检索结果-内蒙古大学图书馆

SYNTHESIZING SPATIAL RSCR MECHANISMS FOR PATH GENERATION USING A DEEP NEURAL NETWORK

SYNTHESIZING SPATIAL RSCR MECHANISMS FOR PATH GENERATION USI...

ASME 2024 International design engineering Technical Conferences and computers and Information in engineering Conference, IDETC-CIE 2024

作者： Deng, Xueting Nurizada, Anar Purwar, Anurag Computer-Aided Design and Innovation Lab Department of Mechanical Engineering Stony Brook University Stony BrookNY11794-2300 United States

ISBN: (纸本)9780791888414

In the recent past, various machine learning approaches have been broadly studied and successfully applied in the planar mechanism synthesis problem. This paves the way for its adoption in the spatial mechanism synthesis that is typically more complex to solve due to dimensionality of the input, large number of mechanism parameters, and highly non-linear relationship between the input and output. This paper introduces a neural network approach for the path synthesis of spatial RSCR mechanisms. We detail the method of database generation with the development of a simulator, data space selection strategies, and a complete data normalization method. A novel way of calculating the coupler curve is utilized, addressing the challenge of describing the absolute position of a point on the rigid body in R3. The database generation uses a spatial mesh grid-base method with specific criteria for preventing circuit defects and duplicate mechanisms. All data in the database is translated, rotated, and reflected to a normalized position. In the end, the classical neural network structure, multi-layer perceptron (MLP), is applied for finding the mapping from the spatial path to mechanism parameters. The MLP with different parameters and techniques, such as batch normalization and dropout, are implemented for finding the best model. The result shows the capability of MLP for complex spatial path synthesis. Moreover, despite the limitation of a single MLP's structure, this study demonstrates the potential of improvement with more advanced neural networks. Copyright © 2024 by ASME.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

GENERATIVE design OF PLANAR FOUR-BAR MOTIONS USING CONDITIONAL VARIATIONAL AUTOENCODER

GENERATIVE DESIGN OF PLANAR FOUR-BAR MOTIONS USING CONDITION...

引用

ASME 2024 International design engineering Technical Conferences and computers and Information in engineering Conference, IDETC-CIE 2024

作者： Halwah, Amro Nurizada, Anar Purwar, Anurag Computer-Aided Design and Innovation Lab Department of Mechanical Engineering Stony Brook University Stony BrookNY11794-2300 United States

ISBN: (纸本)9780791888360

This paper introduces a novel deep generative approach to the approximate motion synthesis of planar four-bar mechanisms. Existing motion synthesis approaches for synthesizing four-bar mechanisms have generally focused on representing the motion as five or less discrete poses while not providing any guarantees on the practicality of the solutions, such as ones without circuit-, branch-, and order-defects. This paper presents a Conditional Variational Autoencoder (C-VAE) based approach for synthesizing practical mechanisms that can capture the overall motion requirement while generating a continuous motion approximately. The mathematical machinery in our work uses quaternion and kinematic mapping to represent the geometric constraints of dyads of four-bar mechanism as algebraic constraint manifolds in a three-dimensional projective space. The parameters describing the manifolds encode information about the type and dimensions. These parameters are used as input to a C-VAE that uses an arbitrarily large number of input poses approximating a motion as the condition. A procedure is presented for normalizing input motions such that they are invariant with respect to rotation, scaling, translation and reflection. The trained model can generate several pairs of constraint manifolds from which four-bar mechanisms with different parameters can be retrieved. These mechanisms’ coupler poses approximate the input’s coupler poses to varying degrees of error. A method for filtering mechanisms by the quality of match of their output motion to the input motion is also proposed. Different metrics for quantifying the similarity of an output mechanism’s motion with the input motion are presented for path and orientation separately. Copyright © 2024 by ASME.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Mathematical Model for Plate Elastic Properties Studying Based on Its Amplitude-Frequency Characteristics 28

Mathematical Model for Plate Elastic Properties Studying Bas...

引用

28th IEEE International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2023

作者： Rebot, Dariia Stefanovych, Tetyana Shcherbovskykh, Serhiy Computer-Aided Design System Department Lviv Polytechnic National University Lviv Ukraine

ISBN: (纸本)9798350315332

the article describes a mathematical model for studying the elastic properties of a plate on its amplitude-frequency characteristics under the influence of an external disturbance. The methods of nonlinear mechanics were used to build the mathematical model. Based on the obtained equations, graphical dependences of amplitude-frequency characteristics for soft, linear, and rigid systems are constructed. The obtained results can be used in future studies of oscillatory processes in resonators. © 2023 IEEE.

关键词： Elasticity

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of YOLO variants on Marine Trash Images: A Comparative Study of YOLOv5, YOLOv7, YOLOv8, and TinyYOLO

Performance Evaluation of YOLO variants on Marine Trash Imag...

引用

2024 IEEE Bangalore Humanitarian Technology Conference, B-HTC 2024

作者： Sawant, Shreedatta D'Souza, Lyzandra Kulkarni, Aditi Uchil, Devika Nagvenkar, Krisha Agnel Institute of Technology and Design Department of Computer Engineering India

ISBN: (纸本)9798350344509

Despite the growing efforts to tackle the issue of marine pollution, the accurate and effective detection of oceanic litter remains a chronic difficulty. The development of a reliable deep learning-based system is vital for accurate and rapid marine trash detection in order to address these issues. This study delves into the comparison of the YOLO (You Only Look Once) variants, YOLOv4 tiny, YOLOv5, YOLOv7, and YOLOv8 so as to identify the best model for underwater plastic waste detection. The results of the experiment show that YOLOv5 has the highest mAP@50 at 0.92 and YOLOv5 also has a higher recall and F1-score compared to the other three models. Our findings also revealed that YOLOv7 had the smallest mAP@50, measuring at 0.847. © 2024 IEEE.

关键词： Marine pollution

来源：评论

学校读者我要写书评

暂无评论

Survey on Recommendation System Combining Hybrid and Popularity Based Approach 2

Survey on Recommendation System Combining Hybrid and Popular...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Bhogan, Snehal Naik, Sagar Gaonkar, Suhesha Prabhudesai, Sharvil Dhond, Gaurish Fernandes, Kevin Agnel Institute of Technology and Design Department of Computer Engineering India

ISBN: (纸本)9798350327533

The rapidly developing e-commerce environment offers consumers a multitude of products and services, making it difficult to find products that suit their interests and budgets. This research work presents a solution consisting of individualized based recommendations on user's behavior and preferences, and base them on the user's shared *** order to enhance user experience,it shows the use of a recommendation model that estimates specific product that a user may wish to buy using a hybrid system and a popularity-based system. This research work places a strong emphasis on data veracity, quality modeling, and user privacy protection. The system is designed to make purchasing decisions easier for e-commerce customers by providing them with information about competitive pricing and product recommendations. It provides e-commerce and research data to create effective solutions to improve online business, creating a win-win situation for the consumer and e-commerce. © 2024 IEEE.

关键词： Hybrid Popularity Recommendation Model

来源：评论

学校读者我要写书评

暂无评论

Development of Microcontroller-Based Pure Sine Wave Inverter with Overload and Overheating Protection 17

Development of Microcontroller-Based Pure Sine Wave Inverter...

引用

17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and computer engineering, TCSET 2024

作者： Holovatyy, Andriy Lobur, Mykhaylo Holovata, Sofia Lukaszewicz, Andrzej Nowakowski, Marek Kolesnyk, Kostyantyn Lviv Polytechnic National University Department of Computer-Aided Design Systems Lviv Ukraine Ukrainian National Forestry University Department of Software Engineering Lviv Ukraine Bialystok University of Technology Department of Machinery Design and Operation Bialystok Poland Military Institute of Armoured and Automotive Technology Development Department Sulejowek Poland Lviv Polytechnic National University Department of Computera-Aided Design Systems Lviv Ukraine

ISBN: (纸本)9798331520564

In the paper, hardware and software of the Arduino based pure sine wave inverter with overload and overheating protection have been developed. The inverter constantly monitors the consumption current, the battery voltage, the temperature of the power switches (radiator) and, if their parameters are normal, forms a sinusoidal voltage of 230 V, 50 Hz at the output of the inverter, similar to the network voltage. The inverter provides the display of information on the LCD screen about current and power consumption, battery voltage, temperature of the inverter power switches, as well as display of emergency icons when the permissible operating parameters are exceeded. The inverter generates sound and visual warning messages with LED indicators and buzzer. The inverter can be used as a lightweight low-power 100 W network inverter with sine-wave voltage for autonomous power supply of low-power electronics. © 2024 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

3D Human Pose Estimation via Graph Extended Spatio-Temporal Convolutional Network 9

3D Human Pose Estimation via Graph Extended Spatio-Temporal ...

引用

9th International Conference on Virtual Reality, ICVR 2023

作者： Jia, Yanhui Fan, Wanshu Zhou, Dongsheng Zhang, Qiang Dalian University National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian China

ISBN: (纸本)9798350345810

3D human pose estimation is an important premise for human behavior analysis and understanding, which has a wide range of applications in intelligent transportation, human-computer interaction, and animation production. Most existing works focus on extracting the feature relationship between frames by combining spatio-temporal information to reduce the error of attitude reconstruction. However, the majority of them often suffer from insufficient joint correlation characteristics. To address this problem, we propose a Graph Expand Spatiotemporal Convolutional Network, named GESC-Net, to improve the limitation of extracting human spatial structure features. To better enrich the feature of extracting local information, we develop a learnable symmetric connection (LSC) block in the spatial structure. Moreover, a CbAttantion block is also designed to obtain a larger view of the acquisition of global structure and get more effective features. We evaluate our approach on two standard benchmark datasets: Human3.6M and HumanEva-I. The quantitative and qualitative evaluation results demonstrate that the GESC-Net can achieve better 3D human posture estimation than existing state-of-the-art methods. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

MeshWGAN: Mesh-to-Mesh Wasserstein GAN with Multi-Task Gradient Penalty for 3D Facial Geometric Age Transformation

引用

IEEE Transactions on Visualization and computer Graphics 2024年第8期30卷 4927-4940页

作者： Zhang, Jie Zhou, Kangneng Luximon, Yan Lee, Tong-Yee Li, Ping The Hong Kong Polytechnic University Department of Computing The School of Design Hong Kong University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China The Hong Kong Polytechnic University School of Design Hong Kong Laboratory for Artificial Intelligence in Design Hong Kong National Cheng-Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

As the metaverse develops rapidly, 3D facial age transformation is attracting increasing attention, which may bring many potential benefits to a wide variety of users, e.g., 3D aging figures creation, 3D facial data augmentation and editing. Compared with 2D methods, 3D face aging is an underexplored problem. To fill this gap, we propose a new mesh-to-mesh Wasserstein generative adversarial network (MeshWGAN) with a multi-task gradient penalty to model a continuous bi-directional 3D facial geometric aging process. To the best of our knowledge, this is the first architecture to achieve 3D facial geometric age transformation via real 3D scans. As previous image-to-image translation methods cannot be directly applied to the 3D facial mesh, which is totally different from 2D images, we built a mesh encoder, decoder, and multi-task discriminator to facilitate mesh-to-mesh transformations. To mitigate the lack of 3D datasets containing children's faces, we collected scans from 765 subjects aged 5-17 in combination with existing 3D face databases, which provided a large training dataset. Experiments have shown that our architecture can predict 3D facial aging geometries with better identity preservation and age closeness compared to 3D trivial baselines. We also demonstrated the advantages of our approach via various 3D face-related graphics applications. © 1995-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Neural Networks for Privacy-Preserving Model Sharing in Power Systems

Physics-Informed Neural Networks for Privacy-Preserving Mode...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Canyakmaz, Ilayda Saner, Can Berk Varvitsiotis, Antonios Singapore University of Technology and Design Engineering Systems and Design Pillar Singapore National University of Singapore Electrical and Computer Engineering Department Singapore

ISBN: (纸本)9789531842976

Data privacy concerns in the power systems sector significantly complicate the sharing and integration of sensitive operational data among various independent entities. This challenge is particularly pronounced when developing system-wide mathematical models, as the reluctance to share sub-system models parametrized by sensitive data hinders effective system analysis and decision-making. To address this issue, this work introduces the application of Physics-Informed Neural Networks (PINNs) to develop surrogate models that accurately replicate power system dynamics without exposing sensitive data, enabling privacy-preserving model sharing. By embedding physical laws into the training process, PINNs utilize both available data and inherent system physics, making them particularly suitable for modeling complex dynamics. We propose a framework for model development, including dataset generation and integration of the physics knowledge during PINN training. As a proof-of-concept, we apply this framework to a simplified Single Machine Infinite Bus (SMIB) system. Case studies demonstrate that the trained PINN model closely follows ground-truth dynamics and consistently achieves higher accuracy compared to generic neural networks, highlighting the potential for accurate, privacy-preserving model sharing and system-wide dynamic simulations in power systems. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Interview Preparation Guide Generation Leveraging GPT-4, ZSL and Hybrid Techniques

Interview Preparation Guide Generation Leveraging GPT-4, ZSL...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

作者： Ramu, Tharaka Naik, Nenavath Srinivas IIIT Design Manufacturing Department of Computer Science and Engineering Kurnool India

ISBN: (纸本)9798350379525

This paper presents a novel approach for automating the creation of personalized interview preparation guides using GPT-4, Zero-Shot Learning (ZSL), and hybrid techniques. Our system dynamically generates tailored interview questions and preparation materials based on specific job descriptions and candidate profiles. By integrating advanced NLP with rule-based methods, it significantly enhances the relevance and quality of the content compared to traditional methods. We analyzed data from 10,000 job descriptions, 10,000 candidate profiles, and 20,000 interview questions to ensure high-quality results. The use of ZSL enables the generation of guides even for new and unfamiliar roles. Our approach achieved a 35% increase in question relevance and a 28% improvement in candidate-job matching accuracy compared to baseline methods. This research also paves the way for enhancing AI tools in HR, supporting personalized learning, performance reviews, and career planning. © 2024 IEEE.

关键词： Zero-shot learning

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：