFDM) on such intensive mobility environment where VAPs move past. Additional proposal is a coordinated multipoint (CoMP) based coverage expansion via multiple VAPs. Simulative evaluation also presents its effectiveness based on street canyon scenario.

This paper proposes a novel semi-blind uplink interference suppression scheme for multicell multiuser massive multiple-input multiple-output (MIMO) systems. The inter-cell interference (ICI) becomes intenser when a number of users are spatially multiplexed via massive MIMO. Here arises a pilot contamination problem due to the limitation of orthogonal sequence set and thus inter-user interference (IUI) also remains unsuppressed. Our proposal employs a constant modulus algorithm (CMA) known as a blind interference suppression scheme and exploits channel state information (CSI)-aided minimum mean square error (MMSE) postcoding weight as an initial weight of CMA. Although MMSE weight cannot suppress ICI and IUI due to the pilot contamination, it can help subsequent CMA to capture the desired signals which is required for CMA to effectively work. Since CMA can fully exploit degree of freedom of massive arrays by using uncorrelated data signal part, derived weight successfully suppresses ICI/IUI while resolving the pilot contamination problem. A decision feedback channel estimation (DFCE) is then introduced to further improve CSI estimation accuracy and subsequent interference suppression performance. A series of signal processing, MMSE-CMA-DFCE, can be iteratively performed. The computer simulation reveals that our proposal can improve outage probability and it satisfies below the fifth percentile of cumulative distribution with saved symbol amount.

In recent, to achieve several services with the information product, high speed and high quality systems of wireless communications are demanded. To achieve this demand, orthogonal frequency division multiple access (OFDMA) has been proposed. In a wireless network, the transmitted signal of each user has independent channel fluctuation characteristics. By using this characteristic, the multiuser diversity (MUDiv) effect can be obtained, and MUDiv/OFDMA has been proposed. Before now, we have proposed a low complexity MUDiv/OFDMA. However, it degrades the system performance compared with the conventional MUDiv/OFDMA in the channel as a Pyramid model. To solve this problem, in this paper, we propose the method to mitigate the deep faded channel for a low complexity MUDiv/OFDMA with the relay node allocation.

STBC is a technique to achieve transmit diversity. QO-STBC is full rate STBC constructed from relaxing orthogonality, and requires a decoder to search symbol pairs with ML decoding. Motivated by this, we have proposed single symbol decodable QO-STBC with full diversity. This code achieves full transmit rate and low system complexity. However, the proposed QO-STBC can achieve a throughput performance like SISO. In order to exploit the advantages of single symbol decodable QO-STBC, the combination of the proposed QO-STBC and an adaptive modulation has been considered. The system performances of non-adaptive QO-STBC, adaptive single symbol decodable QO-STBC are evaluated and compared. It is shown that the proposed scheme can greatly improve the performance of non-adaptive QO-STBC system.

MIMO-OFDM is considered a key technology in emerging high-data rate systems. With MIMO techniques, the transmission quality deteriorates due to co-channel interference (CCI). Several signal detection schemes have been proposed to mitigate this problem. However, it is impractical to use the conventional methods without reducing theirs computational complexity. Previously, we have proposed a parallel detection algorithm using multiple QR decompositions with permuted channel matrix (MQRD-PCM) for MIMO-OFDM to reduce the system complexity. This method achieves a good BER performance with low system complexity. However, since MQRD-PCM is a kind of parallel detection method, the wrong detection probability is increased due to the bad channel SINR of the transmitted signals. As a result, the average BER performance is influenced by the wrong detection probability of the bad channel SINR. To overcome this problem, in this paper, we propose the channel ranking based joint symbols detection for MQRD- PCM/MIMO-OFDM.

In MIMO systems, channel estimation is important to distinguish transmit signals from multiple transmit antennas. When MIMO systems are introduced in cellular systems, we have to measure the received power from all the connectable base station (BS), as well as to identify all the channel state information (CSI) for the combination of transmitter and receiver antenna elements. One of the most typical channel estimation schemes for MIMO in a cellular system is to employ a code division multiplexing (CDM) based scheme in which a unique spreading code is assigned to identify both BS and MS antenna elements. However, by increasing the number of transmit antenna elements, a large spreading code and pilot symbols are required to estimate an accurate CSI. To reduce this problem, in this paper, we propose a high time resolution carrier interferometry (HTRCI) for MIMO/OFDM to achieve an accurate CSI without increasing the number of pilot symbols.

In MIMO systems, the deployment of multiple antenna technique can considerably enhance the system performance. However, this is considering without a price. Since cost of RF is much higher than the antennas, there is growing interest in techniques that use larger number of antennas than the number of transmitter RF. These methods rely on selecting the optimal transmitter antennas and connecting them to respective RF. In this case, the feedback information (FBI) is required to select the optimal transmitter antennas. However, transmission of the FBI through a feedback channel is limited. Moreover, multiple antennas system requires an antenna separation of 5~10 lambda to keep the correlation coefficient below 0.7 for achieving the diversity gain. In this case, base station is required a wide space to set the multiple antenna. To reduce these problems, this paper proposed the link correlation based transmit sector antenna selection for Alamouti coded OFDM without FBI.

Recently, unitary matrix modulation (UMM) has been investigated in multiple antenna systems which is called unitary space-time modulation (USTM). In an OFDM, different channel delay profiles and path strengths bring different frequency selective patterns. Therefore, OFDM system can potentially provide a diversity at the frequency selective fading due to the different channel delay profiles. When we consider only the diagonal components of UMM with splitting over the coherence bandwidth, the system can obtain a frequency diversity in a single antenna, since the channel response of the diagonal components of UMM that split over the coherence bandwidth shows to be totally different. In this paper, we propose the diagonal components of UMM/OFDM with splitting over the coherence bandwidth (UMM-S/OFDM) in a single antenna. The proposed system can obtain the frequency diversity with splitting the diagonal components of UMM/OFDM over the coherence bandwidth. Therefore, the proposed system with a single antenna can obtain good BER performance like the USTM/OFDM with two antennas. Copyright © 2006 John Wiley & Sons, Ltd.

In an AMS/OFDM system, base station is in control of the modulation level of each subcarrier, and then, adaptive modulated packet is transmitted from the base station to the mobile station. In this case, the mobile station is required the modulation level information (MLI) to demodulate the received packet. The MLI is generally transmitted as a data symbol, therefore, the throughput is degraded. In an OFDM, the channel response at a particular subcarrier frequency is not supposed to be totally different from its neighboring frequencies, and hence, they mast have correlation which depends on the coherence bandwidth of the channel B/sub c/. If we could assign the same modulation level for coherently faded subcarrier block, MLI is required only one time for each subcarrier block. Moreover, we can assign the data on the empty space of pilot signals for increasing the total transmission. In this paper, we propose an adaptive subcarrier block modulation with differentially modulated pilot symbol assistance for downlink OFDM using uplink delay spread.

The combination of OFDM and multiple antennas in either the transmitter or receiver is attractive to increase a diversity gain. However, multiple antennas system requires an antenna separation of 510 /spl lambda/ to keep the correlation coefficient below 0.7 for the space diversity, so this may be difficult to implement in a mobile station with high mobility. Recently, the polarization transmit diversity is considered in a mobile station. However, polarization transmit diversity requires twice transmit powers to compare with the conventional transmit diversity, since only vertically polar antenna cannot receive the horizontal signal components. In this paper, we express the cross correlation of each polarization antenna and the cross polarization discrimination (XPD) of multiple polarization antennas with simple model, and we propose a wideband OFDM using Alamouti coded heterogeneous polarization antennas for reducing the previous problem. From the simulated results, the proposed system shows better BER performance than that of the conventional STBC/OFDM.

We propose a new generation mobile communication system that can realize 100 Mbps carrier bit rate under high mobility environment and can access the IP network easily. The new system is based on dynamic parameter controlled orthogonal frequency and time division multiple access (DPC-OF/TDMA) in which users share "slots" that use a certain number of subcarriers and a certain number of OFDM symbols. To access the slots, mobile stations use a packet-reservation-based protocol: packet reservation dynamic time-slotted multiple access (PR-DSMA). In addition, to avoid cochannel interference from adjacent cells and increase frequency utilization efficiency, we use an adaptive modulation scheme that is based on an interference detection algorithm. We mention the concept and the basic transmission performance of the proposed system.