Kuon Akiyama
Research Subjects
Research Interests
Kuon Akiyama has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Ryoichi Shinkuma
Shibaura Institute of Technology, Tokyo, Japan
6 shared publications - Gabriele Trovato
Shibaura Institute of Technology,Japan
2 shared publications - Jernej Hribar
Joef Stefan Institute, Ljubljana, Slovenia
2 shared publications Aramu Mine
GaiaX. Co., Ltd.,Japan
1 shared publication- Blaž Bertalanič
SensorLab, Jožef Stefan Institute, Ljubljana, Slovenia
1 shared publication - George Iosifidis
Department of Software Technology, Delft University of Technology, Delft, The Netherlands
1 shared publication
Latest Publications
- 3 November 2026
- Published by Elsevier in Computer Networks
- Vol. 292
Spatial-importance-aware bandwidth control for multi-LiDAR sensor network in 5G environment
- 3 November 2026
- Published by Elsevier in Computer Networks
- Vol. 292
Spatial-importance-aware bandwidth control for multi-LiDAR sensor network in 5G environment
- Open Access
- 11 June 2026
- Published by Elsevier in Data in Brief
- Vol. 67, 112959
An indoor radio mapping dataset combining 3D point clouds and RSSI
- 11 June 2026
- Published by Elsevier in Data in Brief
- Vol. 67, 112959
Open AccessAn indoor radio mapping dataset combining 3D point clouds and RSSI
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (22) , 38352-38364
Balancing Energy Preservation and Performance in Energy-Harvesting Sensor Networks
The development of environmentally friendly, green communications is at the forefront of designing future Internet of Things (IoT) networks, although many opportunities to improve energy conservation from Energy Harvesting (EH) sensors remain unexplored. Ubiquitous computing power, available in the form of cloudlets, enables processing of the collected observations at the network edge. Often, the information that the Artificial Intelligence of Things (AIoT) application obtains by processing observations from one sensor can also be obtained by processing observations from another sensor. Consequently, a sensor can take advantage of the correlation between processed observations to avoid unnecessary transmissions and save energy. For example, when two cameras monitoring the same intersection detect the same vehicles, the system can recognize this overlap and reduce redundant data transmissions. This approach allows the network to conserve energy while still ensuring accurate vehicle detection, thereby maintaining the overall performance of the AIoT task. In this paper, we consider such a system and develop a novel solution named Balancing Energy Efficiency in Sensor Networks with Multi-Agent Reinforcement Learning (BEES-MARL). Our proposed solution is capable of taking advantage of correlations in a system with multiple EH-powered sensors observing the same scene and transmitting their observations to a cloudlet. We evaluate the proposed solution in two data-driven use cases to verify its benefits and in a general setting to demonstrate scalability. Our solution improves task performance, measured by recall, by up to 16% over a heuristic approach, while minimizing latency and preventing outages.
- 3 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (22) , 38352-38364
Balancing Energy Preservation and Performance in Energy-Harvesting Sensor Networks
The development of environmentally friendly, green communications is at the forefront of designing future Internet of Things (IoT) networks, although many opportunities to improve energy conservation from Energy Harvesting (EH) sensors remain unexplored. Ubiquitous computing power, available in the form of cloudlets, enables processing of the collected observations at the network edge. Often, the information that the Artificial Intelligence of Things (AIoT) application obtains by processing observations from one sensor can also be obtained by processing observations from another sensor. Consequently, a sensor can take advantage of the correlation between processed observations to avoid unnecessary transmissions and save energy. For example, when two cameras monitoring the same intersection detect the same vehicles, the system can recognize this overlap and reduce redundant data transmissions. This approach allows the network to conserve energy while still ensuring accurate vehicle detection, thereby maintaining the overall performance of the AIoT task. In this paper, we consider such a system and develop a novel solution named Balancing Energy Efficiency in Sensor Networks with Multi-Agent Reinforcement Learning (BEES-MARL). Our proposed solution is capable of taking advantage of correlations in a system with multiple EH-powered sensors observing the same scene and transmitting their observations to a cloudlet. We evaluate the proposed solution in two data-driven use cases to verify its benefits and in a general setting to demonstrate scalability. Our solution improves task performance, measured by recall, by up to 16% over a heuristic approach, while minimizing latency and preventing outages.
- 22 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (15) , 17676-17689
Real-Time Adaptive Data Transmission Against Various Traffic Load in Multi-LIDAR Sensor Network for Indoor Monitoring
One of the key components in smart cities is smart monitoring, a process for collecting information to efficiently manage the infrastructures and resources and enables citizens to engage in intelligent activities. For both indoor and outdoor monitoring, light detection and ranging (LIDAR) technology has been used to collect three-dimensional data useful for smart monitoring. Blind spots can be effectively covered by aggregating point clouds from multiple LIDAR sensors (sensors hereafter) with different viewpoints. Although multiple-LIDAR (multi-LIDAR) sensor networks have been investigated, prior studies have focused on monitoring outdoor scenes with a relatively low number of sensors, mostly for road safety. For indoor use, however, ten or more sensors are required to eliminate blind spots, as the placement of sensors is limited by ceilings. When the network bandwidth is limited because of other traffic loads, the transmission size needs to be small while including the highly important points. Therefore, adaptive control is required for sensor networks. We propose a system that adaptively controls the data volume of a multi-LIDAR sensor network considering the current network state in real time. It consists of a single edge computer and multiple sensors. While aggregating data streams, the edge computer monitors the current delay status for each sensor and sends notifications to change the data volume by the sensor.We report on the results of two experimental evaluations conducted in different environments: one to validate the effectiveness of the proposed system and the other to verify its practicality.
- 22 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (15) , 17676-17689
Real-Time Adaptive Data Transmission Against Various Traffic Load in Multi-LIDAR Sensor Network for Indoor Monitoring
One of the key components in smart cities is smart monitoring, a process for collecting information to efficiently manage the infrastructures and resources and enables citizens to engage in intelligent activities. For both indoor and outdoor monitoring, light detection and ranging (LIDAR) technology has been used to collect three-dimensional data useful for smart monitoring. Blind spots can be effectively covered by aggregating point clouds from multiple LIDAR sensors (sensors hereafter) with different viewpoints. Although multiple-LIDAR (multi-LIDAR) sensor networks have been investigated, prior studies have focused on monitoring outdoor scenes with a relatively low number of sensors, mostly for road safety. For indoor use, however, ten or more sensors are required to eliminate blind spots, as the placement of sensors is limited by ceilings. When the network bandwidth is limited because of other traffic loads, the transmission size needs to be small while including the highly important points. Therefore, adaptive control is required for sensor networks. We propose a system that adaptively controls the data volume of a multi-LIDAR sensor network considering the current network state in real time. It consists of a single edge computer and multiple sensors. While aggregating data streams, the edge computer monitors the current delay status for each sensor and sends notifications to change the data volume by the sensor.We report on the results of two experimental evaluations conducted in different environments: one to validate the effectiveness of the proposed system and the other to verify its practicality.
- 8 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 704-705
Blockchain framework for managing machine-learning models for 3D object detection
Smart monitoring plays an important role in securing people's safety in smart cities. In smart monitoring, machine-learning (ML) models are used for detecting objects in the environment, such as pedestrians and vehicles. Such ML models need to be securely managed against malicious attacks, such as tampering. This paper proposes a blockchain framework for securely managing ML models. It demonstrates the performance of a prototype of the proposed framework.
- 8 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 704-705
Blockchain framework for managing machine-learning models for 3D object detection
Smart monitoring plays an important role in securing people's safety in smart cities. In smart monitoring, machine-learning (ML) models are used for detecting objects in the environment, such as pedestrians and vehicles. Such ML models need to be securely managed against malicious attacks, such as tampering. This paper proposes a blockchain framework for securely managing ML models. It demonstrates the performance of a prototype of the proposed framework.
- 8 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 927-928
Prototype of edge sensing and computing system with multi-LIDAR network for autonomous micro-mobility
This demonstration proposes an edge system that enables sensing and computing capacities to be offloaded from vehicles to the system. We developed a prototype of the proposed system, in which a sensor network using multiple light-detection-and-ranging (LIDAR) units works for sensing and computing, while autonomous vehicles are equipped only with lightweight sensing and computation capabilities. This demon-stration presents the performance of the prototype in terms of movement accuracy to verify the feasibility of the proposed system.
- 8 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 927-928
Prototype of edge sensing and computing system with multi-LIDAR network for autonomous micro-mobility
This demonstration proposes an edge system that enables sensing and computing capacities to be offloaded from vehicles to the system. We developed a prototype of the proposed system, in which a sensor network using multiple light-detection-and-ranging (LIDAR) units works for sensing and computing, while autonomous vehicles are equipped only with lightweight sensing and computation capabilities. This demon-stration presents the performance of the prototype in terms of movement accuracy to verify the feasibility of the proposed system.