检索结果-内蒙古大学图书馆

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing

作者： T. Sugiyama P.W.H. Kwan K. Toraichi K. Katagishi Doctoral Program Graduate School of Systems and Information Engineering University of Tsukuba Japan Core Research for Evolutional Science & Technology Program Japan Science and Technology Corporation Japan Institute of Information Sciences and Electronics University of Tsukuba Japan

A boundary tracking method crucial to function approximation-based image coding is proposed that solves the problems caused by duplicate tracking the common boundaries of color regions when methods conventionally applied to bilevel raster images are inappropriately used. Experimental evaluation is performed to verify its effectiveness.

关键词： Function approximation Image coding Colored noise Color Image reconstruction systems engineering and theory Electronic mail Performance evaluation Spline Internet

来源：评论

学校读者我要写书评

暂无评论

The influence of different camera perspectives and display devices on Beyond Visual Line of Sight (BVLOS) UAV operations

The influence of different camera perspectives and display d...

引用

SICE Annual Conference

作者： Nianzi Tu Sungju Maeng Makoto Itoh Doctoral Program in Risk and Resilience Engineering University of Tsukuba Tsukuba Ibaraki Japan Institute of Systems and Information Engineering Center for Artificial Intelligence Research University of Tsukuba Tsukuba Ibaraki Japan

With the growth of the use of drones especially in populated areas, Beyond the Visual Line of Sight (BVLOS) operation is expected as a challenge for drone operation. The layout of the Ground Control System (GCS) interface and the drone camera screen via display devices are anticipated to be crucial to the performance of the BVLOS operation. Moreover, the camera perspectives may influence the behavior of operators as the situation. In this study, participants (n=29) in a variety of situations involving multiple takeoff and landing sites, obstacles, and weather were grouped according to the display devices and camera perspectives used. The result shows the Head Mounted Display (HMD) is physically uncomfortable with the possibility of VR sickness, which is more prevalent with the first-person view than the third-person view, but it crashes less and has a straighter flight path. Landing in a narrow area has a high crash rate but is safer with HMD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Layered neural network training with model switching and hidden layer feature regularization

Layered neural network training with model switching and hid...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： K. Kameyama K. Taga Tsukuha Advanced Research Alliance University of Tsukuba Tsukuba Ibaraki Japan Doctoral Program in Risk Engineering Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki Japan

This work introduces a scheme of layered neural network training, which incorporates a dynamical model alteration during training, and regularization of the features extracted in the hidden layer units. So far, use of Model Switching (MS), which is a simultaneous search scheme for an optimal model and parameter, proved to improve training efficiency and generalization ability as a side effect. In MS, the operation to switch the network to a different model involve orthogonalization of the features extracted in the hidden layer. Assuming that the orthogonalization contributes to the observed merits, joint use of MS and orthogonalization of the hidden layer feature by introducing a regularization term in the training, is introduced. The network trained by the proposed training scheme is applied to a pattern recognition problem, and some improvement in training efficiency and generalization ability were observed.

关键词： Neural networks Pattern recognition Feature extraction Switches Supervised learning systems engineering and theory Data mining Probability density function Size measurement

来源：评论

学校读者我要写书评

暂无评论

Regularization of hidden layer unit response for neural networks

Regularization of hidden layer unit response for neural netw...

引用

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing

作者： K. Taga K. Kameyama K. Toraichi Doctoral Program in Risk Engineering Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki Japan Tsukuba Advanced Research Alliance University of Tsukuba Tsukuba Ibaraki Japan

In this paper, we looked into two issues in pattern recognition using neural networks trained by back propagation (BP), namely inefficient learning and insufficient generalization. We observed that these phenomena are partly caused by the way the hidden layer units responds to the inputs. In order to solve the issues, we introduced regularization of the hidden layer unit response which amounts to suppressing the correlation among the response of the hidden layer units, and pruning the unit with the method unit fusion. The results of using the proposed technique were compared with the case of conventional technique in pattern recognition problems. From the results of the experiments, the rate of correct recognition increased when using regularization in the hidden layer unit response is performed, and it turned out that the required number of training epochs also decreases.

关键词： Neural networks Feature extraction systems engineering and theory Pattern recognition Computer vision Statistics

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

On a criterion of selecting the best mother wavelet based on fluency wavelet analysis

On a criterion of selecting the best mother wavelet based on...

引用

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing

作者： K. Katagishi T. Urushiyama K. Toraichi K. Wada F. Yoshikawa S. Morokami KDD R&D Labs. Saitama Japan Institute of Information Sciences & Electronics University of Tsukuba Doctoral Program in Engineering University of Tsukuba College of Engineering Systems University of Tsukuba

This paper proposes a new criterion to select the mother wavelet suited for precisely detecting characteristic points on signals, such as non-differentiable points and discontinuous ones, and estimating the periodicity of each signal. The criterion is based on fluency wavelet analysis. We introduce the signal space /sup m/S, by which signals are characterized, spanned by piecewise polynomials of degree (m-1) with a parameter of only (m-2) times continuous differentiability and then formulate the fluency wavelet analysis. In addition, we introduce new parameters /spl lambda//sup (1/) and /spl lambda//sup (2/), and then generalize the fluency wavelet analysis. By varying both parameters /spl lambda//sup (1/) and /spl lambda//sup (2/), piecewise polynomials with an asymmetric property can be generated. Generalized "fluency wavelet analysis" can analyze waveforms nearby the above singular points more precisely.

关键词： Wavelet analysis Continuous wavelet transforms Polynomials Signal analysis Wavelet transforms Hilbert space Research and development Laboratories systems engineering and theory Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

An efficient heuristic for routing and wavelength assignment in optical WDM networks

An efficient heuristic for routing and wavelength assignment...

引用

IEEE International Conference on Communications (ICC)

作者： Yongbing Zhang K. Taira H. Takagi S.K. Das Institute of Policy and Planning Sciences University of Tsukuba Tsukuba Ibaraki Japan Doctoral Program in Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki Japan Department of Computer Science and Engineering University of Texas Arlington TX USA

ISBN: (纸本)0780374002

We propose an efficient heuristic algorithm that sets up and releases lightpaths for connection requests dynamically. We partition the routing and wavelength assignment (commonly known as RWA) problem into two subproblems and solves both of them using a well-known shortest path routing algorithm. For solving the routing subproblem, an auxiliary graph is created whereby the nodes and links in the original network are transformed to the edges and vertices, respectively, and the availability of each wavelength on the input and output links of a node as well as the number of available wavelength converters are taken into account in determining the weights of edges. Furthermore, for solving the wavelength assignment subproblem, an auxiliary graph is also utilized and the cost for wavelength conversion is taken into consideration in the edge weight function. A distinguished feature of our algorithm is that it employs more accurate network information on the availability of both the wavelengths and the wavelength converters than the existing algorithms in deciding the routing and the wavelength assignment. Simulation results show that our algorithm performs much better than previously proposed algorithms with comparable computation time, especially when the number of wavelengths is large while the number of converters at each node is limited.

关键词： Wavelength routing Wavelength assignment Optical fiber networks WDM networks Optical wavelength conversion Partitioning algorithms Heuristic algorithms Cost function Availability Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Single-cell transcriptomics uncovers EGFR signaling-mediated gastric progenitor cell differentiation in stomach homeostasis (vol 14, 3750, 2023)

引用

NATURE COMMUNICATIONS 2023年第1期14卷 1-16页

作者： Takada, Hitomi Sasagawa, Yohei Yoshimura, Mika Tanaka, Kaori Iwayama, Yoshimi Hayashi, Tetsutaro Isomura-Matoba, Ayako Nikaido, Itoshi Kurisaki, Akira Laboratory of Stem Cell Technologies Graduate School of Science and Technology Nara Institute of Science and Technology Takayama-cho Ikoma Nara Japan Laboratory for Bioinformatics Research RIKEN Center for Biosystems Dynamics Research Wako Saitama Japan Department of Functional Genome Informatics Biological Data Science Medical Research Institute Tokyo Medical and Dental University Bunkyo Tokyo Japan Master’s/Doctoral Program in Life Science Innovation (Bioinformatics) Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Ibaraki Japan

Defects in gastric progenitor cell differentiation are associated with various gastric disorders, including atrophic gastritis, intestinal metaplasia, and gastric cancer. However, the mechanisms underlying the multilineage differentiation of gastric progenitor cells during healthy homeostasis remain poorly understood. Here, using a single-cell RNA sequencing method, Quartz-Seq2, we analyzed the gene expression dynamics of progenitor cell differentiation toward pit cell, neck cell, and parietal cell lineages in healthy adult mouse corpus tissues. Enrichment analysis of pseudotime-dependent genes and a gastric organoid assay revealed that EGFR-ERK signaling promotes pit cell differentiation, whereas NF-κB signaling maintains gastric progenitor cells in an undifferentiated state. In addition, pharmacological inhibition of EGFR in vivo resulted in a decreased number of pit cells. Although activation of EGFR signaling in gastric progenitor cells has been suggested as one of the major inducers of gastric cancers, our findings unexpectedly identified that EGFR signaling exerts a differentiation-promoting function, not a mitogenic function, in normal gastric homeostasis.

关键词： Adult stem cells Stem-cell differentiation Stem-cell niche

来源：评论

学校读者我要写书评

暂无评论

Sonar spectrum recognition chip designed by evolutionary algorithm

Sonar spectrum recognition chip designed by evolutionary alg...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M. Yasunaga T. Nakamura I. Yoshihara Institute of Information Sciences and Electronics University of Tsukuba Tsukuba Ibaraki Japan Doctoral Program of Engineering University of Tsukuba Tsukuba Ibaraki Japan Large Scale Systems Stage Engineering Laboratory Graduate School of Engineering University of Tohoku Sendai Miyagi Japan

An evolutionary design methodology for sonar spectrum recognition chip is proposed and the prototype chip is developed. In the design, sonar spectrum data are transformed to truth-tables and the truth-tables are evolved to obtain generalization capability by using genetic algorithms. Digital circuits are designed by synthesizing the evolved truth-tables. Parallelism in the data can be embedded in the circuits directly by this direct hardware implementation technique of the sonar spectrum data. The circuit size of the developed chip was 4,134 gates, and this was small enough to be implemented onto a standard FPGA (field programmable gate array) chip. Operation speed of the chip was less than 1.0 micro-second per spectrum. Moreover the chip achieved the recognition accuracy of 91.7%, which was higher than those in the backpropagation and the k-NN algorithm.

关键词： Sonar Algorithm design and analysis Evolutionary computation Field programmable gate arrays Design methodology Prototypes Genetic algorithms Digital circuits Circuit synthesis Hardware

来源：评论

学校读者我要写书评

暂无评论

information technology and the terrorist threat

引用

Survival 1997年第3期39卷 135-155页

作者： Hoo, Kevin Soo Goodman, Seymour Greenberg, Lawrence [a] A researcher at the Center for International Security and Arms Control (CISAC) Stanford University CA [b] Doctoral candidate in Engineering-Economic Systems [c] Director of the IT and National Security Program CISAC [d] Professor of Management Information Systems University of Arizona Tucson AZ [e] General Counsel for The Motley Fool Inc.

Present conditions do not seem to favor information technology terrorism, but the current trends of increasing societal vulnerability and decreasing technical difficulty might encourage it in the future.

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：