arXiv subjects

Soyi Jung

Publications and source records attributed to Soyi Jung.

48 records · Page 3Linked to original sources

arXiv2021

Spatio-Temporal Split Learning for Autonomous Aerial Surveillance using Urban Air Mobility (UAM) Networks

Autonomous surveillance unmanned aerial vehicles (UAVs) are deployed to observe the streets of the city for any suspicious activities. This paper utilizes surveillance UAVs for the purpose of detecting the presence of a fire in the streets. An extensive database is collected from UAV surveillance drones. With the aid of artificial intelligence (AI), fire stations can swiftly identify the presence of a fire emerging in the neighborhood. Spatio-temporal split learning is applied to this scenario to preserve privacy and globally train a fire classification model. Fires are hazardous natural disasters that can spread very quickly. Swift identification of fire is required to deploy firefighters to the scene. In order to do this, strong communication between the UAV and the central server where the deep learning process occurs is required. Improving communication resilience is integral to enhancing a safe experience on the roads. Therefore, this paper explores the adequate number of clients and data ratios for split learning in this UAV setting, as well as the required network infrastructure.

cs.CV↗

arXiv2021

Stable Marriage Matching for Traffic-Aware Space-Air-Ground Integrated Networks: A Gale-Shapley Algorithmic Approach

In keeping with the rapid development of communication technology, a new communication structure is required in a next-generation communication system. In particular, research using High Altitude Platform (HAP) or Unmanned Aerial Vehicle(UAV) in existing terrestrial networks is active. In this paper, we propose matching HAP and UAV using the Gale-Shapley algorithm in a relay communication situation. The numerical simulation results demonstrate that applying the Gale-Shapley algorithm shows superior performance compared to random matching.

eess.SY↗

arXiv2021

Spatio-Temporal Split Learning for Privacy-Preserving Medical Platforms: Case Studies with COVID-19 CT, X-Ray, and Cholesterol Data

Machine learning requires a large volume of sample data, especially when it is used in high-accuracy medical applications. However, patient records are one of the most sensitive private information that is not usually shared among institutes. This paper presents spatio-temporal split learning, a distributed deep neural network framework, which is a turning point in allowing collaboration among privacy-sensitive organizations. Our spatio-temporal split learning presents how distributed machine learning can be efficiently conducted with minimal privacy concerns. The proposed split learning consists of a number of clients and a centralized server. Each client has only has one hidden layer, which acts as the privacy-preserving layer, and the centralized server comprises the other hidden layers and the output layer. Since the centralized server does not need to access the training data and trains the deep neural network with parameters received from the privacy-preserving layer, privacy of original data is guaranteed. We have coined the term, spatio-temporal split learning, as multiple clients are spatially distributed to cover diverse datasets from different participants, and we can temporally split the learning process, detaching the privacy preserving layer from the rest of the learning process to minimize privacy breaches. This paper shows how we can analyze the medical data whilst ensuring privacy using our proposed multi-site spatio-temporal split learning algorithm on Coronavirus Disease-19 (COVID-19) chest Computed Tomography (CT) scans, MUsculoskeletal RAdiographs (MURA) X-ray images, and cholesterol levels.

cs.LG↗

arXiv2021

Trends in Neural Architecture Search: Towards the Acceleration of Search

In modern deep learning research, finding optimal (or near optimal) neural network models is one of major research directions and it is widely studied in many applications. In this paper, the main research trends of neural architecture search (NAS) are classified as neuro-evolutionary algorithms, reinforcement learning based algorithms, and one-shot architecture search approaches. Furthermore, each research trend is introduced and finally all the major three trends are compared. Lastly, the future research directions of NAS research trends are discussed.

cs.LG↗

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

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

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

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

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↗