arXiv subjects

Joongheon Kim

Publications and source records attributed to Joongheon Kim.

At least 91 records · Page 5Linked to original sources

arXiv2021

Introduction to Quantum Reinforcement Learning: Theory and PennyLane-based Implementation

The emergence of quantum computing enables for researchers to apply quantum circuit on many existing studies. Utilizing quantum circuit and quantum differential programming, many research are conducted such as \textit{Quantum Machine Learning} (QML). In particular, quantum reinforcement learning is a good field to test the possibility of quantum machine learning, and a lot of research is being done. This work will introduce the concept of quantum reinforcement learning using a variational quantum circuit, and confirm its possibility through implementation and experimentation. We will first present the background knowledge and working principle of quantum reinforcement learning, and then guide the implementation method using the PennyLane library. We will also discuss the power and possibility of quantum reinforcement learning from the experimental results obtained through this work.

cs.LG↗

arXiv2021

Spatio-Temporal Split Learning

This paper proposes a novel split learning framework with multiple end-systems in order to realize privacypreserving deep neural network computation. In conventional split learning frameworks, deep neural network computation is separated into multiple computing systems for hiding entire network architectures. In our proposed framework, multiple computing end-systems are sharing one centralized server in split learning computation, where the multiple end-systems are with input and first hidden layers and the centralized server is with the other hidden layers and output layer. This framework, which is called as spatio-temporal split learning, is spatially separated for gathering data from multiple end-systems and also temporally separated due to the nature of split learning. Our performance evaluation verifies that our proposed framework shows nearoptimal accuracy while preserving data privacy.

cs.LG↗

arXiv2021

Joint Pilot Design and Channel Estimation using Deep Residual Learning for Multi-Cell Massive MIMO under Hardware Impairments

In multi-cell massive MIMO systems, channel estimation is deteriorated by pilot contamination and the effects of pilot contamination become more severe due to hardware impairments. In this paper, we propose a joint pilot design and channel estimation based on deep residual learning in order to mitigate the effects of pilot contamination under the consideration of hardware impairments. We first investigate a conventional linear minimum mean square error (LMMSE) based channel estimator to suppress the interference caused by pilot contamination. After that, a deep learning based pilot design is proposed to minimize the mean square error (MSE) of LMMSE channel estimation, which is utilized to the joint pilot design and channel estimator for transfer learning approach. For the channel estimator, we use a deep residual learning which extracts the features of interference caused by pilot contamination and eliminates them to estimate the channel information. Simulation results demonstrate that the proposed joint pilot design and channel estimator outperforms the conventional approach in multi-cell massive MIMO scenarios. Furthermore, the joint pilot design and channel estimator using transfer learning enhances the estimation performance by reducing the effects of pilot contamination when the prior knowledge of pilot contamination cannot be exploited.

eess.SP↗

arXiv2021

Quantum Scheduling for Millimeter-Wave Observation Satellite Constellation

In beyond 5G and 6G network scenarios, the use of satellites has been actively discussed for extending target monitoring areas, even for extreme circumstances, where the monitoring functionalities can be realized due to the usage of millimeter-wave wireless links. This paper designs an efficient scheduling algorithm which minimizes overlapping monitoring areas among observation satellite constellation. In order to achieve this objective, a quantum optimization based algorithm is used because the overlapping can be mathematically modelled via a max-weight independent set (MWIS) problem which is one of well-known NP-hard problems.

eess.SY↗

arXiv2021

Quantum Neural Networks: Concepts, Applications, and Challenges

Quantum deep learning is a research field for the use of quantum computing techniques for training deep neural networks. The research topics and directions of deep learning and quantum computing have been separated for long time, however by discovering that quantum circuits can act like artificial neural networks, quantum deep learning research is widely adopted. This paper explains the backgrounds and basic principles of quantum deep learning and also introduces major achievements. After that, this paper discusses the challenges of quantum deep learning research in multiple perspectives. Lastly, this paper presents various future research directions and application fields of quantum deep learning.

quant-ph↗

arXiv2021

Distributed and Autonomous Aerial Data Collection in Smart City Surveillance Applications

The massive growth of Smart City and Internet of Things applications enables safety and security. The data those are produced from surveillance cameras in aerial devices such as unmanned aerial networks (UAVs) are needed to be transferred to ground stations for secure data analysis. When the scale of network is relatively large compare to the wireless communication coverage of device, it is not always available to transmit the data to the ground stations, thus distributed and autonomous algorithms are essentially desired. Based on the needs, we propose a novel algorithm that is for collecting surveillance data under the consideration of mobility and flexibility of UAV networks. Due to the battery limitation in UAVs, we selectively collect data from the UAVs by setting rules under the consideration of distance and similarity. As a sequence, the UAV devices have to compete for a chance to get data processing. For this purpose, this paper designs a Myerson auction-based deep learning algorithm to leverage the UAV's revenue compare to traditional second-price auction while preserving truthfulness. Based on simulation results, we verify that our proposed algorithm achieves desired performance improvements.

eess.SP↗

arXiv2021

Trends in LEO Satellite Handover Algorithms

In this paper, we review well-known handovers algorithms in satellite environment. The modern research trends and contributions are proposed and summarized in order to overcome their considering problems in satellite-air-ground integrated network environment caused by the fast movement of Low Earth Orbit (LEO) satellite and related frequent handover occurrences.

cs.NI↗

arXiv2021

Trends in Blockchain and Federated Learning for Data Sharing in Distributed Platforms

With the development of communication technologies in 5G networks and the Internet of things (IoT), a massive amount of generated data can improve machine learning (ML) inference through data sharing. However, security and privacy concerns are major obstacles in distributed and wireless networks. In addition, IoT has a limitation on system resources depending on the purpose of services. In addition, a blockchain technology enables secure transactions among participants through consensus algorithms and encryption without a centralized coordinator. In this paper, we first review the federated leaning (FL) and blockchain mechanisms, and then, present a survey on the integration of blockchain and FL for data sharing in industrial, vehicle, and healthcare applications.

cs.CR↗

arXiv2021

Secure Aerial Surveillance using Split Learning

Personal monitoring devices such as cyclist helmet cameras to record accidents or dash cams to catch collisions have proliferated, with more companies producing smaller and compact recording gadgets. As these devices are becoming a part of citizens' everyday arsenal, concerns over the residents' privacy are progressing. Therefore, this paper presents SASSL, a secure aerial surveillance drone using split learning to classify whether there is a presence of a fire on the streets. This innovative split learning method transfers CCTV footage captured with a drone to a nearby server to run a deep neural network to detect a fire's presence in real-time without exposing the original data. We devise a scenario where surveillance UAVs roam around the suburb, recording any unnatural behavior. The UAV can process the recordings through its on-mobile deep neural network system or transfer the information to a server. Due to the resource limitations of mobile UAVs, the UAV does not have the capacity to run an entire deep neural network on its own. This is where the split learning method comes in handy. The UAV runs the deep neural network only up to the first hidden layer and sends only the feature map to the cloud server, where the rest of the deep neural network is processed. By ensuring that the learning process is divided between the UAV and the server, the privacy of raw data is secured while the UAV does not overexert its minimal resources.

cs.DC↗

arXiv2021

Joint Mobile Charging and Coverage-Time Extension for Unmanned Aerial Vehicles

In modern networks, the use of drones as mobile base stations (MBSs) has been discussed for coverage flexibility. However, the realization of drone-based networks raises several issues. One of the critical issues is drones are extremely power-hungry. To overcome this, we need to characterize a new type of drones, so-called charging drones, which can deliver energy to MBS drones. Motivated by the fact that the charging drones also need to be charged, we deploy ground-mounted charging towers for delivering energy to the charging drones. We introduce a new energy-efficiency maximization problem, which is partitioned into two independently separable tasks. More specifically, as our first optimization task, two-stage charging matching is proposed due to the inherent nature of our network model, where the first matching aims to schedule between charging towers and charging drones while the second matching solves the scheduling between charging drones and MBS drones. We analyze how to convert the formulation containing non-convex terms to another one only with convex terms. As our second optimization task, each MBS drone conducts energy-aware time-average transmit power allocation minimization subject to stability via Lyapunov optimization. Our solutions enable the MBS drones to extend their lifetimes; in turn, network coverage-time can be extended.

eess.SY↗

arXiv2021

Attention-based Reinforcement Learning for Real-Time UAV Semantic Communication

In this article, we study the problem of air-to-ground ultra-reliable and low-latency communication (URLLC) for a moving ground user. This is done by controlling multiple unmanned aerial vehicles (UAVs) in real time while avoiding inter-UAV collisions. To this end, we propose a novel multi-agent deep reinforcement learning (MADRL) framework, coined a graph attention exchange network (GAXNet). In GAXNet, each UAV constructs an attention graph locally measuring the level of attention to its neighboring UAVs, while exchanging the attention weights with other UAVs so as to reduce the attention mismatch between them. Simulation results corroborates that GAXNet achieves up to 4.5x higher rewards during training. At execution, without incurring inter-UAV collisions, GAXNet achieves 6.5x lower latency with the target 0.0000001 error rate, compared to a state-of-the-art baseline framework.

cs.MA↗

arXiv2021

Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games

In real-time strategy (RTS) game artificial intelligence research, various multi-agent deep reinforcement learning (MADRL) algorithms are widely and actively used nowadays. Most of the research is based on StarCraft II environment because it is the most well-known RTS games in world-wide. In our proposed MADRL-based algorithm, distributed MADRL is fundamentally used that is called QMIX. In addition to QMIX-based distributed computation, we consider state categorization which can reduce computational complexity significantly. Furthermore, self-attention mechanisms are used for identifying the relationship among agents in the form of graphs. Based on these approaches, we propose a categorized state graph attention policy (CSGA-policy). As observed in the performance evaluation of our proposed CSGA-policy with the most well-known StarCraft II simulation environment, our proposed algorithm works well in various settings, as expected.

cs.AI↗

arXiv2021

Visualization of Deep Reinforcement Autonomous Aerial Mobility Learning Simulations

This demo abstract presents the visualization of deep reinforcement learning (DRL)-based autonomous aerial mobility simulations. In order to implement the software, Unity-RL is used and additional buildings are introduced for urban environment. On top of the implementation, DRL algorithms are used and we confirm it works well in terms of trajectory and 3D visualization.

cs.RO↗

arXiv2021

Contra-*: Mechanisms for Countering Spam Attacks on Blockchain's Memory Pools

Blockchain-based cryptocurrencies, such as Bitcoin, have seen on the rise in their popularity and value, making them a target to several forms of Denial-of-Service (DoS) attacks, and calling for a better understanding of their attack surface from both security and distributed systems standpoints. In this paper, and in the pursuit of understanding the attack surface of blockchains, we explore a new form of attack that can be carried out on the memory pools (mempools) and mainly targets blockchain-based cryptocurrencies. We study this attack on Bitcoin mempool and explore the attack effects on transactions fee paid by benign users. To counter this attack, this paper further proposes Contra-*:, a set of countermeasures utilizing fee, age, and size (thus, Contra-F, Contra-A, and Contra-S) as prioritization mechanisms. Contra-*: optimize the mempool size and help in countering the effects of DoS attacks due to spam transactions. We evaluate Contra-* by simulations and analyze their effectiveness under various attack conditions.

cs.CR↗

arXiv2020

Kirchhoff's Circuit Law Applications to Graph Simplification in Search Problems

This paper proposes a new analysis of graph using the concept of electric potential, and also proposes a graph simplification method based on this analysis. Suppose that each node in the weighted-graph has its respective potential value. Furthermore, suppose that the start and terminal nodes in graphs have maximum and zero potentials, respectively. When we let the level of each node be defined as the minimum number of edges/hops from the start node to the node, the proper potential of each level can be estimated based on geometric proportionality relationship. Based on the estimated potential for each level, we can re-design the graph for path-finding problems to be the electrical circuits, thus Kirchhoff's Circuit Law can be directed applicable for simplifying the graph for path-finding problems.

cs.DM↗

arXiv2020

On the Performance of Generative Adversarial Network (GAN) Variants: A Clinical Data Study

Generative Adversarial Network (GAN) is a useful type of Neural Networks in various types of applications including generative models and feature extraction. Various types of GANs are being researched with different insights, resulting in a diverse family of GANs with a better performance in each generation. This review focuses on various GANs categorized by their common traits.

cs.NE↗

arXiv2020

Economic Theoretic LEO Satellite Coverage Control: An Auction-based Framework

Recently, ultra-dense low earth orbit (LEO) satelliteconstellation over high-frequency bands has considered as one ofpromising solutions to supply coverage all over the world. Givensatellite constellations, efficient beam coverage schemes should beemployed at satellites to provide seamless services and full-viewcoverage. In LEO systems, hybrid wide and spot beam coverageschemes are generally used, where the LEO provides a widebeam for large area coverage and additional several steering spotbeams for high speed data access. In this given setting, schedulingmultiple spot beams is essentially required. In order to achievethis goal, Vickery-Clarke-Groves (VCG) auction-based trustfulalgorithm is proposed in this paper for scheduling multiple spotbeams for more efficient seamless services and full-view coverage.

cs.NI↗

arXiv2020

Reinforced Edge Selection using Deep Learning for Robust Surveillance in Unmanned Aerial Vehicles

In this paper, we propose a novel deep Q-network (DQN)-based edge selection algorithm designed specifically for real-time surveillance in unmanned aerial vehicle (UAV) networks. The proposed algorithm is designed under the consideration of delay, energy, and overflow as optimizations to ensure real-time properties while striking a balance for other environment-related parameters. The merit of the proposed algorithm is verified via simulation-based performance evaluation.

cs.DC↗