arXiv subjects

Koji Yamamoto

Publications and source records attributed to Koji Yamamoto.

36 records · Page 2Linked to original sources

arXiv2020

Transfer Learning-Based Received Power Prediction with Ray-tracing Simulation and Small Amount of Measurement Data

This paper proposes a method to predict received power in urban area deterministically, which can learn a prediction model from small amount of measurement data by a simulation-aided transfer learning and data augmentation. Recent development in machine learning such as artificial neural network (ANN) enables us to predict radio propagation and path loss accurately. However, training a high-performance ANN model requires a significant number of data, which are difficult to obtain in real environments. The main motivation for this work was to facilitate accurate prediction using small amount of measurement data. To this end, we propose a transfer learning-based prediction method with data augmentation. The proposed method pre-trains a prediction model using data generated from ray-tracing simulations, increases the number of data using simulation-assisted data augmentation, and then fine-tunes a model using the augmented data to fit the target environment. Experiments using Wi-Fi devices were conducted, and the results demonstrate that the proposed method predicts received power with 50% (or less) of the RMS error of conventional methods.

cs.NI↗

arXiv2020

Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning

Federated learning (FL) enables a neural network (NN) to be trained using privacy-sensitive data on mobile devices while retaining all the data on their local storages. However, FL asks the mobile devices to perform heavy communication and computation tasks, i.e., devices are requested to upload and download large-volume NN models and train them. This paper proposes a novel unsupervised pre-training method adapted for FL, which aims to reduce both the communication and computation costs through model compression. Since the communication and computation costs are highly dependent on the volume of NN models, reducing the volume without decreasing model performance can reduce these costs. The proposed pre-training method leverages unlabeled data, which is expected to be obtained from the Internet or data repository much more easily than labeled data. The key idea of the proposed method is to obtain a ``good'' subnetwork from the original NN using the unlabeled data based on the lottery hypothesis. The proposed method trains an original model using a denoising auto encoder with the unlabeled data and then prunes small-magnitude parameters of the original model to generate a small but good subnetwork. The proposed method is evaluated using an image classification task. The results show that the proposed method requires 35\% less traffic and computation time than previous methods when achieving a certain test accuracy.

cs.NI↗

arXiv2020

Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise

Over-the-air computation (AirComp)-based federated learning (FL) enables low-latency uploads and the aggregation of machine learning models by exploiting simultaneous co-channel transmission and the resultant waveform superposition. This study aims at realizing secure AirComp-based FL against various privacy attacks where malicious central servers infer clients' private data from aggregated global models. To this end, a differentially private AirComp-based FL is designed in this study, where the key idea is to harness receiver noise perturbation injected to aggregated global models inherently, thereby preventing the inference of clients' private data. However, the variance of the inherent receiver noise is often uncontrollable, which renders the process of injecting an appropriate noise perturbation to achieve a desired privacy level quite challenging. Hence, this study designs transmit power control across clients, wherein the received signal level is adjusted intentionally to control the noise perturbation levels effectively, thereby achieving the desired privacy level. It is observed that a higher privacy level requires lower transmit power, which indicates the tradeoff between the privacy level and signal-to-noise ratio (SNR). To understand this tradeoff more fully, the closed-form expressions of SNR (with respect to the privacy level) are derived, and the tradeoff is analytically demonstrated. The analytical results also demonstrate that among the configurable parameters, the number of participating clients is a key parameter that enhances the received SNR under the aforementioned tradeoff. The analytical results are validated through numerical evaluations.

cs.NI↗

arXiv2020

Adversarial Reinforcement Learning-based Robust Access Point Coordination Against Uncoordinated Interference

This paper proposes a robust adversarial reinforcement learning (RARL)-based multi-access point (AP) coordination method that is robust even against unexpected decentralized operations of uncoordinated APs. Multi-AP coordination is a promising technique towards IEEE 802.11be, and there are studies that use RL for multi-AP coordination. Indeed, a simple RL-based multi-AP coordination method diminishes the collision probability among the APs; therefore, the method is a promising approach to improve time-resource efficiency. However, this method is vulnerable to frame transmissions of uncoordinated APs that are less aware of frame transmissions of other coordinated APs. To help the central agent experience even such unexpected frame transmissions, in addition to the central agent, the proposed method also competitively trains an adversarial AP that disturbs coordinated APs by causing frame collisions intensively. Besides, we propose to exploit a history of frame losses of a coordinated AP to promote reasonable competition between the central agent and adversarial AP. The simulation results indicate that the proposed method can avoid uncoordinated interference and thereby improve the minimum sum of the throughputs in the system compared to not considering the uncoordinated AP.

cs.NI↗

arXiv2020

Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data

This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients without gathering their data to central systems. The data of mobile clients is typically non-IID owing to diversity among mobile clients' interests and usage, and FL with non-IID data could degrade the model performance. Therefore, to mitigate the degradation induced by non-IID data, we assume that a limited number (e.g., less than 1%) of clients allow their data to be uploaded to a server, and we propose a hybrid learning mechanism referred to as Hybrid-FL, wherein the server updates the model using the data gathered from the clients and aggregates the model with the models trained by clients. The Hybrid-FL solves both client- and data-selection problems via heuristic algorithms, which try to select the optimal sets of clients who train models with their own data, clients who upload their data to the server, and data uploaded to the server. The algorithms increase the number of clients participating in FL and make more data gather in the server IID, thereby improving the prediction accuracy of the aggregated model. Evaluations, which consist of network simulations and ML experiments, demonstrate that the proposed scheme achieves a 13.5% higher classification accuracy than those of the previously proposed schemes for the non-IID case.

cs.LG↗

arXiv2020

Communication-Efficient Multimodal Split Learning for mmWave Received Power Prediction

The goal of this study is to improve the accuracy of millimeter wave received power prediction by utilizing camera images and radio frequency (RF) signals, while gathering image inputs in a communication-efficient and privacy-preserving manner. To this end, we propose a distributed multimodal machine learning (ML) framework, coined multimodal split learning (MultSL), in which a large neural network (NN) is split into two wirelessly connected segments. The upper segment combines images and received powers for future received power prediction, whereas the lower segment extracts features from camera images and compresses its output to reduce communication costs and privacy leakage. Experimental evaluation corroborates that MultSL achieves higher accuracy than the baselines utilizing either images or RF signals. Remarkably, without compromising accuracy, compressing the lower segment output by 16x yields 16x lower communication latency and 2.8% less privacy leakage compared to the case without compression.

cs.NI↗

arXiv2019

Random Access with Opportunity Detection in Wireless Networks

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 interference causing collisions. Using stochastic geometry, we derive a fixed-point equation to provide the optimal transmission probability maximizing a proportionally fair throughput. Its approximated solution is given in closed form. The proposed MAC is applicable to full-duplex networks, leading to significant throughput improvement by allowing more nodes to transmit.

cs.NI↗

arXiv2019

One Pixel Image and RF Signal Based Split Learning for mmWave Received Power Prediction

Focusing on the received power prediction of millimeter-wave (mmWave) radio-frequency (RF) signals, we propose a multimodal split learning (SL) framework that integrates RF received signal powers and depth-images observed by physically separated entities. To improve its communication efficiency while preserving data privacy, we propose an SL neural network architecture that compresses the communication payload, i.e., images. Compared to a baseline solely utilizing RF signals, numerical results show that SL integrating only one pixel image with RF signals achieves higher prediction accuracy while maximizing both communication efficiency and privacy guarantees.

cs.NI↗

arXiv2019

Cooperative Sensing in Deep RL-Based Image-to-Decision Proactive Handover for mmWave Networks

For reliable millimeter-wave (mmWave) networks, this paper proposes cooperative sensing with multi-camera operation in an image-to-decision proactive handover framework that directly maps images to a handover decision. In the framework, camera images are utilized to allow for the prediction of blockage effects in a mmWave link, whereby a network controller triggers a handover in a proactive fashion. Furthermore, direct mapping allows for the scalability of the number of pedestrians. This paper experimentally investigates the feasibility of adopting cooperative sensing with multiple cameras that can compensate for one another's blind spots. The optimal mapping is learned via deep reinforcement learning to resolve the high dimensionality of images from multiple cameras. An evaluation based on experimentally obtained images and received powers verifies that a mapping that enhances channel capacity can be learned in a multi-camera operation. The results indicate that our proposed framework with multi-camera operation outperforms a conventional framework with single-camera operation in terms of the average capacity.

cs.NI↗

arXiv2019

Deep Reinforcement Learning-Based Channel Allocation for Wireless LANs with Graph Convolutional Networks

Last year, IEEE 802.11 Extremely High Throughput Study Group (EHT Study Group) was established to initiate discussions on new IEEE 802.11 features. Coordinated control methods of the access points (APs) in the wireless local area networks (WLANs) are discussed in EHT Study Group. The present study proposes a deep reinforcement learning-based channel allocation scheme using graph convolutional networks (GCNs). As a deep reinforcement learning method, we use a well-known method double deep Q-network. In densely deployed WLANs, the number of the available topologies of APs is extremely high, and thus we extract the features of the topological structures based on GCNs. We apply GCNs to a contention graph where APs within their carrier sensing ranges are connected to extract the features of carrier sensing relationships. Additionally, to improve the learning speed especially in an early stage of learning, we employ a game theory-based method to collect the training data independently of the neural network model. The simulation results indicate that the proposed method can appropriately control the channels when compared to extant methods.

eess.SP↗

arXiv2019

Deep-Reinforcement-Learning-Based Distributed Vehicle Position Controls for Coverage Expansion in mmWave V2X

In millimeter wave (mmWave) vehicular communications, multi-hop relay disconnection by line-of-sight (LOS) blockage is a critical problem, especially in the early diffusion phase of mmWave-available vehicles, where not all the vehicles have mmWave communication devices. This paper proposes a distributed position control method for autonomous vehicles to make long relays connecting to road side units (RSUs) by avoiding blockages to communicate with each other via LOS paths. Even though vehicles with the proposed method do not use the whole information of the environments and cooperate with each other, they can decide their action (e.g., lane change and overtaking) to form long relays using only information of its surroundings (e.g., surrounding vehicle positions). The decision-making problem is formulated as a Markov decision process so that autonomous vehicles can learn a practical movement strategy of making long relays by a reinforcement learning (RL) algorithm. This paper designs a learning algorithm based on a sophisticated deep reinforcement learning algorithm, asynchronous advantage actor-critic (A3C), which enables vehicles to learn a complex movement strategy quickly by its deepneural-network architecture and multi-agent-learning mechanism. Once the strategy is well trained, vehicles can distributedly move to positions where the long relay to the RSU is established. Simulations results confirm that the proposed method can increase the relay length and coverage even if the traffic conditions and penetration ratio of mmWave communication devices in learning and operation phases are different.

cs.NI↗

arXiv2019

Concurrent Transmission Scheduling for Perceptual Data Sharing in mmWave Vehicular Networks

Sharing perceptual data with other vehicles enhances the traffic safety of autonomous vehicles because it helps vehicles locate other vehicles and pedestrians in their blind spots. Such safety applications require high throughput and short delay, which cannot be achieved by conventional microwave vehicular communication systems. Therefore, millimeter-wave (mmWave) communications are considered to be a key technology for sharing perceptual data because of their wide bandwidth. One of the challenges of data sharing in mmWave communications is broadcasting because narrow-beam directional antennas are used to obtain high gain. Because many vehicles should share their perceptual data to others within a short time frame in order to enlarge the areas that can be perceived based on shared perceptual data, an efficient scheduling for concurrent transmission that improves spatial reuse is required for perceptual data sharing. This paper proposes a data sharing algorithm that employs a graph-based concurrent transmission scheduling. The proposed algorithm realizes concurrent transmission to improve spatial reuse by designing a rule that is utilized to determine if the two pairs of transmitters and receivers interfere with each other by considering the radio propagation characteristics of narrow-beam antennas. A prioritization method that considers the geographical information in perceptual data is also designed to enlarge perceivable areas in situations where data sharing time is limited and not all data can be shared. Simulation results demonstrate that the proposed algorithm doubles the area of the cooperatively perceivable region compared with a conventional algorithm that does not consider mmWave communications because the proposed algorithm achieves high-throughput transmission by improving spatial reuse. The prioritization also enlarges the perceivable region by a maximum of 20%.

cs.NI↗

arXiv2018

Proactive Received Power Prediction Using Machine Learning and Depth Images for mmWave Networks

This study demonstrates the feasibility of the proactive received power prediction by leveraging spatiotemporal visual sensing information toward the reliable millimeter-wave (mmWave) networks. Since the received power on a mmWave link can attenuate aperiodically due to a human blockage, the long-term series of the future received power cannot be predicted by analyzing the received signals before the blockage occurs. We propose a novel mechanism that predicts a time series of the received power from the next moment to even several hundred milliseconds ahead. The key idea is to leverage the camera imagery and machine learning (ML). The time-sequential images can involve the spatial geometry and the mobility of obstacles representing the mmWave signal propagation. ML is used to build the prediction model from the dataset of sequential images labeled with the received power in several hundred milliseconds ahead of when each image is obtained. The simulation and experimental evaluations using IEEE 802.11ad devices and a depth camera show that the proposed mechanism employing convolutional LSTM predicted a time series of the received power in up to 500 ms ahead at an inference time of less than 3 ms with a root-mean-square error of 3.5 dB.

cs.NI↗

arXiv2018

Asymptotic Analysis of Normalized SNR-Based Scheduling in Uplink Cellular Networks with Truncated Channel Inversion Power Control

This paper provides the signal-to-interference-plus-noise ratio (SINR) complimentary cumulative distribution function (CCDF) and average data rate of the normalized SNR-based scheduling in an uplink cellular network using stochastic geometry. The uplink analysis is essentially different from the downlink analysis in that the per-user transmit power control is performed and that the interferers are composed of at most one transmitting user in each cell other than the target cell. In addition, as the effect of multi-user diversity varies from cell to cell depending on the number of users involved in the scheduling, the distribution of the number of users is required to obtain the averaged performance of the scheduling. This paper derives the SINR CCDF relative to the typical scheduled user by focusing on two incompatible cases, where the scheduler selects a user from all the users in the corresponding Voronoi cell or does not select users near cell edges. In each case, the SINR CCDF is marginalized over the distribution of the number of users involved in the scheduling, which is asymptotically correct if the BS density is sufficiently large or small. Through the simulations, the accuracies of the analytical results are validated for both cases, and the scheduling gains are evaluated to confirm the multi-user diversity gain.

cs.IT↗

arXiv2017

Stochastic Geometry Analysis of Normalized SNR-Based Scheduling in Downlink Cellular Networks

The coverage probability and average data rate of normalized SNR-based scheduling in a downlink cellular network are derived by modeling the locations of the base stations and users as two independent Poison point processes. The scheduler selects the user with the largest instantaneous SNR normalized by the short-term average SNR. In normalized SNR scheduling, the coverage probability when the desired signal experiences Rayleigh fading is shown to be given by a series of Laplace transforms of the probability density function of interference. Also, a closed-form expression for the coverage probability is approximately achieved. The results confirm that normalized SNR scheduling increases the coverage probability due to the multi-user diversity gain.

cs.IT↗

arXiv2016

Efficient Call Path Detection for Android-OS Size of Huge Source Code

Today most developers utilize source code written by other parties. Because the code is modified frequently, the developers need to grasp the impact of the modification repeatedly. A call graph and especially its special type, a call path, help the developers comprehend the modification. Source code written by other parties, however, becomes too huge to be held in memory in the form of parsed data for a call graph or path. This paper offers a bidirectional search algorithm for a call graph of too huge amount of source code to store all parse results of the code in memory. It refers to a method definition in source code corresponding to the visited node in the call graph. The significant feature of the algorithm is the referenced information is used not in order to select a prioritized node to visit next but in order to select a node to postpone visiting. It reduces path extraction time by 8% for a case in which ordinary path search algorithms do not reduce the time.

cs.DS↗

arXiv2015

A Comprehensive Survey of Potential Game Approaches to Wireless Networks

Potential games form a class of non-cooperative games where unilateral improvement dynamics are guaranteed to converge in many practical cases. The potential game approach has been applied to a wide range of wireless network problems, particularly to a variety of channel assignment problems. In this paper, the properties of potential games are introduced, and games in wireless networks that have been proven to be potential games are comprehensively discussed.

cs.GT↗

arXiv2014

Analysis and Design Specifications for Full-Duplex Radio Transceivers under RF Oscillator Phase-Noise with Arbitrary Spectral Shape

In this paper, the effects of oscillator phase-noise with arbitrary spectral characteristics on self-interference cancellation capability of a full-duplex radio transceiver are addressed, and design considerations are given for oscillator designers for optimized PLL design for full-duplex radio application. The paper first gives a full-duplex transceiver model that inherently mitigates most of the phase-noise effect from the self-interference signal. The remaining effect of the phase noise is then analysed. Closed-form solutions for the self-interference power are then derived. In the simulations part, a practical phase-locked loop type oscillator is used, which is based on the arbitrary mask phase-noise model. Analytical derivations are verified with the simulations, and the self-interference cancellation performance is thoroughly studied with various parameters. Design considerations are finally given for oscillator design for full-duplex radio transceivers, with the help of tangible parameters of the phase-locked loop type oscillators.

cs.IT↗