检索结果-内蒙古大学图书馆

Variable-speed teaching–playback as real-world data augmentation for imitation learning

Advanced Robotics 2025年

作者： Masuya, Nozomu Sato, Hiroshi Yamane, Koki Kusume, Takuya Sakaino, Sho Tsuji, Toshiaki Doctoral Program in Intelligent and Mechanical Interaction Systems Degree Programs in Systems and Information and Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Master’s Program in Intelligent and Mechanical Interaction Systems Degree Programs in Systems and Information and Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Department of Intelligent Interaction Technologies Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan Graduate School of Science and Engineering Saitama University Saitama Japan

Imitation learning’s inevitable reliance on human demonstrations in hard-to-simulate settings has resulted in a shortage of training data, even with a simple change in speed. Although the field of data augmentation has addressed the lack of data, conventional methods of data augmentation for robot manipulation are limited to simulation-based methods or downsampling for position control. This paper proposes a novel method of data augmentation that is applicable to force control and preserves the advantages of real-world datasets. We applied teaching–playback at variable speeds as real-world data augmentation to increase both the quantity and quality of environmental reactions at variable speeds. An experiment was conducted on bilateral control-based imitation learning using a method of imitation learning equipped with position–force control. We evaluated the effect of real-world data augmentation on two tasks, pick-and-place and wiping, at variable speeds, each from two human demonstrations at fixed speed. The results showed that generation of variable-speed movement from human demonstrations with less than 10% variety of durations is feasible, and improved success rate and accuracy along the duration/frequency command by gathering environmental reactions at variable speeds, rather than simply altering speeds of gathered data. © 2025 Informa UK Limited, trading as Taylor & Francis Group and The Robotics Society of Japan.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Grid environment for computational astrophysics driven by GRAPE-6 with HMCS-G and OmniRPC

Grid environment for computational astrophysics driven by GR...

引用

19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005

作者： Boku, Taisuke Onuma, Kenji Sato, Mitsuhisa Nakajima, Yoshihiro Takahashi, Daisuke Graduate School of Systems and Information Engineering University of Tsukuba Center for Computational Sciences University of Tsukuba Doctoral Program of Systems and Information Engineering University of Tsukuba

ISBN: (纸本)0769523129

In computational astrophysics, the effect of gravity is essential even with very heavy computation of O(N2) for N particles. Several special purpose machines have been implemented as gravity engine to handle this problem extremely fast, however there are few sites in the world to operate such systems. We have developed a grid environment to access such a system based on grid-RFC, named HMCS-G. Using HMCS-G, a multi-physical computational astrophysics simulation can be performed with the combination of a PC-cluster and the gravity engine GRAPE-6. In typical size of problems for galaxy formation, however, the computation power of PC-cluster is much weaker than that of GRAPE-6, and we need multiple sets of PC-clusters to share the power of GRAPE-6 on grid environment. We have developed such a system using OmniRPC, a grid-enabled RPC system. In this system, OmniRPC are used both to distribute jobs for parameter search on multiple PC-clusters and to access GRAPE-6 server from these clusters. We performed an actual problem to search several formations of galaxy on this system, and confirmed such a solution is useful for wide variety of computational astrophysics research.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Gastritis Diagnosis Expert System Using Android-Based Certainty Factor Method 6

Gastritis Diagnosis Expert System Using Android-Based Certai...

引用

6th International Seminar on Research of information Technology and Intelligent systems, ISRITI 2023

作者： Isnanto, R. Rizal Purwanto Windarto, Yudi Eko Setiawan, Annas Diponegoro University Information Systems Doctoral Program Semarang Indonesia Diponegoro University Computer Engineering Department Semarang Indonesia

ISBN: (纸本)9798350358346

In the modern era, an increasing number of diseases are emerging because of human lifestyle choices and bacterial transmission. Gastritis, characterized by inflammation in the stomach lining leading to frequent abdominal pain, is one such ailment. Recognizing the significance of addressing these health issues, there is a need for an expert system application specifically designed for diagnosing gastritis. The primary objective is to disseminate information to the public regarding the early symptoms of gastritis, promoting awareness from a young age. The research method used is the web-based Expert System Development Life Cycle (ESDLC). The diagnostic process employs the Certainty Factor (CF) method to ensure accurate results. By utilizing symptom CF values chosen by the user, the Certainty Factor approach facilitates a diagnosis based on calculations established by medical specialists. The research culminates in the development of an expert system application capable of accurately diagnosing the disease Android based. The accuracy rates for the first, second, and third test cases are reported as 98.848%, 99.8464%, and 99.99115264%, respectively. System testing, conducted through black-box testing, validates the application's functionality, demonstrating a 100% success rate for each component. © 2023 IEEE.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

Expert System for Diagnosis of Diphtheria Disease Using Fuzzy Logic 6

Expert System for Diagnosis of Diphtheria Disease Using Fuzz...

引用

6th International Seminar on Research of information Technology and Intelligent systems, ISRITI 2023

作者： Isnanto, R.Rizal Mustafid Prasetijo, Agung Budi Fitria Ali, Safira Isna Diponegoro University Information Systems Doctoral Program Semarang Indonesia Diponegoro University Computer Engineering Department Semarang Indonesia

ISBN: (纸本)9798350358346

Diphtheria is an infectious disease that affects the upper respiratory system and throat, arising suddenly and caused by Corynebacterium diphtheriae. The symptoms of diphtheria such as fever, swollen neck and slimy nose are often interpreted as influenza or laryngitis. Diphtheria is a contagious and deadly disease that requires specialized and rapid treatment and care. In today's technological era, it can be overcome with a system that can diagnose diphtheria like a doctor's diagnosis ability commonly called an expert system. This study describes the application of an expert system to diagnose diphtheria disease. The research method used is the web-based Expert System Development Life Cycle (ESDLC). The method used to process input values is Forward Chaining. Fuzzy Tsukamoto to calculate the input value from the user. The research has been tested with Blackbox testing showing the results that the expert system works well and accuracy testing with 92% results. The results show effectiveness with a satisfactory level of accuracy in detecting diphtheria disease. This research contributes to the development of expert systems in the health sector with a focus on diagnosing diphtheria disease using a fuzzy logic approach. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Developing an Expert System for Mobile-based Gastroenteritis Detection Using ESDLC and Best First Search Methods 8

Developing an Expert System for Mobile-based Gastroenteritis...

引用

8th International Conference on Informatics and Computing, ICIC 2023

作者： Isnanto, R. Rizal Widodo, Catur Edi Windasari, Ike Pertiwi Saputri, Misik Puspajati Diponegoro University Information Systems Doctoral Program Semarang Indonesia Diponegoro University Computer Engineering Department Semarang Indonesia

ISBN: (纸本)9798350342604

Gastroenteritis is a common gastrointestinal disorder with varying degrees of severity, including cases without dehydration, mild dehydration, moderate dehydration, and severe dehydration. This research focuses on the development of a mobile-based expert system for detecting gastroenteritis, capable of distinguishing between these different dehydration levels. The methodology employed integrates the Extreme Structure Development Life Cycle (ESDLC) and the Best First Search algorithm. The expert system is designed to provide swift and accurate responses to users inputting symptoms, categorizing gastroenteritis cases based on the severity of dehydration. The application of ESDLC ensures a structured and organized development process, while the Best First Search method enhances the efficiency of the diagnostic process, facilitating timely and precise recommendations. Accessible through mobile platforms, the system allows users to input symptoms conveniently and receive rapid recommendations. Rigorous testing and evaluation affirm the system's high accuracy in discerning dehydration levels in gastroenteritis patients. In conclusion, the developed mobile-based expert system exhibits promising potential for advancing diagnostic services, particularly in the categorization of dehydration levels in gastroenteritis cases. The successful implementation of ESDLC and Best First Search paves the way for similar solutions in other healthcare domains, contributing positively to early and accurate disease management efforts. This innovation marks a significant stride towards improving healthcare technology for enhanced decision support in gastroenteritis diagnosis. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Fuzzy c-means and mixture distribution model for clustering based on L1-space 15th

Fuzzy c-means and mixture distribution model for clustering ...

引用

15th International Workshop on Japanese Society for Artificial Intelligence, JSAI 2001

作者： Koga, Takatsugu Miyamoto, Sadaaki Takata, Osamu Graduate School of Systems and Information Engineering University of Tsukuba Ibaraki305-8573 Japan Institute of Engineering Mechanics and Systems University of Tsukuba Japan Doctoral Program in Engineering University of Tsukuba Japan

ISBN: (纸本)9783540455486

This paper aims at proposing and comparing two fuzzy models and a statistical model for clustering based on L1-space. Clustering methods in the fuzzy models are the standard fuzzy c-means and an entropy regularization method based on L1-space. Furthermore, we add new variables to them for improving the cluster division. In the statistical model, a mixture distribution model based on L1-space is proposed and the EM algorithm is applied. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Mixtures

来源：评论

学校读者我要写书评

暂无评论

Classification of Multivariate Time Series Signals Using Self-Supervised Representation Learning for Condition Monitoring 30

Classification of Multivariate Time Series Signals Using Sel...

引用

30th International Symposium on Semiconductor Manufacturing, ISSM 2024

作者： Sumiya, Koichi Arima, Sumika University of Tsukuba Doctoral Program in Policy and Planning Sciences Tsukuba Japan University of Tsukuba Institute of Systems and Information Engineering Tsukuba Japan

ISBN: (纸本)9798331510589

In the analysis of real-world data, two significant challenges often arise: high-dimensional signals and their temporal interactions. To address these issues and identify transitions in process conditions through end-to-end learning, we propose a self-supervised representation learning framework that conceptualizes signals as images. This straightforward approach classifies imaged signals as time-specific conditions by maximizing mutual information within a domain-specific feature space. We applied this methodology to two labeled open datasets and one unlabeled real-world process dataset, yielding promising results. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Optimal dividend distribution policy from the perspective of the impatient and loss-averse investor

引用

Journal of Socio-Economics 2009年第3期38卷 534-540页

作者： Yang, Yang Shoji, Isao Kanehiro, Sumei Doctoral Program in Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki 305-8573 Japan Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki 305-8573 1-1-1 Tennoudai Japan Keihatsusha Inc. Tokyo 135-0042 Kiba Koutou Japan

This paper discusses a problem concerning intertemporal decision-making under uncertainty when its subject has psychological biases. Here, we consider an investment company as a decision maker that invests money from investors in a financial asset and pays some dividend every period depending on the performance of the investment. On the other hand, we assume investors have such psychological biases as inconsistent time preference and loss aversion. Through numerical experiments we show that the optimal dividend distribution under inconsistent time preference and loss aversion is quite different from the distribution without these psychological factors, and that combinations of the two factors produce various patterns of dividend distribution. © 2009 Elsevier Inc. All rights reserved.

关键词： Intertemporal choice Loss aversion Quasi-hyperbolic discounting Reference-dependent preference Time inconsistent preference

来源：评论

学校读者我要写书评

暂无评论

A Player Position Tracking Method Based on a Wide-Area Pan-Tilt-Zoom Video 12

A Player Position Tracking Method Based on a Wide-Area Pan-T...

引用

Proceedings of the 12th International Conference on Sport Sciences Research and Technology Support, icSPORTS 2024

作者： Yamagishi, Shunzo Xie, Chun Shishido, Hidehiko Kitahara, Itaru Master's and Doctoral Program in Intelligent Mechanical Interaction Systems University of Tsukuba Ibaraki Japan Center for Computational Sciences University of Tsukuba Ibaraki Japan Faculty of Science and Engineering Department of Information Systems Engineering Soka University Tokyo Japan

ISBN: (纸本)9789897587191

This paper proposes a method to estimate the posture of an athlete moving on a vast field in a sporting event using a pan-tilt-zoom camera. In order to estimate the posture of an athlete on a sports field from a dynamic video sequence, our method extracts image features to search correspondence points among successive frames and computes the homography transformation matrix that compensates for changes the camera parameters (e.g., angle of view and posture). The effectiveness of this method is qualitatively verified using MLB TV broadcast video. The accuracy and error factors are also quantitatively verified by CG simulation. Copyright © 2024 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Pan-Tilt-Zoom Camera Player Tracking Sports Analytics Video Processing Wide-Area

来源：评论

学校读者我要写书评

暂无评论

Location management for PCS networks with consideration of mobility patterns

Location management for PCS networks with consideration of m...

引用

IEEE INFOCOM 2005

作者： Li, Jie Kubota, Atsushi Kameda, Hisao Department of Computer Science Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Sci. City Ibaraki 305-8573 Japan Doctoral Program in Science and Information Engineering University of Tsukuba Tsukuba Sci. City Ibaraki 305-8573 Japan

ISBN: (纸本)0780389689

This paper addresses the dynamic location management for personal communication service (PCS) networks with consideration of mobility patterns. The popular hexagonal cellular architecture is considered. In this paper, we first introduce a coordinate system for the hexagonal cellular architectures. Then, we develop an all-direction mobility model based on the coordinate system for the hexagonal cellular architecture to cope with the mobility patterns of mobile terminals (MTs). The shape and size of the local area (LA) in the dynamic location management scheme is determined by minimizing the total location management cost with bounding the paging cost The optimization problem is transferred to maximize expected number of cells traversed by the MT in the LA with a given size of the LA. The analytic model of calculating the probabilities of any MT's moving is established. An algorithm is proposed to solve the optimization problem efficiently. © 2005 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：