Yoon-Yeong Kim, Hyemi Kim, Wonsung Lee, Han-Lim Choi, Il-Chul Moon
Tracking an object under a noisy environment is difficult especially when there exist unknown parameters that affect the object’s behavior. In the case of a high-speed ballistic vehicle, the trajectory of the ballistic vehicle is affected by the change of atmospheric conditions as well as the various parameters of the object itself. To filter these latent factors of the dynamics model, this paper proposes a black-box Expectation-Maximization algorithm to estimate the latent parameters for enhancing the accuracy of the trajectory tracking. The Expectation step calculates the likelihood of the observation by the Extended Kalman Smoothing that reflects the forward-backward probability combination. The Maximization step optimizes the unknown parameters to maximize the likelihood by the Bayesian optimization with Gaussian process. Our simulation experiment results show that the error of tracking position of the ballistic vehicle reduced when there exist much noise in the observations, and some important parameters are unknown.
{"title":"Black-Box Expectation-Maximization Algorithm for Estimating Latent States of High-Speed Vehicles","authors":"Yoon-Yeong Kim, Hyemi Kim, Wonsung Lee, Han-Lim Choi, Il-Chul Moon","doi":"10.2514/1.I010831","DOIUrl":"https://doi.org/10.2514/1.I010831","url":null,"abstract":"Tracking an object under a noisy environment is difficult especially when there exist unknown parameters that affect the object’s behavior. In the case of a high-speed ballistic vehicle, the trajectory of the ballistic vehicle is affected by the change of atmospheric conditions as well as the various parameters of the object itself. To filter these latent factors of the dynamics model, this paper proposes a black-box Expectation-Maximization algorithm to estimate the latent parameters for enhancing the accuracy of the trajectory tracking. The Expectation step calculates the likelihood of the observation by the Extended Kalman Smoothing that reflects the forward-backward probability combination. The Maximization step optimizes the unknown parameters to maximize the likelihood by the Bayesian optimization with Gaussian process. Our simulation experiment results show that the error of tracking position of the ballistic vehicle reduced when there exist much noise in the observations, and some important parameters are unknown.","PeriodicalId":129520,"journal":{"name":"2018 18th International Conference on Control, Automation and Systems (ICCAS)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128276402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-10-01DOI: 10.5954/icarob.2020.gs3-3
Yuichi Koizumi, N. Miyake, Huimin Lu, Hyoungseop Kim, S. Murakami, T. Aoki, S. Kido
In recent years, the proportion of deaths from cancer tends to increase in Japan, especially the number of deaths from lung cancer is increasing. CT device is effective for early detection of lung cancer. However, there is concern that an increase in burden on doctors will be caused by high performance of CT improving. Therefore, by presenting the “second opinion” by the CAD system, it reduces the burden on the doctor. In this paper, we develop a CAD system for automatic detection of lesion candidate regions such as lung nodules or ground glass opacity (GGO) from 3D CT images. Our proposed method consists of three steps. In the first step, lesion candidate regions are extracted using temporal subtraction technique. In the second step, the image is reconstructed by sparse coding for the extracted region. In the final step, 3D Convolutional Neural Network (3D-CNN) identification using reconstructed images is performed. We applied our method to 51 cases and True Positive rate (TP) of 79.81 % and False Positive rate (FP) of 37.65 % are obtained.
{"title":"Automatic Extraction of Abnormalities on Temporal CT Subtraction Images Using Sparse Coding and 3D-CNN","authors":"Yuichi Koizumi, N. Miyake, Huimin Lu, Hyoungseop Kim, S. Murakami, T. Aoki, S. Kido","doi":"10.5954/icarob.2020.gs3-3","DOIUrl":"https://doi.org/10.5954/icarob.2020.gs3-3","url":null,"abstract":"In recent years, the proportion of deaths from cancer tends to increase in Japan, especially the number of deaths from lung cancer is increasing. CT device is effective for early detection of lung cancer. However, there is concern that an increase in burden on doctors will be caused by high performance of CT improving. Therefore, by presenting the “second opinion” by the CAD system, it reduces the burden on the doctor. In this paper, we develop a CAD system for automatic detection of lesion candidate regions such as lung nodules or ground glass opacity (GGO) from 3D CT images. Our proposed method consists of three steps. In the first step, lesion candidate regions are extracted using temporal subtraction technique. In the second step, the image is reconstructed by sparse coding for the extracted region. In the final step, 3D Convolutional Neural Network (3D-CNN) identification using reconstructed images is performed. We applied our method to 51 cases and True Positive rate (TP) of 79.81 % and False Positive rate (FP) of 37.65 % are obtained.","PeriodicalId":129520,"journal":{"name":"2018 18th International Conference on Control, Automation and Systems (ICCAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121664619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-31DOI: 10.5302/J.ICROS.2018.18.0036
Daehan Kim, J. Back
We consider the speed control problem for a two-inertia system that consists of two inertias connected by a shaft. In this system, the flexibility produces torsional vibrations that usually result in limited tracking performance when employing a conventional control strategy such as PI control. Moreover, the control problem becomes far more challenging if the load-side speed and torsion torque developed in the shaft are not measurable. This paper presents a disturbance observer-based controller that suppresses vibrations due to torsion torque and external disturbance so that the load speed tracks the desired reference. This is done by constructing an observer that estimates the torsion torque, load speed, and load torque at the same time and a controller that can adjust the torsion torque as desired. The proposed idea is validated through numerical simulations.
{"title":"Load Speed Control of Two-inertia System by Load Speed/Torque Estimation and Torsion Torque Compensation","authors":"Daehan Kim, J. Back","doi":"10.5302/J.ICROS.2018.18.0036","DOIUrl":"https://doi.org/10.5302/J.ICROS.2018.18.0036","url":null,"abstract":"We consider the speed control problem for a two-inertia system that consists of two inertias connected by a shaft. In this system, the flexibility produces torsional vibrations that usually result in limited tracking performance when employing a conventional control strategy such as PI control. Moreover, the control problem becomes far more challenging if the load-side speed and torsion torque developed in the shaft are not measurable. This paper presents a disturbance observer-based controller that suppresses vibrations due to torsion torque and external disturbance so that the load speed tracks the desired reference. This is done by constructing an observer that estimates the torsion torque, load speed, and load torque at the same time and a controller that can adjust the torsion torque as desired. The proposed idea is validated through numerical simulations.","PeriodicalId":129520,"journal":{"name":"2018 18th International Conference on Control, Automation and Systems (ICCAS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126829025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：