检索结果-内蒙古大学图书馆

3rd international conference on Digitalization and Management Innovation, DMI 2024

作者： Xu, Ge Tan, Yun Si, Hansong Long, Xiaobo Wang, Jun China Yangtze Power Co. Ltd. Yichang443002 China Hubei Province Smart Hydropower Technology Innovation Center Yichang443002 China

ISBN: (纸本)9781643685823

Due to the long pipeline distance and weak signals, achieving precise localization of partial discharge occurring in GIL (Gas-Insulated Line) is challenging. This paper conducts key technological research on the automatic localization of partial discharge in GIL, developing an algorithm specifically for the automatic localization of partial discharge in GIL. This algorithm effectively overcomes the difficulties posed by the long distance and weak signals of GIL, enabling accurate identification and localization of defects, as well as assessing the risk levels of these defects. Hence, it ensures the safe and stable operation of power systems in the watershed. © 2025 The Authors.

关键词： automatic location gas insulated line Partial discharge rapid deployment

来源：评论

学校读者我要写书评

暂无评论

Robustly solving PnL problem using Clifford tori

引用

PATTERN RECOGNITION 2025年 166卷

作者： Liu, Yinlong Liu, Xueli Ding, Shengyong Yang, Zhi-Xin Univ Macau State Key Lab Internet Things Smart City Ctr Artificial Intelligence & Robot Taipa 999078 Macao Peoples R China Univ Macau Dept Electromech Engn Ave Univ Macau 999078 Peoples R China Fudan Univ Eye & ENT Hosp 83 Fenyang Rd Shanghai 200032 Peoples R China City Univ Macau Fac Data Sci Ave PadreTomas Pereira Taipa Taipa 999078 Macao Peoples R China

Perspective-n-Line (PnL) problem is to estimate the rigid absolute camera pose from 3D line features and their 2D counterparts, which is a core problem in computer vision and robotics. However, it is rare to obtain perfect inputs in real applications, as there are some unavoidable noise and outliers (mismatches), which might lead to unsatisfactory estimations. To alleviate this problem, we propose an extremely robust solution to solve PnL problem in the presence of noise and outliers. Methodologically, we first demonstrate that given a rotation constraint from a PnL problem, the candidate camera rotation should be in a Clifford torus. Accordingly, the camera orientation can be obtained by finding the intersection of many Clifford tori. After solving the optimal rotation, the translation estimation will be a linear model fitting problem that can be solved easily. Furthermore, to demonstrate the superiority of the proposed method, extensive experiments are conducted.

关键词： Robust pose estimation Perspective-n-Line (PnL) problem Rotation voting

来源：评论

学校读者我要写书评

暂无评论

Digital Transformation and the Improvement of Corporate ESG Performance: An Entrepreneurial Perspective 3

Digital Transformation and the Improvement of Corporate ESG ...

引用

3rd international conference on Digitalization and Management Innovation, DMI 2024

作者： Lyu, Fanfan Lanzhou University of Technology China

ISBN: (纸本)9781643685823

The externality nature inherent in corporate ESG (Environmental, Social, and Governance) endeavors results in suboptimal ESG investment levels. Entrepreneurial endeavors offer a fresh lens through which to capitalize on the digital transformation wave, bolstering firms' capacity to execute ESG practices and harnessing latent internal strengths. Drawing on a cohort of Chinese manufacturing firms spanning 2018 to 2022, this study introduces intermediary constructs encompassing entrepreneurial innovation, societal responsibility, and an entrepreneurial eco-conscious mindset, to scrutinize the effects and underlying mechanisms of digital transformation on corporate ESG outcomes. The findings underscore that digital transformation serves as a catalyst, significantly enhancing corporate ESG performance. Furthermore, the mediation analysis reveals that this enhancement stems from fostering entrepreneurial innovation and societal responsibility, whereas it may be dampened by a diminished entrepreneurial environmental stewardship mindset. These insights offer empirical foundations for shaping digital development strategies and optimizing ESG performance within the entrepreneurial business landscape. © 2025 The Authors.

关键词： digitalization Entrepreneurship ESG

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Machine Learning Algorithms for Text Classification Tasks 3

Evaluation of Machine Learning Algorithms for Text Classific...

引用

3rd international conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Aravindan, M.K. Raajini, X. Mercilin Ingle, Yashwant S. Jangid, Pradeep Kumar Katyal, Ashu Naval, Preeti Faculty of Engineering and Technology Department of Mechanical Engineering Karnataka Ramnagar562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

Assessing machine-learning algorithms for texttype responsibilities is critical to advancing the world of herbal language processing (NLP). As using applications that use NLP grows, so does the want to pick the maximum accurate algorithms out of a pool of to-be-had solutions. This paper reviews the current United States of America research concerning assessing system reading algorithms for textual content-type obligations. Numerous evaluation metrics, consisting of accuracy, precision, consider, and f-degree, are discussed, in addition to the strategies used to examine algorithms and determine the foremost solutions. The diverse challenges confronted in this venture are highlighted, giving readers an outline of the challenges related to assessing the tool and getting to know algorithms for text-kind responsibilities. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of AI-Enabled Financial Domain: Past, Present & Future Aspects 3

A Comprehensive Review of AI-Enabled Financial Domain: Past,...

引用

3rd international conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Bhatt, Shivam Singh, Prabhishek School of Computer Science Engineering & Technology Bennett University Greater Noida India

ISBN: (纸本)9798350303360

In recent years there is an ever increasing demand for digitisation to increase efficiencies and reduce the need for human intervention. The pandemic crisis has exponentially increased and promoted the digitization trends such as incorporation of Artificial intelligence. Two interconnected technologies Artificial intelligence and Machine Learning are further expected to drive competitive advantages for industries such as finance. Historically, reviewing the economics has evolved from qualitative to quantitative, that is, from working on a small sample data to processing vast amounts of data. The arrival of artificial intelligence (AI) is expected to cause major changes in the existing paradigm of the audit profession, ensuring greater reliability and security in financial statement analysis. Identifying the benefits of AI, investors are adopting deep learning models to forecast and assess stock and currency markets. AI deep learning models aid in the realization of intelligent decision-making in economics due to their superiority in learning intrinsic law and representational level. With the advancement of deep learning, we are convinced that economic decision-making will become more intelligent, which will enable potential of AI taking the roles such as financial advisor and insurance advisor. Unfortunately, no study has provided a comprehensive examination of this research to far, and hence with an aim to tackle this challenge, we provide an in-depth overview of Artificial intelligence & Machine Learning in Finance, history of finance, its evolution, past developments, latest trends around the world and research directions while offering outline of latest existing literature and existing applications seen around the world as well as potential applications. We have also identified the challenges faced by researchers to obtain & process quality financial data. Based on the previous analysis, we also highlight prospective future research pathways in this field. The p

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Research on KG and LLM knowledge-enhanced pediatric diseases intelligent diagnosis 3

Research on KG and LLM knowledge-enhanced pediatric diseases...

引用

3rd international conference on Algorithms, Microchips, and Network applications, AMNA 2024

作者： Fu, Wenhui Dai, Dongming Zhang, Kunli Liu, Xiaomei Zhang, Hengxing Ao, Lingxiang Xiao, Jinlong School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou450001 China Kunming Children's Hospital Yunnan Kunming650032 China Zhengzhou Zhongyi Technology Co. Ltd. Henan China

ISBN: (纸本)9781510680098

Pediatric diseases are challenging to diagnose due to their complex and diverse characteristics. To assist doctors in diagnosis and help them make informed decisions, this paper proposes a Knowledge graph and Large language model Knowledge-Enhanced (KLKE) intelligent diagnosis model. The intelligent diagnosis task is treated as a text classification task, where the original Electronic Medical Record are input into MacBERT model encoder to obtain the contextual representation after key information enhancement and KG prompted LLM enhancement respectively. The final text representation is obtained by concatenating and merging the enhanced representations. Graph Convolutional Network is utilized to obtain the knowledge representation and the two representations are fused using a fusion method based on interactive attention mechanism. Experiments are conducted on PeEMR, and compared with models that only fuses triples and graph structures. The KLKE achieved an increase of 9.15% and 2.28% in F1_micro scores respectively. © 2024 SPIE.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Identification of Fake Logo Detection Using Deep Learning 3

Identification of Fake Logo Detection Using Deep Learning

引用

3rd international conference on Artificial intelligence For Internet of Things, AIIoT 2024

作者： Vanitha, P. Mohana Priya, T. Navasakthi, P. Rakshana Devi, V.S. Aarthi, R. Kongu Engineering College Dept. Information Technology Erode India

ISBN: (纸本)9798350372120

The development and distribution of visual content, including logos, has increased as a result of the widespread use of digital media and online platforms. Fake logos, on the other hand, have also become more common as a result of this, and they can be used for misleading activities like disinformation or brand impersonation. It is essential to identify these phony logos to protect brand integrity and guarantee reliable visual data. Convolutional Neural Networks are utilized by the suggested system to automatically identify and extract pertinent features from logo images. The suggested approach focuses on making use of Efficient Net's efficiency and scalability to accurately identify faint visual cues that indicate phony logos. To achieve accurate logo detection in an indoor environment, this work incorporates deep learning algorithms. Resource-constrained environments can benefit from a lightweight yet effective solution for logo detection thanks to MobileNet, which is wellknown for its effectiveness in real-time applications on mobile devices. The project entails building an extensive dataset with real and phony logo images that span a broad spectrum of styles, resolutions, and manipulation methodologies. The model's accuracy in differentiating between real and fake logos is measured using performance metrics like F1 score, precision, and recall. To ensure robust model generalization, the dataset is carefully curated to include variations in scale, orientation, lighting conditions, and digital manipulations. In response to the growing problem of counterfeiting logos, this work presents a ResNet50-based method for identifying phony logos. Identify the logos by using these algorithms whether it is fake or real logos. By applying these different deep learning algorithms like CNN, ResNet50, MobileNet, and EfficientNet and compare the best algorithm based on high accuracy and efficiency. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Lightweight the Focus module in YOLOv5 by Dilated Convolution 3

Lightweight the Focus module in YOLOv5 by Dilated Convolutio...

引用

3rd international conference on Computer Vision, Image and Deep Learning and international conference on Computer Engineering and applications, CVIDL and ICCEA 2022

作者： Song, Aohua Zhao, Ziyun Xiong, Qingyun Guo, Junqi Beijing Norm. Univ. Eng. Research Center of Intelligent Technology and Educational Application Ministry of Education College of Artificial Intelligence Beijing China

ISBN: (纸本)9781665459112

Focus is an advanced module in YOLOv5. However, no detailed work has been published to demonstrate its effectiveness so far. In this paper, we analyze the Focus module from two respects, FLOPs and receptive field, and reveal that it's approximated to convolution layer with the same kernel size, twice the receptive field and quadruple the computational cost. Inspired by dilated convolution, we propose a new module named DFocus. DFocus is comparable in performance to Focus but without any additional computation cost. The experiments on PASCAL VOC dataset demonstrate the effectiveness of our work. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Flexible production line product R&D and manufacturing cloud platform based on intelligent data collaboration 3

Flexible production line product R&D and manufacturing cloud...

引用

3rd international Seminar on Artificial intelligence, Networking, and Information technology, AINIT 2022

作者： Xie, Yanyin Yang, Rui Hu, Ruihan Gan, Lin Ke, Hualin Guangdong HEGII Sanitary Wares Co. Ltd Chaozhou528000 China Guangdong Institute of Intelligent Manufacturing Guangdong Key Laboratory of Modern Control Technology Guangzhou510070 China Faculty of Computing National Pilot School of Software Harbin Institute of Technology Harbin150000 China

ISBN: (纸本)9781510662964

This paper focuses on how to ensure the availability and effectiveness of massive cloud data for industrial robots in the flexible production line, address the technical challenge in building a massive data cloud platform for industrial robots, and resolve the engineering problem of cloud based industrial robot cloud service application. To achieve this purpose, research is conducted on industrial robot hybrid cloud platform architecture, network technology, industrial robot big data system, autonomous learning cloud data processing and other technologies, which provides support for cloud service applications. It is suggested to combine knowledge atlas, digital twins, deep neural network, migration learning and other artificial intelligence technologies, which is conducive to remote monitoring and fault diagnosis cloud service applications. This has been verified and promoted in the handling, polishing, stacking, welding, assembly and other robots in 3C, mold, household appliances, automobile, furniture, electronic equipment manufacturing and other industries. © 2023 SPIE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Intelligent PCB Welding robot Based on Delta Parallel Manipulator 3

Intelligent PCB Welding Robot Based on Delta Parallel Manipu...

引用

3rd international conference on Artificial intelligence and Electromechanical Automation, AIEA 2022

作者： Zhao, YiTing Ma, YiKun Zhu, Yu Chai, YeYu Academy of Automation Wuhan University of Technology Hubei Province Wuhan China

ISBN: (纸本)9781510657281

In this paper, an intelligent PCB welding robot based on delta parallel manipulator is proposed to improve the mechanical structure of the robot, which can improve the efficiency and accuracy of PCB welding. We trained the solder joint recognition model based on YOLOv5, and established the inverse kinematics model, and used the non-uniform B-spline interpolation for trajectory planning to improve the mechanical vibration during the movement. © 2022 SPIE.

关键词： Polychlorinated biphenyls

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：