检索结果-内蒙古大学图书馆

IEEE/SICE International Symposium on System Integration (SII)

作者： Chumkamon, Sakmongkon Hayashi, Eiji Department of Information Systems Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu Iizuka-shi Fukuoka Japan|c|

ISBN: (纸本)9781479926268

Many different types of robots have been developed to facilitate our lives, such as those used in industrial production. However, most robots operate by following human instructions or programs rather than by acting naturally that the action are not behave by robot learning. Conversely, these actions be convinced by the human. Thus, the present research was undertaken as a step toward achieving a natural robot action through consciousness-based architecture (CBA). Our CBA system imitates animal consciousness. Here we present the implementation of a facial expression recognition system that uses constrained local models (CLMs) to fit facial features together with hidden Markov models (HMMs) to classify and recognize emotions. We propose an approach and present our CLM experimental results including time efficiency and accuracy together with the experimental results of emotion recognition such as time efficiency and a confusion matrix. The present experiment demonstrates that our proposed system is an efficient personal facial expression recognition method with the result of the recognition correctness as 96.43 percent.

关键词： time efficiency Hidden Markov models Robot expression recognition Facial Recognition confusion matrix emotion recognition Facial Features ARCHITECTURE Building construction Emotions

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving Data Sharing Solution for Mobile Healthcare 5

A Privacy-Preserving Data Sharing Solution for Mobile Health...

引用

2017 International Conference on Progress in Informatics and Computing(PIC)

作者： Chanying Huang Kedong Yan Songjie Wei Dong Hoon Lee School of Computer Science and Engineering Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science&Technology Graduate School of Information Security Korea University

ISBN: (纸本)9781538619797;9781538619780

Personal Health Records（PHR） is patient-centric healthcare system, which allows patients to control who can get access to their health records and which section of the record can be accessed. Hot issues such as access control, patients control degree, and privacy protection, etc. are still the challenging concerns while designing a secure PHR *** this paper, we propose ds PPS, a secure integrated PHR framework（from health data collection to health data sharing）that meets patients’ full control of their PHR and sufficient privacy preservation. Specifically, ds PPS provides two schemes:Biometric-Based secure health data Collection（BBC） scheme and Attribute-Based health record Accessing（ABA） scheme. While BBC scheme enables patients to collect their scattered health data from multiple typical health systems securely and efficiently,the ABA scheme allows users（health systems） access to the PHR server with their sensitive attributes being protected. Comprehensive analysis is conducted to show the security of ds PPS against typical attacks. In addition, experiments in both smart phone and PC（Intel） platforms demonstrate that ds PPS produces reasonable performance in terms of storage, communication and computational overheads.

关键词： privacy-preserving security biometric attribute mobile health

来源：评论

学校读者我要写书评

暂无评论

CNN Model Compression by Merit-Based Distillation

CNN Model Compression by Merit-Based Distillation

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Takumi Morikawa Keisuke Kameyama Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan

Deep learning has advanced dramatically in recent years, and especially large convolutional neural networks (CNNs) have shown outstanding performance in a wide variety of tasks. However, such large-scale CNNs may not be able to be utilized in practice because they require a lot of computational resources. Therefore, there is a need to realize a CNN in a small model that has high performance similar to the large CNN. One method to solve these problems is Distillation, which uses a model of large scale and high performance as the teacher and a small model as the student model, and performs model compression by transferring the knowledge of the teacher model to the student model. However, in distillation, even when the teacher model incorrectly guesses the training input, the student model learns to mimic the teacher. This can prevent the student model from learning better. In this paper, we propose Meritbased Distillation, in which the accuracy of the teacher model’s output determines the degree to which the student model mimics the teacher model’s output, thereby preventing the student to learn undesired mappings. In the experiment, the effect of the Merit-based Distillation is evaluated. Consequently, the proposed method outperforms the improvements in the generalization by the student models trained by other known methods.

关键词： Training Deep learning Computational modeling Convolutional neural networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

Informative Band Subset Selection for Hyperspectral Image Classification using Joint and Conditional Mutual information

Informative Band Subset Selection for Hyperspectral Image Cl...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： U A Md Ehsan Ali Keisuke Kameyama Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan

ISBN: (纸本)9781665487696

Hundreds of contiguous bands of remotely sensed hyperspectral image (HSI) capture the spectral signatures of observed objects or materials on the earth's surface. Although the HSI data is able to provide huge information with great details, it poses challenges to image analysis because of the high computational cost due to the large dimensionality of the feature space, redundancy in information, and curse of dimensionality. To overcome these difficulties, this paper proposes an information-theoretic feature selection approach for selecting an informative feature subset considering the maximum of the minimum approach. The minimum of conditional mutual information based estimation is used to select a feature among the selected feature subset. This selected feature with the corresponding candidate feature is then exploited using the mutual information and joint mutual information based valuation to find the maximum relevance of the candidate features with the target classes. The effectiveness of the proposed approach, called joint-conditional mutual information for selecting informative feature (JCIF), is assessed by implementing it in some synthetic data and three remotely sensed HSI data. Several known feature selection algorithms are also used for comparison purposes. The results of the experiments with K-Nearest Neighbors and Support Vector Machine classifiers reveal that JCIF performs better in selecting informative features.

关键词： Support vector machines Reflectivity Earth Redundancy Estimation Feature extraction Mutual information

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Curriculums Generated by Classifier Ensembles

Machine Learning Curriculums Generated by Classifier Ensembl...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Tzu-Jui Huang Keisuke Kameyama Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan

Image classification is a fundamental task that attempts to classify the images into the classes they belong to. CNN is commonly used for the classification due to its flexibility and stability. This paper treats Curriculum Learning as an assistant method that decides the procedure the CNN ought to be trained. Curriculum Learning is generally defined as a method that divides and orders the training datasets into several different levels of learning difficulties. This paper utilizes the idea of ensemble classification that trains according to the order based on the consensus of different machine learning models. As a result, the proposed Ensemble-Generated Curriculum Learning model achieves higher accuracy compared to that of a single-stage CNN learning with dog face recognition and CIFAR-10 datasets.

关键词： Training Face recognition Stability criteria Machine learning Dogs Classification algorithms Task analysis

来源：评论

学校读者我要写书评

暂无评论

LSTM-based Forecasting using Policy Stringency and Time-varying Parameters of the SIR Model for COVID-19

LSTM-based Forecasting using Policy Stringency and Time-vary...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Pavodi Maniamfu Keisuke Kameyama Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan

Accurate forecasting of the number of infections is an important task that can allow health care decision makers to allocate medical resources efficiently during a pandemic. Two approaches have been combined, a stochastic model by Vega et al. for modelling infectious disease and Long Short-Term Memory using COVID-19 data and government’s policies. In the proposed model, LSTM functions as a nonlinear adaptive filter to modify the outputs of the SIR model for more accurate forecasts one to four weeks in the future. Our model outperforms most models among the CDC models using the United States data. We also applied the model on the Canadian data from two provinces, Saskatchewan and Ontario where it performs with a low mean absolute percentage error.

关键词： COVID-19 Adaptation models Pandemics Infectious diseases Stochastic processes Predictive models Data models

来源：评论

学校读者我要写书评

暂无评论

Variable-Speed Teaching-Playback as Real-World Data Augmentation for Imitation Learning

arXiv

引用

arXiv 2024年

作者： Masuya, Nozomu Sato, Hiroshi Yamane, Koki Kusume, Takuya Sakaino, Sho Tsuji, Toshiaki 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 Japan 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 Japan Department of Intelligent Interaction Technologies Institute of Systems and Information Engineering University of Tsukuba Japan Graduate School of Science and Engineering Saitama University Saitama Japan

Because imitation learning relies on human demonstrations in hard-to-simulate settings, the inclusion of force control in this method 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 a maximum 55% increase in success rate from a simple change in speed of real-world reactions and improved accuracy along the duration/frequency command by gathering environmental reactions at variable speeds. Copyright © 2024, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Explainable Chance-Constrained Programming for VR Video Resource Allocation 18th

Explainable Chance-Constrained Programming for VR Video Res...

引用

18th International Conference on Intelligent information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Pan, Jeng-Shyang Song, Pei-Cheng Chu, Shu-Chuan Watada, Junzo Li, Jun-Bao College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Graduate School of Information Production and Systems Waseda University Kitakyushu Japan School of Electronics and Information Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819906048

In view of the impact of uncertain factors faced by Virtual Reality (VR) video services in the Internet of Vehicles, if the impact of different uncertain factors can be identified, targeted optimization can be made to achieve a better and more personalized user experience. A stochastic resource allocation model for VR video services is developed and turned into a chance-constrained programming problem, which is solved using an optimization solver. This work discusses the concept of shaply value in cooperative games for the first time in order to analyze the marginal contributions of different random variables in chance-constrained programming, and proposes an Explainable Chance-Constrained Programming (ECCP). The marginal contributions of different random variables under different confidence levels and probability distributions are exhibited and evaluated in the experimental test, allowing the degree of influence of uncertainty factors to be explained and analyzed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Random variables

来源：评论

学校读者我要写书评

暂无评论

Path Planning Considering Energy Consumption of Crawler Robots in Mountain Environments

Path Planning Considering Energy Consumption of Crawler Robo...

引用

IEEE/SICE International Symposium on System Integration

作者： N. Adachi H. Date Graduate School of Science and Technology Degree Programs in Systems and Infomation Engineering University of Tsukuba Tsukuba Ibaraki Japan

In the forestry industry, the demand for task automation is increasing to solve the labor shortage problem. We examine the path planning problem for tasks such as afforestation, harvesting, and surveying, in which a robot travels a predetermined set of locations. We specifically address the problem of path planning for minimization of energy consumption for the operation of a crawler robot in an environment with slopes. This problem requires consideration of the energy loss caused by ascending and descending in the mountainous environment, besides the energy loss due to friction during on-the-spot rotation specific to the crawler robot, and is impossible to treat as the standard Traveling Salesman Problem(TSP). We apply the Generalized Traveling Salesman Problem (GTSP) known as the TSP extension to this problem. This allows the proposed method to account for energy consumption during movement. We modeled the energy consumption of the robot during straight movements and rotations through a preliminary experiment. A graph reflecting the energy consumption model can be generated for evaluation of the path planning by setting the points to be traversed on the point cloud map after 3D scanning of an outdoor unstructured terrain field with flat ground and sloped ground. It is confirmed that the proposed method can plan a path that reduces energy consumption by 22% for a standard TSP solution that quasi-minimizes Euclidean distance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preliminary Evaluation of Kyokko for Inter-FPGA Communication Framework CIRCUS

Preliminary Evaluation of Kyokko for Inter-FPGA Communicatio...

引用

IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Kaito Kitazume Norihisa Fujita Ryohei Kobayashi Taisuke Boku Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Center for Computational Sciences University of Tsukuba

In recent years, Field-Programmable Gate Arrays (FPGAs) are gaining attention as computational acceleration devices in the field of high-performance computing. By implementing specialized circuits that can be customiz... 详细信息

ISBN: (数字)9798350383454

ISBN: (纸本)9798350383461

关键词： Conferences High performance computing Circuits Cluster computing Low latency communication Field programmable gate arrays

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：