检索结果-内蒙古大学图书馆

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

Comparative Analysis of Machine Learning Algorithms in Fish Survival Prediction

Comparative Analysis of Machine Learning Algorithms in Fish ...

引用

2024 IEEE Bangalore Humanitarian Technology Conference, B-HTC 2024

作者： Shirwaikar, Rudresh D. D'Souza, Lyzandra Bhangle, Anirudh Santosh Joshi, Sarang Deepak Jathar, Nupur Ajit Alvares, Jonathan Elroy Agnel Institute of Technology and Design Department of Computer Engineering Mapusa India

ISBN: (纸本)9798350344509

This research paper conducts an exploration of prevalent machine learning classification algorithms, emphasizing the refinement of Random Forest models to optimize performance. The initial phase involves a comparative analysis of Random Forest, k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Logistic Regression, and Naive Bayes Classification algorithms across the dataset, resulting in Random forest to be best performed among all with average accuracy of 61%. Subsequently, then we focus on enhancement of the Random Forest algorithm with random train-test split dataset, resulting in an enhanced average accuracy of 65% which is about 4% improvement to the previous accuracy and choosing the best traintest split dataset, along with fine tuning the model, improved the average accuracy to 73% which is about 12% improvement to previous accuracy which is significantly higher showcasing the significance of precise algorithmic tuning. The completion of our investigation lies in the creation of an integrated model which incorporates multiple Random Forest classifier models, each specifically trained for binary class classification, along with a comprehensive model designed for multiclass classification. This combined model excels with a peak accuracy of 82.75% for the best split, demonstrating its strong performance in classification tasks. This research not only contributes to the theoretical understanding of algorithm performance and optimization but also offers practical insights for the application of machine learning in challenging classification scenarios. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Overview of Emerging Biological Computational Framework for Olfactory Studies Utilizing Contextual Technobiomedical engineering 2

Overview of Emerging Biological Computational Framework for ...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Chaudhri, Shiv Nath Faculty of Engineering & Technology Department of Computer Science and Design Wardha India

ISBN: (纸本)9798331528713

Organoid intelligence (OI), the next paradigm of intelligence, draws inspiration from the biological learning of organs. On the other hand, artificial intelligence (AI) draws its inspiration only from the cognitive processes of the brain. While taking ethical and technological limitations into account, biological learning helps to conceptualize, accept, and apply them. Just as AI helped to make supercomputers possible, OI may help create biocomputers. Even though AI has increased the capabilities of technology to unimaginable heights, it still appears immature and is steadily moving toward cognitive computing to push the envelope even farther. In contrast to AI, OI is a new multidisciplinary computer area that attempts to be more approachable. OI has the ability to produce novel biocomputers, such as organoids, that use parts derived from live organisms to perform computational tasks. Organoids, such as human nasal organoids, are microscopic tissue cultures made from stem cells that mimic some of the functions of real organs. Although they have been used for many different purposes, including drug discovery and illness modeling, scientists are only now beginning to explore their potential for biological information processing. © 2024 IEEE.

关键词： Artificial Intelligence (AI) Biological Information Processing Biological Learning Olfactory Organoids Organoid Intelligence (OI)

来源：评论

学校读者我要写书评

暂无评论

OFDM-structure based waveform designs for integrated sensing and communication

引用

Science China(Information Sciences) 2025年第5期68卷 267-284页

作者： Jiaqi LIU Ping YANG Ke JIANG Jiarong ZHAO Wei XIANG Jianping WEI Ruixiang DUAN Saviour ZAMMIT Tony Q.S.QUEK National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China School of Computing Engineering and Mathematical Sciences La Trobe University Meituan Academy of Robotics Department of Communications and Computer Engineering University of Malta Information Systems Technology and Design Pillar Singapore University of Technology and Design

The future sixth-generation(6G) paradigm aims to seamlessly integrate communication and environmental sensing capabilities into a single radio signal, promising improved efficiency and cost-effectiveness through simultaneous data communications and environmental perception. At the core of this evolution, orthogonal frequency division multiplexing(OFDM) and its advanced waveforms emerge as pivotal for integrated sensing and communications(ISAC). This study introduces a concise and unified ISAC waveform design framework based on orthogonal multicarriers. This framework supports versatile applications of OFDM and its derivative waveforms within a generalized ISAC system, marking a significant leap in integrating communication and sensing capabilities. A distinguishing feature of this framework is its adaptability,allowing users to intelligently select modulation strategies based on their specific environmental needs. This adaptability optimizes performance across diverse scenarios. Central to our innovations is the proposal of discrete Fourier transformspread OFDM with index modulation(DFT-S-OFDM-IM). This framework is paired with newly proposed signal processing methods for single-input single-output and multiple-input multiple-output(MIMO) systems. Extensive evaluations highlight DFT-S-OFDM-IM's superiority, including dramatically reduced peak-to-average power ratios(PAPRs), competitive communication performance, and exceptional sensing capabilities, striking an elegant balance between communication capacity and environmental sensing precision.

关键词： DFT-S-OFDM-IM index modulation integrated sensing and communication OFDM

来源：评论

学校读者我要写书评

暂无评论

Methods and Technologies for Primary Processing, Modeling and Visualization of Industrial Data for Quality Control of Multi-assortment Polymeric Films 5

Methods and Technologies for Primary Processing, Modeling an...

引用

5th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2023

作者： Chistyakova, Tamara Polosin, Andrey Platonenko, Gleb Kohlert, Christian Computer-Aided Design and Control System Department Saint Petersburg Russia Kohlert-Consulting Oberahr Germany

ISBN: (纸本)9798350309126

The methods of primary processing, modeling, visualization of data of large-capacity production of polymeric films of a wide range are described. The methods are implemented in the product quality control system. Industrial data is characterized by a big volume, high accumulation rate, a variety of sources, incompleteness, encoded values, unstructured nature. Therefore, their primary processing consists in converting them into real values, filtering, structuring by types of production parameters. The lack of measurement of a number of important quality indices of the polymeric material at the production stages, including the quality indices of the extrudate, causes incompleteness of data about the control object. This incompleteness led to the creation of a library of adjustable mathematical models for calculating quality indices depending on the control actions measured in production, with different configurations of aggregates and types of films. Complete arrays of measured and calculated parameter values are stored in a database for subsequent analysis, processing (by methods of mathematical statistics and machine learning) and visualization. The data are visualized in the form of parameter trends and histograms for distributions of the specific number of defects of various types across the film rolls. Visualization allows you to study the influence of control actions and technological additives (for example, stabilizers) on the quality of the film to select a rational recipe and production mode of the film. The proposed methods are implemented in the form of a flexible software package. It is adjusted to the range of films produced, configurations of production lines and is designed to support decision-making on the control of consumer characteristics of polymeric films. Testing of the software package according to the data of industrial extrusion-calendering production of rigid packaging films based on polyvinyl chloride has confirmed its operability. The effec

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Data Processing on Edge Locations of CDNNetwork 17

Dynamic Data Processing on Edge Locations of CDNNetwork

引用

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

作者： Kyryk, Marian Pleskanka, Nazar Pleskanka, Maryana Lviv Polytechnic National University Department of Telecommunication Lviv Ukraine Lviv Polytechnic National University Department of Computer-Aided Design Lviv Ukraine

ISBN: (纸本)9798331520564

The main methods and principles of building infrastructure as a code in Cloud, microservice architecture are considered. An algorithm of dynamic data processing in the edge location is proposed to improve quality of service. A simulation modelling of the dynamic application microservice creating, which works based on developed algorithm in the content delivery network (CDN) was performed. Based on the obtained simulation results, graphical dependencies of the efficiency of using dynamic data processing in the edge location depending on the load and the number of requests from clients are presented. The results confirm the effectiveness of using dynamic data processing in the edge locations when the number of requests increases, at the same time keeping the delay time within satisfactory limits. © 2024 IEEE.

关键词： CDN network cloud computing data processing edge server Infrastructure as Code IoT load balancing microservice architecture the edge compute

来源：评论

学校读者我要写书评

暂无评论

Predicting Employee under Stress Using Machine Learning

Predicting Employee under Stress Using Machine Learning

引用

2024 IEEE International Conference on Signal Processing and Advance Research in Computing, SPARC 2024

作者： Javeriya, Thonduru Anjum Kabilan, M. Manoj, Golla Sree, Yarragonda Bhavya Jagadish, Rongala Venkata Satya Mir, Mahmood Hussain Debnath, Saswati Girish, B.M. Alliance College of Engineering and Design Karnataka Bengaluru India Alliance College of Engineering and Design Karnataka Bengaluru India Alliance College of Engineering and Design Karnataka Bengaluru India Alliance College of Engineering and Design Department of Computer Science and Information Technology Karnataka Bengaluru India Alliance College of Engineering and Design Department of Mechanical Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350385199

Because of COVID-19, businesses have had to change how they operate, like having people work from home or having fewer employees in the office. This 'new normal' is sticking around for a while. Workers have had to adjust to these changes, which can make them feel tired and Pressure. Stress happens when people feel overwhelmed and uncertain. There are lots of things that can cause stress for workers, like getting paid less, having too much work to do, feeling lonely while working from home, working longer hours, not having a good place to work, not feeling like part of a team, feeling like they can't do their job well, and worrying about getting sick. If bosses can recognize when workers are starting to feel stressed, they can help fix the problem, which can make things better for both the worker and the company. © 2024 IEEE.

关键词： COVID-19

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：