检索结果-内蒙古大学图书馆

18th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2021

作者： Watanabe, Koei Kikuchi, Kohei Boku, Taisuke Sato, Takuto Kusaka, Hiroyuki Master’s Program in Computer Science Graduate School of Systems and Information Engineering University of Tsukuba Tsukubashi Japan Center for Computational Sciences University of Tsukuba Tsukubashi Tennodi Japan

ISBN: (纸本)9783030935702

In this paper, we describe the Graphics Processing Unit (GPU) implementation of our City-LES code on detailed large eddy simulations, including the multi-physical phenomena on fluid dynamics, heat absorption and reflection by surface and building materials, cloud effects, and even sunlight effect. Because a detailed simulation involving these phenomena is required for analyses at the street level and several meters of resolution, the computation amount is enormous, and ordinary CPU computation cannot provide sufficient performance. Therefore, we implemented the entire code on GPU clusters with large-scale computing. We applied OpenACC coding to incrementally implement relatively easy programming and eliminate data transfers between the CPU and GPU memories. Based on this research, we determined that the elimination of data transfers is effective, even in the case where a part of the code execution on the GPU is slower than the CPU, owing to the absence of spatial parallelism. The objective of this study is to perform a complete climate simulation on a few square-kilometers field around the Tokyo Station, considering the finest resolution of the original highlighted area of the Marathon race in the Olympic Games Tokyo 2020. We successfully transferred the entire code to the GPU to provide approximately eight times the performance of CPU-only computation on multi-GPU per node with a large scale cluster. © 2022, IFIP International Federation for Information Processing.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

On a New Rough Clustering Based on Optimization

On a New Rough Clustering Based on Optimization

引用

International Symposium on Soft Computing and Intelligent systems (SCIS)

作者： Sakuya FURUTA Yasunori ENDO Master's Program in Risk and Resilience Engineering Degree Programs in Systems and Information Engineering Graduate School of Science annd Technology University of Tsukuba Ibaraki Japan Institute of Systems and Information Engineering University of Tsukuba Ibaraki Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

The purpose of this study is to develop and investigate a new rough clustering based on optimization. We propose a restructured algorithm using only one variable, instead of the algorithm described using two variables in existing methods. We also perform numerical examples using artificial data and the Iris and Wine datasets. This research has the potential to be used as a method for determining false negatives and false positives in cancer diagnosis.

关键词： Iris Accuracy Clustering algorithms Computational complexity Optimization Cancer

来源：评论

学校读者我要写书评

暂无评论

Study on Wearable Gaze-Based Communication System for Patients with Amyotrophic Lateral Sclerosis (ALS)

Study on Wearable Gaze-Based Communication System for Patien...

引用

IEEE/SICE International Symposium on System Integration

作者： Sawada Nonoka Akira Uehara Hiroaki Kawamoto Yoshiyuki Sankai Master's Program in Intelligent and Mechanical Interaction Systems University of Tsukuba Ibaraki Japan Institute of Systems and Information Engineering Center for Cybernics Research University of Tsukuba Tsukuba Ibaraki Japan

This study centers its attention on communication among ALS patients with severe symptoms, which is essential to daily life and the part that remains a difficulty. Also, communication is important to promote social participation and ability of independence. To promote social participation and improve the ability of independence without the restrictions for patients, the purpose of this study is to develop a wearable interface that enables communication based on the patient's voluntary intent, without temporal, spatial, or physical restrictions, and to confirm the feasibility of intention transmission using a new text entry algorithm. The developed interface utilized a see-through type head-mounted display (HMD) with a gaze estimation sensor to enable patients themselves to transition between cyberspace and physical space and to communicate by the system without restrictions of posture or usage environment during daily life activities. The letter selection is triggered by a change in the direction of the gaze trajectory. This method of letter selection reduces the burden on the user by avoiding the effects of dwell time and other factors associated with gazing input. The key layout for text input UI considers the characteristics of human eye movements, to minimize key selection errors and allows for quick viewpoint movement. To confirm the feasibility of the basic performance, we conducted the experiment with three able-bodied participants using the developed system and a conventional system as a comparison system, respectively. As a result, the developed system was able to input sentences in the same amount of time as the conventional system. The results show that the developed system has the basic performance of a communication interface with a new character input method based on eye movement functions. Therefore, we confirmed the feasibility of transmitting intention using a new text entry algorithm to enable communication without the restrictions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, Information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Note on Even-Sized Spectral Clustering

A Note on Even-Sized Spectral Clustering

引用

International Symposium on Soft Computing and Intelligent systems (SCIS)

作者： Hiroki MIYAKAWA Yasunori ENDO Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master's Program in Risk and Resilience Engineering University of Tsukuba Tsukuba Ibaraki Japan Institute of Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

Clustering is a typical unsupervised learning method for classifying unsupervised data. One of the clustering meth-ods, even-sized clustering based on optimization (ECBO), is a clustering algorithm that imposes a constraint to equalize the size of each cluster. ECBO has been suggested to be effective in delivery and other problems. However, it is limited to Euclidean space. On the other hand, spectral clustering with a wide range of applicability for partitioning graph data has been proposed. In this paper, we propose even-sized spectral clustering, which imposes a size-equal constraint on spectral clustering, and show that it is an extension of the graph partitioning problem. We also verify the validity of the results through numerical examples.

关键词： Clustering algorithms Partitioning algorithms Classification algorithms Optimization Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

RUL Estimation for Power Electronic Devices Using RNNs

RUL Estimation for Power Electronic Devices Using RNNs

引用

Prognostics and System Health Management Conference (PHM)

作者： Congrui Cai Zhonghai Lu Embedded Systems Master Program School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Department of Electrical Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology

ISBN: (数字)9798350360585

ISBN: (纸本)9798350360592

Recurrent Neural Networks (RNNs) are commonly used in data-driven approaches to estimate the Remaining Useful Lifetime (RUL) of power electronic devices. RNNs are preferred because their intrinsic feedback mechanisms are better suited to model time-series data. However, the impact of RNN complexity on estimation accuracy is rarely discussed in the literature. This issue is important because choosing a lower-complexity model that delivers the same or similar performance as a higher-complexity model can increase implementation efficiency. In the paper, we use three RNN models, namely, the vanilla version, LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) to conduct RUL estimation for power electronic devices. We use two accelerated aging datasets, one dataset targeting the package failure of MOSFETs, and the other dataset targeting package failure of power diodes. Our study shows that a lower-complexity RNN does not necessarily deliver a lower performance. Similarly, a higher-complexity model does not assure a higher performance. As such, our work highlights the importance of selecting a proper neural network for RUL estimation not biased towards complex models. This is especially useful and important for implementing such RUL estimation techniques in embedded resource-constrained and speed-limited computins platforms.

关键词： Performance evaluation Semiconductor device modeling Recurrent neural networks Computational modeling Estimation Power electronics Data models

来源：评论

学校读者我要写书评

暂无评论

Relationship Between Mechanical Deformation and Contact Force Applied by Catheter Tip on Cardiac Muscle: Experimentation and Computer Modeling 5

Relationship Between Mechanical Deformation and Contact Forc...

引用

5th IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2023

作者： Ijima, Yukako Masnok, Kriengsak Perez, Juan J. Gonzalez-Suarez, Ana Berjano, Enrique Watanabe, Nobuo Master's Program Global Course of Engineering and Science Graduate School of Engineering and Science Shibaura Institute of Technology Saitama Japan Functional Control Systems Graduate School of Engineering and Science Shibaura Institute of Technology Biofluid Science and Engineering Laboratory Saitama Japan Universitat Politecnica de Valencia BioMIT Department of Electronic Engineering Valencia Spain School of Engineering University of Galway Translational Medical Device Lab Galway Ireland Functional Control Systems Graduate School of Engineering and Science College of Systems Engineering and Science Shibaura Institute of Technology Biofluid Science and Engineering Laboratory Department of Bio-Science and Engineering Saitama Japan

ISBN: (纸本)9798350320978

The cardiac muscle is elastic and deformable. Pushing a catheter in contact with the cardiac muscle surface to conduct focal energy-based ablative therapies, such as RF ablation, requires an adequate electrode-tissue contact surface to transfer the energy to the target site. In this regard, the relationship between the contact force (CF) and the resulting mechanical response is still unclear, in particular, the insertion depth (ID) and the diameter of the surface deformation. The objective of this study was to quantify these relationships using an ex vivo model and a computational model. A rigid bar with a 2.3 mm diameter blunt tip (mimicking a 7Fr standard ablation catheter) was placed at a perpendicular orientation on a fragment of the porcine heart. CF values ranged from 10 to 80g. We used ANSYS to build a Mooney-Rivlig model of 3 parameters based on hyperelastic material and to simulate the same conditions as in the experiments. The experimental results showed a strong linear correlation between CF and insertion depth ID ($\mathrm{R}^{2}=0.97, \mathrm{P} © 2023 IEEE.

关键词： Catheters

来源：评论

学校读者我要写书评

暂无评论

Factors that Influence E-Satisfaction and Their Impact on Online Purchase Intention of Telemedicine Applications 9

Factors that Influence E-Satisfaction and Their Impact on On...

引用

9th IEEE International Conference on Computing, engineering and Design, ICCED 2023

作者： Gui, Anderes So, Idris Gautama Novantia, Dea Princes, Elfindah Sianipar, Nesti Fronika Haron, Hasnah Bina Nusantara University Information System Program School of Information Systems Jakarta Indonesia Bina Nusantara University Binus Business School Management Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program-Master of Information Systems Management Information Systems Management Department Jakarta Indonesia Bina Nusantara University Faculty of Engineering Food Technology Department Jakarta Indonesia Universiti Sains Islam Malaysia Faculty of Economics and Muamalat Nilai Malaysia

ISBN: (纸本)9798350370126

This study embarked on a rigorous examination of the factors driving user satisfaction and usage behavior in the context of telehealth applications. Utilizing a well- structured Google Form survey, distributed through an array of social media platforms, including WhatsApp, Discord, Instagram, and Line, the research gathered 251 responses. The purposive sampling technique was employed to ensure that the data captured the experiences of individuals who had actively engaged with telehealth services. One hypothesis, relating to the influence of Online Reviews, was found to be unsupported. This surprising result suggests that, contrary to expectations, the opinions and reviews shared online do not significantly affect users' satisfaction or their behavioral decisions in the context of telehealth applications. This finding highlights the need for a more nuanced understanding of the factors influencing user preferences and choices in this rapidly evolving sector. Conversely, other hypotheses examining factors such as Social Influence, Facilitating Conditions, Perceived Reliability, Price Value, and Purchase Intention were substantiated. The positive influence of these factors on customer usage behavior underscores their significance in shaping user experiences and satisfaction within the telehealth ecosystem. Furthermore, the study posits that facilitating conditions should be closely aligned with technological advancements, as this alignment is conducive to the development of enhanced application features. This insight suggests that telehealth providers should continuously innovate and integrate advanced technologies to ensure that the facilitating conditions meet the ever-evolving needs and expectations of users. © 2023 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Preference-based jogging route selection in downtown Tokyo

引用

Cities and Health 2024年第3期8卷 390-404页

作者： Huang, Yumeng Eom, Sunyong Suzuki, Tsutomu Master’s Program in Risk Engineering Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Japan Division of Policy and Planning Sciences Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan

Jogging has become a popular urban outdoor recreational activity because it is inexpensive and easy. Although there are positive responses to leisure-route planning from many regions, the routes with features preferred by joggers are not commonly considered in urban planning. This article explores and evaluates methods for determining optimal urban jogging routes while considering joggers’ preferences. This study combines information about road width, green space, riverbank scenery, and various points of interest with jogging heat map data and uses a decision tree analysis to study joggers’ preferences. Next, routes with high potential considering three different patterns of points of interest and road width are selected using the vehicle routing problem analysis in ArcGIS. This method for preference-based route selection can be used to identify which links in urban road networks are attractive to runners and provide policymakers with useful information for designing built environments. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Jogger preferences jogging route selection urban outdoor recreation vehicle routing problem

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：