arXiv subjects

Kyungchun Lee

Publications and source records attributed to Kyungchun Lee.

16 recordsLinked to original sources

arXiv2026

Integration of TinyML and LargeML: A Survey of 6G and Beyond

The evolution from fifth-generation (5G) to sixth-generation (6G) networks is driving an unprecedented demand for advanced machine learning (ML) solutions. Deep learning has already demonstrated significant impact across mobile networking and communication systems, enabling intelligent services such as smart healthcare, smart grids, autonomous vehicles, aerial platforms, digital twins, and the metaverse. At the same time, the rapid proliferation of resource-constrained Internet-of-Things (IoT) devices has accelerated the adoption of tiny machine learning (TinyML) for efficient on-device intelligence, while large machine learning (LargeML) models continue to require substantial computational resources to support large-scale IoT services and ML-generated content. These trends highlight the need for a unified framework that integrates TinyML and LargeML to achieve seamless connectivity, scalable intelligence, and efficient resource management in future 6G systems. This survey provides a comprehensive review of recent advances enabling the integration of TinyML and LargeML in next-generation wireless networks. In particular, we (i) provide an overview of TinyML and LargeML, (ii) analyze the motivations and requirements for unifying these paradigms within the 6G context, (iii) examine efficient bidirectional integration approaches, (iv) review state-of-the-art solutions and their applicability to emerging 6G services, and (v) identify key challenges related to performance optimization, deployment feasibility, resource orchestration, and security. Finally, we outline promising research directions to guide the holistic integration of TinyML and LargeML for intelligent, scalable, and energy-efficient 6G networks and beyond.

cs.NI↗

arXiv2025

Low Complexity Weight Flexible Decoding Schemes of Linear Block Code for 6G xURLLC

Low complexity error correction code is a key enabler for next generation ultra-reliable low-latency communications (xURLLC) in six generation (6G). Against this background, this paper proposes a decoding scheme for linear block code by leveraging certain interesting properties of dual codewords. It is found that dual codewords with flexible weights can provide useful decoding information for the locations and magnitudes of error bits, which yielding higher reliability performance. In addition, two decoding schemes are proposed, in which one directly utilizes intrinsic information for iterative decoding, and the other combines prior channel information with intrinsic information for decoding. Both schemes are implemented using vector multiplication and real-number comparisons, making them easy to implement in hardware. Simulation results demonstrate the validness of our study.

eess.SP↗

arXiv2023

Dual-Polarized IRS-Assisted MIMO Network

This study considers a dual-polarized intelligent reflecting surface (DP-IRS)-assisted multiple-input multiple-output (MIMO) single-user wireless communication system. The transmitter and receiver are equipped with DP antennas, and each antenna features a separate phase shifter for each polarization. We attempt to maximize the system's spectral efficiency (SE) by optimizing the operations of the reflecting elements at the DP-IRS, precoder/combiner at the transmitter/receiver, and vertical/horizontal phase shifters at the DP antennas. To address this problem, we propose a three-step alternating optimization (AO) algorithm based on the semi-definite relaxation method. Next, we consider asymptotically low/high signal-to-noise ratio (SNR) regimes and propose low-complexity algorithms. In particular, for the low-SNR regime, we derive computationally low-cost closed-form solutions. According to the obtained numerical results, the proposed algorithm outperforms the various benchmark schemes. Specifically, our main algorithm exhibits a 65.6 \% increase in the SE performance compared to random operations. In addition, we compare the SE performance of DP-IRS with that of simple IRS (S-IRS). For $N = 50$, DP-IRS achieves 24.8 \%, 28.2 \%, and 30.3 \% improvements in SE for ${4} \times {4}$, ${8} \times {8}$, and ${16} \times {16}$ MIMO, respectively, compared to S-IRS.

eess.SP↗

arXiv2021

Ultra-Reliable and Low-Latency Short-Packet Communications for Multihop MIMO Relaying

This work considers the multihop multiple-input multiple-output relay network under short-packet communications to facilitate not only ultra-reliability but also low-latency communications. We assume that the transmit antenna selection (TAS) scheme is utilized at the transmit side, whereas either selection combining (SC) or maximum ratio combining (MRC) is leveraged at the receive side to achieve diversity gains. For quasi-static Rayleigh fading channels and the finite-blocklength regime, we derive the approximate closed-form expressions of the end-to-end (e2e) block error rate (BLER) for both the TAS/MRC and TAS/SC schemes. The asymptotic performance in the high signal-to-noise ratio regime is derived, from which the comparison of TAS/MRC and TAS/SC schemes in terms of the diversity order, e2e BLER loss, and SNR gap is provided. The e2e latency and throughputs are also analyzed for the considered schemes. The correctness of our analysis is confirmed via Monte Carlo simulations.

cs.IT↗

arXiv2021

Application of Deep Learning to Sphere Decoding for Large MIMO Systems

Although the sphere decoder (SD) is a powerful detector for multiple-input multiple-output (MIMO) systems, it has become computationally prohibitive in massive MIMO systems, where a large number of antennas are employed. To overcome this challenge, we propose fast deep learning (DL)-aided SD (FDL-SD) and fast DL-aided $K$-best SD (KSD, FDL-KSD) algorithms. Therein, the major application of DL is to generate a highly reliable initial candidate to accelerate the search in SD and KSD in conjunction with candidate/layer ordering and early rejection. Compared to existing DL-aided SD schemes, our proposed schemes are more advantageous in both offline training and online application phases. Specifically, unlike existing DL-aided SD schemes, they do not require performing the conventional SD in the training phase. For a $24 \times 24$ MIMO system with QPSK, the proposed FDL-SD achieves a complexity reduction of more than $90\%$ without any performance loss compared to conventional SD schemes. For a $32 \times 32$ MIMO system with QPSK, the proposed FDL-KSD only requires $K = 32$ to attain the performance of the conventional KSD with $K=256$, where $K$ is the number of survival paths in KSD. This implies a dramatic improvement in the performance--complexity tradeoff of the proposed FDL-KSD scheme.

cs.IT↗

arXiv2021

Intelligent Radio Signal Processing: A Survey

Intelligent signal processing for wireless communications is a vital task in modern wireless systems, but it faces new challenges because of network heterogeneity, diverse service requirements, a massive number of connections, and various radio characteristics. Owing to recent advancements in big data and computing technologies, artificial intelligence (AI) has become a useful tool for radio signal processing and has enabled the realization of intelligent radio signal processing. This survey covers four intelligent signal processing topics for the wireless physical layer, including modulation classification, signal detection, beamforming, and channel estimation. In particular, each theme is presented in a dedicated section, starting with the most fundamental principles, followed by a review of up-to-date studies and a summary. To provide the necessary background, we first present a brief overview of AI techniques such as machine learning, deep learning, and federated learning. Finally, we highlight a number of research challenges and future directions in the area of intelligent radio signal processing. We expect this survey to be a good source of information for anyone interested in intelligent radio signal processing, and the perspectives we provide therein will stimulate many more novel ideas and contributions in the future.

eess.SP↗

arXiv2021

Spectral Efficiency Optimization for Hybrid Relay-Reflecting Intelligent Surface

We propose a novel concept of hybrid relay-reflecting intelligent surface (HR-RIS), in which a single or few elements are deployed with power amplifiers (PAs) to serve as active relays, while the remaining elements only reflect the incident signals. The design and optimization of the HR-RIS is formulated in a spectral efficiency (SE) maximization problem, which is efficiently solved by the alternating optimization (AO) method. The simulation results show that a significant improvement in the SE can be attained by the proposed HR-RIS, even with a limited power budget, with respect to the conventional reconfigurable intelligent surface (RIS). In particular, the favorable design and deployment of the HR-RIS are analytically derived and numerically justified.

eess.SP↗

arXiv2021

Hybrid Beamforming and Adaptive RF Chain Activation for Uplink Cell-Free Millimeter-Wave Massive MIMO Systems

In this work, we investigate hybrid analog-digital beamforming (HBF) architectures for uplink cell-free (CF) millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems. {We first propose two HBF schemes, namely, decentralized HBF (D-HBF) and semi-centralized HBF (SC-HBF). In the former, both the digital and analog beamformers are generated independently at each AP based on the local channel state information (CSI). In contrast, in the latter, only the digital beamformer is obtained locally at the AP, whereas the analog beamforming matrix is generated at the central processing unit (CPU) based on the global CSI received from all APs. We show that the analog beamformers generated in these two HBF schemes provide approximately the same achievable rates despite the lower complexity of D-HBF and its lack of CSI requirement.} Furthermore, to reduce the power consumption, we propose a novel adaptive radio frequency (RF) chain-activation (ARFA) scheme, which dynamically activates/deactivates RF chains and their connected analog-to-digital converters (ADCs) and phase shifters (PSs) at the APs based on the CSI. For the activation of RF chains, low-complexity algorithms are proposed, which can achieve significant improvement in energy efficiency (EE) with only a marginal loss in the total achievable rate.

cs.IT↗

arXiv2021

Hybrid Relay-Reflecting Intelligent Surface-Assisted Wireless Communication

Reconfigurable intelligent surface (RIS) has emerged as a cost- and energy-efficient solution to enhance the wireless communication capacity. However, recent studies show that a very large surface is required for a RIS-assisted communication system; otherwise, they may be outperformed by the conventional relay. Furthermore, the performance gain of a RIS can be considerably degraded by hardware impairments such as limited-resolution phase shifters. To overcome those challenges, we propose a novel concept of hybrid relay-reflecting intelligent surface (HR-RIS), in which a single or few elements are deployed with power amplifiers (PAs) to serve as active relays, while the remaining elements only reflect the incident signals. Two architectures are proposed, including the fixed and dynamic HR-RIS. Their coefficient matrices are obtained based on alternating optimization (AO) and power allocation strategies, which enable understanding the fundamental performances of RIS and relaying-based systems with a trade-off between the two. The simulation results show that a significant improvement in both the spectral efficiency (SE) and energy efficiency (EE) with respect to the conventional RIS-aided system can be attained by the proposed schemes, especially, by the dynamic HR-RIS. In particular, the favorable design and deployment of the HR-RIS are analytically derived and numerically justified.

eess.SP↗

arXiv2020

Learning-Aided Deep Path Prediction for Sphere Decoding in Large MIMO Systems

In this paper, we propose a novel learning-aided sphere decoding (SD) scheme for large multiple-input--multiple-output systems, namely, deep path prediction-based sphere decoding (DPP-SD). In this scheme, we employ a neural network (NN) to predict the minimum metrics of the ``deep'' paths in sub-trees before commencing the tree search in SD. To reduce the complexity of the NN, we employ the input vector with a reduced dimension rather than using the original received signals and full channel matrix. The outputs of the NN, i.e., the predicted minimum path metrics, are exploited to determine the search order between the sub-trees, as well as to optimize the initial search radius, which may reduce the computational complexity of SD. For further complexity reduction, an early termination scheme based on the predicted minimum path metrics is also proposed. Our simulation results show that the proposed DPP-SD scheme provides a significant reduction in computational complexity compared with the conventional SD algorithm, despite achieving near-optimal performance.

cs.IT↗

arXiv2020

Hybrid Combining Based on Constant Phase Shifters and Active/Inactive Switches

In this paper, we propose a new hybrid analog and digital combining architecture for millimeter wave (mmWave) multi-user multiple-input multiple-output (MU-MIMO) systems. The proposed structure employs antenna subset selection per radio frequency (RF) chain based on active/inactive switches and uses constant phase shifters (CPS) to control the phases of signals in the RF circuit. In this scheme, for each RF chain, a subset of receive antennas that contribute more to the desired signal power than the interference power is chosen for signal combining in the analog domain, whereas other receive antennas are excluded from signal combining, thereby enhancing sum-rates. Simultaneously, the proposed structure reduces power consumption in the RF circuit by exclusively activating switches that correspond to the antennas selected for each RF chain. We also develop three low-complexity algorithms for per-RF chain antenna subset selection. Finally, through numerical simulation, we show that the proposed structure provides higher spectral efficiency and higher energy efficiency than conventional hybrid analog and digital combining schemes for mmWave MU-MIMO systems.

cs.IT↗

arXiv2019

Groupwise Neighbor Examination for Tabu Search Detection in Large MIMO systems

In the conventional tabu search (TS) detection algorithm for multiple-input multiple-output (MIMO) systems, the metrics of all neighboring vectors are computed to determine the best one to move to. This strategy requires high computational complexity, especially in large MIMO systems with high-order modulation schemes such as 16- and 64-QAM signaling. This paper proposes a novel reduced-complexity TS detection algorithm called neighbor-grouped TS (NG-TS), which divides the neighbors into groups and finds the best neighbor by using a simplified cost function. Furthermore, based on the complexity analysis of NG-TS, we propose a channel ordering scheme that further reduces its complexity. Simulation results show that the proposed NG-TS with channel ordering can achieve up to 85% complexity reduction with respect to the conventional TS algorithm with no performance loss in both low- and higher-order modulation schemes.

cs.IT↗

arXiv2019

Deep Learning-Aided Tabu Search Detection for Large MIMO Systems

In this study, we consider the application of deep learning (DL) to tabu search (TS) detection in large multiple-input multiple-output (MIMO) systems. First, we propose a deep neural network architecture for symbol detection, termed the fast-convergence sparsely connected detection network (FS-Net), which is obtained by optimizing the prior detection networks called DetNet and ScNet. Then, we propose the DL-aided TS algorithm, in which the initial solution is approximated by the proposed FS-Net. Furthermore, in this algorithm, an adaptive early termination algorithm and a modified searching process are performed based on the predicted approximation error, which is determined from the FS-Net-based initial solution, so that the optimal solution can be reached earlier. The simulation results show that the proposed algorithm achieves approximately 90% complexity reduction for a $32 \times 32$ MIMO system with QPSK with respect to the existing TS algorithms, while maintaining almost the same performance.

cs.IT↗

arXiv2019

Unequally Sub-connected Architecture for Hybrid Beamforming in Massive MIMO Systems

A variety of hybrid analog-digital beamforming architectures have recently been proposed for massive multiple-input multiple-output (MIMO) systems to reduce energy consumption and the cost of implementation. In the analog processing network of these architectures, the practical sub-connected structure requires lower power consumption and hardware complexity than the fully connected structure but cannot fully exploit the beamforming gains, which leads to a loss in overall performance. In this work, we propose a novel unequal sub-connected architecture for hybrid combining at the receiver of a massive MIMO system that employs unequal numbers of antennas in sub-antenna arrays. The optimal design of the proposed architecture is analytically derived, and includes antenna allocation and channel ordering schemes. Simulation results show that an enhancement of up to 10% can be attained in the total achievable rate by unequally assigning antennas to sub-arrays in the sub-connected system at the cost of a marginal increase in power consumption. Furthermore, in order to reduce the computational complexity involved in finding the optimal number of antennas connected to each radio frequency (RF) chain, we propose three low-complexity antenna allocation algorithms. The simulation results show that they can yield a significant reduction in complexity while achieving near-optimal performance.

cs.IT↗

arXiv2017

Cell Coverage Extension with Orthogonal Random Precoding for Massive MIMO Systems

In this paper, we investigate a coverage extension scheme based on orthogonal random precoding (ORP) for the downlink of massive multiple-input multiple-output (MIMO) systems. In this scheme, a precoding matrix consisting of orthogonal vectors is employed at the transmitter to enhance the maximum signal-to-interference-plus-noise ratio (SINR) of the user. To analyze and optimize the ORP scheme in terms of cell coverage, we derive the analytical expressions of the downlink coverage probability for two receiver structures, namely, the single-antenna (SA) receiver and multiple-antenna receiver with antenna selection (AS). The simulation results show that the analytical expressions accurately capture the coverage behaviors of the systems employing the ORP scheme. It is also shown that the optimal coverage performance is achieved when a single precoding vector is used under the condition that the threshold of the signal-to-noise ratio of the coverage is greater than one. The performance of the ORP scheme is further analyzed when different random precoder groups are utilized over multiple time slots to exploit precoding diversity. The numerical results show that the proposed ORP scheme over multiple time slots provides a substantial coverage gain over the space-time coding scheme despite its low feedback overhead.

cs.IT↗

arXiv2014

Interference Alignment for Multicell Multiuser MIMO Uplink Channels

This paper proposes a linear interference alignment (IA) scheme which can be used for uplink channels in a general multicell multiuser MIMO cellular network. The proposed scheme aims to align interference caused by signals from a set of transmitters into a subspace which is established by the signals from only a subset of those transmitters, thereby effectively reducing the number of interfering transmitters. The total degrees of freedom (DoF) achievable by the proposed scheme is given in closed-form expression, and a numerical analysis shows that the proposed scheme can achieve the optimal DoF in certain scenarios and provides a higher total DoF than other related schemes in most cases.

cs.IT↗