Article
Computer Science, Information Systems
Liang Zhao, Fangyu Li, Maria Valero
Summary: The article presents a novel data analytics framework for edge computing using a decentralized algorithm, allowing all nodes to obtain global optimal model without sharing raw data. The local IoT nodes send calculated information to edge nodes, which cooperate with each other by exchanging analytics with their neighbors, demonstrating effective fast data analytics in the edge computing infrastructure.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Aaron Hurst, Daniel E. E. Lucani, Ira Assent, Qi Zhang
Summary: The Internet of Things (IoT) has led to a significant increase in sensor data, necessitating efficient and novel solutions for data transmission, storage, and analytics in sustainable IoT ecosystems. This article presents a thorough stress test of existing methods for direct analytics of generalized deduplication (GD) compressed data and identifies the need for optimization. A new version of GD is developed, and a framework called generalized deduplication-enabled approximate edge analytics (GLEAN) is proposed to address challenges related to data transmission, storage, and analytics in the IoT. Impressive analytics performance is achieved with GLEAN, offering a median increase in clustering error of only 2% relative to uncompressed data, while being significantly faster and requiring less storage at the Edge server compared to universal compressors.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
YiZhuo Yang, HongJin Zeng, TingPing Chen, Meng Lv
Summary: This paper investigates the joint problem of task offloading and heterogeneous protocol device access in command and control communication networks, proposing a real-time data unified access platform and a data parsing/encapsulation algorithm to address the challenges of protocol conversion and device access.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Automation & Control Systems
Jefferson Silva Almeida, Chenxi Huang, Fabricio Gonzalez Nogueira, Surbhi Bhatia, Victor Hugo C. de Albuquerque
Summary: This article proposes a novel lightweight convolutional neural network (CNN) model for wildfire detection through RGB images. The proposed method shows advantages in efficiency and accuracy, and can be combined with unmanned aerial vehicles and video surveillance systems for image processing. The ability to send timely wildfire alerts makes this method significant for forest protection.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Amirhossein Moallemi, Alessio Burrello, Davide Brunelli, Luca Benini
Summary: This article introduces an efficient and scalable anomaly detection pipeline for structural health monitoring systems that relies on edge computation rather than cloud computing, reducing network traffic and minimizing resource utilization. A real-life case study on an Italian highway bridge demonstrates the successful application of the approach in reducing data communication and cloud computing costs without compromising anomaly detection accuracy.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Bing Xie
Summary: The rapid development of mobile Internet and Internet of Things is driving the future network towards higher speed, lower latency, and greater reliability. Edge computing can meet high computing needs of mobile devices by offloading intensive tasks to nearby servers. The open platform for intelligent R&D and technology innovation management services based on edge computing shows significant advantages and can effectively meet different needs while improving user engagement.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2021)
Article
Computer Science, Information Systems
Desoky Abdelqawy, Abeer El-Korany, Amr Kamel, Soha Makady
Summary: The Internet of Things (IoT) faces challenges due to vendor diversity and lack of a common communication interface, resulting in reduced resource utilization and additional costs. This study proposes an IoT computing platform architecture, called Hub-OS, for efficient management of devices and applications from different vendors, enabling seamless integration and real-time processing.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Theory & Methods
Yousung Yang, Seongsoo Lee, Joohyung Lee
Summary: This paper presents the design and implementation of a video analytics based real-time intelligent crossing detection system (RICDS) for smart cities. The system utilizes an adaptive queue management-based object tracking scheme to enhance object tracking on edge devices with limited computational resources. The system also introduces a real-world-real-time tracking scheme to predict the future positions of multiple objects and assign unique IDs to them. Experimental results show that the proposed tracking scheme achieves a significant latency reduction while maintaining similar multi object tracking accuracy compared to benchmark schemes.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Information Systems
Prasad Ramesh Desai, S. Mini, Deepak K. Tosh
Summary: This article emphasizes the importance of using software-defined networking (SDN) and Internet of Things (IoT) to achieve efficient communication and proposes three optimized path algorithms to improve communication efficiency.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Editorial Material
Automation & Control Systems
Syed Hassan Ahmed Shah, Deepika Koundal, Vyasa Sai, Shalli Rani
Summary: The relationship between computing and healthcare has a long history, but the adoption of telemedicine has been slow due to political resistance, lack of infrastructure development frameworks, and lack of resources. The Internet of Medical Things (IoMT) is expected to bring about significant advancements, particularly when combined with edge computing and 5G speed. Artificial intelligence and edge computing have played a crucial role in improving the network for reliable communication in smart healthcare systems.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Jingzheng Tu, Cailian Chen, Qimin Xu, Bo Yang, Xinping Guan
Summary: This article proposes a resource-efficient MOT method for IoT embedded devices, achieving real-time surveillance with low latency through optimization strategies and model compression.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Liang Zhao, Maria Valero, Seyedamin Pouriyeh, Lei Li, Quan Z. Sheng
Summary: In this article, a semi-hierarchical federated analytics framework is proposed which leverages multiple edge servers for model learning and data aggregation without the need for a central server or cloud. The framework aims to improve communication efficiency and data analysis performance in IoT networks by combining the advantages of traditional centralized and fully decentralized approaches.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Francesco Tusa, Stuart Clayman
Summary: Edge microservice applications are a viable solution for real-time IoT analytics due to their rapid response and reduced latency. Microservices are not standalone but are a set of cooperating tasks that feed data over the network through specific APIs. Choice of encoding and transport mechanism has a significant impact on microservice implementation and can lead to excessive resource consumption if not done efficiently.
JOURNAL OF GRID COMPUTING
(2021)
Article
Automation & Control Systems
Xiaohan Tu, Cheng Xu, Siping Liu, Renfa Li, Guoqi Xie, Jing Huang, Laurence Tianruo Yang
Summary: This article addresses the shortcomings of monocular depth estimation (MDE) methods by designing an efficient model and utilizing a reinforcement learning algorithm for automatic channel pruning. Through pruning and compilation optimization, experimental results demonstrate the effectiveness of our methods in achieving accurate depth sensing on different hardware architectures.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Yang Yang, Robbert Elsinghorst, Jayson J. Martinez, Hongfei Hou, Jun Lu, Zhiqun Daniel Deng
Summary: The article describes the design, implementation, and field validation of a cloud-based, real-time underwater acoustic telemetry system with edge computing for estimating fish behavior and monitoring environmental parameters. The system incorporates microcontrollers for edge computing and connects to a cloud-based service for post-processing transmitted data.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Wen Sun, Lu Wang, Jiajia Liu, Nei Kato, Yanning Zhang
Summary: The paper explores how to choose the appropriate BS cooperation set to reduce handover rate, introducing MACH and iMACH schemes. Utilizing stochastic geometry method, the performance expressions of these schemes are derived. Theoretical analyses show that the proposed schemes outperform the existing schemes in terms of coverage probability, handover probability, and throughput, making them more intelligent and suitable for ultra-dense scenarios.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Shikhar Verma, Yuichi Kawamoto, Nei Kato
Summary: To address security threats in WLAN technologies for IoT, regular vulnerability assessments of IoT devices are necessary, along with optimized port scanning processes to ensure the effectiveness of IPSec services and balance network performance.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Tohn Furutani, Yuichi Kawamoto, Hiroki Nishiyama, Nei Kato
Summary: Wi-Fi Direct is a device-to-device communication technology that enables information sharing and diffusion in disaster areas, but is not effective for spreading data widely. A novel method utilizing WFD and DTN has been proposed, involving virtual cell design and communication time assignment to enable efficient information diffusion without interference.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2021)
Article
Engineering, Electrical & Electronic
Hiroaki Hashida, Yuichi Kawamoto, Nei Kato, Masashi Iwabuchi, Tomoki Murakami
Summary: This paper proposes an IRS-user association strategy considering user mobility for IRS-aided multibeam transmission systems, aiming to optimize system capacity and reliability, while reducing channel estimation overhead.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Hiroaki Hashida, Yuichi Kawamoto, Nei Kato
Summary: This study investigates the optimal pilot interval design to reduce channel estimation overheads in intelligent reflecting surface (IRS)-aided communication systems. The proposed method aims to balance the accuracy of the IRS reflection coefficient with system throughput by considering user equipment (UE) velocity and the complex spatial correlation of the channel matrix.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Shikhar Verma, Yuichi Kawamoto, Nei Kato
Summary: The Internet of Things presents security concerns due to weak protocols and limited resources, necessitating vulnerability and risk assessments. The Internet-wide port scan (IWPS) technique is used for discovering IoT devices, but its performance is affected by WLAN conditions. A novel approach to identifying WLAN states using round-trip time and probe-packet responses was proposed and validated through experiments, achieving an accuracy of over 90%.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Hiroaki Hashida, Yuichi Kawamoto, Nei Kato
Summary: The proposed passive beamforming method called selective reflection control (SRC) in distributed IRS communication systems enhances user sum rate and robust transmissions against shielding by determining associations between IRS and user equipment (UE) to reduce channel estimation overheads. The method outperforms benchmark methods and is expected to accelerate large-scale IRS deployment.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Ryuhei Hibi, Yuichi Kawamoto, Nei Kato
Summary: This study proposes a standalone-IRS control method that reduces overhead and improves communication quality through techniques such as hierarchical exploration and codebook storage.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Takahiro Ohyama, Yuichi Kawamoto, Nei Kato
Summary: Intelligent reflecting surface (IRS) is a technology that controls propagation characteristics and is being widely studied to improve energy efficiency in 6th generation mobile communication systems. In cell-free networks, which consist of multiple distributed base stations (BSs), IRS is introduced to effectively manage inter-cell interference at a lower cost and power consumption. This study investigates the use of IRS in a shadowing environment of a cell-free network with distributed BSs and single antenna, and proposes a quadratic unconstrained binary optimization formulation to optimize the IRS reflection coefficient using quantum computing. Simulation results demonstrate that the proposed method significantly improves communication efficiency. This study provides insights into the optimal control methods for different communication environments and contributes to the optimization of the entire cell-free system.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2023)
Article
Computer Science, Information Systems
Yuichi Kawamoto, Takuto Mitsuhashi, Nei Kato
Summary: Collecting and providing information are crucial for safe driving and automatic operation in intelligent transport systems (ITSs). When disasters occur, UAVs can assist in spreading information uninterruptedly and contribute to managing traffic situations through vehicle-to-vehicle communication.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2022)
Article
Computer Science, Information Systems
Takahiro Ohyama, Yuichi Kawamoto, Nei Kato
Summary: Intelligent Reflecting Surface (IRS) improves energy utilization efficiency in 6th generation cellular communication systems. We propose an IRS allocation scheduling method that limits the number of users allocated to each IRS and sets reflection coefficients specifically for assigned users, resulting in maximum IRS array gain.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2022)
Article
Computer Science, Information Systems
Hikaru Tsuchida, Yuichi Kawamoto, Nei Kato, Kazuma Kaneko, Shigenori Tani, Masatake Hangai, Hiroshi Aruga
Summary: In this study, a communication method that controls the transmission power and transmission gain of a satellite antenna based on the deterioration state of the battery is developed to increase the battery's lifetime. The reduction in running costs following the prolongation of the battery's lifetime will allow the development and use of large-scale LEO satellite constellations. The effectiveness of the proposed method is verified through simulation.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2022)
Article
Computer Science, Information Systems
Bomin Mao, Fengxiao Tang, Yuichi Kawamoto, Nei Kato
Summary: Green communications are crucial for reducing energy overhead and fossil fuel usage in the information industry. With the advent of 5G and future 6G eras, the demand for green communications becomes even more urgent. Artificial Intelligence (AI) is recognized as the only solution to meet the stringent requirements of 6G while improving energy efficiency and network management. This paper provides an overview of AI-based green communications and discusses the potential research issues for AI models in the green 6G era.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2022)
Article
Computer Science, Information Systems
Fengxiao Tang, Bomin Mao, Yuichi Kawamoto, Nei Kato
Summary: End-to-end quality of service (QoS) and quality of experience (QoE) guarantee is crucial for network optimization, especially in 5G and future 6G networks. Machine learning algorithms are seen as key solutions for optimizing 6G networks, but there are still many challenges and open issues to be addressed.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2021)