检索结果-内蒙古大学图书馆

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： A Chandrashekhar B Mallikarjuna Thiyagesan M L. Umasankar G. Ezhil Rukmani Devi Department of Mechanical Engineering Faculty of Science and Technology ICFAI Foundation for Higher Education Hyderabad Telangana India Department of Electrical and Electronics Engineering RNS Institute of Technology Bengaluru Karnataka India Department of Electrical and Electronics Engineering R.M.K Engineering College Chennai Tamil Nadu India Department of Electrical and Electronics Engineering S. A. Engineering College Chennai Tamil Nadu India Department of English Bannari Amman Institute of technology Sathyamangalam Tamil Nadu India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The growing demand for electric vehicles (EVs) has highlighted the need for efficient and reliable on-board chargers (OBCs) to reduce charging time and enhance battery life. Nevertheless, there are some issues in classic OBC designs: harmonic distortion may become too large, electromagnetic interference increases, and thermal management is not proper; all of which directly affects other elements of the system. As an optimization approach to enhance the performance of the dual-stage interleaved on-board charger (OBC) for electric vehicles (EVs), this work introduces the Snow Geese Algorithm (SGA). The objective of the proposed method is to enhance charging efficiency and minimize cost. The proposed SGA is used to optimize the dual-stage interleaved converter, focusing on reliable performance and effective operation within EV charging systems. The suggested approach is then put into practice on the MATLAB platform and contrasted with a number of current techniques, including Artificial Bee Colony (ABC), Simulated Annealing (SA), Multi-objective Genetic Algorithm (MOGA), and Particle Swarm Optimization (PSO). The proposed SGO method for dual-stage interleaved EV chargers achieves a cost of $1,050.80 and an efficiency of 97.2 %, demonstrating its effectiveness in reducing expenses while maximizing optimization performance in charging systems.

关键词： Sentiment analysis Costs Heuristic algorithms Snow Electromagnetic interference Simulated annealing Thermal management Harmonic distortion Reliability Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Research on Art Style Rendering Algorithm Based on computer Vision

Research on Art Style Rendering Algorithm Based on Computer ...

引用

2023 International Conference on Internet of Things, Robotics and Distributed Computing, ICIRDC 2023

作者： Wang, Heng Zhou, Yanwei Zhang, Zihao School of Design and Art Tianjin Academy of Fine Arts Tianjin300141 China School of Architecture and Art Design Hebei University of Technology Tianjin300132 China Center for Urban and Rural Renewal and Architectural Heritage Conservation Hebei University of Technology Tianjin300132 China Hebei Key Laboratory of Healthy Living Environment Tianjin300132 China Samueli Electrical and Computer Engineering University of California Los Angeles90024 United States

ISBN: (纸本)9798350375275

For a long time, the art of painting has been mysterious to most ordinary people. Since ancient times, countless artists have devoted their lives to painting works, and many masters have formed their own unique painting style. With the rapid development of computer technology, we can extract and imitate the painting styles of various famous artists, and even ordinary people can pry into the mysteries of artistic style, so as to make works with master artistic style. This style rendering technology is called style style transfer. With the continuous development of stereoscopic display technology, people's demand for more diversified stereoscopic display effects is also increasing. Chinese ink art, as one of the typical representatives of Oriental painting art, has positive significance and far-reaching influence by combining it with three-dimensional display technology. Through the study of Chinese traditional landscape painting and a large number of research on the simulation results of ink style at home and abroad, this paper focuses on the freehand ink style rendering of three-dimensional terrain, and designs a ink style rendering method based on program gray coloring, which can easily observe the effect of ink change when the terrain changes. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Optimized Cascaded Deep Capsule Cell Attention Network for Efficient Music Genre Classification

Optimized Cascaded Deep Capsule Cell Attention Network for E...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Chennaiah Kate R. Sangeethapriya M Revathy J. Mahil A. Anto Spiritus Kingsly S. Rukmani Devi Department of Computer Science and Engineering St. Peter's Engineering College Hyderabad Telangana India Department of Information Technology Sona College of Technology Salem Tamil Nadu India Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Dindigul Tamil Nadu India Department of Electrical and Electronics Engineering K. Ramakrishnan College of Technology Trichy Tamil Nadu India Department of Electronics and Communication Engineering Oasys Institute of Technology Trichy Tamil Nadu India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

This research work develops a new approach towards music genre prediction by fusing high-end signal processing and machine learning methodologies that will improve prediction quality and resilience. The system commences by signal preprocessing comprising Discrete Wavelet Transformation (DWT) in combination with Pre-Gaussian removal of noise. Feature extraction is done with the Mellin Transform that extracts the important features, which immune to changes in pitch and variations in the general characteristics of the different genre of a particular artist or singer. Hierarchical classification is realized by the proposed Cascaded Capsule Cell Attention Network (CCCAN), which utilizes the capsule networks’ advantage of dynamic routing and the spatial hierarchy to capture and identify the intricate structures of audio patterns. The parameter of the network is optimized with Boosted Sooty Tern Optimization so that convergence speed and classification accuracy is above par. Experimental results presented in this study reveal that the proposed model provides around 99.5% of accuracy, precision, recall, and F1-score improved in comparison to the previous method which provides reliable classification of music genres.

关键词： Accuracy Noise Transforms Feature extraction Routing Multiple signal classification Discrete wavelet transforms Reliability Optimization Resilience

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis

arXiv

引用

arXiv 2024年

作者： Qiao, Qiang Wang, Wenyu Qu, Meixia Su, Kun Jiang, Bin Guo, Qiang School of Mechanical Electrical & Information Engineering Shandong University Weihai China Shenzhen Research Institute Shandong University Shenzhen China School of Computer Science and Technology Shandong University of Finance and Economics Jinan China Shandong Provincial Key Laboratory of Digital Media Technology Jinan China

The field of medical image segmentation is challenged by domain generalization (DG) due to domain shifts in clinical datasets. The DG challenge is exacerbated by the scarcity of medical data and privacy concerns. Traditional single-source domain generalization (SSDG) methods primarily rely on stacking data augmentation techniques to minimize domain discrepancies. In this paper, we propose Random Amplitude Spectrum Synthesis (RASS) as a training augmentation for medical images. RASS enhances model generalization by simulating distribution changes from a frequency perspective. This strategy introduces variability by applying amplitude-dependent perturbations to ensure broad coverage of potential domain variations. Furthermore, we propose random mask shuffle and reconstruction components, which can enhance the ability of the backbone to process structural information and increase resilience intra- and cross-domain changes. The proposed Random Amplitude Spectrum Synthesis for Single-Source Domain Generalization (RAS4DG) is validated on 3D fetal brain images and 2D fundus photography, and achieves an improved DG segmentation performance compared to other SSDG models. The source code is available at: https://***/qintianjian-lab/RAS4DG. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Urban Solid Waste-to-Energy Production Systems with Backpropagation Neural Network Model 3

Optimizing Urban Solid Waste-to-Energy Production Systems wi...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Loganathan, P. Devika, S.V. Trivedi, Lalit Mohan Devi, S. Rukmani Malik, Neeru Jayakumar, D. Department of Electrical and Electronics Engineering Salem India Hyderabad Institute of Technology and Management Department of Electronics and Communication Engineering Hyderabad India Moradabad Institute of Technology Department of Ash Mathematics Moradabad India Saveetha College of Liberal Arts and Sciences Simats Deemed to be University Department of Computer Science Chennai India School of Engineering and Technology Pimpri Chinchwad University Pune India Kuppam Engineering College Department of Electronics and Communication Engineering Kuppam India

ISBN: (纸本)9798331508456

Environmental concerns and global MSW generation have spurred waste-to-energy (WtE) research. These projects support the global bioeconomy and biorefineries to generate renewable energy and reduce fossil fuel use. Preprocessing, feature extraction, and model training comprise the approach. Outliers are removed and input values are normalized using zero-mean normalization. For feature extraction, GW was chosen because to its localization and frequency domain capabilities. Model training uses the Backpropagation Neural Network (BPNN). The proposed model outperformed SVMs and ANNs with 91.45% accuracy. Thus, the model's strength is waste-to-energy conversion. The results indicate that the suggested method optimizes MSW processing for renewable energy. This method is promising for WtE technology, which will help the globe switch to renewable energy. © 2025 IEEE.

关键词： Municipal solid waste

来源：评论

学校读者我要写书评

暂无评论

A Novel Network Security Data Resource Description Standard

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第2期7卷 295-305页

作者： Han, Wei Sun, Xiu-Yan He, Chen Tang, Lin-Lin Kumari, Saru Department of Electronic and Information Engineering Laiwu Vocational and Technical College No. 1 Shancai Street Shandong Jinan China Department of Mechanical and Electrical Engineering Laiwu Vocational and Technical College No. 1 Shancai Street Shandong Jinan China Media and Communications College WeiFang University No. 5147 Dongfeng East Street Shandong Weifang China Department of Computer Science and Engineering Harbin Institute of Technology Shenzhen Taoyuan Street Shenzhen China Department of Mathematics Chaudhary Charan Singh University Uttar Pradesh Meerut250004 India

Current network security situational awareness field has problems of poor communication and low efficiency of data resources and information. Therefore, in order to solve these two problems, this paper has established a better network security data resource description standard (metadata standard) for communication of data resource information, so that communication of data resource information has a unified standard basis. Then it provides a more efficient channel for circulation of data resource information, and improve efficiency of data resource information flow through publishing and subscription technology. Finally, a data resource sharing platform was developed, which applied the above metadata standards. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Exploring Electromagnetic Time-Reversal as a Method to Monitor Cable Temperature in Medium-Voltage Networks

Exploring Electromagnetic Time-Reversal as a Method to Monit...

引用

International Conference on Condition Monitoring and Diagnosis, CMD

作者： Antonella Ragusa Peter A. A. F. Wouters Hugh Sasse Alistair Duffy Farhad Rachidi Marcos Rubinstein Faculty of Computing Engineering and Media De Montfort University Leicester UK Department of Electrical Engineering Eindhoven University of Technology Eindhoven The Netherlands School of Engineering École Polytechnique Fédérale de Lausanne Lausanne Switzerland Institute for Information and Communication Technologies University of Applied Sciences and Arts Western Switzerland Yverdon-les-Bains Switzerland

ISBN: (数字)9788986510225

ISBN: (纸本)9798350353877

The paper addresses the research question of whether the electromagnetic time reversal (EMTR) technique can be used to estimate the propagation speed of a signal on power cables. This value changes in the long term due to ageing of the cable insulation and in the short term due to the cable temperature variation. A first numerical investigation of the EMTR effectiveness in estimating the propagation speed in a simple cable system is described showing that EMTR is a promising technique to be used also for the monitoring of power cable temperature. Future research will be directed to implementation of the methodology in more complex networks.

关键词： Temperature sensors Temperature measurement Condition monitoring Power cables Medium voltage Cable insulation Nonhomogeneous media Electromagnetics Integrated circuit reliability Monitoring

来源：评论

学校读者我要写书评

暂无评论

Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference

arXiv

引用

arXiv 2024年

作者： Zhang, Fan Wang, Zhaohan Lyu, Xin Zhao, Siyuan Li, Mengjian Geng, Weidong Ji, Naye Du, Hui Gao, Fuxing Wu, Hao Li, Shunman The Faculty of Humanities and Arts Macau University of Science and Technology China The College of Media Engineering Communication University of Zhejiang China Research Center for Artificial Intelligence and Fine Arts Zhejiang Lab Zhejiang China The School of Animation and Digital Arts Communication University of China Beijing China The Research Center for Artificial Intelligence and Fine Arts Zhejiang Lab Zhejiang China The College of Computer Science and Technology Zhejiang University The Research Center for Artificial Intelligence and Fine Arts Zhejiang Lab Zhejiang China Zhejiang Institute of Economics and Trade Zhejiang China

Speech-driven gesture generation is an emerging field within virtual human creation. However, a significant challenge lies in accurately determining and processing the multitude of input features (such as acoustic, semantic, emotional, personality, and even subtle unknown features). Traditional approaches, reliant on various explicit feature inputs and complex multimodal processing, constrain the expressiveness of resulting gestures and limit their applicability. To address these challenges, we present Persona-Gestor, a novel end-to-end generative model designed to generate highly personalized 3D full-body gestures solely relying on raw speech audio. The model combines a fuzzy feature extractor and a non-autoregressive Adaptive Layer Normalization (AdaLN) transformer diffusion architecture. The fuzzy feature extractor harnesses a fuzzy inference strategy that automatically infers implicit, continuous fuzzy features. These fuzzy features, represented as a unified latent feature, are fed into the AdaLN transformer. The AdaLN transformer introduces a conditional mechanism that applies a uniform function across all tokens, thereby effectively modeling the correlation between the fuzzy features and the gesture sequence. This module ensures a high level of gesture-speech synchronization while preserving naturalness. Finally, we employ the diffusion model to train and infer various gestures. Extensive subjective and objective evaluations on the Trinity, ZEGGS, and BEAT datasets confirm our model’s superior performance to the current state-of-the-art approaches. Persona-Gestor improves the system’s usability and generalization capabilities, setting a new benchmark in speech-driven gesture synthesis and broadening the horizon for virtual human technology. Supplementary videos and code can be accessed at https://***/Diffmotion-v2-website/. © 2024, CC BY.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Exams Item Analysis, Online Examination, and Education Evaluation System Via Internet

Exams Item Analysis, Online Examination, and Education Evalu...

引用

International Conference on electrical engineering/Electronics, computer, Telecommunications and Information technology, ECTI-CON

作者： Kamonlak Chaidee Kanchana Boontasri Ekkachai Chaidee Kittichai Punthura Narong Kumtip Yotsanan Pankham Department of Computer Information System Faculty of Business Administration And Liberal Arts Rajamangala University of Technology Lanna Chiangrai Chiang Rai Thailand Department of Information Technology Faculty of Science and Agricultural Technology Rajamangala University of Technology Lanna Chiangrai Chiang Rai Thailand Department of Electrical Engineering Faculty of Electrical Engineering Rajamangala University of Technology Lanna Chiangrai Chiang Rai Thailand

The objective of this study is to develop an exams item bank management system on the internet. The exam item analysis system is used to determine the reliability of the exams using K-R 20 and K-R 21 formulas. The difficulty and power of discrimination values are determined using a choice analysis and percentages of high and lower groups technique. The create exams set system can be performed randomly or identified through the difficulty level. The examination can be performed online and the exam results can be immediately announced. The grading system is used to support the decision-making to evaluate learning achievement. The system’s accuracy was tested and found to be accurate compared with the hand calculation results. The system was tested with a sample group and satisfaction was assessed through questionnaires. The satisfaction of teachers and students was highest, while that of administrators was high. The developed exams item bank management system operates as a web application with a security system for supporting in learning activity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Weather Impact on Bike Sharing Usage Through a Clustering Analysis

引用

Journal of computers (Taiwan) 2022年第5期33卷 163-173页

作者： Quach, Jessica Malekian, Reza Department of Computer Science and Media Technology Malmö University Malmö205 06 Sweden Department of Electrical Electronic and Computer Engineering University of Pretoria Pretoria0002 South Africa

Bike sharing systems (BSS) have been a popular traveling service for years and are used worldwide. It is attractive for cities and users who wants to promote healthier lifestyles;to reduce air pollution and greenhouse gas emission as well as improve traffic. One major challenge to docked bike sharing system is redistributing bikes and balancing dock stations. Some studies propose models that can help forecasting bike usage;strategies for rebalancing bike distribution;establish patterns or how to identify patterns. Other studies propose to extend the approach by including weather data. This study aims to extend upon these proposals and opportunities to explore how and in what magnitude weather impacts bike usage. Bike usage data and weather data are gathered for the city of Washington D.C. and are analyzed using k-means clustering algorithm. K-means managed to identify three clusters that correspond to bike usage depending on weather conditions. The results show that the weather impact on bike usage was noticeable between clusters. It showed that temperature followed by precipitation weighted the most, out of five weather variables. © 2022 Authors. All rights reserved.

关键词： Cluster analysis

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：