检索结果-内蒙古大学图书馆

28th International Conference on Knowledge Based and Intelligent information and engineering systems, KES 2024

作者： Hoshinoa, Sara Itoa, Taiki Matsuzawaa, Takuya Ozawaa, Haruki Arimab, Sumika Degree Program in Systems and Information Engineering University of Tsukuba Japan Institute of Systems and Information Engineering University of Tsukuba Japan

This study aimed to develop an interaction modeling method for high-dimensional industrial data with sparsity. Particularly, we discussed the potential and limitations of Sparse Factorization Machines (SFM) with feature selection capabilities after examining the applicability of Factorization Machines (FMs) to numerical and categorical mixed data like industrial data. FMs has been already a major recommendation engine outperforms SVM because of robustness to the sparse data. However, conventional FMs and SFM based on the L2 norm regularization tolerate huge False-Positives (FPs), which is fatal in the application to real data to which the oracle model is unknown. Therefore, in this study, we focus on the way to automatically reduce the several millions of FPs in interactions while keeping high True-Positives (TPs). For the purpose, SFM with trigonometric inequality (TI) upper boundaries (Atarashi et al., 2021) is improved by two directions. The first is the development of TI_SFM (L1) with an L1 norm for selection of main factors, particularly for FPs reduction of the main factors. The second is the application of adaptive technique for reducing FPs of interactions (combinatorial features). We newly developed "Adaptive SFM" with adaptive technique to introduce data-driven penalty of the interaction term. As the result of numerical evaluations using a mass production oracle interaction model and several simulation data, False-Positives of the main factors (F) and the interactions (F) are significantly reduced, while keeping high level of True-Positives of the main factor () and the interactions (). Concretely, our proposed Adaptive SFM (L1) outperforms the original TI_SFM (L2) as much reducing F and F by over 99% when applying our proposed penalty considering not only the relationship between the explanatory variable and the objective variable, as basic adaptive technique, but also the factor loading indicating the relationship between the latent vector internally opt

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Value Function Approximation Method with Easy Hyperparameter Tuning and Convergence Guarantee

引用

IEEE Access 2025年 13卷 30117-30126页

作者： Watabe, Yuuya Shibuya, Takeshi University of Tsukuba Master's Program in Intelligent and Mechanical Interaction Systems Ibaraki305-8577 Japan University of Tsukuba Institute of Systems and Information Engineering Ibaraki305-8577 Japan

Reinforcement Learning is a branch of machine learning to learn control strategies that achieve a given objective through trial-And-error in the environment. Because this can be applicable even when the state transition function of the control object is unknown or it is difficult to create its model properly, this can reduce the designer's burden. Reinforcement learning repeats evaluating a policy and improving it based on that evaluation. An algorithm called value function approximation is used in this evaluation. Value function approximation is a general term for algorithms of approximating a function called value function, which maps an arbitrary state to how much reward can be obtained in the future when acting according to a policy from that state. Value function approximation should have high approximation accuracy and hyperparameter easy to tune. Although various value function approximation methods have been proposed so far, some of them does not have convergent guarantee and the others' hyperparameter tuning is difficult. The purpose of this paper is to propose a value function approximation method that have convergence guarantee even with nonlinear function approximator and whose hyperparameter tuning is easy and to verify its performance through numerical experiments. To this end, we focused on GTD2 method, which is one of the value function approximation methods that has convergence guarantee even with a nonlinear function approximator. GTD2 method has the drawback that its hyperparameter is difficult to tune appropriately so that the approximation does not diverge during learning. Therefore, we firstly clarified the cause of the divergence of GTD2 method. Secondly, based on this cause, we proposed Normalized and Regularized GTD2 (NRGTD2) method, that incorporates a method for suppressing divergence into GTD2 method. Finally, through numerical experiments, it was clarified that the proposed method suppresses the divergence and can achieve better approxim

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

EFFECTS OF REFRACTIVE INDEX AND ASPECT RATIO ON THE PARTICLE IMAGES IN A LEVITATED DROPLET

引用

Multiphase Science and Technology 2024年第1期36卷 13-26页

作者： Gatete, Eugene Kaneko, Akiko Shen, Biao University of Tsukuba Systems and Information Engineering Graduate School of Science and Technology Degree Program of Engineering Mechanics and Energy 1-1-1 Tennodai Tsukuba Ibaraki305-8573 Japan University of Tsukuba Faculty of Engineering of Information Engineering and Systems 1-1-1 Tennodai Tsukuba Ibaraki305-8573 Japan

A technique using droplets suspended by ultrasound has attracted attention as one of the containerless processing methods. While this can avoid contamination from the container, it is known that ultrasonic levitation creates flow fields inside and outside the droplet. For more precise droplet control, it is desirable to elucidate the internal flow of the droplet, and measurements of the internal flow have been performed using the particle image velocimetry (PIV). The aim of this study is to elucidate the internal flow field behavior by solving optical problems and improving the accuracy of velocity field measurements in levitated droplets. The fluid that is to be investigated is scattered with small tracer particles and illuminated by a laser to capture the flow on a created laser sheet. The curvature distortion is successfully visualized using the PIV approach toward distortion correction using calibration methods. The curvature distortion illustration was performed based on the refractive index and aspect ratio of the simulated droplet in acrylic materials. The fluid flow, affected by droplet curvature and refractive index, has been visualized for both levitated and simulated droplets. The experimental results showed that the droplet curvature can be distorted in two types such as radial and tangential distortions and increase as the refractive index and aspect ratio increases. © 2024 by Begell House, Inc.

关键词： Refractive index

来源：评论

学校读者我要写书评

暂无评论

A deep learning framework for automatic assessment of presence in virtual reality using multimodal behavioral cues

引用

Neural Computing and Applications 2025年第8期37卷 6283-6303页

作者： Pannattee, Peerawat Shimada, Shogo Yem, Vibol Nishiuchi, Nobuyuki Graduate School of Systems Design Tokyo Metropolitan University Tokyo191-0065 Japan Graduate School of Science and Technology Degree Program in Systems and Information Engineering University of Tsukuba Ibaraki3058573 Japan

Effective development of virtual reality (VR) applications is heavily reliant on the evaluation of user experience (UX). However, traditional methods such as questionnaires have inherent limitations which hinder their ability to capture nuanced behavioral responses and impede the agility of VR content creation: They are time-consuming, burdensome for users, and require significant human effort for interpretation. This study introduces an automated framework aimed at addressing the limitations of questionnaire-based evaluations to assess UX in VR. Our primary focus is to validate the concept of this framework through assessment of the sense of presence (SOP), a crucial psychological perception with significant impact on VR UX. Our proposed framework utilizes a deep neural network (DNN) to analyze patterns in multimodal behavioral cues, including facial expressions, head movements, and hand movements, to predict scores from the Igroup Presence Questionnaire (IPQ). Additionally, we introduce two statistical profiles: the Visual Entropy Profile (VEP), which offers insights into visual complexity by depicting scene entropy, and the Experiential Presence Profile (EPP), which is designed to capture users’ historical SOP levels to enable personalized baseline and sensitivity estimation. The proposed framework achieves a significant correlation between actual and predicted IPQ scores, with a Spearman’s rank correlation coefficient of 0.7303, showcasing the potential of DNNs in analyzing complex behavioral signals and automating SOP assessment. This study represents a pioneering effort in leveraging DNNs for the automatic assessment of SOP and paves the way for future advances in automatically assessing VR UX and unlocking new opportunities in the field. © The Author(s) 2025.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Optimizing Menu Bundling Strategies Through Apriori Algorithm in Sales Analysis 4

Optimizing Menu Bundling Strategies Through Apriori Algorith...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Tama, Ahmad Sambang Setya Hamami, Faqih Adi, Taufik Nur Telkom University Information Systems Study Program Faculty of Industrial Engineering Bandung Indonesia

ISBN: (纸本)9798331506490

Indonesia, as one of the largest coffee producers and exporters in the world, has experienced significant growth in the number of coffee shops, driven by increasing consumer demand for ready-to-drink coffee. This study aims to enhance sales performance at Authen Café and Space through the implementation of a menu bundling strategy. By utilizing data mining techniques and the Apriori algorithm, customer purchasing patterns were analyzed to identify optimal menu combinations. The data was collected directly at Authen Cafe during the period from April to August 2028. The analysis revealed that bundling strategies, such as combining Ayam Rica-Rica with Es Kopi Susu Karamel, are effective in increasing sales volume and product popularity among consumers. Furthermore, this study evaluated the impact of offering discounts on bundled packages on the café's profitability, demonstrating that this approach can boost net profit without sacrificing profit margins. This research provides significant insights into the application of data-driven marketing strategies within the café'industry and offers guidance for more effective managerial decision-making. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Image-Multimodal Data Analysis for Defect Classification: Case Study of Industrial Printing 15th

Image-Multimodal Data Analysis for Defect Classification: Ca...

引用

15th International KES Conference on Intelligent Decision Technologies, KESIDT 2023

作者： Itou, Hiroki Watanabe, Kyo Arima, Sumika Degree Program in Systems and Information Engineering University of Tsukuba Tsukuba Japan Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan

ISBN: (纸本)9789819929689

The final goal of this study is an integrated approach of walk-through from the classification of defect products to the feature estimation for preventing the cause of the defects in real-time or proactively. Particularly, this paper introduced the multimodal data analyses to classify the defect images of final products more accurate with inspection logs and factory process data in integrated manner. Particularly, this paper focused on the industrial printing case in which the tiny and faint defects are difficult to be classified accurately. Motivation of this study is to clarify the possibility of image-wise classification instead of pixel-wise semantic segmentation of high annotation cost as well as low accuracy in partial of the similar shape classes in our previous study. It was introduced and numerically evaluated that various data augmentation as pre-process for imbalanced and small samples issue, image-multimodal data analyses with inspection log and/or the factory data, and ensemble of the multimodal and non-multimodal networks. As the result, the maximum accuracy of multimodal analyses is 79.37% of the model with test log and process data with 10 times augmented data. In addition, a confidence-based ensemble model with conditional branch results more accurate, 81.22% in summary of all classes. It is better than segmentation approach of pixel-wise in the previous study. Moreover, importance of additional variables is visualized as cause after multimodal analysis as aimed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Image-Multimodal Data Analysis for Defect Classification: Case Study of Semiconductor Defect Patterns 15th

Image-Multimodal Data Analysis for Defect Classification: Ca...

引用

15th International KES Conference on Intelligent Decision Technologies, KESIDT 2023

作者： Takada, Daisuke Itou, Hiroki Ohta, Ryo Maeda, Takumi Watanabe, Kyo Arima, Sumika Degree Program in Systems and Information Engineering University of Tsukuba Tsukuba Japan Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan

ISBN: (纸本)9789819929689

The final goal of this study is an integrated approach of walk-through from the classification of defect products to the feature estimation for preventing the cause of the defects in real-time or proactively. Particularly, this paper will introduce the multimodal data analytics in production process integrations to analyze the classification of defect patterns of final product quality and the defect cause impact in integrated manner. There are three steps to summarize the possibilities and limitations of the multimodal data analyses. The first step is the accuracy improvement of the classification of the multi-class defect patterns of images at lower cost by using additional feature/data substituting human-being domain knowledge. That is also to prepare more accurate and effective classifications of superposition pattern of small samples data. The second step is adaptive selections and estimations of important features including interactions and variety within a practical computational time and accuracy. The third step is an integrated approach of walk-through from the classification to the feature estimation for proactively preventing the causes of the defect. As the first report, this paper introduces the first and the third issues through a case study. Particularly, this paper presents the semiconductor defect patterns case. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Toward Parallelization Technique for Stream-based Lossless Data Compression

Toward Parallelization Technique for Stream-based Lossless D...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Kato, Taiki Yamagiwa, Shinichi Wada, Koichi Master's Program in Computer Science Degree Program in Systems and Information Engineering University of Tsukuba Ibalaki Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Ibalaki Tsukuba Japan

ISBN: (纸本)9798350324457

IoT edge platform has become popular in various distributed environments. The edge devices need to communicate BigData among them or with the cloud servers by collaborating with AI technologies for finding events from the applications. Those devices exchange data streams from such as distributed sensors and remote image/video devices. We focus on an acceleration technique for the communication performance using a stream-based lossless data compression technology. This paper proposes a parallelization technique for the compression process in a software environment running on a multicore processor. The technique invokes concurrent compression processes assigned to multiple threads with splitting a data stream to chunks. The paper exposes three scheduling methods for assigning the chunks to the threads: in-order, hybrid and out-of-order. As an original data order of chunks must be obtained in decompression side, the proposed technique introduces packeting mechanisms in each chunk by adding headers to support the scheduling methods. Through experimental performance evaluations, we discuss the packeting overhead focusing on compression ratio and speedup by the parallelization with three scheduling methods. © 2023 IEEE.

关键词： Data Stream IoT Lossless Data Compression Multi-Threading Parallelization

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of Stream-Based Decompression Process by Notifying Compression Buffer Size 28

Performance Enhancement of Stream-Based Decompression Proces...

引用

28th IEEE Symposium on Computers and Communications, ISCC 2023

作者： Kato, Taiki Yamagiwa, Shinichi Marumo, Koichi University of Tsukuba Master's Program in Computer Science Degree Program in Systems and Information Engineering Ibalaki Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Ibalaki Tsukuba Japan

ISBN: (纸本)9798350300482

This paper focuses on a performance enhancement of communication performance by compressing data stream. ASE coding is an effective lossless data compression method for data stream. The software implementation of the coding/decoding method inevitably meets a performance mismatch in memory and storage devices. In the compressor side, it is predictable to decide the size of an original data block and is available to process a flexible buffer memory. However, the decompressor is not able to predict the buffer size because the original data size is not obvious before the decompression. This causes a performance mismatch in the filesystem level. This paper proposes a novel method to address the performance mismatch by applying a notification mechanism of compression size from the compressor. This paper describes the mechanism focusing on the system call usage. Through experimental evaluations, we show the performance improvement of the decompression performance for handling data stream. © 2023 IEEE.

关键词： Virtual storage

来源：评论

学校读者我要写书评

暂无评论

Elderly Pedestrian-Crossing Strategy When Perceiving an Autonomous Vehicle in a Shared Space 4

Elderly Pedestrian-Crossing Strategy When Perceiving an Auto...

引用

4th IEEE International Conference on Human-Machine systems, ICHMS 2024

作者： Dong, Yichen Andrijanto Yano, Hiroaki Itoh, Makoto University Of Tsukuba Degree Program Of Risk And Resilience Engineering Tsukuba Japan Institute Of Systems And Information Engineering University Of Tsukuba Tsukuba Japan University Of Tsukuba Institute Of Systems And Information Engineering Center For Artificial Intelligence Research Tsukuba Japan

ISBN: (纸本)9798350315790

This study clarified a pedestrian crossing strategy for elderly Japanese pedestrians when perceiving an autonomous vehicle in a shared space by eliminating road features. Crossing strategy is the basis of pedestrian crossing behavior, and this study distinguishes two types of crossing strategies: conservative and aggressive. We proposed a process for pedestrians who use a strategy to cross the road. Experimental data collected in a virtual reality facility were analyzed to investigate pedestrian-crossing strategies. The variables contributing to the pedestrian crossing behavior and crossing strategy selection were explored. The results indicated that the proposed crossing strategy predicted the observed behaviors of the participants. Pedestrian crossing behavior is influenced by gender, age, and vehicle speed. Higher vehicle speed and pedestrian age lead to pedestrians increasing their crossing time and selecting a conservative walking strategy. The study also showed that males selected an aggressive strategy more frequently than females and that males needed more time to cross the road than females. © 2024 IEEE.

关键词： Crosswalks

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：