检索结果-内蒙古大学图书馆

6th International Conference on Control and Robotics, ICCR 2024

作者： Xie, Yunfan Pongthanisorn, Goragod Kaneko, Shin-Ichiro Capi, Genci Graduate School of Science and Engineering Hosei University Dept. of Mechanical Eng. Tokyo Japan National Institute of Technology Toyama College Department of Electrical and Control Systems Engineering Toyama Japan

ISBN: (纸本)9798331518158

In dynamic and unpredictable work environments such as manufacturing, logistics, and automated warehouses, achieving high-precision self-localization estimation for efficient object picking are critical challenges for mobile robots. Ensuring accuracy and adaptability is essential for their successful operation. This paper presents a new method that integrates RGB cameras with Contrastive Learning (CL) for self-localization estimation and advanced object picking for mobile manipulators. The effectiveness of the proposed method for location estimation in object picking is verified in indoor environments. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Dual Dynamic Consistency Regularization for Semi-Supervised Domain Adaptation

引用

IEEE Access 2024年 12卷 36267-36279页

作者： Ngo, Ba Hung Lam, Ba Thinh Nguyen, Thanh Huy Dinh, Quang Vinh Choi, Tae Jong Chonnam National University Graduate School of Data Science Gwangju61186 Korea Republic of University of Science Faculty of Information Technology Ho Chi Minh City700000 Viet Nam National Cheng Kung University Department of Biomedical Engineering Tainan70101 Taiwan Vietnamese-German University School of Electrical Engineering and Computer Science Ho Chi Minh City72000 Viet Nam

The Vision Transformer (ViT) model serves as a powerful model to capture and comprehend global information, particularly when trained on extensive datasets. Conversely, the Convolutional Neural Network (CNN) model is beneficial to training with small datasets for retaining essential local information. Inspired by these properties of ViT and CNN models, we introduce a hybrid framework that smoothly increases the cross-domain generalization in Semi-supervised Domain Adaptation (SSDA). To achieve this goal, we first train the ViT model on abundant labeled source data, while the CNN model is trained on a few labeled target samples. Then, these models dynamically exchange their knowledge for potential generalization to unlabeled target data via the proposed method, named Dual Dynamic Consistency Regularization (D2CR). Specifically, the ViT model provides its pseudo labels to update the global perspective for the CNN model. Similarly, the CNN model offers pseudo labels to complement the local perspective for the ViT model. The previous methods use a fixed threshold algorithm for the pseudo-labeling process. However, we utilize the dynamic threshold strategy to create pseudo labels for the bi-directional consistency regularization learning between the ViT and CNN models. We verify our approach across several SSDA benchmark datasets. The outstanding experimental results provide strong evidence of the effectiveness and superiority of our approach over previous state-of-the-art SSDA methods. © 2013 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Physical Capabilities of Individual Elderly People using Muscle Synergy and a Standing Assistance Robot based on this Analysis 50

Analysis of the Physical Capabilities of Individual Elderly ...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Asai, Haruki Miyahara, Masataka Chugo, Daisuke Muramatsu, Satoshi Yokota, Sho Tabei, Ken-Ichi She, Jin-Hua Hashimoto, Hiroshi Graduate School of Science and Technology Kwansei Gakuin University Hyogo Sanda Japan School of Engineering Kwansei Gakuin University Hyogo Sanda Japan School of Information Science and Technology Tokai University Kanagawa Hiratsuka Japan Faculty of Science and Engineering Toyo University Saitama Kawagoe Japan Advanced Institute of Industrial Technology Shinagawa Tokyo Japan School of Engineering Tokyo University of Technology Hachioji Tokyo Japan

ISBN: (纸本)9781665464543

The aim of this paper is to realize a robot that supports standing motion for elderly people with low care needs, using the person's residual physical strength to prevent further decline in their physical strength. To realize this objective, the two key ideas proposed in this paper are as follows. The first idea is to identify the multiple basic movements that make up the standing motion of the elderly through a muscle synergy analysis of the standing motion of the elderly. This makes it possible to design standing assistance procedures according to the physical condition of the elderly person, as the basic motions can be matched to the stability margin range, which varies from one elderly person to another. The second idea proposes standing assistance procedures that allow the voluntary standing motion of the elderly to demonstrate their remaining physical abilities in standing motions. Even if an elderly person performs a standing assistance procedure that differs from the designed standing assistance procedure, our standing assistance robot allows the posture of the elderly person if it is within the stability margin of the individual elderly person, and only gives force assistance to the elderly person if the posture is not within the stability margin. This leads to safety and voluntary movement during standing motion. The above proposed method was implemented in our standing assistance robot prototype, and through experiments with subjects, we confirmed that it brought out the subject's remaining physical strength in standing assistance procedures. © 2024 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Towards Gradient Equalization and Feature Diversification for Long-Tailed Multi-Label Image Recognition

引用

IEEE Transactions on Multimedia 2025年 27卷 3489-3500页

作者： Chen, Zhao-Min Cui, Quan Zhang, Xiaoqin Deng, Ruoxi Xia, Chaoqun Lu, Shijian Nanjing University National Key Laboratory for Novel Software Technology Nanjing210093 China Waseda University Graduate School of Information Production and Systems Fukuoka169-8050 Japan Wenzhou University College of Computer Science and Artificial Intelligence Wenzhou325060 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

Multi-label image recognition with convolutional neural networks has achieved remarkable progress in the past few years. However, most existing multi-label image recognition methods suffer from the long-tailed data distribution problem, i.e., head categories occupy most training samples, while tailed classes have few samples. This work firstly studies the influence of long-tailed data distribution on existing multi-label image recognition methods. Based on this, two crucial issues of the existing methods are identified: 1) severe gradient imbalance between head and tailed categories, even though re-balancing strategies are adopted;2) the lack of diversity of tail category training samples. To tackle the first issue, this paper proposes a group sampling strategy to create group- wise balanced data distribution. Meanwhile, a dynamic gradient balancing loss is proposed to equalize the gradient for all categories. To tackle the second issue, this paper proposes a diversity enhancement module to fuse the information across all categories, preventing the network from overfitting tail classes. Furthermore, it also balances the gradient, promoting the discriminability of learned classifiers. Our method significantly outperforms the baseline method and achieves competitive performance with state-of-the-art methods on VOC-LT and COCO-LT datasets. Extensive ablation studies are conducted to verify the effectiveness of the essential proposals. © 1999-2012 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of Spine and Femur Bone Using Atrous Spatial Pyramid Pooling-based U-Net with Fully Connected CRF

Semantic Segmentation of Spine and Femur Bone Using Atrous S...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Tani, Yuki Ono, Keiko Yamakawa, Sohei Yakushijin, Shoma Tawara, Daisuke Graduate School of Science and Engineering Doshisha University Kyotanabe-shi Kyoto Japan Doshisha University Faculty of Science and Engineering Kyotanabe-shi Kyoto Japan School of Science and Engineering Doshisha University Kyotanabe-shi Kyoto Japan Graduate School of Science and Technology Ryukoku University Kyoto-shi Kyoto Japan Ryukoku University Faculty of Advanced Science and Technology Kyoto-shi Kyoto Japan

ISBN: (纸本)9798350337020

Semantic segmentation of bone structures requires pixel-wise classification and high accuracy to build a precise bone model capable of diagnoses. Various segmentation methods have been developed, and state-of-the-art models, such as DeepLabv3+, are generally based on a Convolutional Neuronal Network (CNN). A CNN requires many images for training, and high performance is not expected when few training images are available. In general, it is costly to obtain training images, known as ground truth for bone segmentation, because ground truth images are usually handcrafted by experts. Considering the lack of training images, we aim to develop a robust method in an environment with few images. U-Net is a well-known CNN and is often adopted for medical image segmentation because it can train with very few images compared to other models, thanks to its U-shaped encoder-decoder architecture. However, it is reported that U-Net cannot capture complex shapes in spine images. In this paper, we propose combing the advantages of both U-Net and DeepLabv3+. Specifically, we incorporate atrous spatial pyramid pooling (ASPP), which is used in DeepLabv3+, into U-Net to adopt varying-sized convolutions to capture precise bone structure. Because applying ASPP to all convolution layers of U-Net would be computationally expensive, it was applied after the encoder as the first step. It is known that the last convolution layer before the fully connected layer expresses visual features in a classification model;therefore, we hypothesized that the layer after the encoder would provide more inherent specific features than other layers in U-Net. Moreover, the Gaussian conditional random field (CRF) was utilized to refine the output semantic segmentation map. We evaluated the proposed model on spine and femur image datasets from Cancer Imaging Archive. We confirmed that the proposed method outperforms U-Net, and observed that both ASPP and CRF are effective for the performance improvement of U-Ne

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temperature Sensor Circuit for a Wearable Perspiration Monitoring System

Temperature Sensor Circuit for a Wearable Perspiration Monit...

引用

2023 International Symposium on Devices, Circuits and systems, ISDCS 2023

作者： Ichimura, Yuichiro Goto, Kenta Johguchi, Koh Graduate School of Science and Technology Shinshu University Electrical and Computer Engineering Division Department of Engineering Nagano Japan Shinshu University Faculty of Engineering Department of Electrical and Computer Engineering Nagano Japan

ISBN: (纸本)9798350315042

In this work, a prototype system has been designed with a 0.18-μm CMOS technology to capture perspiration rate in daily life. To calculate an amount of perspiration, a temperature sensor is necessary concurrently with a relative humidity sensing. The designed temperature sensor consists of 8-bit binary digital-to-analog converter and an analog front-end circuit for thermistors. The designed circuits for temperature and humidity sensors have successfully verified. © 2023 IEEE.

关键词： Humidity sensors

来源：评论

学校读者我要写书评

暂无评论

Development of a Model for Discriminating Electroencephalograms of Patients with Mild Cognitive Impairment and Healthy Individuals Using a Support Vector Machine 13

Development of a Model for Discriminating Electroencephalogr...

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on Advanced Intelligent systems, SCIS and ISIS 2024

作者： Tanabe, Akifumi Nakatani, Kyosuke Harachi, Kento Yamamoto, Yusuke Muramatsu, Ayumi Nagahara, Hajime Takemura, Noriko Shimojo, Shinji Furihata, Daisuke Mizuno-Matsumoto, Yuko Kamae-Shigenobu, Kazue Shinosaki, Kazuhiro Graduate School of Information Science University of Hyogo Kobe Japan School of Life Science and Technology Tokyo Institute of Technology Yokohama Japan Aino University Department of Medical Engineering Ibaraki Japan Institute for Datability Science Osaka University Suita Japan Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Aomori University Faculty of Software and Information Technology Aomori Japan Osaka University Cyber Media Center Suita Japan Asakayama General Hospital Sakai Japan

ISBN: (纸本)9798350373332

We performed machine learning using spectrum analysis and power spectra of electroencephalograms (EEGs) of patients with mild cognitive impairment (MCI). Spectrum analysis was performed on the EEGs of MCI patients and healthy individuals, and the power spectrum values of the two groups were calculated and compared. Based on the power spectrum values of the theta and alpha bands, models for discriminating MCI patients were created using a support vector machine (SVM), and their accuracies were compared. In the spectrum analysis, the theta band showed significantly higher power spectrum values in the MCI group. In the comparison of the accuracies of SVM models, the model using the theta band showed higher values in parameters, such as accuracy rate. These results suggested that the power spectrum values of the theta band are useful for discriminating MCI patients. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Neutrosophic Model for Evaluation Healthcare Security Criteria for Powerful and Lightweight Secure Storage System in Cloud-Based E-Healthcare Services

引用

Neutrosophic Sets and systems 2023年 58卷 367-378页

作者： El-Douh, Ahmed A. Lu, SongFeng Abdelhafeez, Ahmed Ali, Ahmed M. Aziz, Alber S. School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Faculty of Information Systems and Computer Science October 6th University Giza12585 Egypt Faculty of Computers and Informatics Zagazig University Sharqiyah Zagazig44519 Egypt

Large data volumes make manually keeping and preserving health records for future reference problematic. Most unusual is the coronavirus epidemic's overcrowding of hospitals. The Secure Pattern Electronic Healthcare Records (SPEHR) scheme provides a powerful and lightweight secure storage system for cloud-based E-healthcare services that meets remote healthcare security criteria. So we proposed a neutrosophic model with a multi-criterion decision-making (MCDM) method for the analysis and evaluation of these criteria. The neutrosophic model is used to deal with vague and uncertain data. Then we integrated the neutrosophic model with the AHP method to rank and compute the weights of the criteria. Offering stakeholders a secure interface and avoiding unwanted access to cloud-stored data mitigates E-healthcare risks. The key derivation ensures end-to-end data. ciphering to prevent unauthorized use (KDF). This work provides robust security solutions for various environments. This work can meet security needs for people and secure-communicating organizations. We found the data privacy is the best criterion. © (2023). All Rights Reserved.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Effect of Tensile Loading on the Residual Stress Relaxation Behavior of Induction Hardened SCM440 Steel with a Shallow Hardened Layer

引用

ISIJ International 2025年第2期65卷 308-314页

作者： Aoki, Tomofumi Hayama, Motoaki Takesue, Shogo Ezura, Atsushi Tsukahara, Masahiro Misaka, Yoshitaka Kikuchi, Shoichi Komotori, Jun School of Integrated Design Engineering Graduate School of Science and Technology Keio University 3-14-1 Hiyoshi Yokohama Kohoku-ku Kanagawa223-8522 Japan Department of Mechanical Engineering Faculty of Science and Technology Keio University 3-14-1 Hiyoshi Yokohama Kohoku-ku Kanagawa223-8522 Japan Department of Mechanical Engineering Kyoto Institute of Technology Matsugasakigoshokaido-cho Sakyo-ku Kyoto Kyoto606-8585 Japan Faculty of Engineering Sanjo City University 5002-5 Kamisugoro Sanjo Niigata955-0091 Japan Neturen Co. Ltd 7-4-10 Tamura Kanagawa Hiratsuka245-0013 Japan Department of Mechanical Engineering Faculty of Engineering Shizuoka University 3-5-1 Johoku Chuo-ku Shizuoka Hamamatsu432-8561 Japan

Fatigue tests under axial loading were conducted on steel with a shallow hardened layer induced by induction hardening, and in situ X-ray stress measurements were performed to investigate the relaxation of residual stresses during fatigue. The residual stresses were relaxed owing to tensile loading and not compressive loading. The two conditions that bring about this phenomenon are (i) a high peak of tensile residual stress just below the hardened layer, and (ii) the hardened layer coinciding with the compressive residual stress field that prevents the yielding of the compressive residual stress field under compressive loading. In this case, tensile yielding occurred just below the hardened layer under tensile loading, the residual stresses are redistributed, and the compressive residual stress on the material surface is relaxed. The experimental results also showed that the fatigue fracture morphology changed depending on the residual stress relaxation behavior. © 2025 The Iron and Steel Institute of Japan.

关键词： Stress relaxation

来源：评论

学校读者我要写书评

暂无评论

Shortest Beer Path Queries Based on Graph Decomposition 34

Shortest Beer Path Queries Based on Graph Decomposition

引用

34th International Symposium on Algorithms and Computation, ISAAC 2023

作者： Hanaka, Tesshu Ono, Hirotaka Sadakane, Kunihiko Sugiyama, Kosuke Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan Graduate School of Informatics Nagoya University Japan Graduate School of Information Science and Technology The University of Tokyo Japan

ISBN: (纸本)9783959772891

Given a directed edge-weighted graph G = (V, E) with beer vertices B ⊆ V , a beer path between two vertices u and v is a path between u and v that visits at least one beer vertex in B, and the beer distance between two vertices is the shortest length of beer paths. We consider indexing problems on beer paths, that is, a graph is given a priori, and we construct some data structures (called indexes) for the graph. Then later, we are given two vertices, and we find the beer distance or beer path between them using the data structure. For such a scheme, efficient algorithms using indexes for the beer distance and beer path queries have been proposed for outerplanar graphs and interval graphs. For example, Bacic et al. (2021) present indexes with size O(n) for outerplanar graphs and an algorithm using them that answers the beer distance between given two vertices in O(α(n)) time, where α(·) is the inverse Ackermann function;the performance is shown to be optimal. This paper proposes indexing data structures and algorithms for beer path queries on general graphs based on two types of graph decomposition: the tree decomposition and the triconnected component decomposition. We propose indexes with size O(m + nr2) based on the triconnected component decomposition, where r is the size of the largest triconnected component. For a given query u, v ∈ V , our algorithm using the indexes can output the beer distance in query time O(α(m)). In particular, our indexing data structures and algorithms achieve the optimal performance (the space and the query time) for series-parallel graphs, which is a wider class of outerplanar graphs. © Tesshu Hanaka, Hirotaka Ono, Kunihiko Sadakane, and Kosuke Sugiyama;licensed under Creative Commons License CC-BY 4.0.

关键词： Graphic methods

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：