检索结果-内蒙古大学图书馆

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Fukino, Aoi Ikeoka, Hiroshi Hamamoto, Takavuki Graduate School of Engineering Fukuyama University Information Processing Engineering Course Hiroshima Japan Fukuyama University Faculty of Engineering Department of Computer Science Hiroshima Japan

ISBN: (纸本)9798350395914

Camera-based depth estimation methods are useful for various automobile applications. For example, depth estimation methods based on stereo cameras triangulate the depth between objects and cameras. However, they are susceptible to baseline distortion owing to vibrations, aging, and thermal expansion. On the contrary, depth estimation methods based on a monocular camera, such as depth-from-defocus, use a focusing mechanism or spectroscopic optics to calculate the depth from the difference of defocus images. However, because the change in sharpness, which is the inverse of defocus, is slightly in the depth direction, it is unsuitable for deep-range estimation. Therefore, we are developing depth-estimation methods that use a monocular camera with special focus images obtained through tilted optics, which have no baseline distortion problem and have a deep estimation range. When tilted optics are used, the plane of sharp focus (POF) appears tilted, while the depth of field (DOF) lies and increases toward the depth direction. Moreover, to allow for the use of only one image-sensor, a one-shot, we studied a depth estimation method using tilted optics with two different aperture sizes for each color wavelength by introducing concentric color filter apertures. However, as with conventional methods, the Gaussian sharpness model does not strictly fit to the actual sharpness, resulting in reduced estimation accuracy. In this study, we propose a method for high-speed and high-accuracy depth estimation that involves adding a split color filter aperture to a tilted optic and using a different sharpness model for each DOF side. © 2024 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Privacy Concerns from Single-Word Search Query Leakage from Web Browsers Through DNS

IEEE Networking Letters

引用

IEEE Networking Letters 2022年第1期4卷 48-52页

作者： Isobe, Katsuki Kondo, Daishi Tode, Hideki Computer Science Course College of Engineering Osaka Prefecture University Sakai599-8531 Japan Department of Computer Science and Intelligent Systems Graduate School of Engineering Osaka Prefecture University Sakai599-8531 Japan

Some Web browsers working on certain operating systems (OSs) specify that a single-word search query entered into the search bar be sent to the recursive resolver of the domain name system (DNS) as a DNS request that includes the word. Such behavior is unexpected for users and induces privacy concerns through single-word search query leakage. We present our survey on the conditions during which this behavior occurs. By analyzing the DNS traffic captured at the recursive resolvers, we demonstrate that a considerable number of queries are leaked and the interests of individuals or organizations can be inferred through passive eavesdroppers. © 2019 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Deceptive Topographic Path Planning 23

Deceptive Topographic Path Planning

引用

Proceedings of the 22nd Brazilian Symposium on Games and Digital Entertainment

作者： Crhistopher Lenhard Henrique L. Krever Ricardo K. Schlsener Rafael H. Bordini Luis A. L. Silva Graduate Program in Computer Science UFSM Brazil Undergraduate Course in Computer Science UFSM Brazil School of Technology PUCRS Brazil

ISBN: (纸本)9798400716270

Deception is essential to model real-world agent behaviors in entertainment and serious games. This paper approaches the challenge of planning deceptive routes on topographic terrains where topographic path costs and other deceptive path factors are analyzed. The work explores alternative deceptive strategies tuned to explore the terrain costs to determine how deceptive the path search nodes are and to return paths with low topographic costs. In addition to the A* algorithm, the Theta* algorithm is explored in the search for smoother deceptive routes, which better represent routes used by terrestrial agents in real-world adversarial situations. It also analyzes deceptive topographic paths computed according to the Last Deceptive Point (LDP) and Last Topographic Deceptive Point (LDPT) notions, where examples of returned paths are presented with the help of terrain relief scenarios. Experimental results with the proposed methods are statistically analyzed according to various path search metrics, showing that all deceptive strategies with A* compute topographic paths with higher numbers of deceptive nodes on reduced execution times. Moreover, the strategies with Theta* and LDPT return paths that show a useful combination of topographic path quality and number of deceptive nodes.

关键词： Deception Deceptive path planning strategies. Path planning Topographic path planning

来源：评论

学校读者我要写书评

暂无评论

Perceptual Analysis of Groups of Virtual Humans Animated using Interactive Platforms

arXiv

引用

arXiv 2024年

作者： Montanha, Rubens Raupp, Giovana Schmitt, Ana Carolina Schneider, Gabriel Araujo, Victor Musse, Soraia Raupp VHLab Graduate Course in Computer Science Pontifical Catholic University of Rio Grande do Sul Brazil

Virtual humans (VH) have been used in computer Graphics (CG) for many years, and perception studies have been applied to understand how people perceive them. Some studies have already examined how realism impacts the comfort of viewers. In some cases, the user’s comfort is related to human identification. For example, people from a specific group may look positively at others from the same group. Gender is one of those characteristics that have in-group advantages. For example, in terms of VHs, studies have shown that female humans are more likely to recognize emotions in female VHs than in male VHs. However, there are many other variables that can impact the user perception. To aid this discussion, we conducted a study on how people perceive comfort and realism in relation to interactive VHs with different genders and expressing negative, neutral, or positive emotions in groups. We created a virtual environment for participants to interact with groups of VHs, which are interactive and should evolve in real-time, using a popular game engine. To animate the characters, we opted for cartoon figures that are animated by tracking the facial expressions of actors, using available game engine platforms to conduct the driven animation. Our results indicate that the emotion of the VH group impacts both comfort and realism perception, even by using simple cartoon characters in an interactive environment. Furthermore, the findings suggest that individuals reported feeling better with a positive emotion compared to a negative emotion, and that negative emotion recognition is impacted by the gender of the VHs group. Additionally, although we used simple characters, the results are consistent with the perception obtained when analysing realistic the state-of-the-art virtual humans, which positive emotions tend to be more correctly recognized than negative ones. © 2024, CC BY.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit graduated Optimization

arXiv

引用

arXiv 2023年

作者： Sato, Naoki Iiduka, Hideaki Computer Science Course Graduate School of Science and Technology Meiji University Japan Department of Computer Science Meiji University Japan

The graduated optimization approach is a method for finding global optimal solutions for nonconvex functions by using a function smoothing operation with stochastic noise. We show that stochastic noise in stochastic gradient descent (SGD) has the effect of smoothing the objective function, the degree of which is determined by the learning rate, batch size, and variance of the stochastic gradient. Using this finding, we propose and analyze a new graduated optimization algorithm that varies the degree of smoothing by varying the learning rate and batch size, and provide experimental results on image classification tasks with ResNets that support our theoretical findings. We further show that there is an interesting relationship between the degree of smoothing by SGD’s stochastic noise, the well-studied "sharpness" indicator, and the generalization performance of the model. © 2023, CC BY.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of Pre Shoplifting Suspicious Behavior Using Deep Learning 16

Detection of Pre Shoplifting Suspicious Behavior Using Deep ...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Shrestha, Sujan Taniguchi, Yoji Tanaka, Tetsuo Graduate school of Engineering Kanagawa Institute of Tehnology Course of Information and computer sciences Atsugi Japan Daiichi Institute of Technology Artificial Intelligence and Data Science Department of Information Tokyo Japan Kanagawa Institute of Technology Faculty of Information Technology Dept. of Information and Computer Sciences Atsugi Japan

ISBN: (纸本)9798350377903

Shoplifting presents a significant challenge for retailers, leading to substantial financial losses and security concerns. Current surveillance systems effectively identify shoplifting incidents postoccurrence;however, the capability to detect and prevent such activities preemptively remains limited. This research focuses on identifying behaviors that likely precede shoplifting events. To this end, we introduce a novel benchmark dataset, specifically designed for the early detection of suspicious behavior that may lead to shoplifting. This dataset is curated by selecting and segmenting relevant sequences from the UCF101-Crime dataset, encompassing suspicious behavior, actual shoplifting incidents, and normal activities. Our approach addresses the limitations of existing datasets where the brief duration of shoplifting events may skew neural network performance. The dataset includes clips of only a few seconds each, for which we propose a robust neural network architecture combining the strengths of convolutional neural networks (CNN) for efficient feature extraction and Bidirectional long short-term memory (BiLSTM) networks for capturing temporal dependencies within action sequences. Our model achieves an impressive classification accuracy of 86.21 % on the newly created dataset. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Proposal of a novel peeling of nano-particle (PNP) process for localized material removal on a hard material surface by controllable magnetic fields 22

Proposal of a novel peeling of nano-particle (PNP) process f...

引用

22nd International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2022

作者： Permpatdechakul, Thitipat Khajornrungruang, Panart Suzuki, Keisuke Kutomi, Shotaro Graduate School of Computer Science and System Engineering Mechanical Information Science and Technology Course Kyushu Institute of Technology Fukuoka Japan Department of Intelligent and Control Systems Avanced Mechanical Division Kyushu Institute of Technology Fukuoka Japan School of Computer Science and System Engineering Advanced Mechanical Course Kyushu Institute of Technology Fukuoka Japan

ISBN: (纸本)9781998999118

This article proposes a novel Peeling of Nano-Particle (PNP) process to locally remove material on a hard material surface using controllable magnetic fields. Fe3O4 particles in the size range of 50-100 nm in aqueous solution (pH value 11 adjusted by KOH) were magnetically controlled to adhere and remove from a 4H-SiC surface by two electromagnetic coils, which were sandwiched between the substrate. The particle controlling phenomenon on the surface was experimentally observed and verified by our developed apparatus applying an evanescent field. According to the results, particles could be controlled to approach and remove from the substrate surface with 12mT of magnetic field at the selective area on the substrate surface to realise the proposed PNP process. © European Society for Precision Engineering and Nanotechnology, Conference Proceedings - 22nd International Conference and Exhibition, EUSPEN 2022. All rights reserved.

关键词： Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Scaled conjugate gradient method for nonconvex optimization in deep neural networks

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 19301-19337页

作者： Naoki Sato Koshiro Izumi Hideaki Iiduka Computer Science Course Graduate School of Science and Technology Meiji University Kanagawa Japan Visual Solutions Department 1 Technology Development Division SECOM Co. Ltd. Tokyo Japan Department of Computer Science Meiji University Kanagawa Japan

A scaled conjugate gradient method that accelerates existing adaptive methods utilizing stochastic gradients is proposed for solving nonconvex optimization problems with deep neural networks. It is shown theoretically that, whether with a constant or diminishing learning rate, the proposed method can obtain a stationary point of the problem. Additionally, its rate of convergence with a diminishing learning rate is verified to be superior to that of the conjugate gradient method. The proposed method is shown to minimize training loss functions faster than the existing adaptive methods in practical applications of image and text classification. Furthermore, in the training of generative adversarial networks, one version of the proposed method achieved the lowest Fréchet inception distance score among those of the adaptive methods.

关键词： adaptive method conjugate gradient method deep neural network generative adversarial network nonconvex optimization scaled conjugate gradient method

来源：评论

学校读者我要写书评

暂无评论

Regular languages that can be approximated by testing subword occurrences

Computer Software

引用

computer Software 2023年第2期40卷 49-60页

作者： Sin'ya, Ryoma Yamaguchi, Yutaro Nakamura, Yoshiki Mathematical Science Course Akita University Japan Graduate School of Information Science and Technology Osaka University Japan Department of Computer Science School of Computing Tokyo Institute of Technology Japan

A language L is said to be regular-measurable if there exists an infinite sequence of pairs of regular languages that "converges" to L. Instead of regular languages, this paper examines measuring power of several fragments of regular languages: piecewise testable (PT) and alphabet testable (AT) languages. In particular, we showed that, while AT-measurability for regular languages is co-NP complete, PT-measurability is decidable in linear time. © 2023 Japan Society for Software science and Technology. All rights reserved.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Absolute longitudinal distance measurement verification of a standard polystyrene nanoparticle near a surface in water by means of multi-wavelength evanescent field 22

Absolute longitudinal distance measurement verification of a...

引用

22nd International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2022

作者： Blattler, Aran Khajornrungruang, Panart Suzuki, Keisuke Baba, Akiyoshi Goto, Daiki Graduate School of Computer Science and System Engineering Mechanical Information Science and Technology Course Kyushu Institute of Technology Fukuoka Japan Department of Intelligent and Control Systems Advanced Mechanical Division Kyushu Institute of Technology Fukuoka Japan Center of Microelectronic System Kyushu Institute of Technology Fukuoka Japan School of Computer Science and System Engineering Advanced Mechanical Course Kyushu Institute of Technology Fukuoka Japan

ISBN: (纸本)9781998999118

In the wet semiconductor process, abrasive nanoparticles are widely used in the chemical mechanical polishing (CMP) process to polish wafer surfaces for high planarization. During polishing, nanoparticles move with a high-speed three-dimensional (3D) position in the solution. In the 3D particles's moving positions, Z is a perpendicular longitudinal distance between the surface to the nanoparticle that plays a significant role in polishing, which could not be measured by general microscopy without longitudinal scanning. To understand nanoparticle phenomena near-surface, we have proposed and developed the apparatus with real-time fastmotion tracking on optical multi-wavelength evanescent fields microscopy to measure the 3D motion of the nanoparticle in water without scanning. In euspen's 2020, we could verify the relative distance ?Z of nanoparticles in water, but the absolute distance Z is unknown yet. In this manuscript, we have therefore developed an invisible nano-step height in water to verify the absolute height Z of an individual nanoparticle. The invisible nano-step height in water is made from an optical resin with a refractive index of 1.35 that is close to a refractive index of water to avoid unnecessary light during experimental verification. The nano-step height was less than 100 nm on a glass surface, fabricated using nanoimprint lithography. Polystyrene f100 nm standard particles in water were used to verify the height Z. The results of height Z of nanoparticles could be measured less than 100 nm with the measurement uncertainty ±10 nm (2s), which is related to the interferometer result of the nano-step height. © European Society for Precision Engineering and Nanotechnology, Conference Proceedings - 22nd International Conference and Exhibition, EUSPEN 2022. All rights reserved.

关键词： Nanoparticles

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：