检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Zheng, Xiaohu Chen, Yufan Xu, Xiuliang Liu, Bing Institute of Artificial Intelligence Donghua University Shanghai201620 China Shanghai Industrial Big Data and Intelligent Systems Engineering Technology Center Shanghai201620 China College of Information Science and Technology Donghua University Shanghai201620 China Hangzhou Zhongfu Technology&Innovation Research Institute Co. Ltd Shanghai201620 China Precise Machinery Scientific & Technology Co. Ltd Shanghai201599 China

In order to solve the problem of motion blur caused by sewing speed, an image DeblurGAN-BSV3 algorithm is proposed. Firstly, different attention fusion mechanisms are introduced to achieve accurate extraction of image features. Secondly, the depth-separable convolution of the trunk network is replaced by blueprint convolution to ensure the processing speed of the detection algorithm and the clarity of the output image. In order to solve the difficulty of rapid detection of pin defects, a student-teacher feature pyramid matching method was proposed. Firstly, the abnormal region interpretation technology was used to explicitly visualize the defect area of the identified abnormal instances, and then the abnormal detection score was performed on the detected images to make good judgment. The experimental results show that the combination of the above two methods has a good ability for rapid defect detection. Rapid detection of common pin defects is realized. © 2023, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Job-Related Stress in Long-Term Care Workers in Japan and China 9

A Comparative Study of Job-Related Stress in Long-Term Care ...

引用

9th International Congress on Advanced Applied Informatics, IIAI-AAI 2020

作者： Yu, Yating Taki, Seiko Takanokura, Masato Kawakami, Masaru Yamada, Tetsuo Liang, Shuyu Kitami Institute of Technology Regional Management Engineering Course Kitami Japan Chiba Institute of Technology Faculty of Social Systems Science Department of Management Information Science Chiba Japan Kanagawa University Faculty of Engineering Department of Industrial Engineering and Management Yokohama Japan Jichi Medical University Faculty of Nursing Tochigi Japan The University of Electro-Communications Department of Informatics Tokyo Japan Shandong University Data Science Institute Jian China

ISBN: (纸本)9781728173979

Japan revised and implemented the Occupational Safety and Health Act in December 2015 to mandate that businesses with 50 or more workers have all of their workers tested for stress annually. In China, one effect of the 'one child policy' and the nuclearization of the family has been that the number of children has decreased, while the number of elderly people living alone continues to grow. This growth is increasing the demand for long-term care workers. However, because the aging of the Chinese population has been more rapid than in Japan, and China has yet to develop a long-term care system to cope with the aging of its population, the burden on long-term care staff appears to be increasing. Although the resulting need for more support for long-term care staff has become an issue, China has yet to develop a mental health policy like that of Japan that mandates the monitoring of mental health, for example, through annual testing of workers for stress. As a result, the factors underlying long-term care worker stress have yet to be *** study attempted to discover, through a comparison of long-term care worker stress in Japan and China, the kinds of job-related stress care workers tended to have and what the principal underlying factors resulting in high levels of stress may be in each country. To that end, data were collected on workers' psychological and physical stress using the Brief Job Stress Questionnaire (BJSQ) and analyzed to find out how stress may differ by country, gender, job responsibilities, having to work night shifts, or having certain qualifications. © 2020 IEEE.

关键词： Health

来源：评论

学校读者我要写书评

暂无评论

A hybrid model for post-treatment mortality rate classification of patients with breast cancer

引用

Healthcare Analytics 2023年 4卷 100254-100254页

作者： Folorunso, Sakinat Oluwabukonla Awotunde, Joseph Bamidele Adigun, Adepeju Abeke Prasad, L.V. Narasimha Lalitha, Vuyyuru Lakshmi Department of Mathematical Sciences Olabisi Onabanjo University Ogun State Ago-Iwoye Nigeria Artificial Intelligent Systems Research Group (ArISRG) Department of Mathematical Sciences Olabisi Onabanjo University Ago-iwoye Nigeria Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Ilorin 240003 Nigeria Department of Information and Communication Technology Osun State University Osogbo Nigeria Department of CSE Institute of Aeronautical Engineering Hyderabad India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation India

Terminal cancer is not curable and eventually results in death. Breast cancer (BC) is a prevalent malignancy affecting women. Although there are prognostic indicators, BC prognosis is still challenging because of the intricate connections between various survival factors and influencing factors. This study proposes an ensemble classifier for predicting BC survivability using a new BC post-treatment dataset for the number of survivals. However, the classes survival cases dataset for BC is skewed, which caused a sub-optimal classification performance. Hence, a hybrid sampling scheme of Synthetic Minority Over-Sampling TEchnique (SMOTE) and Wilson's Edited Nearest Neighbor (ENN) is employed to treat the class imbalance in the dataset. Random Forest (RF) ensemble classifier is for classifying the dataset. The proposed framework performs well in terms of accuracy, recall of the two classes, Receiver Operating Characteristics (ROC) and Kappa Statistic (KS) metric on the dataset. The results demonstrated that the RF, with 97.0% accuracy on the holdout sample, is the best predictor. This prediction accuracy is superior to any noted in the literature, compared with Logistic Regression (LR) and Bagging classifiers. © 2023 The Authors

关键词： Breast cancer Class imbalance Ensemble learners Machine learning Random forest Sampling

来源：评论

学校读者我要写书评

暂无评论

Robust Watermarking Approach for 3D Multiresolution Meshes Based on Multi-wavelet Transform, SHA512 and Turbocodes 19th

Robust Watermarking Approach for 3D Multiresolution Meshes B...

引用

19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021

作者： Jallouli, Malika Sayahi, Ikbel Mabrouk, Anouar Ben Mahjoub, Mohamed Ali Amar, Chokri Ben LATIS Laboratory of Advanced Technology and Intelligent Systems Université de Sousse Ecole Nationale d’Ingénieurs de Sousse Sousse4023 Tunisia Research Groups on Intelligent Machines Laboratory Private National Engineering School of Monastir University of Sfax Monastir Tunisia Department of Mathematics Higher Institute of Applied Mathematics and Computer Science University of Kairouan Kairouan3100 Tunisia Department of Mathematics Faculty of Science University of Tabuk Tabuk Saudi Arabia College of Computers and Information Technology Taif University Taif Saudi Arabia

ISBN: (纸本)9783030891305

Since the 3D mesh security 3D mesh security has become intellectual property, 3D watermarking algorithms have continued to appear to secure 3D meshes shared by remote users. The originality of this approach is to insert copyright data in multiresolution domain using multi-wavelet transform which allowed us to significantly increase the size of the watermark. Our algorithm includes then two rounds of insertion where each one applies a different type of wavelet transform. The first one undergoes coefficients generated by Haar wavelet transform. As for the second iteration, it inserts data into coefficients resulting from Schauder wavelet transform. The watermark, which is a combination of the mesh description and source mesh signature (generated using SHA512) are encoded using a Turbo-code before being inserted into wavelet coefficients. Embedding data includes a transformation of these later to spherical coordinate system and a modulation steps. Finally watermarked mesh is reconstructed using inverse wavelet transform. The experimentation of our approach has shown a very high insertion rate due to the use of the hybrid insertion domain, while maintaining the mesh quality. Watermarked mesh and extracted data are obtained in real time. Our approach is also robust against the most popular attacks. Our results showed that the present approach improves the existing works. © 2021, Springer Nature Switzerland AG.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A review of constraints and adjustable parameters in microgrids for cost and carbon dioxide emission reduction

引用

Heliyon 2024年第6期10卷 e27489页

作者： Hoummadi, Mohammed Amine Aroussi, Hala Alami Bossoufi, Badre Karim, Mohammed Mobayen, Saleh Zhilenkov, Anton A. H. Alghamdi, Thamer LIMAS Laboratory Faculty of Sciences Dhar El Mahraz Sidi Mohammed Ben Abdellah University Fez 30003 Morocco LGEM Laboratory Higher School of Technology Mohamed First University Oujda 60000 Morocco Graduate School of Intelligent Data Science National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin 640301 Taiwan Department of Cyber-Physical Systems St. Petersburg State Marine Technical University Saint-Petersburg 190121 Russian Federation Wolfson Centre for Magnetics School of Engineering Cardiff University Cardiff CF24 3AA United Kingdom Electrical Engineering Department School of Engineering Al-Baha University Al-Baha 65779 Saudi Arabia

In a world grappling with escalating energy demand and pressing environmental concerns, microgrids have risen as a promising solution to bolster energy efficiency, alleviate costs, and mitigate carbon emissions. This article delves into the dynamic realm of microgrids, emphasizing their indispensable role in addressing today's energy needs while navigating the hazards of pollution. Microgrid operations are intricately shaped by a web of constraints, categorized into two essential domains: those inherent to the microgrid itself and those dictated by the external environment. These constraints, stemming from component limitations, environmental factors, and grid connections, exert substantial influence over the microgrid's operational capabilities. Of particular significance is the three-tiered control framework, encompassing primary, secondary, and energy management controls. This framework guarantees the microgrid's optimal function, regulating power quality, frequency, and voltage within predefined parameters. Central to these operations is the energy management control, the third tier, which warrants in-depth exploration. This facet unveils the art of fine-tuning parameters within the microgrid's components, seamlessly connecting them with their surroundings to streamline energy flow and safeguard uninterrupted operation. In essence, this article scrutinizes the intricate interplay between microgrid constraints and energy management parameters, illuminating how the nuanced adjustment of these parameters is instrumental in achieving the dual objectives of cost reduction and Carbon Dioxide emission minimization, thereby shaping a more sustainable and eco-conscious energy landscape. This study investigates microgrid dynamics, focusing on the nuanced interplay between constraints and energy management for cost reduction and Carbon Dioxide minimization. We employ a three-tiered control framework—primary, secondary, and energy management controls—to regulate microgrid f

关键词： Energy costs Energy demand Load Load forecast Microgrid Power rate

来源：评论

学校读者我要写书评

暂无评论

Structured learning of rigid-body dynamics: A survey and unified view from a robotics perspective

arXiv

引用

arXiv 2020年

作者： René Geist, A. Trimpe, Sebastian Intelligent Control Systems Group Max Planck Institute for Intelligent Systems Stuttgart Germany Institute for Data Science in Mechanical Engineering RWTH Aachen University Aachen Germany

Accurate models of mechanical system dynamics are often critical for model-based control and reinforcement learning. Fully data-driven dynamics models promise to ease the process of modeling and analysis, but require considerable amounts of data for training and often do not generalize well to unseen parts of the state space. Combining data-driven modelling with prior analytical knowledge is an attractive alternative as the inclusion of structural knowledge into a regression model improves the model’s data efficiency and physical integrity. In this article, we survey supervised regression models that combine rigid-body mechanics with data-driven modelling techniques. We analyze the different latent functions (such as kinetic energy or dissipative forces) and operators (such as differential operators and projection matrices) underlying common descriptions of rigid-body mechanics. Based on this analysis, we provide a unified view on the combination of data-driven regression models, such as neural networks and Gaussian processes, with analytical model priors. Further, we review and discuss key techniques for designing structured models such as automatic differentiation. © 2020, CC BY-NC-SA.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Contrastive graph poisson networks: semi-supervised learning with extremely limited labels 21

Contrastive graph poisson networks: semi-supervised learning...

引用

Proceedings of the 35th International Conference on Neural Information Processing systems

作者： Sheng Wan Yibing Zhan Liu Liu Baosheng Yu Shirui Pan Chen Gong PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology and JD Explore Academy JD Explore Academy The University of Sydney Department of Data Science and AI Faculty of IT Monash University

ISBN: (纸本)9781713845393

Graph Neural Networks (GNNs) have achieved remarkable performance in the task of semi-supervised node classification. However, most existing GNN models require sufficient labeled data for effective network training. Their performance can be seriously degraded when labels are extremely limited. To address this issue, we propose a new framework termed Contrastive Graph Poisson Networks (CGPN) for node classification under extremely limited labeled data. Specifically, our CGPN derives from variational inference; integrates a newly designed Graph Poisson Network (GPN) to effectively propagate the limited labels to the entire graph and a normal GNN, such as Graph Attention Network, that fexibly guides the propagation of GPN; applies a contrastive objective to further exploit the supervision information from the learning process of GPN and GNN models. Essentially, our CGPN can enhance the learning performance of GNNs under extremely limited labels by contrastively propagating the limited labels to the entire graph. We conducted extensive experiments on different types of datasets to demonstrate the superiority of CGPN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-rank reduced biquaternion tensor ring decomposition and tensor completion

引用

Applied Mathematics and Computation 2025年 504卷

作者： Luo, Hui Liu, Xin Liu, Wei Zhang, Yang School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology China Macau Institute of Systems Engineering Faculty of Innovation Engineering Macau University of Science and Technology China School of Artificial Intelligence at Sun Yat-sen University the Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Department of Mathematics University of Manitoba MB Canada

We define the reduced biquaternion tensor ring (RBTR) decomposition and provide a detailed exposition of the corresponding algorithm RBTR-SVD. Leveraging RBTR decomposition, we propose a novel low-rank tensor completion algorithm RBTR-TV integrating RBTR ranks with total variation (TV) regularization to optimize the process. Numerical experiments on color image and video completion tasks indicate the advantages of our method. © 2025 Elsevier Inc.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning

arXiv

引用

arXiv 2023年

作者： Caufield, J. Harry Hegde, Harshad Emonet, Vincent Harris, Nomi L. Joachimiak, Marcin Matentzoglu, Nicolas Kim, HyeongSik Moxon, Sierra Reese, Justin T. Haendel, Melissa A. Robinson, Peter N. Mungall, Christopher J. Division of Environmental Genomics and Systems Biology Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Institute of Data Science Faculty of Science and Engineering Maastricht University Maastricht Netherlands Semanticly Ltd Athens Greece Robert Bosch LLC SunnyvaleCA94085 United States University of Colorado Anschutz Medical Campus AuroraCO80217 United States The Jackson Laboratory for Genomic Medicine FarmingtonCT06032 United States

Creating knowledge bases and ontologies is a time consuming task that relies on manual curation. AI/NLP approaches can assist expert curators in populating these knowledge bases, but current approaches rely on extensive training data, and are not able to populate arbitrarily complex nested knowledge schemas. Here we present Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES), a Knowledge Extraction approach that relies on the ability of Large Language Models (LLMs) to perform zero-shot learning (ZSL) and general-purpose query answering from flexible prompts and return information conforming to a specified schema. Given a detailed, user-defined knowledge schema and an input text, SPIRES recursively performs prompt interrogation against an LLM to obtain a set of responses matching the provided schema. SPIRES uses existing ontologies and vocabularies to provide identifiers for matched elements. We present examples of applying SPIRES in different domains, including extraction of food recipes, multi-species cellular signaling pathways, disease treatments, multi-step drug mechanisms, and chemical to disease orange relationships. Current SPIRES accuracy is comparable to the mid-range of existing Relation Extraction (RE) methods, but greatly surpasses an LLM’s native capability of grounding entities with unique identifiers. SPIRES has the advantage of easy customization, flexibility, and, crucially, the ability to perform new tasks in the absence of any new training data. This method supports a general strategy of leveraging the language interpreting capabilities of LLMs to assemble knowledge bases, assisting manual knowledge curation and acquisition while supporting validation with publicly-available databases and ontologies external to the LLM. SPIRES is available as part of the open source OntoGPT package: https://***/monarch-initiative/ontogpt. © 2023, CC BY.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects

arXiv

引用

arXiv 2023年

作者： Wen, Haomin Lin, Youfang Wu, Lixia Mao, Xiaowei Cai, Tianyue Hou, Yunfeng Guo, Shengnan Liang, Yuxuan Jin, Guangyin Zhao, Yiji Zimmermann, Roger Ye, Jieping Wan, Huaiyu The Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The Key Laboratory of Intelligent Passenger Service of Civil Aviation CAAC Beijing101318 China The School of Computing National University of Singapore Singapore College of Systems Engineering National University of Defense Technology Changsha China The School of Information Science and Engineering Yunnan University Kunming650091 China The Cainiao Network Hangzhou China The Alibaba Group Hangzhou China INTR Thrust and DSA Thrust The Hong Kong University of Science and Technology Guangzhou China

Instant delivery services, such as food delivery and package delivery, have achieved explosive growth in recent years by providing customers with daily-life convenience. An emerging research area within these services is service Route&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker. As one of the most crucial tasks in those service platforms, RTP stands central to enhancing user satisfaction and trimming operational expenditures on these platforms. Despite a plethora of algorithms developed to date, there is no systematic, comprehensive survey to guide researchers in this domain. To fill this gap, our work presents the first comprehensive survey that methodically categorizes recent advances in service route and time prediction. We start by defining the RTP challenge and then delve into the metrics that are often employed. Following that, we scrutinize the existing RTP methodologies, presenting a novel taxonomy of them. We categorize these methods based on three criteria: (i) type of task, subdivided into only-route prediction, only-time prediction, and joint route&time prediction;(ii) model architecture, which encompasses sequence-based and graph-based models;and (iii) learning paradigm, including Supervised Learning (SL) and Deep Reinforcement Learning (DRL). Conclusively, we highlight the limitations of current research and suggest prospective avenues. We believe that the taxonomy, progress, and prospects introduced in this paper can significantly promote the development of this field. © 2023, CC BY.

关键词： Taxonomies

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：