Wonjun Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Wonjun Kim has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Byonghyo Shim
Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, Republic of Korea
9 shared publications - Hyoungju Ji
Samsung Electronics
3 shared publications - Yongjun Ahn
Samsung Electronics, Seoul, South Korea
2 shared publications - Hyojin Lee
Department of Chemical Engineering, Konkuk University, 1 Hwayang-dong, Gwangjin-gu, Seoul 143-701, South Korea
1 shared publication - Jiao Wu
Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
1 shared publication - Jin-Hong Kim
Department of Biological Sciences, College of Natural Sciences, Seoul National University, Seoul, South Korea
1 shared publication
Latest Publications
- Open Access
Towards Deep Learning-aided Wireless Channel Estimation and Channel State Information Feedback for 6G
Deep learning (DL), a branch of artificial intelligence (AI) techniques, has shown great promise in various disciplines such as image classification and segmentation, speech recognition, language translation, among others. This remarkable success of DL has stimulated increasing interest in applying this paradigm to wireless channel estimation in recent years. Since DL principles are inductive in nature and distinct from the conventional rule-based algorithms, when one tries to use DL technique to the channel estimation, one might easily get stuck and confused by so many knobs to control and small details to be aware of. The primary purpose of this paper is to discuss key issues and possible solutions in DL-based wireless channel estimation and channel state information (CSI) feedback including the DL model selection, training data acquisition, and neural network design for 6G. Specifically, we present several case studies together with the numerical experiments to demonstrate the effectiveness of the DL-based wireless channel estimation framework.
Open AccessTowards Deep Learning-aided Wireless Channel Estimation and Channel State Information Feedback for 6G
Deep learning (DL), a branch of artificial intelligence (AI) techniques, has shown great promise in various disciplines such as image classification and segmentation, speech recognition, language translation, among others. This remarkable success of DL has stimulated increasing interest in applying this paradigm to wireless channel estimation in recent years. Since DL principles are inductive in nature and distinct from the conventional rule-based algorithms, when one tries to use DL technique to the channel estimation, one might easily get stuck and confused by so many knobs to control and small details to be aware of. The primary purpose of this paper is to discuss key issues and possible solutions in DL-based wireless channel estimation and channel state information (CSI) feedback including the DL model selection, training data acquisition, and neural network design for 6G. Specifically, we present several case studies together with the numerical experiments to demonstrate the effectiveness of the DL-based wireless channel estimation framework.
- 6 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 21 (12) , 10755-10765
Partial Sample Transmission and Deep Neural Decoding for URLLC V2X System
With the rapid development of intelligent transportation systems (ITS), mission-critical vehicular services such as vehicle platooning, safety alarming, and remote driving play a key role in the future ITS. In order to support these emerging services, low-latency and high reliability transmission should be ensured. In the 4G Long Term Evolution (LTE) and 5G New Radio (NR) vehicle-to-everything (V2X) systems, it is very difficult to meet the latency requirement since group of orthogonal frequency division multiplexing (OFDM) symbols are processed in a form of the resource block. In this paper, we propose a novel low-latency packet transmission scheme for V2X systems, referred to as partial sample transmission (PST). In PST, we map the transmit information into subcarrier positions and then decode it using a small fraction of received samples at the receiver. To perform the efficient decoding, we propose a deep learning (DL)-based PST decoding. From the numerical evaluations on the V2X system, we demonstrate that the proposed PST technique outperforms conventional transmission schemes in terms of the block error rate (BLER) and the signaling latency.
- 6 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 21 (12) , 10755-10765
Partial Sample Transmission and Deep Neural Decoding for URLLC V2X System
With the rapid development of intelligent transportation systems (ITS), mission-critical vehicular services such as vehicle platooning, safety alarming, and remote driving play a key role in the future ITS. In order to support these emerging services, low-latency and high reliability transmission should be ensured. In the 4G Long Term Evolution (LTE) and 5G New Radio (NR) vehicle-to-everything (V2X) systems, it is very difficult to meet the latency requirement since group of orthogonal frequency division multiplexing (OFDM) symbols are processed in a form of the resource block. In this paper, we propose a novel low-latency packet transmission scheme for V2X systems, referred to as partial sample transmission (PST). In PST, we map the transmit information into subcarrier positions and then decode it using a small fraction of received samples at the receiver. To perform the efficient decoding, we propose a deep learning (DL)-based PST decoding. From the numerical evaluations on the V2X system, we demonstrate that the proposed PST technique outperforms conventional transmission schemes in terms of the block error rate (BLER) and the signaling latency.
- 3 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 9 (14) , 11904-11917
Active User Detection and Channel Estimation for Massive Machine-Type Communication: Deep Learning Approach
Recently, massive machine-type communications (mMTCs) have become one of key use cases for 5G. In order to support massive users transmitting small data packets at low rates, grant-free (GF) access and nonorthogonal multiple access (NOMA) have been suggested. Since each device transmits information without scheduling in the GF-NOMA systems, the device identification process, called active user detection (AUD), is required at the base station (BS). For the NOMA-based systems, the channel estimation (CE), an operation after the AUD, is a challenging task since multiple devices’ transmit signals and channels are superimposed in the same wireless resources. In this article, we propose a deep learning (DL)-based AUD and CE in the GF-NOMA systems. In our work, DL figures out the direct mapping between the received NOMA signal and the indices of active devices and associated channels using the long short-term memory (LSTM). From numerical experiments, we show that the proposed scheme is effective in handling the AUD and CE in the mMTC environments.
- 3 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 9 (14) , 11904-11917
Active User Detection and Channel Estimation for Massive Machine-Type Communication: Deep Learning Approach
Recently, massive machine-type communications (mMTCs) have become one of key use cases for 5G. In order to support massive users transmitting small data packets at low rates, grant-free (GF) access and nonorthogonal multiple access (NOMA) have been suggested. Since each device transmits information without scheduling in the GF-NOMA systems, the device identification process, called active user detection (AUD), is required at the base station (BS). For the NOMA-based systems, the channel estimation (CE), an operation after the AUD, is a challenging task since multiple devices’ transmit signals and channels are superimposed in the same wireless resources. In this article, we propose a deep learning (DL)-based AUD and CE in the GF-NOMA systems. In our work, DL figures out the direct mapping between the received NOMA signal and the indices of active devices and associated channels using the long short-term memory (LSTM). From numerical experiments, we show that the proposed scheme is effective in handling the AUD and CE in the mMTC environments.
- 19 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (8) , 9117-9120
Pilot-Less One-Shot Sparse Coding for Short Packet-Based Machine-Type Communications
This paper presents a novel transmission scheme to support massive machine-type communications (MTC) devices sending very short packets for Internet-of-Things (IoT) applications. The proposed scheme, termed as pilot-less one-shot (PLOS) transmission, does not require the pilot signaling. The key idea behind PLOS is to encode information into the inter-block nonzero positions and intra-block nonzero positions of a sparse vector. In the receiver, we propose a deep neural network-based scheme, referred to as deep learning-based PLOS (DL-PLOS) to recover the nonzero positions of the sparse vector. From the simulations results, we demonstrate that PLOS is effective in the short packet transmission and DL-PLOS outperforms the conventional greedy algorithms.
- 19 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (8) , 9117-9120
Pilot-Less One-Shot Sparse Coding for Short Packet-Based Machine-Type Communications
This paper presents a novel transmission scheme to support massive machine-type communications (MTC) devices sending very short packets for Internet-of-Things (IoT) applications. The proposed scheme, termed as pilot-less one-shot (PLOS) transmission, does not require the pilot signaling. The key idea behind PLOS is to encode information into the inter-block nonzero positions and intra-block nonzero positions of a sparse vector. In the receiver, we propose a deep neural network-based scheme, referred to as deep learning-based PLOS (DL-PLOS) to recover the nonzero positions of the sparse vector. From the simulations results, we demonstrate that PLOS is effective in the short packet transmission and DL-PLOS outperforms the conventional greedy algorithms.
- 30 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (5) , 5698-5702
Enhanced Sparse Vector Coding for Ultra-Reliable and Low Latency Communications
An important observation in the ultra-reliable and low latency communications is that the size of transmit information is tiny. To support the effective short packet transmission, a sparse vector coding (SVC) scheme where an information is encoded into the positions of the sparse vector was proposed. In this paper, we propose a novel SVC technique further improving the reliability of the short packet transmission. Key idea of the proposed technique is to encode information both in the position as well as symbols. From the performance analysis and numerical evaluations on realistic channel models, we demonstrate that the proposed scheme outperforms the conventional SVC scheme in terms of the block error rate (BLER) and transmission latency.
- 30 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (5) , 5698-5702
Enhanced Sparse Vector Coding for Ultra-Reliable and Low Latency Communications
An important observation in the ultra-reliable and low latency communications is that the size of transmit information is tiny. To support the effective short packet transmission, a sparse vector coding (SVC) scheme where an information is encoded into the positions of the sparse vector was proposed. In this paper, we propose a novel SVC technique further improving the reliability of the short packet transmission. Key idea of the proposed technique is to encode information both in the position as well as symbols. From the performance analysis and numerical evaluations on realistic channel models, we demonstrate that the proposed scheme outperforms the conventional SVC scheme in terms of the block error rate (BLER) and transmission latency.
- Open Access
- 26 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Vehicular Technology Magazine
- Vol. 15 (3) , 32-39
Sparse Vector Transmission: An Idea Whose Time Has Come
- 26 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Vehicular Technology Magazine
- Vol. 15 (3) , 32-39
Open AccessSparse Vector Transmission: An Idea Whose Time Has Come
- 24 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (4) , 2143-2155
Deep Neural Network-Based Active User Detection for Grant-Free NOMA Systems
- 24 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (4) , 2143-2155
Deep Neural Network-Based Active User Detection for Grant-Free NOMA Systems
- 25 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (2) , 1175-1186
Channel Aware Sparse Transmission for Ultra Low-Latency Communications in TDD Systems
Major goal of ultra reliable and low latency communication (URLLC) is to reduce the latency down to a millisecond (ms) level while ensuring reliability of the transmission. Since the current uplink transmission scheme requires a complicated handshaking procedure to initiate the transmission, to meet this stringent latency requirement is a challenge in wireless system design. In particular, in the time division duplexing (TDD) systems, supporting the URLLC is difficult since the mobile device has to wait until the transmit direction is switched to the uplink. In this paper, we propose a new approach to support a low latency access in TDD systems, called channel aware sparse transmission (CAST). Key idea of the proposed scheme is to encode a grant signal in a form of sparse vector. This together with the fact that the sensing mechanism preserves the energy of the sparse vector allows us to use the compressed sensing (CS) technique in CAST decoding. From the performance analysis and numerical evaluations, we demonstrate that the proposed CAST scheme achieves a significant reduction in access latency over the 4G LTE-TDD and 5G NR-TDD systems.
- 25 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 68 (2) , 1175-1186
Channel Aware Sparse Transmission for Ultra Low-Latency Communications in TDD Systems
Major goal of ultra reliable and low latency communication (URLLC) is to reduce the latency down to a millisecond (ms) level while ensuring reliability of the transmission. Since the current uplink transmission scheme requires a complicated handshaking procedure to initiate the transmission, to meet this stringent latency requirement is a challenge in wireless system design. In particular, in the time division duplexing (TDD) systems, supporting the URLLC is difficult since the mobile device has to wait until the transmit direction is switched to the uplink. In this paper, we propose a new approach to support a low latency access in TDD systems, called channel aware sparse transmission (CAST). Key idea of the proposed scheme is to encode a grant signal in a form of sparse vector. This together with the fact that the sensing mechanism preserves the energy of the sparse vector allows us to use the compressed sensing (CS) technique in CAST decoding. From the performance analysis and numerical evaluations, we demonstrate that the proposed CAST scheme achieves a significant reduction in access latency over the 4G LTE-TDD and 5G NR-TDD systems.
- 12 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 8 (4) , 1036-1039
Pilot-Less Sparse Vector Coding for Short Packet Transmission
- 12 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 8 (4) , 1036-1039
Pilot-Less Sparse Vector Coding for Short Packet Transmission