The Experts below are selected from a list of 315 Experts worldwide ranked by ideXlab platform

Eiji Kamioka - One of the best experts on this subject based on the ideXlab platform.

  • AINA - Uncertain Low Penetration Rate -- A Practical Issue in Mobile Intelligent Transportation Systems
    2012 IEEE 26th International Conference on Advanced Information Networking and Applications, 2012
    Co-Authors: Quang Tran Minh, Muhammad Ariff Baharudin, Eiji Kamioka
    Abstract:

    Low penetration rate is one of the essential issues in the mobile phone based traffic State Estimation model. This paper proposes an appropriate genetic algorithm (GA) mechanism to optimize the traffic State Estimation model even in cases of low penetration rate. This mechanism also reduces the critical penetration rate, thus improves the error-tolerance as well as the scalability of the traffic State Estimation System. The paper also investigates the ANN-based prediction model to overcome the weakness of the GA-based traffic State Estimation approach when the penetration rate becomes unacceptably low. In addition, the effect of different level related road segments on the prediction effectiveness is thoroughly discussed. Consequently, this study provides practically useful instructions in verifying the data missing rate at different level related road segments to ensure the prediction accuracy. The experimental evaluations reveal the effectiveness and the robustness of the proposed solutions.

  • VTC Fall - Assuring Accuracy on Low Penetration Rate Mobile Phone-Based Traffic State Estimation System
    2011 IEEE Vehicular Technology Conference (VTC Fall), 2011
    Co-Authors: Quang Tran Minh, Eiji Kamioka
    Abstract:

    This paper investigates the effect of the penetration rate on the effectiveness of the mobile phone-based traffic State Estimation. As a result, the acceptable penetration rate is identified. This recognition is useful for the investigating to bring the traffic State Estimation using mobile phones as traffic probes into the real world application. In addition, an adaptive velocity-density Estimation model, namely the velocity-density inference circuit, is proposed to improve the accuracy of the average velocity and the density Estimations in cases of low penetration rate. Furthermore, a neural network-based prediction model is introduced to assure the effectiveness of the velocity/density Estimation when the penetration rate degrades to zero. The experimental evaluations reveal the effectiveness as well as the robustness of the proposed solutions.

  • Assuring Accuracy on Low Penetration Rate Mobile Phone-Based Traffic State Estimation System
    2011 IEEE Vehicular Technology Conference (VTC Fall), 2011
    Co-Authors: Quang Tran Minh, Eiji Kamioka
    Abstract:

    This paper investigates the effect of the penetration rate on the effectiveness of the mobile phone-based traffic State Estimation. As a result, the acceptable penetration rate is identified. This recognition is useful for the investigating to bring the traffic State Estimation using mobile phones as traffic probes into the real world application. In addition, an adaptive velocity-density Estimation model, namely the velocity-density inference circuit, is proposed to improve the accuracy of the average velocity and the density Estimations in cases of low penetration rate. Furthermore, a neural network-based prediction model is introduced to assure the effectiveness of the velocity/density Estimation when the penetration rate degrades to zero. The experimental evaluations reveal the effectiveness as well as the robustness of the proposed solutions.

  • Pinpoint: An Efficient Approach to Traffic State Estimation System Using Mobile Probes
    2010 6th International Conference on Wireless Communications Networking and Mobile Computing (WiCOM), 2010
    Co-Authors: Quang Tran Minh, Eiji Kamioka
    Abstract:

    This paper proposes a novel, nicknamed the "Pinpoint", method for an efficient and robust traffic Estimation System using mobile phones as traffic probes. In this approach, the real-time traffic data is collected and sent to the server at the right time by the right players. Only the utilized data is reported to the server by the travelling vehicles. The mobile phones from walkers are prevented from sending data thus the data transmission load is controlled, improving efficiency and effectiveness of the System significantly. In additions, this approach consists of a robust vehicle classification method based on only the GPS data. This novel feature improves not only the accuracy in estimating the seriousness of congestions but also the scalability of the System. This proposed approach can be flexibly applied in any traffic System structure and in any country, especially in developing countries where a lot of motorbikes are travelling on the roads. The evaluation shows that our proposed method is more efficient, effective and scalable compared to the existing ones.

Quang Tran Minh - One of the best experts on this subject based on the ideXlab platform.

  • AINA - Uncertain Low Penetration Rate -- A Practical Issue in Mobile Intelligent Transportation Systems
    2012 IEEE 26th International Conference on Advanced Information Networking and Applications, 2012
    Co-Authors: Quang Tran Minh, Muhammad Ariff Baharudin, Eiji Kamioka
    Abstract:

    Low penetration rate is one of the essential issues in the mobile phone based traffic State Estimation model. This paper proposes an appropriate genetic algorithm (GA) mechanism to optimize the traffic State Estimation model even in cases of low penetration rate. This mechanism also reduces the critical penetration rate, thus improves the error-tolerance as well as the scalability of the traffic State Estimation System. The paper also investigates the ANN-based prediction model to overcome the weakness of the GA-based traffic State Estimation approach when the penetration rate becomes unacceptably low. In addition, the effect of different level related road segments on the prediction effectiveness is thoroughly discussed. Consequently, this study provides practically useful instructions in verifying the data missing rate at different level related road segments to ensure the prediction accuracy. The experimental evaluations reveal the effectiveness and the robustness of the proposed solutions.

  • VTC Fall - Assuring Accuracy on Low Penetration Rate Mobile Phone-Based Traffic State Estimation System
    2011 IEEE Vehicular Technology Conference (VTC Fall), 2011
    Co-Authors: Quang Tran Minh, Eiji Kamioka
    Abstract:

    This paper investigates the effect of the penetration rate on the effectiveness of the mobile phone-based traffic State Estimation. As a result, the acceptable penetration rate is identified. This recognition is useful for the investigating to bring the traffic State Estimation using mobile phones as traffic probes into the real world application. In addition, an adaptive velocity-density Estimation model, namely the velocity-density inference circuit, is proposed to improve the accuracy of the average velocity and the density Estimations in cases of low penetration rate. Furthermore, a neural network-based prediction model is introduced to assure the effectiveness of the velocity/density Estimation when the penetration rate degrades to zero. The experimental evaluations reveal the effectiveness as well as the robustness of the proposed solutions.

  • Assuring Accuracy on Low Penetration Rate Mobile Phone-Based Traffic State Estimation System
    2011 IEEE Vehicular Technology Conference (VTC Fall), 2011
    Co-Authors: Quang Tran Minh, Eiji Kamioka
    Abstract:

    This paper investigates the effect of the penetration rate on the effectiveness of the mobile phone-based traffic State Estimation. As a result, the acceptable penetration rate is identified. This recognition is useful for the investigating to bring the traffic State Estimation using mobile phones as traffic probes into the real world application. In addition, an adaptive velocity-density Estimation model, namely the velocity-density inference circuit, is proposed to improve the accuracy of the average velocity and the density Estimations in cases of low penetration rate. Furthermore, a neural network-based prediction model is introduced to assure the effectiveness of the velocity/density Estimation when the penetration rate degrades to zero. The experimental evaluations reveal the effectiveness as well as the robustness of the proposed solutions.

  • Pinpoint: An Efficient Approach to Traffic State Estimation System Using Mobile Probes
    2010 6th International Conference on Wireless Communications Networking and Mobile Computing (WiCOM), 2010
    Co-Authors: Quang Tran Minh, Eiji Kamioka
    Abstract:

    This paper proposes a novel, nicknamed the "Pinpoint", method for an efficient and robust traffic Estimation System using mobile phones as traffic probes. In this approach, the real-time traffic data is collected and sent to the server at the right time by the right players. Only the utilized data is reported to the server by the travelling vehicles. The mobile phones from walkers are prevented from sending data thus the data transmission load is controlled, improving efficiency and effectiveness of the System significantly. In additions, this approach consists of a robust vehicle classification method based on only the GPS data. This novel feature improves not only the accuracy in estimating the seriousness of congestions but also the scalability of the System. This proposed approach can be flexibly applied in any traffic System structure and in any country, especially in developing countries where a lot of motorbikes are travelling on the roads. The evaluation shows that our proposed method is more efficient, effective and scalable compared to the existing ones.

Myoungho Sunwoo - One of the best experts on this subject based on the ideXlab platform.

  • Probabilistic lane detection and lane tracking for autonomous vehicles using a cascade particle filter
    Proceedings of the Institution of Mechanical Engineers Part D: Journal of Automobile Engineering, 2015
    Co-Authors: Chulhoon Jang, Myoungho Sunwoo
    Abstract:

    This paper proposes a robust lane detection algorithm with a cascade particle filter that incorporates a model decomposition approach. Despite the sophisticated tracking mechanism of a particle filter, the conventional particle-filter-based lane detection System suffers from an Estimation accuracy problem and a high computational load. In order to improve the robustness and the computation time for lane detection Systems, the proposed cascade particle filter decomposes a lane model into two submodels: a straight model and a curve model. By dividing the lane model, not only can the computation time be decreased, but also the accuracy of the lane State Estimation System can be increased. The proposed lane detection algorithm and the cascade particle filter were evaluated on various roads and environmental conditions with the autonomous vehicle A1, which was the winner of the 2010 and 2012 Autonomous Vehicle Competition in the Republic of Korea organized by the Hyundai motor group. The proposed algorithm pro...

  • ITSC - Distributed vehicle State Estimation System using information fusion of GPS and in-vehicle sensors for vehicle localization
    2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), 2011
    Co-Authors: Kichun Jo, Myoungho Sunwoo
    Abstract:

    This paper proposes a distributed vehicle State Estimation System to improve the performance of vehicle positioning using Global Positioning System (GPS) and in-vehicle sensor components. The distributed architecture of the Estimation System can reduce the computational complexity of high-order Estimation by dividing it into several small-order Estimation modules, and simplifies fault detection and isolation problems. The distributed vehicle State Estimation algorithm consists of three Estimation modules. The first is a longitudinal vehicle State Estimation module which estimates the longitudinal vehicle speed and road slope. The road slope estimate is used to compensate for the vertical speed on the sloped road. The second module is a lateral vehicle State estimator which estimates yaw rate, yaw, and side slip angle using an Interacting Multiple Model (IMM) filter. The last is a position Estimation module which integrates the vehicle States from the previous two modules with GPS data to obtain more accurate position information. The proposed Estimation algorithm was verified through simulation with the aid of a commercial vehicle model. The results demonstrate the efficiency and accuracy of the proposed algorithm.

  • Distributed vehicle State Estimation System using information fusion of GPS and in-vehicle sensors for vehicle localization
    2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), 2011
    Co-Authors: Kichun Jo, Myoungho Sunwoo
    Abstract:

    This paper proposes a distributed vehicle State Estimation System to improve the performance of vehicle positioning using Global Positioning System (GPS) and in-vehicle sensor components. The distributed architecture of the Estimation System can reduce the computational complexity of high-order Estimation by dividing it into several small-order Estimation modules, and simplifies fault detection and isolation problems. The distributed vehicle State Estimation algorithm consists of three Estimation modules. The first is a longitudinal vehicle State Estimation module which estimates the longitudinal vehicle speed and road slope. The road slope estimate is used to compensate for the vertical speed on the sloped road. The second module is a lateral vehicle State estimator which estimates yaw rate, yaw, and side slip angle using an Interacting Multiple Model (IMM) filter. The last is a position Estimation module which integrates the vehicle States from the previous two modules with GPS data to obtain more accurate position information. The proposed Estimation algorithm was verified through simulation with the aid of a commercial vehicle model. The results demonstrate the efficiency and accuracy of the proposed algorithm.

Toshiyuki Matsumoto - One of the best experts on this subject based on the ideXlab platform.

  • Development of Swallowing-Movement-Sensing Device and Swallowing-State-Estimation System
    IEEE Sensors Journal, 2019
    Co-Authors: Yosuke Kurihara, Takashi Kaburagi, Satoshi Kumagai, Toshiyuki Matsumoto
    Abstract:

    In elderly nursing care, various food-related problems, such as low nutrition, dehydration, binge eating, aspiration, and suffocation, arise. To prevent such problems, caregivers must continuously monitor elderly patients’ swallowing of food/water, which is burdensome. Hence, a monitoring System that can automatically estimate whether an elderly patient has swallowed food, water, or a highly viscous bolus is required. In this paper, we propose a sensing device based on the bi-directional electret condenser microphone that measures vibrations due to swallowing, along with an Estimation System that estimates elderly swallowing behavior utilizing the developed sensing device. To verify the validity of the proposed method, we perform verification experiments with four swallowing States $\text{f}_{1}$ – $\text{f}_{4}$ corresponding to swallowing of nothing, tea, tea with thickener, and rice cake, respectively. The proposed method is validated based on the Estimation of $\text{f}_{1}$ – $\text{f}_{4}$ , and the accuracies of 0.99, 0.81, 0.84, and 0.91, respectively, are achieved. Therefore, this technique can be feasibly applied in elderly nursing care.

  • Development of Swallowing-Movement-Sensing Device and Swallowing-State-Estimation System
    IEEE Sensors Journal, 2019
    Co-Authors: Yosuke Kurihara, Takashi Kaburagi, Satoshi Kumagai, Toshiyuki Matsumoto
    Abstract:

    In elderly nursing care, various food-related problems, such as low nutrition, dehydration, binge eating, aspiration, and suffocation, arise. To prevent such problems, caregivers must continuously monitor elderly patients' swallowing of food/water, which is burdensome. Hence, a monitoring System that can automatically estimate whether an elderly patient has swallowed food, water, or a highly viscous bolus is required. In this paper, we propose a sensing device based on the bi-directional electret condenser microphone that measures vibrations due to swallowing, along with an Estimation System that estimates elderly swallowing behavior utilizing the developed sensing device. To verify the validity of the proposed method, we perform verification experiments with four swallowing States f1-f4 corresponding to swallowing of nothing, tea, tea with thickener, and rice cake, respectively. The proposed method is validated based on the Estimation of f1-f4, and the accuracies of 0.99, 0.81, 0.84, and 0.91, respectively, are achieved. Therefore, this technique can be feasibly applied in elderly nursing care.

Alberto Rodriguez - One of the best experts on this subject based on the ideXlab platform.

  • IROS - Realtime State Estimation with Tactile and Visual Sensing for Inserting a Suction-held Object
    2018 IEEE RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
    Co-Authors: Kuan-ting Yu, Alberto Rodriguez
    Abstract:

    We develop a real-time State Estimation System to recover the pose and contact formation of an object relative to its environment. In this paper, we focus on the application of inserting an object picked by a suction cup into a tight space, a key technology for robotic packaging. We propose a framework that fuses tactile and visual sensing. Visual sensing is versatile and non-intrusive, but suffers from occlusions and limited accuracy, especially for tasks involving contact. Tactile sensing is local, but provides accuracy and robustness to occlusions. The proposed algorithm to fuse them is based on iSAM, an on-line Estimation technique, which we use to incorporate kinematic measurements from the robot, contact geometry of the object and the container, and visual tracking. In this paper, we generalize previous results in planar settings [1] to a 3D task with more complex contact interactions. A key challenge is that we do not observe contact locations between the suction-held object and the container directly. We propose a data-driven method to infer the contact formation, which is then used in real-time by the State estimator. We demonstrate and evaluate the algorithm in a setup instrumented to provide groundtruth.

  • Realtime State Estimation with Tactile and Visual Sensing for Inserting a Suction-held Object
    arXiv: Robotics, 2018
    Co-Authors: Kuan-ting Yu, Alberto Rodriguez
    Abstract:

    We develop a real-time State Estimation System to recover the pose and contact formation of an object relative to its environment. In this paper, we focus on the application of inserting an object picked by a suction cup into a tight space, an enabling technology for robotic packaging. We propose a framework that fuses force and visual sensing for improved accuracy and robustness. Visual sensing is versatile and non-intrusive, but suffers from occlusions and limited accuracy, especially for tasks involving contact. Tactile sensing is local, but provides accuracy and robustness to occlusions. The proposed algorithm to fuse them is based on iSAM, an on-line optimization technique, which we use to incorporate kinematic measurements from the robot, contact geometry of the object and the container, and visual tracking. In this paper, we generalize previous results in planar settings to a 3D task with more complex contact interactions. A key challenge in using force sensing is that we do not observe contact point locations directly. We propose a data-driven method to infer the contact formation, which is then used in real-time by the State estimator. We demonstrate and evaluate the algorithm in a setup instrumented to provide groundtruth.