詳細

水谷　后宏 （ミズタニ　キミヒロ）

  • 情報学部 情報学科　准教授
Last Updated :2024/05/19

コミュニケーション情報 byコメンテータガイド

  • コメント

    膨大なデータを効率的に管理・解析するためのシステムやその利活用方法に関する研究を行っております。企業出身のため、基礎的な研究成果だけでなく実用的な成果の創出を目指しております。

研究者情報

学位

  • 博士（工学）（2015年09月 奈良先端科学技術大学院大学）

ホームページURL

J-Global ID

プロフィール

  • 2005 年同志社大学知識工学科入学．2008 年に同大学を退学し，奈良先端科学技術大学院大学情報科学研究科に飛び級入学．2010 年同大学院を修了し，NTTに入社（先端技術総合研究所未来ねっと研究所に配属）．2018年よりNTT西日本技術革新部(主査)．2019年より近畿大学理工学部情報学科講師．2023年4月より同大学情報学部情報学科准教授．NTT在職中の2014年-2015年にかけて博士(工学)を短期取得．電子情報通信学会会員．


研究キーワード

  • データセンタネットワーク   情報ネットワーク   IoT   人工知能   オーバレイネットワーク   

現在の研究分野（キーワード）

    膨大なデータを効率的に管理・解析するためのシステムやその利活用方法に関する研究を行っております。企業出身のため、基礎的な研究成果だけでなく実用的な成果の創出を目指しております。

研究分野

  • 情報通信 / 情報ネットワーク

経歴

  • 2023年04月 - 現在  近畿大学情報学部准教授
  • 2021年01月 - 現在  近畿大学情報学研究所
  • 2020年04月 - 現在  近畿大学大学院 総合理工学研究科Senior Assistant Professor/Lecturer
  • 2022年04月 - 2023年03月  近畿大学情報学部情報学科講師
  • 2019年04月 - 2022年03月  近畿大学理工学部情報学科講師
  • 2018年04月 - 2019年03月  NTT西日本技術革新部主査
  • 2010年04月 - 2018年03月  NTT未来ねっと研究所研究員
  • 2008年09月 - 2009年03月  IPA 未踏ユースプロジェクトチーフクリエータ

学歴

  • 2014年10月 - 2015年09月   奈良先端科学技術大学院大学   情報科学研究科   博士後期課程
  • 2008年04月 - 2010年03月   奈良先端科学技術大学院大学   情報科学研究科   博士前期課程
  • 2005年04月 - 2008年03月   同志社大学   工学部   大学院への飛び級のため退学

所属学協会

  • IEEE   日本ソフトウェア科学会   電子情報通信学会   

研究活動情報

論文

  • Daisuke Hanamitsu; Kimihiro Mizutani
    IEEJ Transactions on Electrical and Electronic Engineering 2024年05月 [査読有り]
  • Shoma Kitagawa; Kimihiro Mizutani
    2023 Fourteenth International Conference on Mobile Computing and Ubiquitous Network (ICMU) 2023年11月 [査読有り]
  • Shunsuke Nakagawa; Kimihiro Mizutani
    2023 Fourteenth International Conference on Mobile Computing and Ubiquitous Network (ICMU) 2023年11月 [査読有り]
  • Eigo Yamamoto; Kimihiro Mizutani
    2023 IEEE 12th Global Conference on Consumer Electronics (GCCE) 2023年10月 [査読有り]
  • Toru Mano; Takeru Inoue; Kimihiro Mizutani; Osamu Akashi
    IEEE Transactions on Network and Service Management 20 3 2558 - 2574 2023年09月 [査読有り]
  • Tomoki Tokunaga; Kimihiro Mizutani
    Sensors 22 5 1930 - 1930 2022年03月
  • Kimihiro Mizutani
    Sensors 22 2 611 - 611 2022年01月 [査読有り]
  • Mamoru Kawaguchi; Kimihiro Mizutani; Nobukazu Iguchi
    International Conference on Emerging Technologies for Communications 2022年 [査読有り]
  • A Novel Automatic Checkout System without Relearning Additional Item Information
    Daisuke Hanamitsu; Kimihiro Mizutani
    International Conference on Emerging Technologies for Communications 2022年 [査読有り]
  • Toshiki Kawakita; Kimihiro Mizutani; Satoru Kobayashi; Kensuke Fukuda; Osamu Akashi
    International Conference on Emerging Technologies for Communications 2022年 [査読有り]
  • Masaya Suzuki; Kimihiro Mizutani; Satoru Kobayashi; Kensuke Fukuda; Osamu Akashi
    International Conference on Emerging Technologies for Communications 2022年 [査読有り]
  • A Fuel Cost-less Bus Driver Allocation through Bus IoT Data Analysis
    Riku Miura; Kimihiro Mizutani
    International Conference on Emerging Technologies for Communications 2022年 [査読有り]
  • Daisuke Hanamitsu; Kimihiro Mizutani; Satoru Kobayashi; Kensuke Fukuda; Osamu Akashi
    International Conference on Emerging Technologies for Communications 2021年 [査読有り]
  • Issei Komeda; Kimihiro Mizutani
    International Conference on Emerging Technologies for Communications 2021年 [査読有り]
  • Kazuki Otomo; Satoru Kobayashi; Kensuke Fukuda; Osamu Akashi; Kimihiro Mizutani; Hiroshi Esaki
    IEEE 45th Annual Computers, Software, and Applications Conference(COMPSAC) 1443 - 1448 2021年 [査読有り]
  • Kimihiro Mizutani
    IEEE Access 9 88737 - 88745 2021年 [査読有り]
  • Masaya Suzuki; Kimihiro Mizutani
    IEICE Communications Express 2021年 [査読有り]
  • Tomoki Tokunaga; Kimihiro Mizutani
    IEICE Communications Express 2021年 [査読有り]
  • Kimihiro Mizutani
    IEICE Communications Express (Comex) 10 1 13 - 17 2021年01月 [査読有り]
  • A Novel Light Implementation of Face Reorganization System with Edge Device
    Katsuma Kumaki; Kimihiro Mizutani
    in Proc. International Conference on Emerging Technologies for Communications 1 - 1 2020年12月 [査読有り]
  • Masaya Suzuki; Kimihiro Mizutani
    in Proc. International Conference on Emerging Technologies for Communications 1 - 4 2020年12月 [査読有り]
  • Toru MANO; Takeru INOUE; Kimihiro MIZUTANI; Osamu AKASHI
    IEICE Transactions on Communications 103 4 347 - 362 2020年04月 [査読有り]
  • Increasing Capacity of the Clos Structure for Optical Switching Networks
    Toru Mano; Takeru Inoue; Kimihiro Mizutani; Osamu Akashi
    Proc. of IEEE Global Communications Conference (GLOBECOM) 2019年12月 [査読有り]
  • 吉田 学; 水谷 后宏; 秦 崇洋; 社家一平; 柏井 忠大
    自動車技術会論文集 50 2 622 - 628 2019年03月 [査読有り]
  • Kohei Watabe; Toru Mano; Takeru Inoue; Kimihiro Mizutani; Osamu Akashi; Kenji Nakagawa
    IEICE Transactions 102-B 1 76 - 87 2019年 [査読有り]
     
    Traffic matrix (TM) estimation has been extensively studied for decades. Although conventional estimation techniques assume that traffic volumes are unchanged between origins and destinations, packets are often lost on a path due to traffic burstiness, silent failures, etc. Counting every path at every link, we could easily get the traffic volumes with their change, but this approach significantly increases the measurement cost since counters are usually implemented using expensive memory structures like a SRAM. This paper proposes a mathematical model to estimate TMs including volume changes. The method is established on a Boolean fault localization technique; the technique requires fewer counters as it simply determines whether each link is lossy. This paper extends the Boolean technique so as to deal with traffic volumes with error bounds that requires only a few counters. In our method, the estimation errors can be controlled through parameter settings, while the minimum-cost counter placement is determined with submodular optimization. Numerical experiments are conducted with real network datasets to evaluate our method.
  • Zubair Fadlullah; Fengxiao Tang; Bomin Mao; Nei Kato; Osamu Akashi; Takeru Inoue; Kimihiro Mizutani
    IEEE Communications Letters 22 12 2479 - 2482 2018年12月 [査読有り]
  • Fengxiao Tang; Bomin Mao; Zubair Md. Fadlullah; Nei Kato; Osamu Akashi; Takeru Inoue; Kimihiro Mizutani
    IEEE Wireless Communications 25 1 154 - 160 2018年02月 [査読有り]
     
    Recently, deep learning has appeared as a breakthrough machine learning technique for various areas in computer science as well as other disciplines. However, the application of deep learning for network traffic control in wireless/heterogeneous networks is a relatively new area. With the evolution of wireless networks, efficient network traffic control such as routing methodology in the wireless backbone network appears as a key challenge. This is because the conventional routing protocols do not learn from their previous experiences regarding network abnormalities such as congestion and so forth. Therefore, an intelligent network traffic control method is essential to avoid this problem. In this article, we address this issue and propose a new, real-time deep learning based intelligent network traffic control method, exploiting deep Convolutional Neural Networks (deep CNNs) with uniquely characterized inputs and outputs to represent the considered Wireless Mesh Network (WMN) backbone. Simulation results demonstrate that our proposal achieves significantly lower average delay and packet loss rate compared to those observed with the existing routing methods. We particularly focus on our proposed method's independence from existing routing protocols, which makes it a potential candidate to remove routing protocol(s) from future wired/ wireless networks.
  • Bomin Mao; Zubair Md. Fadlullah; Fengxiao Tang; Nei Kato; Osamu Akashi; Takeru Inoue; Kimihiro Mizutani
    2017 IEEE Global Communications Conference, GLOBECOM 2017 - Proceedings 2018- 1 - 6 2018年01月 [査読有り]
     
    Recently, network operators are confronting the challenge of exploding traffic and more complex network environments due to the increasing number of access terminals having various requirements for delay and package loss rate. However, traditional routing methods based on the maximum or minimum single metric value aim at improving the network quality of only one aspect, which makes them become incapable to deal with the increasingly complicated network traffic. Considering the improvement of deep learning techniques in recent years, in this paper, we propose a smart packet routing strategy with Tensor-based Deep Belief Architectures (TDBAs) that considers multiple parameters of network traffic. For better modeling the data in TDBAs, we use the tensors to represent the units in every layer as well as the weights and biases. The proposed TDBAs can be trained to predict the whole paths for every edge router. Simulation results demonstrate that our proposal outperforms the conventional Open Shortest Path First (OSPF) protocol in terms of overall packet loss rate and average delay per hop.
  • 水谷后宏; 吉田学; 秦崇洋; 社家一平
    計測自動制御学会論文集 54 11 793‐801(J‐STAGE)  2018年 [査読有り]
  • Taichi Kawabata; Takashi Kurimoto; Kimihiro Mizutani
    2018 IEEE International Symposium on Local and Metropolitan Area Networks, LANMAN 2018, Washington, DC, USA, June 25-27, 2018 125 - 126 IEEE 2018年 [査読有り]
  • Bomin Mao; Fengxiao Tang; Zubair; Md. Fadlullah; Nei Kato; Osamu Akashi; Takeru Inoue; Kimihiro Mizutani
    IEEE Wireless Commun. 25 4 74 - 81 2018年 [査読有り]
  • Takeru Inoue; Toru Mano; Kimihiro Mizutani; Shin-ichi Minato; Osamu Akashi
    Computer Communications 116 101 - 117 2018年01月 [査読有り]
     
    Packet classification has been a key technology to quickly identify an action to be taken on a packet at a switch. Several advanced applications, most of which have been introduced recently with the advent of software-defined networking, commonly require the identification of a combination of switch actions, i.e., the network-wide forwarding behavior of a packet. Conventional classification methods, however, fail to well support network-wide behaviors, since the search space is partitioned in convoluted manner due to the complexity posed by the combinations possible. This paper proposes a novel packet classification method that supports the fast determination of network-wide forwarding behaviors. To avoid the inefficiencies of existing methods, which are revealed for the first time by our research, we base our method on a compressed data structure named the multi-valued decision diagram. On the solid foundation of decision diagrams, several algorithms are introduced with thorough theoretical analyses, and the construction process and the classification performance are highly optimized for the new classification problem. Experiments on real network datasets show that our method identifies the network-wide forwarding behaviors at the line basic rate, e.g., 10 Mpps, on a single CPU core with only tens of MB of memory.
  • 永田尚志; 井上武; 間野暢; 水谷后宏; 明石修
    電子情報通信学会論文誌 B(Web) J100-B 12 1068‐1072 (WEB ONLY)  2017年12月
  • Takeru Inoue; Richard Chen; Toru Mano; Kimihiro Mizutani; Hisashi Nagata; Osamu Akashi
    IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 14 4 1113 - 1127 2017年12月 [査読有り]
     
    Modern networks have complex configurations to provide advanced functions. Network softwarization, a promising new movement in the networking community, could make networks more complexly configured due to the nature of software. Since these complexities make the networks error-prone, network verification is attracting attention as a key technology to detect inconsistencies between a configuration and an operational policy. Existing verifiers are, unfortunately, either inefficient or incomplete (operational policies are not rigorously checked). This paper presents a novel framework of data-plane verification. So as to efficiently manage the large search space defined by packet headers, our framework formalizes the consistency check by applying simple set operations defined in a small quotient space of packet header. This paper also reveals that the two spaces can be connected via the windowing query in computational geometry. Two windowing algorithms are proposed and backed by solid theoretical analyses. Experiments on real network datasets show that our framework with the windowing algorithms is surprisingly fast; when verifying policy compliance in a real network with thousands of switches, our framework reduces the verification time of all-pairs reachability from ten hours to ten minutes.
  • Bomin Mao; Zubair Md. Fadlullah; Fengxiao Tang; Nei Kato; Osamu Akashi; Takeru Inoue; Kimihiro Mizutani
    IEEE TRANSACTIONS ON COMPUTERS 66 11 1946 - 1960 2017年11月 [査読有り]
     
    Recent years, Software Defined Routers (SDRs) (programmable routers) have emerged as a viable solution to provide a cost-effective packet processing platform with easy extensibility and programmability. Multi-core platforms significantly promote SDRs' parallel computing capacities, enabling them to adopt artificial intelligent techniques, i.e., deep learning, to manage routing paths. In this paper, we explore new opportunities in packet processing with deep learning to inexpensively shift the computing needs from rule-based route computation to deep learning based route estimation for high-throughput packet processing. Even though deep learning techniques have been extensively exploited in various computing areas, researchers have, to date, not been able to effectively utilize deep learning based route computation for high-speed core networks. We envision a supervised deep learning system to construct the routing tables and show how the proposed method can be integrated with programmable routers using both Central Processing Units (CPUs) and Graphics Processing Units (GPUs). We demonstrate how our uniquely characterized input and output traffic patterns can enhance the route computation of the deep learning based SDRs through both analysis and extensive computer simulations. In particular, the simulation results demonstrate that our proposal outperforms the benchmark method in terms of delay, throughput, and signaling overhead.
  • Nei Kato; Zubair Md. Fadlullah; Bomin Mao; Fengxiao Tang; Osamu Akashi; Takeru Inoue; Kimihiro Mizutani
    IEEE WIRELESS COMMUNICATIONS 24 3 146 - 153 2017年06月 [査読有り]
     
    Recently, deep learning, an emerging machine learning technique, is garnering a lot of research attention in several computer science areas. However, to the best of our knowledge, its application to improve heterogeneous network traffic control (which is an important and challenging area by its own merit) has yet to appear because of the difficult challenge in characterizing the appropriate input and output patterns for a deep learning system to correctly reflect the highly dynamic nature of large-scale heterogeneous networks. In this vein, in this article, we propose appropriate input and output characterizations of heterogeneous network traffic and propose a supervised deep neural network system. We describe how our proposed system works and how it differs from traditional neural networks. Also, preliminary results are reported that demonstrate the encouraging performance of our proposed deep learning system compared to a benchmark routing strategy (Open Shortest Path First (OSPF)) in terms of significantly better signaling overhead, throughput, and delay.
  • Kohei Watabe; Toru Mano; Kimihiro Mizutani; Osamu Akashi; Kenji Nakagawa; Takeru Inoue
    2017 IEEE 37TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2017) 2636 - 2637 2017年 [査読有り]
     
    Traffic matrix (TM) estimation has been extensively studied for decades. Although conventional estimation techniques assume that traffic volumes are unchanged between origins and destinations, packets are often discarded on a path due to traffic burstiness, silent failures, etc. This paper proposes a novel TM estimation method that works correctly even under packet drops. The method is established on a Boolean fault localization technique; the technique requires fewer counters though it only determines whether each link is healthy. This paper extends the Boolean technique so as to deal with traffic volumes with error bounds just by a small number of counters. Along with submodular optimization for the minimum counter placement, we evaluate our method with real network datasets.
  • Zubair Md. Fadlullah; Fengxiao Tang; Bomin Mao; Nei Kato; Osamu Akashi; Takeru Inoue; Kimihiro Mizutani
    IEEE COMMUNICATIONS SURVEYS AND TUTORIALS 19 4 2432 - 2455 2017年 [査読有り]
     
    Currently, the network traffic control systems are mainly composed of the Internet core and wired/wireless heterogeneous backbone networks. Recently, these packet-switched systems are experiencing an explosive network traffic growth due to the rapid development of communication technologies. The existing network policies are not sophisticated enough to cope with the continually varying network conditions arising from the tremendous traffic growth. Deep learning, with the recent breakthrough in the machine learning/intelligence area, appears to be a viable approach for the network operators to configure and manage their networks in a more intelligent and autonomous fashion. While deep learning has received a significant research attention in a number of other domains such as computer vision, speech recognition, robotics, and so forth, its applications in network traffic control systems are relatively recent and garnered rather little attention. In this paper, we address this point and indicate the necessity of surveying the scattered works on deep learning applications for various network traffic control aspects. In this vein, we provide an overview of the state-of-the-art deep learning architectures and algorithms relevant to the network traffic control systems. Also, we discuss the deep learning enablers for network systems. In addition, we discuss, in detail, a new use case, i.e., deep learning based intelligent routing. We demonstrate the effectiveness of the deep learning-based routing approach in contrast with the conventional routing strategy. Furthermore, we discuss a number of open research issues, which researchers may find useful in the future.
  • Toru Mano; Takeru Inoue; Dai Ikarashi; Koki Hamada; Kimihiro Mizutani; Osamu Akashi
    IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 13 3 477 - 488 2016年09月 [査読有り]
     
    Building optimal virtual networks across multiple domains is an essential technology for offering flexible network services. However, existing research is founded on an unrealistic assumption: providers will share their private information including resource costs. Providers, as well known, never actually do that so as to remain competitive. Secure multi-party computation, a computational technique based on cryptography, can be used to secure optimization, but it is too time consuming. This paper presents a novel method that can optimize virtual networks built over multiple domains efficiently without revealing any private information. Our method employs secure multi-party computation only for masking sensitive values; it can optimize virtual networks under limited information without applying any time-consuming techniques. It is solidly based on the theory of optimality and is assured of finding reasonably optimal solutions. Experiments show that our method is fast and optimal in practice, even though it conceals private information; it finds near optimal solutions in just a few minutes for large virtual networks with tens of nodes. This is the first work that can be implemented in practice for building optimal virtual networks across multiple domains.
  • Kimihiro Mizutani; Takeru Inoue; Toru Mano; Osamu Akashi; Satoshi Matsuura; Kazutoshi Fujikawa
    IEICE TRANSACTIONS ON COMMUNICATIONS E99B 4 830 - 840 2016年04月 [査読有り]
     
    The routing efficiency of structured overlay networks depends on the consistency of pointers between nodes, where a pointer maps a node identifier to the corresponding address. This consistency can, however, break temporarily when some overlay nodes fail, since it takes time to repair the broken pointers in a distributed manner. Conventional solutions utilize "backpointers" to quickly discover any failure among the pointing nodes, which allow them to fix the pointers in a short time. Overlay nodes are, however, required to maintain backpointers for every pointing node, which incurs significant memory and consistency check overhead. This paper proposes a novel light-weight protocol; an overlay node gives a "living will" containing its acquaintances (backpointers) only to its successor, thus other nodes are freed from the need to maintain it. Our carefully-designed protocol guarantees that all acquaintances are registered via the living will, even in the presence of churn, and the successor notifies the acquaintances for the deceased. Even if the successor passes away and the living will is lost, the successor to the successor can identify the acquaintances with a high success ratio. Simulations show that our protocol greatly reduces memory overhead as well as the detection time for node failure with the cost being a slight increase in messaging load.
  • Mizutani Kimihiro; Inoue Takeru; Mano Toru; Akashi Osamu; Matsuura Satoshi; Fujikawa Kazutoshi
    Information and Media Technologies 11 1 - 10 Information and Media Technologies 編集運営会議 2016年 
    Structured overlay networks that support range queries cannot hash data IDs for load balancing, in order to preserve the total order on the IDs. Since data and queries are not equally distributed on the ID-space without hashing in range-based overlay networks, uneven loads are imposed on the overlay nodes. Existing load balancing techniques for range-based overlay networks distribute the loads by using data reallocation or node migration, which makes the networks very unstable due to heavy data reallocation or frequent churn. This paper proposes a novel scheme that distributes, fairly, the loads without node migration and with little data reallocation, by sharing some ID-space regions between neighboring nodes. Our "overlapping" ID-space management scheme derives the optimal overlap based on kernel density estimations; the query loads based on the statistical theory are used to calculate the best overlap regions. This calculation is executed in a distributed manner with no central coordinator. We conduct thorough computer simulations, and show that our scheme alleviates the worst node load by 20-90% against existing techniques without node migration and with least data reallocation.
  • Tiago Gama Rodrigues; Katsuya Suto; Hiroki Nishiyama; Nei Kato; Kimihiro Mizutani; Takeru Inoue; Osamu Akashi
    2016 IEEE 84TH VEHICULAR TECHNOLOGY CONFERENCE (VTC FALL) 1 - 5 2016年 [査読有り]
     
    There are many applications which cannot be executed by mobile devices due to their limitations in memory, processing, battery, among others. One solution to this would be offloading heavy tasks to cloud servers in the edge of the network, in a service model called Edge Cloud Computing. The main Quality of Service requirement of this model is a low Service Delay, which can be achieved by lowering Transmission Delay and Processing Delay. Works in literature focus on either one of those two types of delay. This paper, however, argues that an approach which combines transmission and processing technologies to lower Service Delay would be more efficient. This idea is defended by an analysis of the service model and existing stochastic modeling of the Edge Cloud Computing system. We conclude that a dual focus approach would be the only way of truly minimizing the Service Delay, therefore being the desired method to improve Quality of Service. We conclude by laying the foundation for a future model that follows such concept.
  • Toru Mano; Takeru Inoue; Kimihiro Mizutani; Osamu Akashi
    IEEE INFOCOM 2016 - THE 35TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATIONS 1 - 9 2016年 [査読有り]
     
    Virtual network embedding has been intensively studied for a decade. The time complexity of most conventional methods has been reduced to the cube of the number of links. Since customers are likely to request a dense virtual network that connects every node pair directly (vertical bar E vertical bar = O(vertical bar V vertical bar(2))) based on a traffic matrix, the time complexity is actually O (vertical bar E vertical bar(3) = vertical bar V vertical bar(6)). If we were allowed to reduce this dense network into a sparse one before embedding, the time complexity could be decreased to O (vertical bar V vertical bar(3)); the time gap can be a million times for vertical bar V vertical bar = 100. The network reduction, however, combines several virtual links into a broader link, which makes the embedding cost (solution quality) much worse. This paper analytically and empirically investigates the trade-off between the embedding time and cost for the virtual network reduction. We define two simple reduction algorithms and analyze them with several interesting theorems. The analysis indicates that the embedding cost increases only linearly with exponential decay of embedding time. Thorough numerical evaluation justifies the desirability of the trade-off.
  • Takeru Inoue; Richard Chen; Toru Mano; Kimihiro Mizutani; Hisashi Nagata; Osamu Akashi
    2016 IEEE 24TH INTERNATIONAL CONFERENCE ON NETWORK PROTOCOLS (ICNP) 1 - 10 2016年 [査読有り]
     
    Modern networks have complex configurations to provide advanced functions, but the complexity also makes them error-prone. Network verification is attracting attention as a key technology to detect inconsistencies between a configuration and a policy before deployment. Existing verifiers, however, either generally verify various properties over the policy at the cost of efficiency, or efficiently perform configuration analysis without paying much attention to the policy. This paper presents a novel framework of data-plane verification, which flexibly checks the inconsistency with great efficiency. For the purpose of generality, our framework formalizes a verification process with three abstract steps: each step is related to 1) packet behaviors defined by a configuration, 2) operator intentions described in a policy, and 3) the inspection of their relation. These steps work efficiently with each other on the simple quotient set of packet headers. This paper also reveals how the second step can be regarded as the windowing query problem in computational geometry. Two novel windowing algorithms are proposed with solid theoretical analyses. Experiments on real network datasets show that our framework with the windowing algorithms is surprisingly fast even when verifying the policy compliance; e.g., in a medium-scale network with thousands of switches, our framework reduces the verification time of all-pairs reachability from ten hours to ten minutes.
  • Richard Chen; Toru Mano; Takeru Inoue; Kimihiro Mizutani; Hisashi Nagata; Osamu Akashi
    PROCEEDINGS 2016 IEEE 36TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS ICDCS 2016 743 - 744 2016年 [査読有り]
     
    Network verification is attracting attention as a key technology to detect configuration errors before deploying the network. In verification, a set of packets to be inspected is usually specified by a window - a multi-dimensional rectangle defined by packet header fields (e.g., address prefixes and port ranges). Network operators have to know the forwarding behaviors of packets inside the window; this can be regarded as the windowing query problem in computation geometry. This paper proposes a novel windowing algorithm for network verification. Unlike existing windowing algorithms, our algorithm runs on a compressed data structure, because the search space has to be represented in a compressed form due to the space complexity.
  • Hideki Kuribayashi; Katsuya Suto; Hiroki Nishiyama; Nei Kato; Kimihiro Mizutani; Takeru Inoue; Osamu Akashi
    2016 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC) 56 - 61 2016年 [査読有り]
     
    Wireless communication devices have spread widely in our society. However, they usually depend heavily on communication infrastructure, leaving them vulnerable to disasters or congestion of base stations. In these situations, a method to send out data without the support of infrastructure is required. Data transmission by D2D communication is a reliable method that does not rely on infrastructure. In this paper, we aim to improve the data dissemination using D2D transmission by applying the concept of assigning "modes" to devices according to their own mobility. In our study, we assume a multi-channel environment, where devices will be allocated different amounts of frequency channels according to their modes. We propose a mode selection function that uses velocity information of the devices to assign modes. By using this function, it is possible to allocate more frequency channels to devices of high mobility, so that they can transmit their data to more devices as they move through a wide area. By mathematical analysis, we evaluate the fairness of disseminated data density among devices of various velocities and the obtained results indicate the effectiveness of the proposed method for improving the efficiency of data dissemination.
  • Toru Mano; Takeru Inoue; Kimihiro Mizutani; Osamu Akashi
    IEICE TRANSACTIONS ON COMMUNICATIONS E98B 3 437 - 448 2015年03月 [査読有り]
     
    Network virtualization is one of the promising technologies that can increase flexibility, diversity, and manageability of networks. Building optimal virtual networks across multiple domains is getting much attention, but existing studies were based on an unrealistic assumption, that is, providers' private information can be disclosed; as is well known, providers never actually do that. In this paper, we propose a new method that solves this multi-domain problem without revealing providers' private information. Our method uses an advanced secure computation technique called multi-party computation (MPC). Although MPC enables existing unsecured methods to optimize virtual networks securely, it requires very large time to finish the optimization due to the MPC's complex distributed protocols. Our method, in contrast, is designed to involve only a small number of MPC operations to find the optimal solution, and it allows providers to execute a large part of the optimization process independently without heavy distributed protocols. Evaluation results show that our method is faster than an existing method enhanced with MPC by several orders of magnitude. We also unveil that our method has the same level of embedding cost.
  • MIZUTANI Kimihiro; INOUE Takeru; MANO Toru; AKASHI Osamu; MATSUURA Satoshi; FUJIKAWA Kazutoshi
    コンピュータ ソフトウェア 32 3 3_101 - 3_110 日本ソフトウェア科学会 2015年 [査読有り]
     
    Structured overlay networks that support range queries cannot hash data IDs for load balancing, in order to preserve the total order on the IDs. Since data and queries are not equally distributed on the ID-space without hashing in range-based overlay networks, uneven loads are imposed on the overlay nodes. Existing load balancing techniques for range-based overlay networks distribute the loads by using data reallocation or node migration, which makes the networks very unstable due to heavy data reallocation or frequent churn.This paper proposes a novel scheme that distributes, fairly, the loads without node migration and with little data reallocation, by sharing some ID-space regions between neighboring nodes. Our "overlapping" ID-space management scheme derives the optimal overlap based on kernel density estimations; the query loads based on the statistical theory are used to calculate the best overlap regions. This calculation is executed in a distributed manner with no central coordinator. We conduct thorough computer simulations, and show that our scheme alleviates the worst node load by 20-90 % against existing techniques without node migration and with least data reallocation.
  • Kimihiro Mizutani; Takeru Inoue; Toru Mano; Osamu Akashi; Satoshi Matsuura; Kazutoshi Fujikawa
    2015 21ST ASIA-PACIFIC CONFERENCE ON COMMUNICATIONS (APCC) 514 - 518 2015年 [査読有り]
     
    The routing efficiency of structured overlay networks depends on the consistency of pointers between nodes. This consistency can, however, break temporarily when some overlay nodes fail, since it takes time to repair the broken pointers in a distributed manner. Conventional solutions utilize "backpointers" to quickly know the failure among the pointing nodes, which allows them to fix the pointers in a short time. Overlay nodes are, however, required to maintain backpointers for every pointing node which incurs significant consistency check and memory overheads. This paper proposes a novel light-weight protocol; an overlay node gives a "testament" containing its acquaintances (backpointers) only to its successor (i.e., clockwise closest node), and other nodes are freed from maintaining it. Our carefully-designed protocol guarantees that all acquaintances are registered with the testament even in the presence of churn, and the successor notifies the acquaintances for the deceased. Even if the successor passes away and the testament is lost, the successor of the successor can identify the acquaintances at a high success ratio. Simulations show that our protocol greatly reduces the mean time to repair (MTTR) and memory overheads while messaging cost increases.
  • Katsuya Suto; Hiroki Nishiyama; Nei Kato; Kimihiro Mizutani; Osamu Akashi; Atsushi Takahara
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING 2 3 292 - 301 2014年07月 [査読有り]
     
    Management scheme for highly scalable big data mining has not been well studied in spite of the fact that big data mining provides many valuable and important information for us. An overlay based parallel data mining architecture, which executes fully distributed data management and processing by employing the overlay network, can achieve high scalability. However, the overlay-based parallel mining architecture is not capable of providing data mining services in case of the physical network disruption that is caused by router/communication line breakdowns because numerous nodes are removed from the overlay network. To cope with this issue, this paper proposes an overlay network construction scheme based on node location in physical network, and a distributed task allocation scheme using overlay network technology. The numerical analysis indicates that the proposed schemes considerably outperform the conventional schemes in terms of service availability against physical network disruption.
  • Takeru Inoue; Toru Mano; Kimihiro Mizutani; Shin-ichi Minato; Osamu Akashi
    2014 IEEE 22ND INTERNATIONAL CONFERENCE ON NETWORK PROTOCOLS (ICNP) 296 - 307 2014年 [査読有り]
     
    In software-defined networking, applications are allowed to access a global view of the network so as to provide sophisticated functionalities, such as quality-oriented service delivery, automatic fault localization, and network verification. All of these functionalities commonly rely on a well-studied technology, packet classification. Unlike the conventional classification problem to search for the action taken at a single switch, the global network view requires to identify the network-wide behavior of the packet, which is defined as a combination of switch actions. Conventional classification methods, however, fail to well support network-wide behaviors, since the search space is complicatedly partitioned due to the combinations. This paper proposes a novel packet classification method that efficiently supports network-wide packet behaviors. Our method utilizes a compressed data structure named the multi-valued decision diagram, allowing it to manipulate the complex search space with several algorithms. Through detailed analysis, we optimize the classification performance as well as the construction of decision diagrams. Experiments with real network datasets show that our method identifies the packet behavior at 20.1 Mpps on a single CPU core with only 8.4 MB memory; by contrast, conventional methods failed to work even with 16 GB memory. We believe that our method is essential for realizing advanced applications that can fully leverage the potential of software-defined networking.
  • Toru Mano; Takeru Inoue; Dai Ikarashi; Koki Hamada; Kimihiro Mizutani; Osamu Akashi
    2014 23RD INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND NETWORKS (ICCCN) 1 - 8 2014年 [査読有り]
     
    Building optimal virtual networks across multiple domains is an essential technology to offer flexible network services. However, existing research is founded on an unrealistic assumption; providers will share their private information including resource costs. Providers, as is well known, never actually do that to remain competitive. Technically, secure multiparty computation, which is a computational technique based on the cryptography, can be used to secure optimization, but it is too time-consuming. This paper presents a novel method to optimize virtual networks built over multiple domains, with great efficiency but without revealing any private information. Our method employs secure multi-party computation but only for masking sensitive values; it can optimize virtual networks under limited information without any time-consuming technique. It is solidly based on the theory of optimality, and is assured of finding reasonably optimal solutions. Experiments show that our method is fast and optimal in practice even concealing private information; it finds nearly optimal solutions in just a few minutes for large virtual networks with tens of nodes. This is the first work that can be implemented in practice for building optimal virtual networks across multiple domains.
  • 釘本 健司; 三宅 茂樹; 水谷 后宏
    コンピュータ ソフトウェア 31 3 3_246 - 3_258 日本ソフトウェア科学会 2014年 [査読有り]
     
    近年，TCP (Transmission Control Protocol)を利用するストリーミングサービスの普及とともに，安定したデータ伝送を実現するために可用帯域を正確かつ短時間に測定することがますます重要となってきている．そこで，我々はソケットAPI (Application Programming Interface)を備えるTCPのリアルタイムな可用帯域測定機能を提案する．提案機能では，TCPコネクションをプロトコルスタック内部で観測し，ACK (Acknowledgement)パケット受信時刻に基づく測定手法により，TCPのスループットを損なうことなく可用帯域を推定する．これにより，(1)試験用のダミーパケットを要しないためネットワークに無用な影響を与えずに測定可能とし，(2)ネットワークの混雑等によって生じるACKパケットの受信時刻のゆらぎを考慮して測定に必要な確認応答パケット数を決定するため，測定精度を維持しつつ，リアルタイムに測定値を更新できる．また，本機能はソケットAPIを備えており，アプリケーションはソケットAPI経由で測定値を利用できる．これらの可用帯域測定手法を提案するだけでなく，TCPプロトコルスタックへ実装し，実験ネットワーク上で既存の可用帯域測定専用ツールとの比較を行った．その結果，従来の代表的な可用帯域測定専用ツールと比較しても同程度の精度で測定が可能であることを確認した．実装規模は300行程度と小規模ながら，本機能の効果が高いことが分かった．
  • Toru Mano; Takeru Inoue; Dai Ikarashi; Koki Hamada; Kimihiro Mizutani; Osamu Akashi
    2014 23RD INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND NETWORKS (ICCCN) 13 3 477 - 488 2014年 [査読有り]
     
    Building optimal virtual networks across multiple domains is an essential technology to offer flexible network services. However, existing research is founded on an unrealistic assumption; providers will share their private information including resource costs. Providers, as is well known, never actually do that to remain competitive. Technically, secure multiparty computation, which is a computational technique based on the cryptography, can be used to secure optimization, but it is too time-consuming. This paper presents a novel method to optimize virtual networks built over multiple domains, with great efficiency but without revealing any private information. Our method employs secure multi-party computation but only for masking sensitive values; it can optimize virtual networks under limited information without any time-consuming technique. It is solidly based on the theory of optimality, and is assured of finding reasonably optimal solutions. Experiments show that our method is fast and optimal in practice even concealing private information; it finds nearly optimal solutions in just a few minutes for large virtual networks with tens of nodes. This is the first work that can be implemented in practice for building optimal virtual networks across multiple domains.
  • Kimihiro Mizutani; Toru Mano; Osamu Akashi; Kensuke Fukuda
    IEICE TRANSACTIONS ON COMMUNICATIONS E96B 7 1680 - 1690 2013年07月 [査読有り]
     
    In DHT network, a node can get/put a requested data by only log N look-up steps. However, conventional DHT network only supports single query look-up to search data. From the reason, each node in a DHT network must execute look-up process for each query even if a large number of put and get operations are executed. Therefore, this results in high network load in massive data management such as Map Reduce, sensor network, and web information. To address the problem, we propose multiple queries look-up architecture using range information feedback (MARIF). MARIF extends the conventional KBR protocol to supports range information that is a scope of ID space a node keeps. When a source node receives range information from a destination node, the source node checks all queries in the range information and forwards queries matching the range information to the destination node directly. This effectively reduces the number of look-up queries and the network load for the IP network. In addition, MARIF can be implemented into conventional DHT networks and can easily be combined to effective DHT routing algorithms such as Chord, Kademlia, Pastry, and one-hop DHT. In evaluation, we implement MARIF into three DHT networks and compare its performance with that of conventional query bundling mechanisms based on the KBR protocol. The results show that MARIF reduces by up to 40% the total number of forwarding queries to put data compared with other mechanisms. In addition, MARIF saves the number of forwarding queries per look-up process by up to 85% compared to other mechanisms with low bundling overhead.
  • Meng Li,Array; Nei Kato; Kimihiro Mizutani; Osamu Akashi; Atsushi Takahara
    International Conference on Wireless Communications and Signal Processing, WCSP 2013, Hangzhou, China, October 24-26, 2013 1 - 6 IEEE 2013年 [査読有り]
  • Toru Mano; Kimihiro Mizutani; Osamu Akashi
    2013 IFIP/IEEE International Symposium on Integrated Network Management (IM 2013), Ghent, Belgium, May 27-31, 2013 1129 - 1134 IEEE 2013年 [査読有り]
  • 水谷 后宏; 間野 暢; 明石 修; 福田 健介
    コンピュータ ソフトウェア 30 2 2_101 - 2_118 日本ソフトウェア科学会 2013年 [査読有り]
     
    近年，時系列データや地理位置データといった連続データの管理・解析手法が注目を浴びている．これらの連続データは，分散環境上で膨大に生成されることが想定され，オーバレイネットワークなどに代表される分散ストレージ上で管理されるようになった．一方で，蓄積した連続データを解析する手法としてMapReduceを用いた手法が提案されている．しかし，分散ストレージ上の連続データに対してMapReduce処理を行う際，データの連続性や局所性により，特定のノード(計算機)に偏ってReduce処理が割り当てられ，Shuffle処理にて膨大なトラヒックが発生することがある．また，刻々と蓄積されていく連続データに対して，MapReduce処理の同期をとることも難しい．<BR>本提案基盤は，連続データに対して非同期かつ，並列性の高いMapReduce処理を達成する．具体的には，分散ストレージに対してSkipListを改良した平衡木構造を適用し，ノード間で親子関係を構築させる．構築した親子関係を用いて，各ノードが自身の子ノードのShuffle処理やReduce処理の結果を集約したり，Map処理とReduce処理の同期，および生存管理を行うことで，MapReduce処理の同期を細分化する．さらに，木構造の特性を生かし，各ノードの負荷情報を集約し，ノード間の負荷を均一にする．これにより，各ノードの計算量を平滑化できるためMapReduce処理の並列性を向上させる．
  • Kimihiro Mizutani; Toru Mano; Osamu Akashi; Tetsuo Kawano; Hiroshi Shimizu
    2012 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) 3548 - 3553 2012年 [査読有り]
     
    In this paper, we propose an efficient video streaming server management scheme for streaming service that minimizes power consumption while satisfying client's requests. In conventional schemes, the power minimizing policy is calculated by means of simple dynamic programming or linear programing systems. However, these schemes may suffer changing the power minimizing policy substantially when the client's requests change even slightly. This increases the cost of changing streaming servers. On the other hand, our approach minimizes power consumption while satisfying client's requests by considering the number of times the policy is changed. To reduce the number of changes, our scheme uses dynamic programming by considering trends in client's requests and the stream length for each server. Evaluations shows that our scheme reduces power consumption by up to 35%-45% of conventional schemes.
  • Kimihiro Mizutani; Toru Mano; Osamu Akashi; Kensuke Fukuda
    2012 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) 2695 - 2700 2012年 [査読有り]
     
    A distributed hash table (DHT) network can be used for many distributed services and systems. In DHT networks, it takes log N look-up steps to search for required data where N is the number of nodes. However, the look-up process is redundant in the IP network because each look-up process generates a lot of communication among nodes. In massive data management such as sensor and web information management, this results in high network load even if each the search process takes only log N look-up steps. To solve this problem, we propose an efficient query bundling mechanism that makes it possible to bundle multiple queries by using range information. Range information consists of ID space information kept by a node. When a source node receives range information from a destination node, the source node matches all queries for the range information and forwards queries matching the range information to the destination node directly. This effectively reduces the number of look-up processes and the network load for the IP network. In addition, our mechanism can be implemented into conventional DHT networks and can easily be combined to effective DHT routing algorithms such as Chord, Kademlia, and Pastry. In evaluation, we implement our mechanism into DHT networks and compare its performance with that of conventional query bundling mechanisms. The results show that our mechanism reduces by up to 75% the total number of forwarding operations to put data compared with other mechanisms. In addition, our mechanism realizes the reduction of the number of forwarding operations per look-up process by up to 85% compared to other mechanisms.
  • Kimihiro Mizutani; Osamu Akashi; Atsushi Terauchi; Takeshi Kugimoto; Mitsuru Maruyama
    2012 IEEE NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM (NOMS) 599 - 602 2012年 [査読有り]
     
    Many studies have focused on developing Transmission Control Protocol (TCP) flow control mechanisms to enable more effective use of bandwidth in data center networks. However, the studies cannot achieve total optimization of bandwidth use for data center networks. This is because they do not take into account the path design of TCP flows and the hierarchical structure in data center networks through which TCP flows. To address this issue, we propose a TCP flow control mechanism for effectively using bandwidth by dynamically controlling paths through which TCP flows. To achieve this dynamic control, a hierarchical feedback model is used to obtain an optimal path establishment policy. With the model, all network components exchange their resource states with each other when each network component establishes a TCP flow. This enables each network component to learn the best TCP flow path for effective bandwidth use. An evaluation process shows that the mechanism achieves more effective bandwidth use and more efficient flow control than the conventional TCP flow control.
  • Kimihiro Mizutani; Izumi Koyanagi; Takuji Tachibana
    INTERNATIONAL MULTICONFERENCE OF ENGINEERS AND COMPUTER SCIENTISTS (IMECS 2010), VOLS I-III 905 - 910 2010年 [査読有り]
     
    In a virtualized server environment, machine resources such as CPU and memory are shared by multiple services. In such an environment, as the number of sessions for each service increases, the amount of resources that are utilized by the services increases. If thrashing occurs due to a lack of resources, the performance of the server is degraded. It is effective to estimate the amount of used resources; however, it is hard to estimate the amount of resources that are used dynamically by multiple services. In this paper, we propose a dynamic session management based on reinforcement learning in order to utilize the resources effectively and avoid the thrashing. In the proposed method, a learning agent estimates the amount of used resources from the response time for a service request. Then, the agent decides the acceptance or rejection of an arriving session request with Q-learning. Because this method can be implemented easily in a physical machine, it is expected that our proposed method is used in a real environment. We evaluate the performance of our proposed method with a simulation. From the simulation results, we show that the proposed method can allocate the resources to multiple services effectively while avoiding the thrashing and can perform the priority control for multiple services.
  • Kimihiro Mizutani; Satoshi Matsuura; Shinichi Doi; Kazutoshi Fujikawa; Hideki Sunahara
    6th International Conference on Networking and Services, ICNS 2010, Includes LMPCNA 2010; INTENSIVE 2010 282 - 287 2010年 [査読有り]
     
    Structured overlay networks are widely used as platforms for distributed systems. However, in a high churn situation, it is highly costly to maintain the structure and service availability of an overlay network because there is a limitation in churn handling. Several cooperation mechanisms among overlay networks are proposed to improve service availability of overlay networks in a high-churn situation. Several cooperation mechanisms are proposed among overlay networks. The cooperation mechanisms can group structured overlay networks to simplify routing functions. However, the existing mechanisms do not consider managing churn information among overlay networks. In this paper, we propose a new framework that can share states of the nodes and spread churn information to neighbor nodes among different overlay networks. Using our framework, we are able to maintain each overlay network effectively and improve the reachability of messages under churn. We evaluate our framework with Chord, Kademlia, and Pastry. Our framework improves the detection time of churn by about 30% and decreases the stabilization messages by about 30-40%. We discuss combinatorial effects of the sharing state of the nodes among different overlay networks. © 2010 IEEE.

MISC

産業財産権

受賞

  • 2023年12月 IPSJ ICMU Best Poster/Demo Award (指導学生の受賞)
     An Implementation of Intelligent Image Analysis Load Balancing for Virtualized Environment 
    受賞者: Shunsuke Nakagawa;Kimihiro Mizutani
  • 2023年09月 電子情報通信学会 通信ソサイエティ活動功労賞
     英文論文誌編集委員としての貢献 
    受賞者: 水谷后宏
  • 2022年11月 IEICE ICETC Best Short Paper Award (指導学生の受賞)
     A Novel Automatic Checkout System without Relearning Additional Item Information 
    受賞者: Daisuke Hanamitsu;Kimihiro Mizutani
  • 2022年09月 情報処理学会関西支部 支部大会奨励賞（指導学生の受賞）
     言語モデルを用いたAnsibleのプレイブックファイル作成時におけるヒューマンエラー発生防止システムの開発 
    受賞者: 川口 真護;水谷 后宏;井口 信和
  • 2022年09月 情報処理学会関西支部 支部大会奨励賞（指導学生の受賞）
     ネットワークコンフィグの潜在的特徴抽出手法の提案と評価 
    受賞者: 花光 大輔;水谷 后宏;小林 諭;福田 健介;明石 修
  • 2022年09月 情報処理学会関西支部 学生優秀発表賞（指導学生の受賞）
     オンチェーンデータ解析を用いた仮想通貨の価格推移に関する考察 
    受賞者: 徳永 翔;水谷 后宏
  • 2022年09月 情報処理学会関西支部 支部大会奨励賞（指導学生の受賞）
     運転特性を考慮したバス運転手の配置換えによる燃料費削減手法の提案 
    受賞者: 三浦 陸, 水谷 后宏
  • 2022年09月 情報処理学会関西支部 支部大会奨励賞（指導学生の受賞）
     実仮想環境下における深層強化学習を用いた効率的なリソース管理手法の提案 
    受賞者: 川北 英輝;水谷 后宏
  • 2021年01月 電子情報通信学会関西支部 優秀発表賞（指導学生の受賞）
     Distributed Skip Mesh Listを用いた大規模ニューラルネットワークの永続的管理手法 
    受賞者: 鈴木 雅也;水谷 后宏
  • 2021年01月 電子情報通信学会関西支部 奨励賞（指導学生の受賞）
     Conditional SR-GANを用いたモバイルトラフィックデータの圧縮・復元 
    受賞者: 徳永 智紀;水谷 后宏
  • 2020年06月 電子情報通信学会 最優秀論文賞
     Reducing Dense Virtual Networks for Fast Embedding 
    受賞者: Toru Mano;Takeru Inoue;Kimihiro Mizutani;Osamu Akashi
  • 2020年03月 電子情報通信学会関西支部 支部長賞（奨励賞）（指導学生の受賞）
     Conditional SRGAN を用いたモバイルトラフィックデータの推論手法 
    受賞者: 徳永 智紀;水谷 后宏
  • 2018年 電子情報通信学会IN研究会 情報ネットワーク研究賞
     仮想NW埋込高速化のための総容量変化を最小化するNW簡約手法 
    受賞者: 間野暢;井上武;水谷后宏;湊真一;明石修
  • 2018年 電子情報通信学会NV研究会 優秀講演賞
     動作検証可能な機械学習を用いた仮想サーバリソース割り当て方式の実装と評価 
    受賞者: 水谷 后宏
  • 2017年 IEEE Global Communications Conference (GLOBECOM) Best Paper Award
     A Tensor Based Deep Learning Technique for Intelligent Packet Routing 
    受賞者: B. Mao;Z. Md. Fadlullah;F. Tang;N. Kato;O. Akashi;T. Inoue;K. Mizutani
  • 2017年 日本ソフトウェア科学会 第21回研究論文賞
     Stable Load Balancing with Overlapping ID-space Management in Range-based Structured Overlay Networks 
    受賞者: Kimihiro Mizutani;Takeru Inoue;Toru Mano;Osamu Akashi;Satoshi Matsuura;Kazutoshi Fujikawa
  • 2016年 IEEE International Conference on Communications (ICC), Best Paper Award
     A Mobility-Based Mode Selection Technique for fair Spatial Dissemination of Data in Multi-Channel Device-to- Device Communication 
    受賞者: H. Kuribayashi;K. Suto;H. Nishiyama;N. Kato;K. Mizutani;T. Inoue;O. Akashi
  • 2016年 電子情報通信学会IA研究会 インターネットアーキテクチャ研究賞
     MDDを用いたハイパーキューブ探索によるネットワーク検証の高速化 
    受賞者: チェン・リチャード;井上武;間野暢;水谷后宏;永田尚志;明石修
  • 2015年 電子情報通信学会IN研究会 情報ネットワーク研究賞
     情報ネットワーク研究賞 MDDを用いたSDNグローバルビューのためのパケット分類手法 
    受賞者: 井上武;間野暢;水谷后宏;湊真一;明石修
  • 2014年 電子情報通信学会ICM研究会 情報通信マネジメント研究賞
     構造化オーバーレイを用いた大規模分散計算基盤の実装と基礎評価 
    受賞者: 水谷后宏;間野暢;明石修;福田健介
  • 2013年 電子情報通信学会IA研究会 インターネットアーキテクチャ研究賞
     複数設備提供者間の情報秘匿型ネットワーク資源割当手法 
    受賞者: 間野 暢;水谷 后宏;明石 修
  • 2010年 IAENG International MultiConference of Engineers and Computer Scientists(IMECS) Best Student Paper Award
     Dynamic Session Management Based on Reinforcement Learning in Virtual Server Environment 
    受賞者: Kimihiro Mizutani;Izumi Koyanagi;Takuji Tachibana
  • 2010年 情報処理学会MBL研究会 優秀プレゼンテーション賞
     An Implementation of a Framework for Integrating Churn Managements among Structured Overlay Networks 
    受賞者: 水谷后宏;洞井晋一;松浦知史;藤川和利;砂原秀樹

共同研究・競争的資金等の研究課題

  • 多種多様なニューラルネットワークを収容可能にするネットワーク設計・制御技術
    日本学術振興会：科学研究費助成事業 若手研究
    研究期間 : 2023年04月 -2026年03月 
    代表者 : 水谷 后宏
  • 日本学術振興会：科学研究費助成事業 基盤研究(B)
    研究期間 : 2020年04月 -2024年03月 
    代表者 : 明石 修; 水谷 后宏; 福田 健介
     
    本研究ではサービス設定ワークフローを高い抽象度で表現することにより環境・実装依存の部分を隠蔽し，ワークフロー全体としてネットワークオペレータが意図する通りの実行結果であったことの妥当性の検証を目指す．本年度は基本となる構成要素として，実際に運用されるネットワーク機器の設定情報へのラベル付けや構造化された状態での操作情報の取出しなどの解釈抽出パート，および，その設定が運用者の意図として妥当であることの検証パートの関連技術構築に注力した. 解釈抽出パートにおける構造化データ抽出手法としては，通常の設定情報から操作記述を表すテンプレートと，テンプレートに対するパラメータ値に分離した上で，data-driven解析の手法を用いてこれらを意味付けし構造化した形で取出すことを目指す．まずは設定記述を教師なしの学習器に与え，関連する設定記述のテンプレートを返すレコメンデーション機能の実装をターゲットに，タッカー分解を用いてテンプレートブロックを抽出する手法を提案し，実験評価を行った．また提案手法の性能評価にタッカー分解の手法と類似した非負値行列分解(NMF)を用いて，テンプレートブロックの抽出精度に関する比較評価を行い，有効性を評価した．本研究は査読付き国際会議に採録された． 検証パートに関しては，ネットワークの挙動が運用者の意図通りであることの検証を目的とし，コントロールプレーン検証，データプレーン検証の両視点から，検証手法設計・構築を進めた．特に，対象とするネットワークの形態や，様々なレイヤの管理運用手法が複雑に混在する現実のネットワークを意識し，そのモデル化，規模拡張性を解析しながら構築を進め，初期実装を通じて実験・評価を行った．
  • 日本学術振興会：科学研究費助成事業 若手研究
    研究期間 : 2020年04月 -2023年03月 
    代表者 : 水谷 后宏
     
    本研究では、膨大なニューラルネットワークの分散学習手法について、通信ネットワークおよびその構成機器となるサーバの有機的な連携を通して、学習効率を向上させることを目的としていた。特に、分割したニューラルネットワークを分散的に管理する上で、ニューラルネットワークの部分構造を維持するサーバの故障によって、ニューラルネットワーク全体の学習効率が下がる問題を解決する分散ニューラルネットワーク管理技術の確立を目指した。2021年度では、当該問題を解決および明確にするため、以下の研究開発を実施した。(1)複雑な構造を持つニューラルネットワークを分散管理する手法に着目し、高速かつニューラルネットワークの演算処理効率の低下を防ぐ分散ネットワーク復旧手法に関する研究を実施した。具体的には、連携しているサーバ間にて、サーバの故障を他のサーバが発見した際に、故障サーバの代わりとなるサーバを短時間かつ低負荷にて発見する手法を開発した。(2)故障・演算効率が低下したサーバに対して演算要求の割当を自律的に防ぐ手法に関する研究も実施した。具体的には、サーバ同士の相互連携によって、通常とは異なる処理速度になったサーバを発見し、そのサーバに割り当てる演算処理を回避する手法を開発した。(3)さらに、複雑なニューラルネットワークの演算処理効率について、学習データ量・データ自体の複雑さ・ニューラルネットワーク自体の複雑さが、どのように寄与しているかの調査を行い、ニューラルネットワークの分散化を最適化するための考察を行った。
  • 強化学習を用いた帯域管理ツールの開発
    奈良先端科学技術大学院大：Creative and International Competitiveness Project
    研究期間 : 2009年 -2010年 
    代表者 : 小柳衣津美
  • Programmable Overlay Networkの開発
    情報処理推進機構：未踏ユースプロジェクト
    研究期間 : 2008年09月 -2009年03月 
    代表者 : 水谷 后宏

委員歴

  • 2013年09月 - 現在   電子情報通信学会   常任査読員
  • 2024年05月 - 2024年11月   International Conference on Emerging Technologies for Communications 2024   TPC member
  • 2024年05月 - 2024年07月   ADMNET 2024: The 12th IEEE International Workshop on Architecture, Design, Deployment & Management of Networks & Applications   PC Member
  • 2023年04月 - 2023年09月   情報処理学会DPS・EIP研究会   ローカル担当
  • 2023年05月 - 2023年07月   ADMNET 2023: The 11th IEEE International Workshop on Architecture, Design, Deployment & Management of Networks & Applications   PC Member
  • 2018年06月 - 2023年06月   IEICE Transactions on Communications   Associate Editor
  • 2022年04月 - 2022年12月   International Conference on Emerging Technologies for Communications 2022   TPC member
  • 2022年05月 - 2022年07月   ADMNET 2022: The 10th IEEE International Workshop on Architecture, Design, Deployment & Management of Networks & Applications   PC member
  • 2021年06月 - 2022年06月   電子情報通信学会   代議員
  • 2020年06月 - 2022年06月   電子情報通信学会   会誌編集委員
  • 2020年06月 - 2022年06月   電子情報通信学会関西支部   会計幹事
  • 2021年06月 - 2021年12月   International Conference on Emerging Technologies for Communications 2021   TPC Member
  • 2017年06月 - 2021年06月   情報処理学会   論文誌/Journal of Information Processing (JIP) 編集委員
  • 2020年12月 - 2021年03月   IEICE   Guest Associate Editors, Communications Express, Special Cluster on Advanced Communication Technologies in Conjunction with Main Topics of ICETC2020
  • 2020年06月 - 2020年12月   International Conference on Emerging Technologies for Communications 2022   TPC Member
  • 2016年06月 - 2018年06月   電子情報通信学会   IN研究会専門委員

担当経験のある科目

  • プログラミング実習Ⅱ近畿大学
  • 卒業研究ゼミナール近畿大学
  • 情報実習Ⅱ近畿大学
  • 基礎ゼミ2近畿大学
  • 卒業研究近畿大学
  • 基礎ゼミ1近畿大学
  • プログラミング実習Ⅰ近畿大学
  • 実務訓練長岡科学技術大学
  • 情報通信システム論Ⅰ筑波大学
  • 社会情報学実習近畿大学
  • データベース論近畿大学
  • 情報学基礎ゼミナール1近畿大学
  • IoT近畿大学
  • 計測・情報システム専門基礎近畿大学大学院
  • 大規模情報処理システム特論近畿大学大学院
  • ネットワーク技術Ⅱ近畿大学

その他

  • 2021年04月 - 2022年03月  ポストコロナ時代の安全/安心なキャンパスライフを支える AI 技術の研究 
    令和３年度 オール近大 新型コロナウイルス感染症対策支援プロジェクトへの採択案（採択額300万円）

その他のリンク

researchmap


Copyright © MEDIA FUSION Co.,Ltd. All rights reserved.