Seong-Lyun Kim

Seong-Lyun Kim
Yonsei University · Department of Electrical and Electronic Engineering

Doctor of Engineering

About

266
Publications
39,726
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,940
Citations

Publications

Publications (266)
Preprint
Full-text available
This paper studies a hybrid language model (HLM) architecture that integrates a small language model (SLM) operating on a mobile device with a large language model (LLM) hosted at the base station (BS) of a wireless network. The HLM token generation process follows the speculative inference principle: the SLM's vocabulary distribution is uploaded t...
Article
Full-text available
Recent studies on semantic communication commonly rely on neural network (NN) based transceivers such as deep joint source and channel coding (DeepJSCC). Unlike traditional transceivers, these neural transceivers are trainable using actual source data and channels, enabling them to extract and communicate semantics. On the flip side, each neural tr...
Article
Full-text available
A smartphone-based user mobility tracking could be effective in finding his/her location, while the unpredictable error therein due to low specification of built-in inertial measurement units (IMUs) rejects its standalone usage but demands the integration to another positioning technique like WiFi positioning. This paper aims to propose a novel i...
Article
Non-terrestrial networks (NTNs), including low Earth orbit (LEO) satellites, play a critical role in achieving comprehensive Internet-of-Things (IoT) coverage in sixth-generation (6G) systems. Despite the assignment of specific frequency bands, the persistent issue of spectrum scarcity necessitates the implementation of efficient spectrum-sharing s...
Article
Full-text available
A distributed control of vehicle platooning is referred to as distributed consensus (DC) since many autonomous vehicles (AVs) reach a consensus to achieve coordinated movement with the same velocity and inter-distance. For DC control to be stable, each AV utilizes other AVs’ real-time position information obtained via vehicle-to-vehicle (V2V)...
Article
Full-text available
Due to the emergence of various wireless sensing technologies, numerous positioning algorithms have been introduced in the literature, categorized into geometry-driven positioning (GP) and data-driven positioning (DP). These approaches have respective limitations, e.g., a non-line-of-sight issue for GP and the lack of a high-dimensional and lab...
Article
Full-text available
The vision of pervasive artificial intelligence (AI) services can be realized by training an AI model on time using real-time data collected by internet of things (IoT) devices. To this end, IoT devices require offloading their data to an edge server in proximity. However, transmitting high-dimensional and voluminous data from energy-constraine...
Article
The forthcoming 6G systems are expected to address a wide range of non-stationary tasks. This poses challenges to traditional medium access control (MAC) protocols that are static and predefined. In response, data-driven MAC protocols have recently emerged, offering ability to tailor their signaling messages for specific tasks. This article present...
Preprint
This paper proposes new framework of communication system leveraging promising generation capabilities of multi-modal generative models. Regarding nowadays smart applications, successful communication can be made by conveying the perceptual meaning, which we set as text prompt. Text serves as a suitable semantic representation of image data as it h...
Article
italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Pedestrian dead reckoning (PDR) is one key localization technique using inertial measurement unit (IMU) installed on a smartphone. However, IMU measurements are affected by the user’s unpredictable smartphone-carrying pattern, degrading the resulting...
Article
Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications. By contrast, neural network (NN) based protocol models (NPMs) learn to generate task-specific CMs, but their rationale and impact lack interpretability. To fill this v...
Preprint
Full-text available
Automatic modulation classification (AMC) is a technology that identifies a modulation scheme without prior signal information and plays a vital role in various applications, including cognitive radio and link adaptation. With the development of deep learning (DL), DL-based AMC methods have emerged, while most of them focus on reducing computationa...
Article
Full-text available
In recent years, split learning (SL) has emerged as a promising distributed learning framework that can utilize big data in parallel without privacy leakage while reducing client-side computing resources. In the initial implementation of SL, however, the server serves multiple clients sequentially incurring high latency. Parallel implementation of...
Preprint
Full-text available
The vision of pervasive machine learning (ML) services can be realized by training an ML model on time using real-time data collected by internet of things (IoT) devices. To this end, IoT devices require offloading their data to an edge server in proximity. On the other hand, high dimensional data with a heavy volume causes a significant burden to...
Preprint
Full-text available
With the rise of edge computing, various AI services are expected to be available at a mobile side through the inference based on deep neural network (DNN) operated at the network edge, called edge inference (EI). On the other hand, the resulting AI quality (e.g., mean average precision in objective detection) has been regarded as a given factor, a...
Preprint
Full-text available
Recently, vision transformer (ViT) has started to outpace the conventional CNN in computer vision tasks. Considering privacy-preserving distributed learning with ViT, federated learning (FL) communicates models, which becomes ill-suited due to ViT' s large model size and computing costs. Split learning (SL) detours this by communicating smashed dat...
Preprint
Full-text available
Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications. By contrast, neural network (NN) based protocol models (NPMs) learn to generate task-specific CMs, but their rationale and impact lack interpretability. To fill this v...
Preprint
Full-text available
This article seeks for a distributed learning solution for the visual transformer (ViT) architectures. Compared to convolutional neural network (CNN) architectures, ViTs often have larger model sizes, and are computationally expensive, making federated learning (FL) ill-suited. Split learning (SL) can detour this problem by splitting a model and co...
Data
This data is IMU data from accelerometer, gyroscope, and magnetometer collected by carrying a smartphone in three patterns, i.e., chest, swing, pocket, in about 120 paths of four types.
Article
Full-text available
Recently, round-trip time (RTT) measured by a finetiming measurement protocol has received great attention in the area of WiFi positioning. It provides an acceptable ranging accuracy in favorable environments when a line-of-sight (LOS) path exists. Otherwise, a signal is detoured along with non-LOS paths, making the resultant ranging results differ...
Poster
Full-text available
Verify at coursera.org/verify/4TJE2B5SRUYZ Coursera has confirmed the identity of this individual and their participation in the course.
Preprint
Full-text available
The lottery ticket hypothesis (LTH) claims that a deep neural network (i.e., ground network) contains a number of subnetworks (i.e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground network. Federated learning (FL) has recently been applied in LotteryFL to discover such winning tickets in a...
Preprint
Full-text available
To minimize enormous havoc from disasters, permanent environment monitoring is necessarily required. Thus we propose a novel energy management protocol for energy harvesting wireless sensor networks (EH-WSNs), named the adaptive sensor node management protocol (ASMP). The proposed protocol makes system components to systematically control their per...
Article
Full-text available
Machine learning (ML) is a promising enabler for the fifth-generation (5G) communication systems and beyond. By imbuing intelligence into the network edge, edge nodes can proactively carry out decision-making and, thereby, react to local environmental changes and disturbances while experiencing zero communication latency. To achieve this goal, it i...
Preprint
Full-text available
In this book chapter, we study a problem of distributed content caching in an ultra-dense edge caching network (UDCN), in which a large number of small base stations (SBSs) prefetch popular files to cope with the ever-growing user demand in 5G and beyond. In a UDCN, even a small misprediction of user demand may render a large amount of prefetched d...
Preprint
Full-text available
Due to the massive deployment of WiFi APs and its accessibility to various positioning elements, WiFi positioning is a key enabler to provide seamless and ubiquitous location services to users. There are various kinds of WiFi positioning technologies, depending on the concerned positioning element. Among them, round-trip time (RTT) measured by a fi...
Preprint
Full-text available
Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under limited communication resources, however, such a method becomes extremely costly particularly for modern deep...
Article
To cope with the lack of on-device machine learning samples, this article presents a distributed data augmentation algorithm, coined federated data augmentation (FAug). In FAug, devices share a tiny fraction of their local data, i.e., seed samples, and collectively train a synthetic sample generator that can augment the local datasets of devices. T...
Article
Full-text available
In this paper, we investigate the possibility of the cross-layer design of a distributed random access scheme with considering physical (PHY) and multiple access control (MAC) layers, which utilizes the interference cancellation technique. In this regard, we propose a new multiple access protocol, named carrier sense non-orthogonal multiple access...
Article
Full-text available
With the envisioned massive connectivity era, one of the challenges for 5G/Beyond 5G (B5G) wireless systems will be handling the unprecedented spectrum crunch. A potential solution has emerged in the form of spectrum sharing, which deviates from a monopolistic spectrum usage system. This paper investigates the medium access control (MAC) as a means...
Preprint
Full-text available
Machine learning (ML) is a promising enabler for the fifth generation (5G) communication systems and beyond. By imbuing intelligence into the network edge, edge nodes can proactively carry out decision-making, and thereby react to local environmental changes and disturbances while experiencing zero communication latency. To achieve this goal, it is...
Preprint
Full-text available
This paper is presented at 28th International Joint Conference on Artificial Intelligence (IJCAI-19) 1st Wksp. Federated Machine Learning for User Privacy and Data Confidentiality (FML'19), Macau, August 2019.
Article
Full-text available
This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federate...
Preprint
This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federate...
Conference Paper
Full-text available
To introduce the most energy-efficient adaptive sampling algorithm for the disaster monitoring system, this study proposes a novel algorithm based on sampling period estimation for gathering only valuable information. It is called an adaptive sampling algorithm for monitoring (ASA-m). This method estimates the next sampling period to get the inform...
Preprint
Full-text available
User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and identically distributed (non-IID) data problem, in this work we develop a privacy-preserving XOR based mixup data augmentation technique, coined XorMixup, and thereby propose a...
Preprint
Full-text available
Due to the edge's position between the cloud and the users, and the recent surge of deep neural network (DNN) applications, edge computing brings about uncertainties that must be understood separately. Particularly, the edge users' locally specific requirements that change depending on time and location cause a phenomenon called dataset shift, defi...
Article
Full-text available
Traditional distributed deep reinforcement learning (RL) commonly relies on exchanging the experience replay memory (RM) of each agent. Since the RM contains all state observations and action policy history, it may incur huge communication overhead while violating the privacy of each agent. Alternatively, this article presents a communication-effic...
Preprint
Full-text available
Traditional distributed deep reinforcement learning (RL) commonly relies on exchanging the experience replay memory (RM) of each agent. Since the RM contains all state observations and action policy history, it may incur huge communication overhead while violating the privacy of each agent. Alternatively, this article presents a communication-effic...
Preprint
Full-text available
In this paper, we propose a reinforcement learning-based flexible duplex system for B5G with Sub-6 GHz. This system combines full-duplex radios and dynamic spectrum access to maximize the spectral efficiency. We verify this method's feasibility by implementing an FPGA-based real-time testbed. In addition, we compare the proposed algorithm with the...
Preprint
Full-text available
Are 5G connection and UAVs merely parts of an extravagant and luxurious world, or are they essential parts of a practical world in a way we have yet to see? To aid in a direction to address the issue, we provide a practical framework for immersive aerial monitoring for public safety. Because the framework is built on top of actual realizations and...
Conference Paper
Are 5G connection and UAVs merely parts of an extravagant and luxurious world, or are they essential parts of a practical world in a way we have yet to see? To aid in a direction to address the issue, we provide a practical framework for immersive aerial monitoring for public safety. Because the framework is built on top of actual realizations and...
Article
Full-text available
Despite the widespread popularity of stochastic geometry analysis for cellular networks, most analytical results lack the perspective of channel-adaptive user scheduling. This study presents a stochastic geometry analysis of the SINR distribution and scheduling gain of normalized SNR-based scheduling in an uplink Poisson cellular network, in which...
Preprint
Full-text available
This letter proposes a novel random medium access control (MAC) based on a transmission opportunity prediction, which can be measured in a form of a conditional success probability given transmitter-side interference. A transmission probability depends on the opportunity prediction, preventing indiscriminate transmissions and reducing excessive int...
Article
Full-text available
This letter proposes a novel random medium access control (MAC) based on a transmission opportunity prediction, which can be measured in a form of a conditional success probability given transmitter-side interference. A transmission probability depends on the opportunity prediction, preventing indiscriminate transmissions, and reducing excessive in...
Article
We are delighted to introduce the readers to this special section of the IEEE Transactions on Cognitive Communications and Networking (TCCN), which is devoted to selected papers from the IEEE DySPAN 2018 conference.
Preprint
Full-text available
Devices at the edge of wireless networks are the last mile data sources for machine learning (ML). As opposed to traditional ready-made public datasets, these user-generated private datasets reflect the freshest local environments in real time. They are thus indispensable for enabling mission-critical intelligent systems, ranging from fog radio acc...
Preprint
Full-text available
Devices at the edge of wireless networks are the last mile data sources for machine learning (ML). As opposed to traditional ready-made public datasets, these user-generated private datasets reflect the freshest local environments in real time. They are thus indispensable for enabling mission-critical intelligent systems, ranging from fog radio acc...
Conference Paper
Full-text available
On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a central entity. However, for privacy guarantee, it is inevitable at each device to compensate for the quality of data or learning performance, especially when it has a no...
Conference Paper
Full-text available
In distributed reinforcement learning, it is common to exchange the experience memory of each agent and thereby collectively train their local models. The experience memory, however, contains all the preceding state observations and their corresponding policies of the host agent, which may violate the privacy of the agent. To avoid this problem, in...
Preprint
Full-text available
In distributed reinforcement learning, it is common to exchange the experience memory of each agent and thereby collectively train their local models. The experience memory, however, contains all the preceding state observations and their corresponding policies of the host agent, which may violate the privacy of the agent. To avoid this problem, in...
Preprint
Full-text available
On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a central entity. However, for privacy guarantee, it is inevitable at each device to compensate for the quality of data or learning performance, especially when it has a no...
Article
Full-text available
By leveraging blockchain, this letter proposes a blockchained federated learning (BlockFL) architecture where local learning model updates are exchanged and verified. This enables on-device machine learning without any centralized training data or coordination by utilizing a consensus mechanism in blockchain. Moreover, we analyze an end-to-end late...