arXiv subjects
Publications and source records attributed to Joongheon Kim.
This paper proposes a method of extracting an RGB-D image usingAzure Kinect, a depth camera, creating afragment,i.e., 6D images (RGBXYZ), usingOpen3D, creatingit as a point cloud object, and implementing webVR usingthree.js. Furthermore, it presents limitations and potentials for development.
Convolutional Neural Network (CNN) is a popular model in computer vision and has the advantage of making good use of the correlation information of data. However, CNN is challenging to learn efficiently if the given dimension of data or model becomes too large. Quantum Convolutional Neural Network (QCNN) provides a new solution to a problem to solve with CNN using a quantum computing environment, or a direction to improve the performance of an existing learning model. The first study to be introduced proposes a model to effectively solve the classification problem in quantum physics and chemistry by applying the structure of CNN to the quantum computing environment. The research also proposes the model that can be calculated with O(log(n)) depth using Multi-scale Entanglement Renormalization Ansatz (MERA). The second study introduces a method to improve the model's performance by adding a layer using quantum computing to the CNN learning model used in the existing computer vision. This model can also be used in small quantum computers, and a hybrid learning model can be designed by adding a quantum convolution layer to the CNN model or replacing it with a convolution layer. This paper also verifies whether the QCNN model is capable of efficient learning compared to CNN through training using the MNIST dataset through the TensorFlow Quantum platform.
This paper proposes a quantum approximate optimization algorithm (QAOA) method for wireless scheduling problems. The QAOA is one of the promising hybrid quantum-classical algorithms for many applications and it provides highly accurate optimization solutions in NP-hard problems. QAOA maps the given problems into Hilbert spaces, and then it generates Hamiltonian for the given objectives and constraints. Then, QAOA finds proper parameters from classical optimization approaches in order to optimize the expectation value of generated Hamiltonian. Based on the parameters, the optimal solution to the given problem can be obtained from the optimum of the expectation value of Hamiltonian. Inspired by QAOA, a quantum approximate optimization for scheduling (QAOS) algorithm is proposed. First of all, this paper formulates a wireless scheduling problem using maximum weight independent set (MWIS). Then, for the given MWIS, the proposed QAOS designs the Hamiltonian of the problem. After that, the iterative QAOS sequence solves the wireless scheduling problem. This paper verifies the novelty of the proposed QAOS via simulations implemented by Cirq and TensorFlow-Quantum.
Developing agents that can perform challenging complex tasks is the goal of reinforcement learning. The model-free reinforcement learning has been considered as a feasible solution. However, the state of the art research has been to develop increasingly complicated techniques. This increasing complexity makes the reconstruction difficult. Furthermore, the problem of reward dependency is still exists. As a result, research on imitation learning, which learns policy from a demonstration of experts, has begun to attract attention. Imitation learning directly learns policy based on data on the behavior of the experts without the explicit reward signal provided by the environment. However, imitation learning tries to optimize policies based on deep reinforcement learning such as trust region policy optimization. As a result, deep reinforcement learning based imitation learning also poses a crisis of reproducibility. The issue of complex model-free model has received considerable critical attention. A derivative-free optimization based reinforcement learning and the simplification on policies obtain competitive performance on the dynamic complex tasks. The simplified policies and derivative free methods make algorithm be simple. The reconfiguration of research demo becomes easy. In this paper, we propose an imitation learning method that takes advantage of the derivative-free optimization with simple linear policies. The proposed method performs simple random search in the parameter space of policies and shows computational efficiency. Experiments in this paper show that the proposed model, without a direct reward signal from the environment, obtains competitive performance on the MuJoCo locomotion tasks.
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 essential to cater for high ML inference accuracy at scale under time-varying channel and network dynamics, by continuously exchanging fresh data and ML model updates in a distributed way. Taming this new kind of data traffic boils down to improving the communication efficiency of distributed learning by optimizing communication payload types, transmission techniques, and scheduling, as well as ML architectures, algorithms, and data processing methods. To this end, this article aims to provide a holistic overview of relevant communication and ML principles, and thereby present communication-efficient and distributed learning frameworks with selected use cases.
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 novel one-shot FL framework, termed XorMixFL. The core idea is to collect other devices' encoded data samples that are decoded only using each device's own data samples. The decoding provides synthetic-but-realistic samples until inducing an IID dataset, used for model training. Both encoding and decoding procedures follow the bit-wise XOR operations that intentionally distort raw samples, thereby preserving data privacy. Simulation results corroborate that XorMixFL achieves up to 17.6% higher accuracy than Vanilla FL under a non-IID MNIST dataset.
This paper comprehensively studies a content-centric mobile network based on a preference learning framework, where each mobile user is equipped with a finite-size cache. We consider a practical scenario where each user requests a content file according to its own preferences, which is motivated by the existence of heterogeneity in file preferences among different users. Under our model, we consider a single-hop-based device-to-device (D2D) content delivery protocol and characterize the average hit ratio for the following two file preference cases: the personalized file preferences and the common file preferences. By assuming that the model parameters such as user activity levels, user file preferences, and file popularity are unknown and thus need to be inferred, we present a collaborative filtering (CF)-based approach to learn these parameters. Then, we reformulate the hit ratio maximization problems into a submodular function maximization and propose two computationally efficient algorithms including a greedy approach to efficiently solve the cache allocation problems. We analyze the computational complexity of each algorithm. Moreover, we analyze the corresponding level of the approximation that our greedy algorithm can achieve compared to the optimal solution. Using a real-world dataset, we demonstrate that the proposed framework employing the personalized file preferences brings substantial gains over its counterpart for various system parameters.
In wireless caching networks, a user generally has a concrete purpose of consuming contents in a certain preferred category, and requests multiple contents in sequence. While most existing research on wireless caching and delivery has focused only on one-shot requests, the popularity distribution of contents requested consecutively is definitely different from the one-shot request and has been not considered. Also, especially from the perspective of the service provider, it is advantageous for users to consume as many contents as possible. Thus, this paper proposes two cache allocation policies for categorized contents and consecutive user demands, which maximize 1) the cache hit rate and 2) the number of consecutive content consumption, respectively. Numerical results show how categorized contents and consecutive content requests have impacts on the cache allocation.
For downlink multiple-user (MU) transmission based on non-orthogonal multiple access (NOMA), the advanced receiver strategy is required to cancel the inter-user interference, e.g., successive interference cancellation (SIC). The SIC process can be applicable only when information about the co-scheduled signal is known at the user terminal (UT) side. In particular, the UT should know whether the received signal is OMA or NOMA, whether SIC is required or not, and which modulation orders and power ratios have been used for the superposed UTs, before decoding the signal. An efficient network, e.g., vehicular network, requires that the UTs blindly classify the received signal and apply a matching receiver strategy to reduce the high-layer signaling overhead which is essential for high-mobility vehicular networks. In this paper, we first analyze the performance impact of errors in NOMA signal classification and address ensuing receiver challenges in practical MU usage cases. In order to reduce the blind signal classification error rate, we propose transmission schemes that rotate data symbols or pilots to a specific phase according to the transmitted signal format. In the case of pilot rotation, a new signal classification algorithm is also proposed. The performance improvements by the proposed methods are verified by intensive simulation results.
This demo abstract introduces a new light-weight programming language koa which is suitable for blockchain system design and implementation. In this abstract, the basic features of koa are introduced including working system (with playground), architecture, and virtual machine operations. Rum-time execution of software implemented by koa will be presented during the session.
This paper proposes a distributed deep learning framework for privacy-preserving medical data training. In order to avoid patients' data leakage in medical platforms, the hidden layers in the deep learning framework are separated and where the first layer is kept in platform and others layers are kept in a centralized server. Whereas keeping the original patients' data in local platforms maintain their privacy, utilizing the server for subsequent layers improves learning performance by using all data from each platform during training.
State-of-the-art drone technologies have severe flight time limitations due to weight constraints, which inevitably lead to a relatively small amount of available energy. Therefore, frequent battery replacement or recharging is necessary in applications such as delivery, exploration, or support to the wireless infrastructure. Mobile charging stations (i.e., mobile stations with charging equipment) for outdoor ad-hoc battery charging is one of the feasible solutions to address this issue. However, the ability of these platforms to charge the drones is limited in terms of the number and charging time. This paper designs an auction-based mechanism to control the charging schedule in multi-drone setting. In this paper, charging time slots are auctioned, and their assignment is determined by a bidding process. The main challenge in developing this framework is the lack of prior knowledge on the distribution of the number of drones participating in the auction. Based on optimal second-price-auction, the proposed formulation, then, relies on deep learning algorithms to learn such distribution online. Numerical results from extensive simulations show that the proposed deep learning-based approach provides effective battery charging control in multi-drone scenarios.
Millimeter-wave (mmWave) base station can offer abundant high capacity channel resources toward connected vehicles so that quality-of-service (QoS) of them in terms of downlink throughput can be highly improved. The mmWave base station can operate among existing base stations (e.g., macro-cell base station) on non-overlapped channels among them and the vehicles can make decision what base station to associate, and what channel to utilize on heterogeneous networks. Furthermore, because of the non-omni property of mmWave communication, the vehicles decide how to align the beam direction toward mmWave base station to associate with it. However, such joint problem requires high computational cost, which is NP-hard and has combinatorial features. In this paper, we solve the problem in 3-tier heterogeneous vehicular network (HetVNet) with multi-agent deep reinforcement learning (DRL) in a way that maximizes expected total reward (i.e., downlink throughput) of vehicles. The multi-agent deep deterministic policy gradient (MADDPG) approach is introduced to achieve optimal policy in continuous action domain.
In wireless caching networks, the design of the content delivery method must consider random user requests, caching states, network topology, and interference management. In this paper, we establish a general framework for content delivery in wireless caching networks without stringent assumptions that restrict the network structure, delivery link, and interference model. Based on the framework, we propose a dynamic and distributed link scheduling and power allocation scheme for content delivery that is assisted by belief-propagation (BP) algorithms. Considering content-requesting users and potential caching nodes, the scheme achieves three critical purposes of wireless caching networks: 1) limiting the delay of user request satisfactions, 2) maintaining the power efficiency of caching nodes, and 3) managing interference among users. In addition, we address the intrinsic problem of the BP algorithm in our network model, proposing a matching algorithm for one-to-one link scheduling. Simulation results show that the proposed scheme provides almost the same delay performance as the optimal scheme found through an exhaustive search at the expense of a little additional power consumption and does not require a clustering method and orthogonal resources in a large-scale D2D network.
The average accuracy is one of major evaluation metrics for classification systems, while the accuracy deviation is another important performance metric used to evaluate various deep neural networks. In this paper, we present a new ensemble-like fast deep neural network, Harmony, that can reduce the accuracy deviation among categories without degrading overall average accuracy. Harmony consists of three sub-models, namely, Target model, Complementary model, and Conductor model. In Harmony, an object is classified by using either Target model or Complementary model. Target model is a conventional classification network for general categories, while Complementary model is a classification network especially for weak categories that are inaccurately classified by Target model. Conductor model is used to select one of two models. Experimental results demonstrate that Harmony accurately classifies categories, while it reduces the accuracy deviation among the categories.
The rapid increase of diverse Internet of things (IoT) services and devices has raised numerous challenges in terms of connectivity, computation, and security, which networks must face in order to provide satisfactory support. This has led to networks evolving into heterogeneous IoT networking infrastructures characterized by multiple access technologies and mobile edge computing (MEC) capabilities. The heterogeneity of the networks, devices, and services introduces serious vulnerabilities to security attacks, especially distributed denial-of-service (DDoS) attacks, which exploit massive IoT devices to exhaust both network and victim resources. As such, this study proposes MECshield, a localized DDoS prevention framework leveraging MEC power to deploy multiple smart filters at the edge of relevant attack-source/destination networks. The cooperation among the smart filters is supervised by a central controller. The central controller localizes each smart filter by feeding appropriate training parameters into its self-organizing map (SOM) component, based on the attacking behavior. The performance of the MECshield framework is verified using three typical IoT traffic scenarios. The numerical results reveal that MECshield outperforms existing solutions.
With the evolution of various advanced driver assistance system (ADAS) platforms, the design of autonomous driving system is becoming more complex and safety-critical. The autonomous driving system simultaneously activates multiple ADAS functions; and thus it is essential to coordinate various ADAS functions. This paper proposes a randomized adversarial imitation learning (RAIL) method that imitates the coordination of autonomous vehicle equipped with advanced sensors. The RAIL policies are trained through derivative-free optimization for the decision maker that coordinates the proper ADAS functions, e.g., smart cruise control and lane keeping system. Especially, the proposed method is also able to deal with the LIDAR data and makes decisions in complex multi-lane highways and multi-agent environments.
This paper proposes a video delivery strategy for dynamic streaming services which maximizes time-average streaming quality under a playback delay constraint in wireless caching networks. The network where popular videos encoded by scalable video coding are already stored in randomly distributed caching nodes is considered under adaptive video streaming concepts, and distance-based interference management is investigated in this paper. In this network model, a streaming user makes delay-constrained decisions depending on stochastic network states: 1) caching node for video delivery, 2) video quality, and 3) the quantity of video chunks to receive. Since wireless link activation for video delivery may introduce delays, different timescales for updating caching node association, video quality adaptation, and chunk amounts are considered. After associating with a caching node for video delivery, the streaming user chooses combinations of quality and chunk amounts in the small timescale. The dynamic decision making process for video quality and chunk amounts at each slot is modeled using Markov decision process, and the caching node decision is made based on the framework of Lyapunov optimization. Our intensive simulations verify that the proposed video delivery algorithm works reliably and also can control the tradeoff between video quality and playback latency.