检索结果-内蒙古大学图书馆

2023 International Conference on computer science, information Technology and engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program - Doctor of Computer Science Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Bina Nusantara University Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, the language translation is not an easy computation task when there is a language-resource gap. This paper presents empirical results on the performance of two models: the Long Short-term Memory and the Bidirectional Long Short-term Memory models as machine language translation models involving Bahasa Indonesia and the Sundanese language. The empiric results showed that the Bidirectional Long Short-term Memory model achieves higher performance as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.95 and 0.95 average training accuracy respectively;and 0.90 and 0.89 average testing BLEU scores respectively) than the Long Short-term Memory model as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.93 and 0.92 average training accuracy respectively;and 0.91 and 0.88 average testing BLEU scores). These results validate some previously reported studies that claim the Bidirectional Long Short-term Memory model potentially outperform the Long Short-term Memory model when it is used to process a sequence dataset. © 2023 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

SynthEcho Watermarking for Secure and Robust Image-to-Image Generation

SynthEcho Watermarking for Secure and Robust Image-to-Image ...

引用

International Conference on Distributed Computing Systems Workshop

作者： Xiang Xin Honggang Wang Hua Fang Graduate Computer Science and Engineering Department Katz School of Health and Science Yeshiva University Dept. of Computer and Information Science University of Massachusetts Dartmouth and Chan Medical

ISBN: (数字)9798350354713

ISBN: (纸本)9798350354720

The boundaries between human creativity and artificial intelligence are blurring, posing challenges for digital copyright protection. This article introduces a novel img-to-img invisible watermarking technology called SynthEcho Watermarking, which adds watermarks to the diffusion model and combines with the BLIP(Bootstrapping Language-Image Pre-training) model to generate the imgto-img(image-to-image) model with built-in robust watermarks that can be detected without training. By embedding these patterns into the initial noise vector of the diffusion model, we use Fourier transform to implement a watermark that maintains robustness to common image operations while being invisible to human *** utilized the COCO dataset to test our model’s effectiveness, demonstrating significant resilience against common image manipulations while maintaining high image fidelity. Our results underscore the potential of integrating robust watermarking within AI-driven content creation processes. This method demonstrates its application in various image-to-image generation tasks, not only ensuring the integrity and copyright of generated images, but also playing a key role in navigating the complexity of AI-generated content, ensuring transparent attribution, and ethical use.

关键词： Training Semantics Refining Watermarking Copyright protection Diffusion models Vectors

来源：评论

学校读者我要写书评

暂无评论

Utilization of Augmented Reality Technology in the Campus Environment 4th

Utilization of Augmented Reality Technology in the Campus En...

引用

4th International Conference on Inventive Computation and information Technologies, ICICIT 2022

作者： Gaol, Ford Lumban Kamil, Mufti Ikhsan Iswardhana, Aria Muhammad Firnandes, Steven Gusda Fahrezi, Fazri Matsuo, Tokuro Hutagalung, Fonny Binus Graduate Program—Doctor of Computer Science Jakarta Indonesia Alam Sutera School of Information System Bina Nusantara University Jakarta Indonesia Advanced Institute of Industrial Technology Tokyo Japan University of Malaya Kuala Lumpur Malaysia

ISBN: (纸本)9789811974014

Technological advancements are accelerating in the modern day;one such advancement is augmented reality (AR) technology. Naturally, these advancements have an effect on various sectors of life, one of which is education. The education industry will be the most impacted if campuses implement and deploy augmented reality technology. One of these is through the use of augmented reality technology as an application-based learning medium for students in order to motivate them to learn and make it easier for them to improve their academic performance on campus. The issue at hand is the absence of utilization of augmentation reality technology as a learning medium on campus, which, of course, does not capitalize on technical advancements to improve student interest in learning. This study employs a research and development model. The method is divided into four phases: (1) planning;(2) data collecting;(3) analysis, discussion, and development;and (4) documentation. The findings of this study reveal that students enthusiastically support the usage of augmented reality technology as a learning medium in order to boost accomplishment and introduce new experiences through its use. However, it is required to have a system capable of serving as a technological medium, so that the construction of a system capable of serving as a medium for augmented reality may be easily accessed by students, who hope that this system would enable them to better their academic performance. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Development of Dementia Care Training System Using AR and Large Language Model

Development of Dementia Care Training System Using AR and La...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Tomoya Miyawaki Yuuki Nishiura Ryouta Fukuda Kazuto Nakashima Ryo Kurazume Graduate School of Information Science and Electrical Engineering Kyushu University Japan Department of Electrical Engineering and Computer Science Faculty of Engineering Kyushu University Japan Faculty of Information Science and Electrical Engineering Kyushu University Japan

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

We have developed HEARTS, a dementia care training system using augmented reality based on Humanitude. Humanitude is a multimodal comprehensive care technique for dementia, and has attracted attention as a method to reduce the burden on both caregivers and patients. However, the HEARTS developed so far could not evaluate “speaking” skills based on the content of conversations among “seeing,” “touching,” and “speaking,” all of which are fundamental skills in Humanitude. Therefore, we attempted a new quantitative evaluation of trainees' “speaking” skills by estimating the emotional value of conversational content using GPT-4 named HEARTS 5. A survey of caregivers was conducted using the developed system and was well received by the participants. We also developed a HEARTS 5 conversational version based on HEARTS 5, with the addition of GPT-4 conversation generation and Azure Text-to-Speech.

关键词： Heart Training Surveys Large language models Oral communication Text to speech Robots Cybernetics Augmented reality Dementia

来源：评论

学校读者我要写书评

暂无评论

CapSight: A Social Aid System for the Visually Impaired Using Facial Recognition and Haptic Feedback 13

CapSight: A Social Aid System for the Visually Impaired Usin...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Chi, Chun-Nan Hsu, Jia-Lien Hung, Chi-Huang Huang, Shih-Yung Chen, Cheng-Hsuan Hsu, Chia-Hsun Fu Jen Catholic University Graduate Institute of Applied Science and Engineering New Taipei City Taiwan Fu Jen Catholic University Department of Computer Science and Information Engineering New Taipei City Taiwan National Central University Fu Jen Catholic University Department of Electrical Engineering Taoyuan City Taiwan Fu Jen Catholic University Lee-Ming Institute of Technology Graduate Institute of Applied Science and Engineering Dept. of Information Technology New Taipei City Taiwan Kang Chiao International School Dept. of International High School New Taipei City Taiwan

ISBN: (纸本)9798350355079

This study introduces "CapSight,"a system for enhancing social interaction in visually impaired individuals. It includes a single-board computer, camera, vibration motors, and Bluetooth bone conduction headphones on a baseball cap. The camera identifies people using facial recognition and announces names through the headphones, with vibration motors indicating face positions. Users can add new friends by taking a photo and recording their name. This system helps visually impaired individuals recognize and locate social partners, boosting confidence and independence. © 2024 IEEE.

关键词： Headphones

来源：评论

学校读者我要写书评

暂无评论

DAGait: Generalized Skeleton-Guided Data Alignment for Gait Recognition

arXiv

引用

arXiv 2025年

作者： Wu, Zhengxian Zhang, Chuanrui Xu, Hangrui Jiao, Peng Wang, Haoqian The Shenzhen International Graduate School Tsinghua University Shenzhen China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Gait recognition is emerging as a promising and innovative area within the field of computer vision, widely applied to remote person identification. Although existing gait recognition methods have achieved substantial success in controlled laboratory datasets, their performance often declines significantly when transitioning to wild datasets. We argue that the performance gap can be primarily attributed to the spatio-temporal distribution inconsistencies present in wild datasets, where subjects appear at varying angles, positions, and distances across the frames. To achieve accurate gait recognition in the wild, we propose a skeleton-guided silhouette alignment strategy, which uses prior knowledge of the skeletons to perform affine transformations on the corresponding silhouettes. To the best of our knowledge, this is the first study to explore the impact of data alignment on gait recognition. We conducted extensive experiments across multiple datasets and network architectures, and the results demonstrate the significant advantages of our proposed alignment strategy. Specifically, on the challenging Gait3D dataset, our method achieved an average performance improvement of 7.9% across all evaluated networks. Furthermore, our method achieves substantial improvements on cross-domain datasets, with accuracy improvements of up to 24.0%.Code is available at: https://***/DingWu1021/DAGait Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Brain Function Assessment of EEG in Mild Cognitive Impairment using Timelag Analysis

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, information and Systems 2025年第4期145卷 467-473页

作者： Tanabe, Akifumi Harachi, Kento Yamamoto, Yusuke Muramatsu, Ayumi Nagahara, Hajime Takemura, Noriko Shimojo, Shinji Furihata, Daisuke Mizuno-Matsumoto, Yuko Graduate School of Information Science University of Hyogo 7-1-28 Minatojima Minami Chuo-ku Hyogo Kobe650-0047 Japan Department of Medical Engineering Aino University 4-5-4 Higashi-Ohda Ibaraki Osaka567-0012 Japan D3 Center The University of Osaka 2-8 Yamadaoka Osaka Suita565-0871 Japan D3 Center The University of Osaka 5-1 Mihogaoka Ibaraki Osaka567-0047 Japan Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu Fukuoka Iizuka820-8502 Japan Faculty of Software and Information Technology Aomori University 2-3-1 Shachihata Aomori-shi Aomori030-0943 Japan

This research aimed to reveal the information process in the brain of the patients who suffered from mild cognitive impairment (MCI) using the power spectra and timelag analysis in electroencephalogram (EEG). The patients with MCI have memory or thinking problems, and are at a great risk of developing Alzheimer's disease or a related dementia. Ten patients with MCI and 13 healthy adults (non-MCI) were examined. The EEGs (122.88 seconds/subject) during a state of relaxation with the eyes closed, were analyzed using the Fourier analysis (power spectrum) and the timelag analysis. The results showed that the mean value of the power spectra in MCI was significantly higher than the mean value in non-MCI in the theta band. The mean value of the absolute timelag values (ATL) in MCI was significantly lower than the mean value in non-MCI in the frontal and left temporal areas. Our findings suggest that the features from EEG of MCI were abstracted in the theta band, and the propagation of information related to memory in brain would becoming fast in MCI. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Electroencephalography

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

Human-Robot Interaction through an Object Grasped with Two Fingers Based on Plastic Deformation Control

Human-Robot Interaction through an Object Grasped with Two F...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Taku Senoo Atsushi Konno Hiromichi Kawahara Idaku Ishii Course of Systems Science and Informatic Graduate School of Information Science and Technology Hokkaido University Hokkaido Japan Smart Innovation Program Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Japan

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

In this study, two-finger grasping based on plastic deformation control for human-robot interaction is designed and implemented. This control strategy is derived based on the concept that balances both retention of grasping force on objects and plastic behavior in response to external forces. The control law consists of a set of constraints and offsets with respect to the springs that appear in the Maxwell model. In particular, the inner loop that is robust against parameter errors is implemented for actual machine experiments. Simulation and actual experiments with a robotic hand are executed to validate the proposed control law.

关键词： Hands Deformation Force Human-robot interaction Position control Grasping Robot sensing systems Maintenance Plastics Springs

来源：评论

学校读者我要写书评

暂无评论

DSPI - Dual Semantic Parsing Image: A Robust Person Representation for Person Re-Identification

DSPI - Dual Semantic Parsing Image: A Robust Person Represen...

引用

International Conference on Communications and Electronics, ICCE

作者： Dau Anh Dung Yasuhiro Nakamura Department of Information and Mathematical Sciences Graduate School of Science and Engineering National Defense Academy Yokosuka Japan Department of Computer Science School of Electrical and Computer Engineering National Defense Academy Yokosuka Japan

ISBN: (数字)9798350379792

ISBN: (纸本)9798350379808

One method to significantly enhance the performance of Person-ReID models is to leverage segmentation models to extract semantic parsing information, thus emphasizing the characteristics of human body parts. Studies employing this approach typically utilize CNN architectures as the backbone of Person-ReID, integrating human semantic parsing information into the output of the backbone model, resulting in substantial performance improvement. However, Transformer architectures, utilizing self-attention mechanisms and employing different image data processing techniques from CNN architectures, necessitate a direct integration method for human semantic parsing information into the model’s input. In this study, we propose a novel, simple, and highly adaptable method for integrating human semantic parsing information into input data, called Dual Semantic Parsing Image (DSPI). In this method, a pre-trained segmentation model is employed to extract human pixels from the background and create a new foreground image. The DSPI is formed by horizontally merging the foreground image with the original image, which serves as the input image for the Re-ID model. Our study demonstrates that the Person Re-ID Backbone model ViT+DSPI achieves 93.1% Rank-1 accuracy and 91.1% mAP in the same-domain test of DukeMTMC-ReID, thus attaining state-of-the-art performance. Additionally, significant performance enhancements were observed in cross-domain tests.

关键词： Degradation Adaptation models Image segmentation Electric potential Semantics Merging Transformers

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：