研究者詳細 - 重野　寛

論文 - 重野　寛

分割表示 133 件中 1 - 20 件目／全件表示 >>

Poster: Virtual Platoon Considering Connected Human-Driven Vehicles at Unsignalized Intersection

Kitatani M., Iwashina Y., Shigeno H.

IEEE Vehicular Networking Conference, VNC 245 - 246 2024年

ISSN 21579857

Reducing traffic accidents and congestion remains a significant challenge, especially at intersections crucial for safety and efficiency. Virtual Platooning has been proposed to improve traffic efficiency. However, existing research has focused on Connected Autonomous Vehicles (CAVs), without taking into account human-driven vehicles, which lead to issues such as delay in reaction to stimulus onset and difficulty in controlling acceleration. In this paper, we propose method accounts for Connected Human-driven Vehicles (CHVs) and address these challenges through control interval adjustments, a target speed determination, and larger minimum following distances. Simulation using a traffic simulator confirms that our approach improves traffic safety and efficiency.

Access to Document (DOI)

Poster: Risk and Redundancy-Based Object Selection Method for Collective Perception Messages in Cellular-V2x

Miyata Y., Iwashina Y., Shigeno H.

IEEE Vehicular Networking Conference, VNC 249 - 250 2024年

ISSN 21579857

Connected and Automated Vehicles (CAVs) utilize Vehicle-To-Everything (V2X) communication to exchange messages and share information with surrounding vehicles. Collective Perception Messages (CPMs) contain object information detected by the onboard sensors. Through the exchange with nearby CAVs, CAVs can perceive the surrounding objects. Higher vehicle traffic densities, however, can lead to a shortage of communication resources and degradation of communication quality. This, as a result, leads to a decreased object recognition frequency. To mitigate such degradation, it is necessary to reduce the traffic volume of CPMs. Therefore, it is important to decrease the message size of CPMs. Various existing studies aimed at it have reduced the redundancy of CPMs. Most of the studies, however, do not prioritize the inclusion of high-Accident risk objects in CPMs, which leads to a higher Age of Information (AoI) for such objects. In this paper, we propose a risk and redundancy-based object selection method, called RRS, which selects objects for CPMs based on the accident risks for surrounding CAVs and the redundancy of CPMs in C-V2X. In this proposal, we define an accident avoidance acceleration a as an indicator of the accident risks. Based on a for surrounding CAVs and the number of CPM receptions indicating the redundancy, CAV s calculate the priority of objects for CPMs. CAV s select a fixed number of objects based on the priority for CPMs. We evaluate RRS through simulation experiments in an intersection scenario. The results show that RRS decreases the AoI for objects with high accident risks and the number of the highest risks.

Access to Document (DOI)

Evaluation of a Negotiation Acceptance Scheme in Maneuver Coordination within a Congested Environment

Iwashina Y., Kato S., Shigeno H.

Journal of Information Processing 32 223 - 231 2024年

A maneuver coordination service (MCS) is a generic cooperative driving method for connected and automated vehicles. In an MCS, each vehicle periodically broadcasts its planned trajectory by vehicular communication. When a vehicle wants to change its planned trajectory, it can send a desired trajectory and initiate negotiation with surrounding vehicles. A vehicle that receives the desired trajectory decides whether to accept the negotiation and updates its planned trajectory so as not to conflict with the desired trajectory for coordination. Most previous works evaluated MCSs assuming that the number of vehicles is small and that negotiation is always accepted. However, in a congested environment, accepting all negotiations may not be optimal for traffic efficiency because accepting negotiation affects both the negotiation participants and the surrounding vehicles that are not involved in the negotiation. In this paper, we propose a negotiation acceptance scheme in maneuver coordination for efficient traffic. This paper also proposes a utility function that takes the negotiation effect into account. In addition, the agreement phase is incorporated into the negotiation protocol to maintain acceptance consistency among several negotiation participants. Simulation results show that making appropriate settings for the negotiation acceptance scheme improves traffic efficiency in congested environments.

Access to Document (DOI)

Adaptive Message Prioritization for Vehicular Cooperative Perception at Target Intervals

Kunibe M., Yamazaki R., Murakawa T., Shigeno H.

Journal of Information Processing （Journal of Information Processing） 31 57 - 65 2023年

In this paper, we propose adaptive message prioritization for vehicular cooperative perception at target intervals. The purpose of this paper is to ensure that Connected and Autonomous Vehicles (CAVs) can perceive the surrounding traffic environment by exchanging wireless messages such as Cooperative Awareness Messages (CAMs) and Cooperative Perception Messages (CPMs). Especially, under challenging conditions such as the wireless congestion control or the mixed-traffic of CAVs and human-driven vehicles, the number of perceptible objects by these messages decreases due to the message transmission rate control under the congestion control or the less message transmission under the low CAV penetration rate. To perceive the surrounding objects under the challenging conditions, the proposed method assigns high transmission priority to CPMs that include the information of multiple objects perceived by in-vehicle sensors. Specifically, the method controls the transmission frequency of CAMs and CPMs by assigning transmission priority to them such that the maximum perception interval approaches the target interval. Simulation result shows that 75% CAVs perceive surrounding vehicles within the target interval even under both the wireless congestion control and 20% CAV penetration rate.

Access to Document (DOI)

Data Generation With Filtered β-VAE for the Preoperative Prediction of Adverse Events

Yamasaki Y., Doi C., Kitagawa S., Seki H., Shigeno H.

IEEE Access （IEEE Access） 11 48667 - 48676 2023年

Adverse events after surgery not only affect the patient's recovery but also increase the burden on doctors and patients due to prolonged hospitalization. Predicting adverse events from patient data before surgery with a machine learning method is highly expected. It is difficult to collect a large amount of patient data since the number of surgeries in a year is limited and predict the occurrence of adverse events accurately since patient data are imbalanced data. To improve the accuracy of adverse event prediction, this paper proposes data generation with Filtered VAE for the preoperative prediction of adverse events. Filtered VAE has filters by the reconstruction error and by a machine learning method. After VAE generates minority class data, the two layers of filtering are used to remove low-quality minority class data that have little contribution to the adverse event prediction. In the evaluations, patient data obtained from Tokyo Dental University Ichikawa General Hospital were used. The proposed method can predict adverse events with a recall of 0.848, which is 5.6% more accurate than existing methods. The effects of filtering in Filtered VAE are visualized, and the reasons for the improvement in prediction accuracy are clarified. Furthermore, this paper shows that VAE can generate arbitrary patient data even in table data, corresponding to the distribution of the original patient data.

Access to Document (DOI)

Pedestrian Clustering Method of Vehicle-To-Pedestrian Communication Considering Awareness Rate in Urban Environments

Ryu S., Murakawa T., Shigeno H.

2023 14th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2023 2023年

The European Telecommunication Standards Insti-Tute (ETSI) defined message including information of surrounding objects in V2P (Vehicle to Pedestrian) for traffic safety such as Cooperative Awareness Message (CAM), Vulnerable road user Awareness Message (VAM) and Collective Perception Message (CPM) In urban environment, convergence is occurred because large number of vehicles and pedestrians send messages. Some works suggested methods of reduction traffic of messages which are clustering or changing traffic rate. In clustering methods, cluster participation conditions are strict for pedestrian in the environment.The methods of changing traffic rate don't consider the are which require high awareness rate to avoid traffic accidents. In this paper, we propose the new threshold to relax joining conditions and the method to determinate VAM generation time in areas designated by vehicles. We compare our threshold with conventional method's one to show improving awareness rate. And we evaluate proposed methods to improve awareness rate in the specific area. In the result, the proposed method increased the object recognition rate, and showed a higher object recognition rate than the conventional method.

Access to Document (DOI)

UAV Path Planning in Urban Environments with Dynamic Risk-Map Generation by Vehicle and Pedestrian Perception

Iwashina Y., Kunibe M., Kato S., Shigeno H.

IEEE Vehicular Technology Conference （IEEE Vehicular Technology Conference） 2022-September 2022年

ISSN 15502252

In this paper, we propose the UAV path planning method in urban environments with dynamic risk-map generation by vehicle and pedestrian perception. In urban environments, it is the challenging task for Unmanned Aerial Vehicles (UAVs) to generate the safety flight path such that they will not collide with the ground vehicles and pedestrians in case of accidental fall. To mitigate the collision risk, the proposed method dynamically generates the risk-map, where collision risks within specific areas are mapped based on mobility of ground vehicles and pedestrians. To perceive the mobility of them, the proposed method utilizes Vehicle-to-Everything (V2X) messages that include position, velocity, and acceleration of the ground vehicles and pedestrians. Based on the proposed risk-map, UAVs seek their flight paths that minimize the collision risk by Rapidly-exploring Random Tree Star (RRT*) algorithm. Simulation result shows that the flight path of the proposed method decreases the collision risk compared with the shortest path and previous safety path in the situation that there are 200 vehicles and 400 pedestrians in 1250 m×1050m city.

Access to Document (DOI)

Q-Learning-Based Spatial Reuse Method Considering Throughput Fairness by Negative Reward for High Throughput

Takematsu M., Sakai S., Kunibe M., Shigeno H.

Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST （Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST） 419 LNICST 207 - 219 2022年

ISSN 18678211

In this paper, we propose a Q-learning-based spatial reuse method considering throughput fairness in Wireless LANs (WLANs). In Spatial Reuse (SR) methods, wireless nodes try to use wireless resources efficiently by controlling both the Transmission Power (TP) and Carrier Sense Threshold (CST). When wireless nodes are densely deployed, the SR methods have difficulty to achieve both the high aggregate throughput and throughput fairness because the mutual interference among the wireless nodes becomes severe. The proposed method removes the difficulty by utilizing Q-learning where wireless nodes can learn the adequate CST and TP by themselves. The proposed method motivates nodes to use wireless resources actively by rewards, while it suppresses nodes with high throughput using the resources by negative rewards. As a result, the wireless resources are distributed among nodes with low throughput, and the proposed method achieves both the high aggregate throughput and throughput fairness. Simulation results show that the proposed method improves the aggregate throughput with keeping throughput fairness.

Access to Document (DOI)

Multihop Cooperative Perception with Mitigating Sidelink Resource Breaks by Packet Filtering

Kunibe M., Shigeno H.

2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022 （2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022） 599 - 604 2022年

In this paper, we utilize multihop communication in sidelink Cellular Vehicle-to-Everything (C-V2X) communication for extending the perceptible range of surrounding environments. The challenging task of the sidelink multihop communication is to maintain periodically reserved wireless resources. Since the multihop communication generates aperiodic traffic, it has the potential to break the reserved resources in C-V2X. The proposed method filters the packets that will break the reserved resources. Furthermore, to avoid degrading the perception quality due to the packet filtering, the proposed method prompts vehicles to forward packets when there is enough room in their resources for forwarding the packets. In the simulation results, we confirm that the proposed method extends the perceptible range compared with single-hop communication and multihop communication with several ETSI parameters.

Access to Document (DOI)

A Dynamic Mix-zone Scheme Considering Communication Delay for Location Privacy in Vehicular Networks

Yamazaki R., Yoshida M., Shigeno H.

2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2021 （2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2021） 245 - 250 2021年03月

研究論文（国際会議プロシーディングス）

In vehicular networks, vehicles periodically exchange messages that include their positions and IDs. On the other hand, adversaries can violate the vehicles' location privacy by obtaining the vehicles' movement history from the messages. In recent studies, mix-zone-based schemes protect the vehicles' location privacy. In the schemes, vehicles utilize pseudonyms instead of their IDs in encrypted messages, and therefore adversaries cannot track them by their IDs. However, since the messages are encrypted by public keys of Road Side Units (RSUs), the vehicles can change their pseudonyms only around the RSUs. In this paper, we propose a Dynamic Mix-zone scheme considering Communication delay for Location Privacy (DMCLP). The DMCLP enables vehicles to change their pseudonyms even if there are no RSUs around them by removing necessity of RSUs from the mix-zone-based schemes. To remove the necessity, the DMCLP adopts both Identity-Based Signature (IBS) and proposed two-stage mix-zones. The IBS enables vehicles to certify the correctness of public keys by themselves. Therefore, it removes the necessity to tell the correctness to trusted authorities through RSUs. Furthermore, since RSUs guarantee connectivity of vehicular networks, influence of communication delay on pseudonym change becomes a problem without RSUs. The proposed two-stage mix-zones mitigate the influence of communication delay by removing vehicles that will cause communication delay from pseudonym change processes. Simulation results show that the proposed scheme improves update frequency of pseudonyms by 50 at most in 1000 seconds compared with the previous mix-zone-based scheme.

Access to Document (DOI)

Intraoperative Hypotension Prediction System by Considering Personal Lifestyle and Medical History

Inada R., Doi C., Yamasaki Y., Shigeno H., Seki H.

Intraoperative hypotension may occur during surgery, depending on the patient's condition and the amount of anesthetics administered. Intraoperative hypotension causes adverse events such as myocardial infarction, acute kidney injury, and stroke, which may affect patient prognosis and should be avoided. However, it is challenging to predict intraoperative hypotension before surgery. Therefore, the authors propose a system that predicts the occurrence of intraoperative hypotension with higher accuracy than existing studies to help preventing intraoperative hypotension. Specifically, the occurrence of intraoperative hypotension is predicted by using information about personal lifestyle and medical history obtained from the pre-anesthesia questionnaire in addition to the patients' baseline characteristics such as age and gender that have already been used. The authors constructed prediction model, that predicted intraoperative hypotension with an F-measure of 0.724.

Access to Document (DOI)

A Dynamic Task Offloading Method with Centralized Controller to Improve Task Success Rate

Toyoda M., Satake H., Shigeno H.

As the Internet of Vehicles (IoV) develops, vehicular applications become more complex. The existing offloading methods in the vehicular networks predict the time it takes to process a task and offload it to the computation resources that minimize the delay in execution. However, these methods do not adequately consider other vehicles on the road or the time constraints of the applications. Therefore, we propose a dynamic task offloading method with a centralized controller to improve the task success rate considering all vehicles on the road. We formulate the objective function which maximizes the success rate as a multiple knapsack problem by using an approximation algorithm. In the proposed method, the centralized controller gathers the information on vehicles and edge servers, and based on the algorithm it determines the edge server that maximizes the task success rate in the entire area. The algorithm calculates vehicle priority depending on the task success status of vehicles and determines the edge server based on that priority. In this paper, we conducted the experiments in which we implemented the prototype of the proposed method, and evaluated its performance. The experiments showed that the offloading method improved the task success rate by up to 38% compared to the existing methods.

Access to Document (DOI)

A scheduling scheme for autonomous vehicle highway merging with an outflow traffic and fairness analysis

Kunibe M., Asahina H., Shigeno H., Sasase I.

IEEE Access （IEEE Access） 9 49219 - 49232 2021年

Recently, vehicle-to-infrastructure (V2I) communication-based scheduling schemes for connected and automated vehicles (CAVs) on highway on-ramps have received attention because the schemes assign optimal merging times to CAVs based on their criteria, such as first-in first-out order or minimizing CAV total travel time. However, these schemes cause traffic congestion due to the criteria when the vehicle inflow traffic becomes high. To mitigate traffic congestion, a scheduling scheme should assign merging times to CAVs to decrease road vehicle density. In this paper, we propose a scheduling scheme for autonomous vehicle highway merging with an outflow traffic and fairness analysis. We formulate a multiobjective function that achieves both outflow traffic maximization and fairness in assigned merging times. Since more vehicles pass a highway on-ramp as highway on-ramp outflow traffic increases, the proposed scheme decreases vehicle density on roads by maximizing the outflow traffic. Furthermore, the proposed scheme distributes the vehicle density on both the main and ramp roads by fairly assigning their merging times. Simulation results show that the proposed scheme mitigates the potential traffic congestion of previous scheduling schemes. Furthermore, the proposed scheme improves outflow traffic from highway on-ramps by more than 200 veh/h compared with the previous scheduling schemes.

Access to Document (DOI)

Group Formation for Cooperative Highway Merging Considering Undetected Vehicles in Mixed Traffic

Kato S., Kunibe M., Yamazaki R., Shigeno H.

IEEE Vehicular Networking Conference, VNC （IEEE Vehicular Networking Conference, VNC） 2021-November 68 - 71 2021年

ISSN 21579857

Connected and Automated Vehicles (CAVs) have potential to improve the traffic efficiency near the highway on-ramps by sharing their merging times through wireless communication. For the traffic efficiency and vehicle safety, it has been the technical challenge to determine the merging times without collision of vehicles merging from different roads. Especially in the mixed traffic of CAVs and human-driven vehicles (hereinafter called non-CAVs), CAVs cannot detect all the non-CAVs even by their sensors. Therefore, it is necessary to determine CAVs' merging times for preventing the undetected non-CAVs from colliding with other vehicles. In this paper, we propose a group-based CAVs control method considering undetected non-CAVs in mixed traffic. The main idea of the proposed method is that it indirectly controls the undetected non-CAVs by CAVs. Specifically, the method forms vehicle groups each of which consists of a leading CAV and following non-CAVs. The method assigns merging times to the leading CAVs such that different groups do not merge onto the main road simultaneously. As a result, the undetected non-CAVs in a group do not collide with vehicles in the other groups. Simulation results show that the proposed method mitigates stop-and-go driving near the merging zone and improves outflow traffic.

Access to Document (DOI)

A Scheduling Scheme for Cooperative Merging at a Highway On-Ramp with Maximizing Average Speed of Automated Vehicles

Yoshida M., Asahina H., Shigeno H., Sasase I.

IEEE Vehicular Technology Conference （IEEE Vehicular Technology Conference） 2020-November 2020年11月

Recently, connected and automated vehicles have potential to mitigate traffic congestion and improve traffic efficiency at a highway on-ramp. Especially, vehicle to infrastructure communication based scheduling schemes are paid attention because a central control server can assign merging timing to automated vehicles to improve traffic efficiency on whole roads. Although several schemes calculate merging timing based on their criteria, these schemes cause traffic congestion when inflow traffic becomes high. In order to solve this problem, it is necessary to schedule merging timing of vehicles such that density of vehicles decreases on whole roads. In this paper, we propose a scheduling scheme for cooperative merging at a highway on-ramp with maximizing average speed of automated vehicles. The main idea of the proposed scheme is to utilize the traffic model that density and speed of vehicles have a negative correlation. By utilizing the traffic model, the proposed scheme preferentially assigns merging timing to vehicles which are on a congested road by maximizing average speed of all vehicles on whole roads. Simulation result shows that the proposed scheme decreases density of vehicles on whole roads even if inflow traffic becomes high. Furthermore, the proposed scheme improves outflow traffic from a highway on-ramp by 400 (veh/h) at most in comparison with related schemes.

Access to Document (DOI)

Dynamic Task Offload System Adapting to the State of Network Resources in Mobile Edge Computing

Satake H., Kobayashi Y., Tani R., Shigeno H.

2020 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2020 （2020 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2020） 2020年03月

© 2020 IEEE. In disaster situation, collecting information about victims and disaster area quickly is required. However, it is expected that the communication environment is not fully prepared because communication facilities may be damaged. Mobile Edge Computing (MEC) is attracting attention, in which servers are distributed to the vicinity of end users. Thus, dynamic task offloading adapting to changes of network resources is useful in unstable network. This paper proposes a dynamic task offload system based on the state of network. The proposed offload system consists of two mechanisms. First mechanism is Software Defined Mobile Edge Computing (SDMEC) architecture. Second mechanism is dynamic task placement based on the state of network resources. We formulated an optimization problem to minimize the total response time while application execution. In the proposed offload system, multiple tasks are placed dynamically depending on the load of servers and network resources to minimize response time of application. We implemented the prototype of the proposed offload system and evaluated its performance.

Access to Document (DOI)

モバイルクラウドセンシングにおける持続的な協力のためのインセンティブメカニズム

浅井菜々香, 五箇奏乃子, 重野寛

情報処理学会論文誌 61 （ 2 ） 397 - 405 2020年02月

研究論文（学術雑誌）, 共著, 査読有り

A Task Placement System for Face Recognition Applications in Edge Computing

Satake H., Tani R., Shigeno H.

2020 IEEE 17th Annual Consumer Communications and Networking Conference, CCNC 2020 （2020 IEEE 17th Annual Consumer Communications and Networking Conference, CCNC 2020） 2020年01月

© 2020 IEEE. Mobile devices have certain restrictions such as processing power and network bandwidth. Edge computing can reduce load and delay by migrating the parts of application processing from mobile devices to edge servers. Edge computing is a method that extends cloud computing to the edge of network. Conventional schemes of face recognition based on edge computing can reduce the amount of network transmission data between the edge servers and the cloud servers by preprocessing data on the edge servers. However, the schemes execute each task on a certain resource, thus application response time may increase according to the conditions of computational resources and network. Hence, a task placement system considering the conditions of computational resources and network is necessary. This paper proposes a task placement system for face recognition applications in edge computing. The proposed system calculates estimated response time of possible task placements based on the task placement decision formula. The formula parameterizes power and CPU utilization of computational resources and delay and bandwidth of network. The task placement that minimizes estimated response time is determined. We implemented a prototype of the proposed task placement system and evaluated its performance through experiment.

Access to Document (DOI)

Throughput Modeling and Analysis under Power Control in High Efficiency Wireless LAN

Iwai K., Ohnuma T., Inada R., Shigeno H.

2019 12th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2019 （2019 12th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2019） 2019年11月

© 2019 IPSJ. Carrier sense multiple access/collision avoidance (CSMA/CA) in wireless local area network (WLAN) is considered as a complex protocol for modeling due to its autonomous function and influence of interference with medium shared by multiple nodes. IEEE 802.11ax, a sixth generation WLAN standard, enables various flows with different modulation coding scheme (MCS) and traffic load, transmission power (TxP), clear channel assessment threshold (CCAT) to coexist in a WLAN. This variation makes modeling of WLAN system more difficult. This paper proposes a throughput model for high efficiency WLAN analysis under any traffic load and MCS condition. This model factorizes throughput into five elements. This flexible model can be applied to any complex topology. In simulation evaluation, a correlation coefficient between the results of the proposed model and simulation is observed by at most 0.981. Furthermore, The results shows that the influence on the throughput due to the change in TxP is correctly modeled and minimum TxP for maximum throughput is revealed on a condition.

Access to Document (DOI)

Prediction of Post-induction Hypotension Using Stacking Method

Iwai K., Doi C., Asai N., Shigeno H., Ideno S., Kato J., Yamada T., Morisaki H., Seki H.

2019 12th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2019 （2019 12th International Conference on Mobile Computing and Ubiquitous Network, ICMU 2019） 2019年11月

© 2019 IPSJ. Electronic anesthesia record data have been accumulated, and efforts to solve medical problems using data analysis methods and machine learning have been conducted. Post-induction hypotension frequently occurred after induction of anesthesia. Intraoperative hypotension is associated with various adverse events such as myocardial infarction and cerebral infarction. In a related study, eight machine learning methods were used to construct hypotension prediction models and evaluated by area under the curve (AUC), using data collected from an institution in the United States. Nevertheless, it was not focused on improving prediction power. This paper aims to predict post-induction hypotension with high prediction power using 1,626 electronic anesthesia record data. Our hypotension prediction model using a stacking method is introduced. F-measure 0.60 was achieved by using our method through the evaluation.

Access to Document (DOI)

　前のページ - 次のページ　

重野 寛

論文 - 重野 寛

重野　寛

論文 - 重野　寛