检索结果-内蒙古大学图书馆

14th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2023

作者： Zhang, Zhang Zhang, Xiaoyong Ichiji, Kei Bukovsky, Ivo Chou, Shuoyan Homma, Noriyasu Tohoku University Graduate School of Biomedical Engineering Sendai Japan National Institute of Technology Sendai College Department of General Engineering Sendai Japan Tohoku University Graduate School of Medicine Sendai Japan University of South Bohemia in Ceske Budejovice Faculty of Science Department of Computer Science Ceske Budejovice Czech Republic National Taiwan University of Science and Technology Department of Industrial Management Taipei Taiwan

ISBN: (纸本)9798350324228

During the COVID-19 pandemic, many deep learning-based methods has been proposed to diagnose COVID-19 in chest X-ray (CXR) screening. A previous study validated the performance of the deep learning-based methods and suggested the different data sources in training data could lead to unreliable performance. However, it is unclear whether and how the data sources influence the performance. In this study, we utilized a cross-dataset test, where a deep learning model is trained and tested on two different COVID-19 datasets, to investigate how different data sources affect deep learning performance. During the cross-dataset test, one dataset was collected from different data sources and the other was collected from a single data source. We compared the performance of a deep learning model trained by the different datasets and evaluated the image features that contributed to the predictions by using a local interpretable model-agnostic explanations (LIME) method. As a result, the different data sources-trained deep learning model learned improper features outside lung regions and could not classify the CXR images from the same data source. In contrast, the same data source-trained model focused more inside lung regions and performed well on data from different data sources. This study revealed a hidden risk that the features of images representing data sources can lead to unreliable performance. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Deaf Helper Mobile Application for Interaction of Hearing Disorders Communities 2

Deaf Helper Mobile Application for Interaction of Hearing Di...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Setyawan, Adrian Naphan, Gilbert Xervaxius Dynata, Kevin Friry, Jovano Edmund Warnars, Harco Leslie Hendric Spits Bina Nusantara University School of Information System Information Systems Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665400527

People with hearing loss in this world have not received much serious attention from the authorities. This makes these sufferers confused in choosing learning media to interact with and isolated from their social environment. This application was created to help people with hearing loss to be noticed and understood from the way they communicate using sign language through the mobile application called Assistant for the Deaf, which has many features such as registration, interactive videos, sign language translator, forums, customer service, library, information, history, events, donations, and shops. The application is designed using use case diagrams and class diagrams modeling the database, and the implementation used Android Studio and MySQL database. © 2022 IEEE.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense

arXiv

引用

arXiv 2024年

作者： Qiu, Yixiang Yu, Hongyao Fang, Hao Zhuang, Tianqu Yu, Wenbo Chen, Bin Wang, Xuan Xia, Shu-Tao Xu, Ke School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Tsinghua Shenzhen International Graduate School Tsinghua University China Department of Computer Science and Technology Tsinghua University China

Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising critical concerns regarding the privacy vulnerabilities of Deep Neural Networks (DNNs). Unfortunately, in tandem with the rapid evolution of MI attacks, the absence of a comprehensive benchmark with standardized metrics and reproducible implementations has emerged as a formidable challenge. This deficiency has hindered objective comparison of methodological advancements and reliable assessment of defense efficacy. To address this critical gap, we build the first practical benchmark named MIBench for systematic evaluation of model inversion attacks and defenses. This benchmark bases on an extensible and reproducible modular-based toolbox which currently integrates a total of 19 state-of-the-art attack and defense methods and encompasses 9 standardized evaluation protocols. Capitalizing on this foundation, we conduct extensive evaluation from multiple perspectives to holistically compare and analyze various methods across different scenarios, such as the impact of target resolution, model predictive power, defense performance and adversarial robustness. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

The Effects of Selected Preferred Music on Perceived Emotions through Audiovisual Stimuli

The Effects of Selected Preferred Music on Perceived Emotion...

引用

Big Data, Cloud Computing, Data science & Engineering (BCD)

作者： Thunrada Thaiwong Makoto Fukumoto Graduate School of Computer Science and Engineering Fukuoka Institute of Technology Fukuoka Japan Dept. of Computer Science and Engineering Fukuoka Institute of Technology Fukuoka Japan

ISBN: (数字)9798350394191

ISBN: (纸本)9798350394207

Music surrounds us, and there is no denying that music in visual media can shape and evoke emotions. Yet, understanding how musical preference influences emotions through audio and visual stimuli remains an important task. To address this task, we investigated the role of musical preference effect on perceived emotions induced through music and visual stimuli (i.e., animation), using a 7-point scale for valence-arousal ratings and physiological responses in electroencephalogram (EEG) band power. The perceived emotions are categorized into four states: happiness, calmness, fear, and sadness. One emotional state contains 4 sessions: (1) Preferred Music, (2) Unfamiliar Music, (3) Preferred Music+Animation, and (4) Unfamiliar Music+ Animation. Behavior-wise, the rating results showed that the presence of preferred music resulted in higher perceived valence ratings, particularly in happiness. However, no stimulus had a significant effect on perceived arousal ratings and satisfaction ratings. Physiologically, the EEG indexes showed that the presence of preferred music appears to affect an increase in alpha power across various emotions except sadness, whereas unfamiliar music seems to affect beta power, particularly in happiness and calmness. Overall, these findings supported that musical preference is an affective factor reflecting the levels of valence and alpha power in EEG. Nevertheless, our findings did not confirm a significant difference between only preferred music and combining it with animation. Interestingly, we also found that participants were more likely to be attracted to and perceive positive (i.e., happiness and calmness) emotions easily through preferred music and/or visual stimuli than negative (i.e., fear) emotions.

关键词： Visualization Cloud computing Shape Music Media Data science Animation Physiology Electroencephalography Indexes

来源：评论

学校读者我要写书评

暂无评论

Towards Trajectory Planning for a 6-Degree-of-Freedom Robot Manipulator Considering the Orientation of the End-effector Using computer Algebra 10

Towards Trajectory Planning for a 6-Degree-of-Freedom Robot ...

引用

10th International Symposium on Symbolic Computation in Software science - Work in Progress Workshop, SCSS 2024 WiP

作者： Okazaki, Takumu Terui, Akira Mikawa, Masahiko Master's Program in Mathematics Graduate School of Science and Technology University of Tsukuba Tsukuba305-8571 Japan Institute of Pure and Applied Sciences University of Tsukuba Tsukuba305-8571 Japan Institute of Library Information and Media Science University of Tsukuba Tsukuba305-8550 Japan

We consider the trajectory planning of a 6-Degree-of-Freedom (DOF) robot manipulator using computer algebra, with controlling the orientation of the end-effector. As a first step towards the objective, we present a solution to the inverse kinematics problem of the manipulator such that the orientation of the end-effector remains constant using computer algebra. © 2024 CEUR-WS. All rights reserved.

关键词： End effectors

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

An Optimized Path Planning of Manipulator with Spline Curves Using Real Quantifier Elimination Based on Comprehensive Gröbner Systems 10

An Optimized Path Planning of Manipulator with Spline Curves...

引用

10th International Symposium on Symbolic Computation in Software science - Work in Progress Workshop, SCSS 2024 WiP

作者： Shirato, Yusuke Oka, Natsumi Terui, Akira Mikawa, Masahiko Master's Program in Mathematics Graduate School of Science and Technology University of Tsukuba Tsukuba305-8571 Japan Institute of Pure and Applied Sciences University of Tsukuba Tsukuba305-8571 Japan Institute of Library Information and Media Science University of Tsukuba Tsukuba305-8550 Japan

This paper presents an advanced method for addressing the inverse kinematics and optimal path planning challenges in robot manipulators. The inverse kinematics problem involves determining the joint angles for a given position and orientation of the end-effector. Furthermore, the path planning problem seeks a trajectory between two points. Traditional approaches in computer algebra have utilized Gröbner basis computations to solve these problems, offering a global solution but at a high computational cost. To overcome the issue, the present authors have proposed a novel approach that employs the Comprehensive Gröbner System (CGS) and CGS-based quantifier elimination (CGS-QE) methods to efficiently solve the inverse kinematics problem and certify the existence of solutions for trajectory planning. This paper extends these methods by incorporating smooth curves via cubic spline interpolation for path planning and optimizing joint configurations using shortest path algorithms to minimize the sum of joint configurations along a trajectory. This approach significantly enhances the manipulator's ability to navigate complex paths and optimize movement sequences. © 2024 CEUR-WS. All rights reserved.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Marine Predators Algorithm with Deep Learning-Based Leukemia Cancer Classification on Medical Images

引用

computer Modeling in Engineering & sciences 2024年第10期141卷 893-916页

作者： Sonali Das Saroja Kumar Rout Sujit Kumar Panda Pradyumna Kumar Mohapatra Abdulaziz S.Almazyad Muhammed Basheer Jasser Guojiang Xiong Ali Wagdy Mohamed Department of Computer Science&Engineering Gandhi Institute for TechnologyBPUTBhubaneswar752054India Department of Information Technology Vardhaman College of Engineering(Autonomous)Hyderabad501218TelanganaIndia Department of Electronic&Communication Engineering Vedang Institute of TechnologyBhubaneswar752010India Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Computing and Information Systems School of Engineering and TechnologySunway UniversityJalan UniversitiBandar SunwaySelangor Darul Ehsan47500Malaysia Research Centre for Human-Machine Collaboration(HUMAC) School of Engineering and TechnologySunway UniversityJalan UniversitiBandar SunwaySelangor Darul Ehsan47500Malaysia Guizhou Key Laboratory of Intelligent Technology in Power System College of Electrical EngineeringGuizhou UniversityGuiyang550025China Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research Center Applied Science Private UniversityAmman11931Jordan

In blood or bone marrow,leukemia is a form of cancer.A person with leukemia has an expansion of white blood cells(WBCs).It primarily affects children and rarely affects *** depends on the type of leukemia and the extent to which cancer has established throughout the *** leukemia in the initial stage is vital to providing timely patient *** image-analysis-related approaches grant safer,quicker,and less costly solutions while ignoring the difficulties of these invasive *** can be simple to generalize computer vision(CV)-based and image-processing techniques and eradicate human *** researchers have implemented computer-aided diagnosticmethods andmachine learning(ML)for laboratory image analysis,hopefully overcoming the limitations of late leukemia detection and determining its *** study establishes a Marine Predators Algorithm with Deep Learning Leukemia Cancer Classification(MPADL-LCC)algorithm onMedical *** projectedMPADL-LCC system uses a bilateral filtering(BF)technique to pre-process medical *** MPADL-LCC system uses Faster SqueezeNet withMarine Predators Algorithm(MPA)as a hyperparameter optimizer for feature ***,the denoising autoencoder(DAE)methodology can be executed to accurately detect and classify leukemia *** hyperparameter tuning process using MPA helps enhance leukemia cancer classification *** results are compared with other recent approaches concerning various measurements and the MPADL-LCC algorithm exhibits the best results over other recent approaches.

关键词： Leukemia cancer medical imaging image classification deep learning marine predators algorithm

来源：评论

学校读者我要写书评

暂无评论

A Self-Supervised Transformer-Based Model for Early Recurrence Prediction of HCC with Multimodal MRI 12

A Self-Supervised Transformer-Based Model for Early Recurren...

引用

12th IEEE Global Conference on Consumer Electronics, GCCE 2023

作者： Zhang, Xianru Zhan, Gan Wang, Fang Li, Yinhao Lin, Lanfen Hu, Hongjie Chen, Yen-Wei Ritsumeikan University Graduate School of Information Science and Engineering Shiga Japan Zhejiang University Sir Run Run Shaw Hospital Department of Radiology Hangzhou China Zhejiang University College of Computer Science and Technology Hangzhou China

ISBN: (纸本)9798350340181

Hepatocellular carcinoma (HCC) is a representative primary liver cancer with high incidence and mortality. Surgical resection is the first option of treatment, but patients are usually at a high risk of tumor recurrence within the first 2 years, resulting in poor overall outcomes. Thus, it is of great clinical significance to predict HCC early recurrence to improve the survival rate. Existing transformer-based methods typically rely on models pretrained on ImageNet, which may not effectively extract features from medical images. Thus, we propose a self-supervised transformer-based method for HCC early recurrence prediction. We first leverage a vision transformer trained through self-supervised learning to capture more informative semantic features from multimodal MRI. These enhanced features are subsequently fused with a transformer architecture to predict the early recurrence of HCC. Experiments show that our method achieved better results than other methods. © 2023 IEEE.

关键词： Forecasting

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

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

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：