检索结果-内蒙古大学图书馆

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

Image reconstruction framework for helical cone-beam CT by combining compressed sensing and deep learning

Image reconstruction framework for helical cone-beam CT by c...

引用

International Forum on Medical Imaging in Asia 2021, IFMIA 2021

作者： Kawamata, Kentaro Kazuo, Subaru Takizawa, Hotaka Kudo, Hiroyuki Degree Programs in Systems and Information Engineering Graduate School of Systems and Information Engineering University of Tsukuba Tennoudai 1-1-1 Tsukuba305-8573 Japan

ISBN: (数字)9781510644212

ISBN: (纸本)9781510644205

Compressed sensing (CS) image reconstruction in CT suffers from the drawbacks such as 1) appearance of staircase artifacts and 2) loss in image textures and smooth intensity changes. These drawbacks stem from the fact that CS is based on approximating the image by a piecewise-constant function. To overcome this drawback, we have already proposed a framework to improve image quality in CS using deep learning. In this framework, FBP reconstructed image and CS (TV or Nonlocal TV) reconstructed image are inputted to CNN with two input channels and single output channel, and a final reconstructed image is obtained by the output of CNN. Parameters (weight and bias) of CNN together with a regularization parameter of CS are estimated by minimizing an average least-squares loss function by using learning data, i.e. a set of triplet of degraded FBP reconstruction, CS reconstruction, and answer image. In this paper, this framework is extended to 3-D image reconstruction in helical cone-beam CT operated with lowdose scanning protocol. Parameters (weight and bias) of CNN together with a regularization parameter of CS are estimated by minimizing an average least-squares loss function by using learning data, i.e. a set of triplet of degraded FBP reconstruction, CS reconstruction, and answer image. In this paper, this framework was extended to 3-D image reconstruction in helical cone-beam CT operated with lowdose scanning protocol. The extension was done in the following way. First, we prepare N different 2-D denoising CNN (CNN1, CNN2, ?, CNNN) dependent on the slice position n. Each slice of the short-scan FDK reconstruction without denoising yi and with 3-D TV (or Nonlocal TV) denoising zi are inputted to CNNn with the closest slice index n, which yields a corresponding output image for each slice xi. The final reconstructed image is obtained by stacking every slice xi (i = 1, 2, ?, I). © 2021 SPIE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Unified Framework to Construct Fast Row-Action-Type Iterative CT Reconstruction Methods with Total Variation Using Multi Proximal Splitting 21

Unified Framework to Construct Fast Row-Action-Type Iterativ...

引用

6th International Conference on Biomedical Signal and Image Processing, ICBIP 2021

作者： Kim, Heejeong Sadakata, Kazuya Kudo, Hiroyuki Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Japan Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Japan

ISBN: (纸本)9781450390507

Recently, to realize low-dose scan in CT imaging, a number of iterative reconstruction methods with Total Variation (TV) regularization have been investigated. In particular, reconstruction methods based on proximal splitting framework have been actively researched thanks to the following two reasons. First, they allow to use the TV regularization term, which is known to be a non-differentiable function that cannot be handled with classical optimization methods. Second, using the proximal splitting leads to a new class of iterative reconstruction methods which cannot be found in the literature. The major drawback of existing research in this direction is that most of them use the proximal splitting which divides the cost function into a sum of only two terms like famous Chambolle-Pock algorithm and FISTA. In this paper, we propose a unified framework to construct a class of row-action-type iterative methods which converge very fast using frameworks of multi proximal splitting which divides the cost function into a sum of arbitrary number of sub-cost functions (more than two). The use of multi proximal splitting naturally allows us to construct row-action-type iterative methods converging to an exact minimizer of the cost function very quickly. In mathematical literature, there exist only three different frameworks of multi proximal splitting, which are the Passty splitting, Dykstra-like splitting, and modified Dykstra-like splitting. We develop three new iterative methods, i.e. the Passty iterative method, Dykstra-like iterative method, and modified Dykstra-like iterative method, by using these frameworks, for the case where the cost function is a sum of the standard least-squares data fidelity and the TV regularization term. We have compared the proposed three iterative methods with an empirical standard method using ordered-subset technique called OS-SIRT-TV method. The results demonstrate that the performances of proposed methods significantly outperform OS-SIRT

关键词： Image reconstruction

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

Affinity-Weighted RandAugment for Problem-Oriented Augmentation

Affinity-Weighted RandAugment for Problem-Oriented Augmentat...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yuna Park Tomoumi Takase Keisuke Kameyama Masaki Onishi Degree Programs in Systems and Information Engineering and Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Artificial Intelligence Research Center National Institute of Advanced Industrial Science and Technology (AIST) Japan Institute of Systems and Information Engineering University of Tsukuba

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Data augmentation is a technique with the potential to improve model generalization performance. Automatic Augmentation, which autonomously designs suitable data augmentation strategies, has significantly improved performance. One of the effective Automatic Augmentation is RandAugment (RA), which randomly selects methods to apply from the set of available augmentations. However, its selection with equal probabilities for all available augmentations is not ideal. In this study, we propose Affinity-Weighted RandAugment which assigns weights to the selection probabilities for the available augmentations in RA. The weights are calculated based on the value of Affinity, which represents the distributional similarity between original and augmented data. Affinity provides the prediction of the effect of each augmentation according to both the model and the dataset in advance. This enables the assignment of weights to the selection probabilities with low computational cost. As an additional effort, whether Affinity could be obtained at a much lower computational cost was considered. Based on these insights we implemented Single-Pass Affinity-Weighted RA, which can achieve effective weighting for RA without additional or separate learning. Experiments in image classification using CIFAR-10/100 and Describable Textures Dataset (DTD) demonstrated that Affinity-Weighted RandAugment achieves better test accuracy in comparison with the other known RA methods.

关键词： Accuracy Computational modeling Neural networks Probability Predictive models Data augmentation Data models

来源：评论

学校读者我要写书评

暂无评论

2D Slice-driven Physics-based 3D Motion Estimation Framework for Pancreatic Radiotherapy

arXiv

引用

arXiv 2023年

作者： Hara, Yuki Kadoya, Noriyuki Mitsume, Naoto Ienaga, Naoto Umezawa, Rei Jingu, Keiichi Kuroda, Yoshihiro The Degree Programs in Systems and Information Engineering University of Tsukuba Tsukuba Japan The Department of Radiation Oncology Tohoku University Graduate School of Medicine Sendai Japan The Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan

Pancreatic diseases are difficult to treat with high doses of radiation, as they often present both periodic and aperiodic deformations. Nevertheless, we expect that these difficulties can be overcome, and treatment results may be improved with the practical use of a device that can capture 2D slices of organs during irradiation. However, since only a few 2D slices can be taken, the 3D motion needs to be estimated from partially observed information. In this study, we propose a physics-based framework for estimating the 3D motion of organs, regardless of periodicity, from motion information obtained by 2D slices in one or more directions and a regression model that estimates the accuracy of the proposed framework to select the optimal slice. Using information obtained by slice-to-slice registration and setting the surrounding organs as boundaries, the framework drives the physical models for estimating 3D motion. The R2 score of the proposed regression model was greater than 0.9, and the RMSE was 0.357 mm. The mean errors were 5.11 ± 1.09 mm using an axial slice and 2.13 ± 0.598 mm using concurrent axial, sagittal, and coronal slices. Our results suggest that the proposed framework is comparable to volume-to-volume registration, and is feasible. Copyright © 2023, The Authors. All rights reserved.

关键词： Radiotherapy

来源：评论

学校读者我要写书评

暂无评论

A Method of Detecting Port Bay Numbers and Optimizing Effects Under Various Weather Scenarios

A Method of Detecting Port Bay Numbers and Optimizing Effect...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Jiazheng Li Lei Ao Kai Sheng Yoshiki Yamaguchi Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Japan Key Laboratory of Collaborative Intelligence Systems Ministry of Education School of Electronic Engineering Xidian University Xi'an Shaanxi China Academy of Advanced Interdisciplinary Research Xidian University Xi'an Shaanxi China Institute of Systems and Information Engineering University of Tsukuba Japan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Ports are transportation hubs located along coasts, rivers, lakes, and reservoirs, with water and land transport facilities that allow ships to enter, exit, and berth safely. The port bay numbers are located on the land side of the port and are rectangular frames of specific sizes designated by port management, containing unique codes. These codes identify where containers are stacked under various weather conditions. Therefore, the ability to quickly and accurately recognize bay numbers in all weather conditions has become a significant issue affecting work efficiency, especially in rainy ports. However, collecting images of bay numbers during rainy days is not permitted due to safety restrictions. In this article, we first generate images of rainy scenes based on images collected in sunny weather. We then compare two detection algorithms and select the one with a smaller decrease in detection metrics but fewer model parameters. Finally, we incorporate an attention mechanism into the chosen algorithm to optimize and enhance target detection performance across various weather scenarios.

关键词： YOLO Measurement Codes Attention mechanisms Seaports Reservoirs Safety Rivers Marine vehicles Meteorology

来源：评论

学校读者我要写书评

暂无评论

Implementation and Evaluation of 0.6 µm CMOS Complex RCPF for Accurate Frequency Response Measurement

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, information and systems 2025年第1期145卷 25-37页

作者： Sato, Lina Fukagawa, Kanta Shouno, Kazuhiro Tanimoto, Hiroshi Muto, Cosy Moriyama, Seijiro Takahashi, Chikau Yoshino, Michitaka Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan Anagix Corporation 3-22-27 Numama Kanagawa Zushi249-0004 Japan Takamori Corporation Japan Research Center for Micro-Nano Technology Hosei University 3-11-15 Midori-cho Koganei Tokyo184-0003 Japan

This paper describes the implementation and evaluation of an RC polyphase filter (RCPF) and circuitry for measuring its frequency characteristics. The integrated circuit is fabricated on a 0.6 µm CMOS process and its supply voltage is 5 V. The integrated circuit includes a filter under test (FUT), a four-phase square wave generator, several analog switches and differential amplifiers to amplify the high-impedance signals of the RCPF. This FUT is a third-order complex RCPF whose passband is 8 − 40 MHz. This paper describes the design of these circuits in detail. This integrated circuit can select two measurement methods by means of external control signals. The first method uses a four-phase square wave. The frequency characteristics are measured by using an on-chip four-phase square wave generator driven by an external clock generator and by a spectrum analyzer tuned to the fundamental frequency. The second method uses an external network analyzer. Furthermore, this integrated circuit is equipped with a calibration circuit to measure the frequency characteristics of the circuitry except FUT by passing through the input / output signals of the FUT. As a result, the frequency characteristics of the FUT itself can be accurately measured. The effectiveness is confirmed through evaluation of the fabricated integrated circuit. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Differential amplifiers

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

Evaluating a How-to Tip Machine Comprehension Model with QA Examples collected from a Community QA Site 35

Evaluating a How-to Tip Machine Comprehension Model with QA ...

引用

35th Pacific Asia Conference on Language, information and Computation, PACLIC 2021

作者： Li, Tingxuan Bai, Shuting Zhu, Fuzhu Utsuro, Takehito Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba 1-1-1 Tennodai Ibaraki Tsukuba305-8573 Japan

In the field of factoid question answering (QA), it is known that the state-of-the-art technology has achieved an accuracy comparable to human. However, in the area of non-factoid QA, there are only limited numbers of datasets for training QA models. So within the field of the non-factoid QA, Chen et al. (2020) developed a dataset for training Japanese tip QA models. Although it can be shown that the trained Japanese tip QA model outperforms the factoid QA model, this paper further aims at answering tip questions more closely related to daily lives. Specifically, we collect community QA examples from a community QA site and then apply the trained Japanese tip QA model to those community QA examples. Evaluation results show that the trained tip QA model outperforms the factoid QA model when testing against those community QA examples. © Proceedings of the 35th Pacific Asia Conference on Language, information and Computation, PACLIC 2021.

关键词：

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：