研究者詳細 - 野林　大起

論文 - 野林　大起

分割表示108 件中 41 - 60 件目／全件表示 >>

P4-based In-Network RL inference for Efficient Flow-Level Bandwidth Allocation 査読有り国際誌

Qadeer A., Lee M.J., Nobayashi D.

Proceedings - IEEE Global Communications Conference, GLOBECOM 1247 - 1252 2023年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Software-defined networking (SDN) has notably improved networks by providing Machine Learning-Powered programming capabilities at the control plane (CP), making it easier to dynamically manage the network resources according to varying traffic conditions. However, the geographically remote location of the CP from the data plane (DP) leads to significant round-trip delays in the order of milliseconds, which can ad-versely impact the performance of delay-sensitive and real-time traffic. To address this issue, this paper proposes a novel in-network reinforcement learning (RL) inference framework that extends programming capability from the CP to the DP for fine-grained control of network resources to meet the Quality of Service (QoS) demands of real-time applications. The in-network RL inference is achieved by adopting a match-action table mapping strategy in the DP and validating it through programming protocol-independent packet processors (P4). A P4 meter extern is utilized to allocate bandwidth to individual traffic flows based on their QoS requirements. Our proposed strategy achieves in-network RL inference at the line rate with negligible processing overhead while reducing packet loss rate and jitter by up to 92% and 57%, respectively, compared to the CP-based approach. Additionally, we evaluate the performance of our proposed bandwidth allocation framework using a state-of-the-art deep-deterministic policy gradient (DDPG)-based RL agent with a heuristic priority experience replay (hPER) technique. Our proposed DDPG agent achieves a faster convergence rate, higher reward, superior training stability, and up to 56 % reduction in operational cost compared to two alternative agents

DOI： 10.1109/GLOBECOM54140.2023.10437488

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85187352797&origin=inward

Integrated Artificial Intelligence Technology for Mobility Load Balancing and Coverage Optimization 査読有り

Yi-We Ma, Chun-Yao Chang, Yi-Hao Tu, Jiann-Liang Chen, Kazuya Tsukamoto, Masahiro Shibata, Daiki Nobayashi, Takeshi Ikenaga

The 10th International Symposium on Applied Engineering and Sciences (2022) 2022年12月

Spatio-temporal Data Retention System for Floating Cyber Physical System 査読有り

Hotaka Kaneyasu, Daiki Nobayashi, Kazuya Tsukamoto, Takeshi Ikenaga, Myung Lee

The 10th International Symposium on Applied Engineering and Sciences (2022) 2022年12月

Implementation and Performance Evaluation of TCP/IP Communication over Private LoRa 査読有り

Sakamoto J., Nobayashi D., Tsukamoto K., Ikenaga T., Sato G., Takizawa K.

Proceedings - International Conference on Network Protocols, ICNP 2022-October 2022年10月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Low-power wide-area (LPWA) is a major communication technology used in the Internet of Things (IoT). However, since LPWA does not conform to the TCP/IP protocol stack and employs its own unique protocol, it is difficult for sensors equipped with LPWA I/F to connect to the Internet directly. In the present study, to realize general TCP/IP communication on LPWA networks, we construct a TCP/IP network over Private LoRa, and evaluate its communication performance. Moreover, we verify the feasibility of TCP/IP communication over LoRa by using a popular Internet application.

DOI： 10.1109/ICNP55882.2022.9940334

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85142704148&origin=inward

Evaluation of MPTCP with BBR Performance on Wi-Fi/Cellular networks for Video Streaming 査読有り

Masayoshi Kondo, Dirceu Cavendish, Daiki Nobayashi, Takeshi Ikenaga

The Fourteenth International Conference on Evolving Internet (INTERNET 2022) 2022年05月

Data Completeness-aware Transmission Control for Large Spatio-Temporal Data Retention 査読有り国際誌

Kaneyasu H., Nobayashi D., Tsukamoto K., Ikenaga T., Lee M.

Digest of Technical Papers - IEEE International Conference on Consumer Electronics 2022-January 2022年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

With the development of IoT technology, various kinds of data are generated by IoT devices. Some of this data contains information on geographical location and time. We refer to such data as spatio-temporal data (STD). Since the 'local production and consumption' of STD is effective for location-dependent applications, we have proposed an STD retention system that utilizes vehicles as data sources. STD sources ranges from simple sensory data to large video data. However, since previous methods assumed to retain an STD consisting of only one packet, retention of large STD sources may suffer from frequent packet collisions due to the increase in the number of packet transmissions. In this paper, we propose a data completeness-aware transmission control mechanism for large STD retention. Our simulation results showed that the proposed scheme reduces channel collision by suppressing the forwarding of incomplete data, and achieved a nearly 100% coverage rate.

DOI： 10.1109/ICCE53296.2022.9730495

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85127053175&origin=inward

Unknown Malicious Domain Detection based on DNS Query Analysis using Word2Vec 査読有り国際誌

Yamada H., Nobayashi D., Satoh A., Nakamura Y., Ikenaga T.

Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022 1096 - 1097 2022年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Malware infection of network user devices is a critical threat to users on the Internet. A major countermeasure against malware infection is a signature-type detection method that uses a blacklist to prevent communication with a Command and Control (C&C) server when the malware attempts a malicious attack. However, if the malicious domain name is unknown to the C&C server, it is difficult for this method to detect the malware. This paper focuses on the behavior of devices infected with malware. We propose a method for unknown malicious domain detection based on domain name system (DNS) query analysis using Word2Vec, a popular machine learning method. We then evaluate the effectiveness of our proposed method using an actual DNS Query log.

DOI： 10.1109/CSCI58124.2022.00196

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85172003150&origin=inward

Study of Ultrasonic Data Collection System for Anomaly Detection for Mechanical Equipment 査読有り国際誌

Shigyo R., Nobayashi D., Tsukamoto K., Mizumachi M., Ikenaga T.

Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022 1237 - 1238 2022年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

loT-based acoustic data collection systems have been proposed for detecting anomalies in equipment. However, such systems do not work well in outdoor environments due to interference caused by various sound sources (e.g., wildlife sounds and traffic noise). Outdoor noise has unique frequency characteristics, with energy localized in the low-frequency domain. In contrast, mechanical equipment such as motors mainly generates harmonics, including ultrasonic components, during operation. This paper proposes a noise-robust ultrasonic data collection system for outdoor use. To reduce the size of collected data, which increases in proportion to the sampling frequency, the proposed system uses bandpass filtering and data compression.

DOI： 10.1109/CSCI58124.2022.00222

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85172008371&origin=inward

Collision Avoidance Method for Broadcast Communication Over Multi-Hop HD-PLC Network 査読有り国際誌

Furuhama Y., Nobayashi D., Tsukamoto K., Ikenaga T.

Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022 1185 - 1186 2022年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

High Definition Power Line Communication (HD-PLC) is a communication technology that enables high-speed communications with a maximum PHY rate of 240 Mb/s using power lines. HD-PLC with multi-hop technology has been developed as a means of enabling long-distance communications. Multi-hop HD-PLC is expected to be used in BACnet for factory equipment and building management. However, the communication performance of BACnet is degraded by frequent data collisions caused by simultaneous broadcast message transmissions from multiple nodes. In this paper, we propose a transmission method to avoid collisions and reduce packet loss by using RTS/CTS control only in sections where collisions occur frequently. Simulation results show that the proposed method can reduce packet loss.

DOI： 10.1109/CSCI58124.2022.00212

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85171976279&origin=inward

Development of Wireless Communication System for Reliable Acoustic Data Collection Toward Anomaly Detection on Mechanical Equipment 査読有り

Chinari Takano, Shinya Fujino, Daiki Nobayashi, Kazuya Tsukamoto, Mitsunori Mizumachi, Takeshi Ikenaga

The 2021 International Conference on Computational Science & Computational Intelligence (CSCI 2021) 2021年12月

Path Schedulers Performance on Cellular/Wi-Fi Multipath Video Streaming 査読有り国際誌

Masayoshi Kondo, Dirceu Cavendish, Daiki Nobayashi, Takeshi Ikenaga

The Thirteenth International Conference on Evolving Internet (INTERNET 2020) 2021年07月

An Approach for Identifying Malicious Domain Names Generated by Dictionary-Based DGA Bots 査読有り国際誌

Akihiro Satoh, Yutaka Nakamura, Yutaka Fukuda, Daiki Nobayashi, Takeshi Ikenaga

IEICE Transactions on Information Systems E104-D ( 5 ) 2021年05月

IEEE802.11ac準拠の機器におけるチャネルボンディング機能の性能評価査読有り

田村瞳, 藤井一樹, 野林大起, 塚本和也

情報処理学会デジタルプラクティス 2 ( 2 ) 99 - 113 2021年04月

Transmission Control Method for Data Retention Taking into Account the Low Vehicle Density Environments 査読有り

Goto I., Nobayashi D., Tsukamoto K., Ikenaga T., Lee M.

IEICE Transactions on Information and Systems ( 電子情報通信学会 ) E104.D ( 4 ) 508 - 512 2021年04月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

SUMMARY With the development and spread of Internet of Things (IoT) technology, various kinds of data are now being generated from IoT devices. Some data generated from IoT devices depend on geographical location and time, and we refer to them as spatio-temporal data (STD). Since the “locally produced and consumed” paradigm of STD use is effective for location-dependent applications, the authors have previously proposed a vehicle-based STD retention system. However, in low vehicle density environments, the data retention becomes difficult due to the decrease in the number of data transmissions in this method. In this paper, we propose a new data transmission control method for data retention in the low vehicle density environments.

DOI： 10.1587/TRANSINF.2020EDL8088

Scopus

CiNii Article

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85105061121&origin=inward

Geolocation-centric information platform for resilient spatio-temporal content management 査読有り

Tsukamoto K., Tamura H., Taenaka Y., Nobayashi D., Yamamoto H., Ikenaga T., Lee M.

IEICE Transactions on Communications ( 電子情報通信学会 ) E104B ( 3 ) 199 - 209 2021年03月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

In IoT era, the growth of data variety is driven by cross-domain data fusion. In this paper, we advocate that “local production for local consumption (LPLC) paradigm” can be an innovative approach in cross-domain data fusion, and propose a new framework, geolocation-centric information platform (GCIP) that can produce and deliver diverse spatio-temporal content (STC). In the GCIP, (1) infrastructure-based geographic hierarchy edge network and (2) adhoc-based STC retention system are interplayed to provide both of geolocation-awareness and resiliency. Then, we discussed the concepts and the technical challenges of the GCIP. Finally, we implemented a proof-of-concepts of GCIP and demonstrated its efficacy through practical experiments on campus IPv6 network and simulation experiments.

DOI： 10.1587/transcom.2020NVI0003

Scopus

CiNii Article

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85102174288&origin=inward

Beacon-less autonomous transmission control method for spatio-temporal data retention 査読有り

Goto I., Nobayashi D., Tsukamoto K., Ikenaga T., Lee M.

Advances in Intelligent Systems and Computing 1263 AISC 503 - 513 2021年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

With the development and spread of Internet of Things (IoT) technology, the number of devices connected to the Internet is increasing, and various kinds of data are now being generated from IoT devices. Some data generated from IoT devices depends on geographical location and time. We refer to such data as spatio-temporal data (STD). Since the “local production and consumption” of STD is effective for location-dependent applications, we have proposed a STD retention system using vehicles equipped with storage modules, computing resources, and short-range wireless communication equipment. In this previous system, each vehicle controls the data transmission probability based on the neighboring vehicle density in order to achieve effective data retention. However, since the overhead of beacon messages required for estimation of the neighboring vehicle density becomes a critical problem with the increase in the number of vehicles, thereby preventing the effective data retention. In this paper, we propose a new data transmission control method to realize effective and reliable STD retention without beacon. Simulation results showed that our proposed scheme can achieve effective data retention.

DOI： 10.1007/978-3-030-57796-4_48

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85090094496&origin=inward

Efficient data diffusion and elimination control method for spatio-temporal data retention system 査読有り

Yamasaki S., Nobayashi D., Tsukamoto K., Ikenaga T., Lee M.J.

IEICE Transactions on Communications E104B ( 7 ) 805 - 816 2021年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

With the development and spread of Internet of Things technologies, various types of data for IoT applications can be generated anywhere and at any time. Among such data, there are data that depend heavily on generation time and location. We define these data as spatio-temporal data (STD). In previous studies, we proposed a STD retention system using vehicular networks to achieve the “Local production and consumption of STD” paradigm. The system can quickly provide STD for users within a specific location by retaining the STD within the area. However, this system does not take into account that each type of STD has different requirements for STD retention. In particular, the lifetime of STD and the diffusion time to the entire area directly influence the performance of STD retention. Therefore, we propose an efficient diffusion and elimination control method for retention based on the requirements of STD. The results of simulation evaluation demonstrated that the proposed method can satisfy the requirements of STD, while maintaining a high coverage rate in the area.

DOI： 10.1587/transcom.2020CQP0010

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85109677215&origin=inward

An approach for identifying malicious domain names generated by dictionary-based DGA bots 査読有り国際誌

Satoh A., Nakamura Y., Fukuda Y., Nobayashi D., Ikenaga T.

IEICE Transactions on Information and Systems ( 一般社団法人電子情報通信学会 ) E104.D ( 5 ) 669 - 672 2021年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

Computer networks are facing serious threats from the emergence of sophisticated new DGA bots. These DGA bots have their own dictionary, from which they concatenate words to dynamically generate domain names that are difficult to distinguish from human-generated domain names. In this letter, we propose an approach for identifying the callback communications of DGA bots based on relations among the words that constitute the character string of each domain name. Our evaluation indicates high performance, with a recall of 0.9977 and a precision of 0.9869.

DOI： 10.1587/transinf.2020NTL0001

Scopus

CiNii Article

CiNii Research

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85106744554&origin=inward

Development of a Wireless Communication System for Reliable Acoustic Data Collection Toward Anomaly Detection in Mechanical Equipment 査読有り

Takano C., Fujino S., Nobayashi D., Tsukamoto K., Mizumachi M., Ikenaga T.

Proceedings - 2021 International Conference on Computational Science and Computational Intelligence, CSCI 2021 1544 - 1547 2021年01月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

With the recent proliferation of Internet of Things (IoT) devices that can send and receive data via wireless communication, we are able to monitor and operate these devices remotely. An example of an IoT system using wireless communication is a system for anomaly detection in mechanical equipment using acoustic data. In order to detect anomalies using acoustic data, continuous recording is essential, thereby increasing the data size. Although Wi-Fi networks provide high-capacity data transfer, performance degradation cannot be avoided due to reasons such as packet losses caused by collisions with data from other devices using the same frequency and the increase in distance between two communicating devices. In the present study, we developed a wireless communication system for reliable acoustic data collection for anomaly detection in mechanical equipment. First, as preliminary experiments, we investigated the communication characteristics for the transmission of large-size data by Wi-Fi in indoor and outdoor environments. The results indicated the communication performance was insufficient for transferring all recorded data handled by this system. Therefore, we developed a simple heuristic transmission timing control method and a method that can reduce the amount of transmission data in order to realize a stable acoustic data collection system. Finally, through demonstration experiments using mechanical equipment in the field, we verified the feasibility of the acoustic data collection system.

DOI： 10.1109/CSCI54926.2021.00300

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85133931264&origin=inward

Development of Data Collection Platform for Running Cars by using 920MHz LoRa Communication in Urban Area 査読有り国際誌

Yasufumi Niwa, Daiki Nobayashi, Kazuya Tsukamoto, Takeshi Ikenag

2020 International Conference on Emerging Technologies for Communications (ICETC2020) 2020年12月

　前のページ - 次のページ　

<野林 大起>

論文 - 野林 大起

<野林　大起>

論文 - 野林　大起