检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Sun, Qingyun Li, Jianxin Yang, Beining Fu, Xingcheng Peng, Hao Yu, Philip S. Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Department of Computer Science University of Illinois at Chicago Chicago United States

Most Graph Neural Networks follow the message-passing paradigm, assuming the observed structure depicts the ground-truth node relationships. However, this fundamental assumption cannot always be satisfied, as real-world graphs are always incomplete, noisy, or redundant. How to reveal the inherent graph structure in a unified way remains under-explored. We proposed PRI-GSL, a Graph Structure Learning framework guided by the Principle of Relevant Information, providing a simple and unified framework for identifying the self-organization and revealing the hidden structure. PRI-GSL learns a structure that contains the most relevant yet least redundant information quantified by von Neumann entropy and Quantum Jensen-Shannon divergence. PRI-GSL incorporates the evolution of quantum continuous walk with graph wavelets to encode node structural roles, showing in which way the nodes interplay and self-organize with the graph structure. Extensive experiments demonstrate the superior effectiveness and robustness of PRI-GSL. Copyright © 2022, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation

arXiv

引用

arXiv 2024年

作者： Tao, Wei Zhou, Yucheng Wang, Yanlin Zhang, Hongyu Wang, Haofen Zhang, Wenqiang Shanghai Engineering Research Center of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China School of Software Engineering Sun Yat-sen University Guangdong Zhuhai519082 China School of Big Data and Software Engineering Chongqing University Chongqing China College of Design and Innovation Tongji University Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Academy for Engineering and Technology Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University 220 Handan Road Shanghai200433 China

Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i.e., good-practice commits), while the rest do not. On the basis of our empirical study, we discover that training on good-practice commits significantly contributes to the commit message generation. Motivated by this finding, we propose a novel knowledge-aware denoising learning method called KADEL. Considering that good-practice commits constitute only a small proportion of the dataset, we align the remaining training samples with these good-practice commits. To achieve this, we propose a model that learns the commit knowledge by training on good-practice commits. This knowledge model enables supplementing more information for training samples that do not conform to good practice. However, since the supplementary information may contain noise or prediction errors, we propose a dynamic denoising training method. This method composes a distribution-aware confidence function and a dynamic distribution list, which enhances the effectiveness of the training process. Experimental results on the whole MCMD dataset demonstrate that our method overall achieves state-of-the-art performance compared with previous methods. © 2024, CC BY.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

Influence of Marine Shewanella Putrefaciens and Mediated Calcium Deposition on Q235 Carbon Steel Corrosion

SSRN

引用

SSRN 2023年

作者： Lou, Yuntian Huang, Luyao Chang, Weiwei Chen, Xudong Hao, Xiangping Qian, Hongchang Zhang, Dawei Beijing Advanced Innovation Center for Materials Genome Engineering Institute for Advanced Materials and Technology University of Science and Technology Beijing Beijing100083 China National Materials Corrosion and Protection Data Center University of Science and Technology Beijing Beijing100083 China Shunde Innovation School University of Science and Technology Beijing Foshan528399 China State Key Laboratory of Advanced Power Transmission Technology State Grid Smart Grid Research Institute Co. Ltd. Beijing102209 China School of Materials Science and Hydrogen Energy Foshan University Foshan528000 China

Microbiologically influenced corrosion inhibition (MICI) of Q235 carbon steel by Shewanella putrefaciens and mediated calcium deposition was investigated via regulation of microbial mineralization. In calcium-rich medium, S. putrefaciens rapidly created a protective calcium carbonate layer on the steel surface, blocking Cl-diffusion. Without calcium, the biofilm and rust layer mitigated pitting corrosion but couldn't prevent Cl-penetration. The potentiodynamic polarization results indicated that the corrosion current density (icorr value) in the S. putrefaciens-inoculated media with and without calcium were 0.38 μA/cm2 and 0.61 μA/cm2, respectively. The corrosion inhibition rates compared to the sterile condition were 92.18% and 87.44%. Electrochemical Impedance Spectroscopy (EIS) and Scanning Electrochemical Microscopy (SECM) results confirmed MICI was due to microbial aerobic respiration and deposited layers. Even in non-biological conditions, S. putrefaciens-induced calcium carbonate deposition could inhibit corrosion © 2023, The Authors. All rights reserved.

关键词： Scanning electron microscopy

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach to Lung Nodule Growth Prediction using CT image combined with Demographic and image features 23

A deep learning approach to Lung Nodule Growth Prediction us...

引用

7th International Conference on Medical and Health Informatics, ICMHI 2023

作者： Li, Ai-Hsien Adams Nguyen, Duc-Khanh Lai, Yen-Jun Chien, Ting-Ying Chiu, Yen-Ling Chan, Chien-Lung Yang, Pan-Chyr Division of Cardiology Far Eastern Memorial Hospital Taipei220 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan City Taiwan Department of Information Management Yuan Ze University Taoyuan320 Taiwan Department of Radiology Far Eastern Memorial Hospital Taipei220 Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital Taipei Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan320 Taiwan Institute of Biomedical Sciences Academia Sinica Taipei106 Taiwan Department of Internal Medicine College of Medicine National Taiwan University Taipei100 Taiwan Center of Genomic Medicine National Taiwan University Taipei100 Taiwan

ISBN: (纸本)9798400700712

Lung cancer remains a significant global public health concern, being the leading cause of cancer-related deaths worldwide. Despite recent medical advancements, the disease still has a high mortality rate, making early detection and treatment critical for improving patient outcomes. Accurate prediction of nodule growth is key to early lung cancer treatment, but current assessments offer unclear indications of future growth, leading physicians to recommend costly and anxiety-provoking follow-up appointments every 3 to 12 months. To address this need, this study develops an ensemble deep learning approach that combines demographic data with existing CT images to predict whether lung nodules will grow, potentially reducing unnecessary examinations and easing the burden on patients. Our study, conducted on 862 patients with 1004 nodules, produced promising preliminary results with Accuracy, Sensitivity, Precision, F1 Score, and AUC of 0.66, 0.66, 0.67, 0.66, and 0.71, respectively. The proposed method provides a promising support system to empower patients to make informed decisions about seeking medical attention and helps physicians facilitate early treatment regimens, leading to improved patient outcomes and potentially saving lives. © 2023 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Two dimensional quantum central limit theorem by quantum walks

arXiv

引用

arXiv 2024年

作者： Asahara, Keisuke Funakawa, Daiju Seki, Motoki Suzuki, Akito Data Science and AI Innovation Research Center Shiga University 1-1-1 Banba hikone Shiga522-8522 Japan Department of Electronics and Information Engineering Hokkai-Gakuen University Hokkaido Sapporo062-8605 Japan Department of Mathematics Faculty of Science Hokkaido University Sapporo060-0810 Japan Department of Production Systems Engineering and Sciences Komatsu University Awazu Campus Nu 1-3 Shicho-machi Ishikawa Komatsu923-8511 Japan

Quantum walks, mathematical models referred to as the quantum counterparts of random walks, have garnered significant attention in recent years with the advancement of quantum computing. The weak limit theorem for quantum walks, analogous to the central limit theorem for random walks, is one of the most important theorems in this field. In this study, we investigated the weak limit theorem for a two-state discrete-time quantum walk on a two-dimensional square lattice. As a result, we derived a two-dimensional probability distribution whose support is the intersection of two ellipses. The probability distribution we obtained resembles the distribution of one-dimensional quantum walks while possessing a unique form specific to two dimensions. © 2024, CC BY-NC-ND.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Fabrication a sustainable adsorbent nanocellulose-mesoporous hectorite bead for methylene blue adsorption

引用

Case Studies in Chemical and Environmental engineering 2024年 10卷

作者： Holilah Asranudin El Messaoudi, Noureddine Ulfa, Maria Hamzah, Amir Hamid, Zuratul Ain Abdul Ramadhani, Dini Viandi Suryanegara, Lisman Mahardika, Melbi Melenia, Alvina Tata Pratama, Agus Wedi Prasetyoko, Didik Research Center for Biomass and Bioproducts National Research and Innovation Agency of Indonesia (BRIN) Research Collaboration Center for Nanocellulose BRIN-Andalas University Research Collaboration Center for Biomass and Biorefinery Between BRIN and Universitas Padjadjaran Laboratory of Applied Chemistry and Environment Faculty of Sciences Ibn Zohr University Chemistry Education Study Program Faculty of Teacher Training and Education Sebelas Maret University Deputy for Infrastructure Research and Innovation National Research and Innovation Agency of Indonesia (BRIN) School of Materials & Mineral Resources Engineering Universiti Sains Malaysia Department of Biology Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Department of Chemistry Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember (ITS) Kampus ITS Sukolilo

In this study, fabrication of mesoporous nanocellulose-hectorite-alginate bead (B-NcH) composites and their application for adsorption of MB from water was carried out. The synthesis of nanocellulose (NC) was conducted from mangosteen waste peel (Garcinia mangostana L.). Garcinia mangostana L. peel had 58.9 ± 0,41 % content of cellulose. NCs was successfully isolated using the acid hydrolysis method. NC from Garcinia mangostana L. peel had a diameter of 24.5 ± 0.2 nm and a length of 381.2 ± 10.4 nm. The superabsorbent was composed of nanocrystalline cellulose, mesoporous hectorite, and alginate. The functional group, phase, and morphology of composite was investigated. The composite with 5 % NC had excellent mechanical strength. The B-NcH5 showed a high adsorption capacity of methylene blue (MB), reaching 98.64 % at an adsorbent dose of 30 mg for 90 min. The presence of hectorite can increase the adsorption ability compared to NCs-alginate. The equilibrium adsorption data followed the Freundlich isotherm;however, the kinetics of adsorption showed the usefulness of adopting the PSO kinetic model. The highest adsorption capacity of B-NcH5 for MB was determined to be 57.59 mg/g. For thermodynamic studies, it was revealed that the adsorption of MB on BNcH-5 is a spontaneous and endothermic process. The removal efficiency was observed in six consecutive cycles, indicating at the favorable reusability of this adsorbent. These results validate the potential use of this B-NcH5 adsorbent for water treatment applications. © 2024

关键词： Adsorption Bead Hectorite Methylene blue Nanocellulose Water treatment

来源：评论

学校读者我要写书评

暂无评论

Spin-exchange relaxation of naturally abundant Rb in a K-Rb-21Ne self-compensated atomic comagnetometer

引用

Chinese Physics B 2020年第4期29卷 258-266页

作者： Yan Lu Yueyang Zhai Yong Zhang Wenfeng Fan Li Xing Wei Quan School of Instrumentation Science and Opto-electronics Engineering Beihang UniversityBeijing 100191China Research Institute of Frontier Science Beihang UniversityBeijing 100191China Beijing Academy of Quantum Information Sciences Beijing 100191China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang UniversityBeijing 100191China

The total effective spin-exchange relaxation of naturally abundant Rb in a K–Rb–21Ne comagnetometer is analyzed,and the results show that the coexistence of 87Rb and 85Rb isotopes in the same volume can lead to a large extra spinexchange broadening compared to pure *** broadening mainly comes from the contribution of the equivalent reduction in the Rb spin-exchange *** this basis,an approximate relaxation model is proposed and experimentally demonstrated to be more accurate than that from a previous *** study also provides a method for determining the properties of alkali-metal vapor cells.

关键词： comagnetometer naturally abundant Rb spin-exchange relaxation spin polarization

来源：评论

学校读者我要写书评

暂无评论

Mandari: Multi-Modal Temporal Knowledge Graph-aware Sub-graph Embedding for Next-POI Recommendation

Mandari: Multi-Modal Temporal Knowledge Graph-aware Sub-grap...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoqian Liu Xiuyun Li Yuan Cao Fan Zhang Xiongnan Jin Jinpeng Chen School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China The Technology Innovation Center of Cultural Tourism Big Data of Hebei Province Chengde China Hebei Normal University for Nationalities Chengde China Knowledge Discovery and Data Mining Research Center Zhejiang Lab Hangzhou China

Next-POI recommendation aims to explore from user check-in sequence to predict the next possible location to be visited. Existing methods are often difficult to model the implicit association of multi-modal data with user choices. Moreover, traditional methods struggle to fully explore the variation of user preferences at variable time intervals. To tackle these limitations, we propose a Multi-Modal Temporal Knowledge Graph-aware Sub-graph Embedding approach (Mandari). We first construct a novel Multi-Modal Temporal Knowledge Graph. Based on the proposed knowledge graph, we integrate multi-modal information and leverage the graph attention network to calculate sub-graph prediction probability. Next, we implement a temporal knowledge mining method to model the segmentation and periodicity of user check-in and obtain temporal prediction probability. Finally, we fuse temporal prediction probability with the previous sub-graph prediction probability to obtain the final result. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lower Limb Muscle State Transition Control Based on Complex Network

Lower Limb Muscle State Transition Control Based on Complex ...

引用

Chinese Control Conference (CCC)

作者： Junjie Geng Lingling Chen Xin Guo Rui Chen Mengge Wang School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Intelligent Rehabilitation Device and Detection Technology Engineering Research Centre of the Ministry of Education Tianjin China Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Tianjin P. R. China School of Electrical Engineering Hebei University of Technology Tianjin China

Muscle activation cannot achieve the activation state experienced during normal activity throughout the rehabilitation process, and effectiveness of rehabilitation will be enhanced if the muscle state can be controlled from the “zero EMG” state to the normal motion state. It is challenging to precisely regulate the muscle state during the model establishment process because the lower limb muscle group is a highly interconnected complicated system. Therefore, this study provides a muscle state transfer control method based on complex network control theory. A linear time-invariant functional myoelectric network model is modeled, and the structural controllability of the network is demonstrated using the PBH rank criterion to determine the optimal set of control nodes. Functional Electrical Stimulation is used as an exogenous input to drive state transfer between muscles. The results suggest that the method we propose is effective in controlling muscle state transitions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Update of kaon semileptonic form factor using Nf = 2 + 1 PACS10 configurations

arXiv

引用

arXiv 2024年

作者： Yamazaki, Takeshi Ishikawa, Ken-Ichi Ishizuka, Naruhito Kuramashi, Yoshinobu Namekawa, Yusuke Taniguchi, Yusuke Ukita, Naoya Institute of Pure and Applied Sciences University of Tsukuba Ibaraki Tsukuba305-8571 Japan Center for Computational Sciences University of Tsukuba Ibaraki Tsukuba305-8577 Japan Core of Research for the Energetic Universe Graduate School of Advanced Science and Engineering Hiroshima University Higashi-Hiroshima739-8526 Japan Education and Research Center for Artificial Intelligence and Data Innovation Hiroshima University Higashi-Hiroshima739-8521 Japan

We calculate the form factors for the kaon semileptonic decay process using the PACS10 configurations, whose physical volume is more than (10 fm)4 very close to the physical point. The configurations were generated with the Iwasaki gauge action and Nf = 2 + 1 stout-smeared nonperturbatively O(a)-improved Wilson quark action at the three lattice spacings, 0.085, 0.063, and 0.041 fm. We present updated results for the form factors, and discuss their continuum extrapolations, momentum transfer interpolation, and short chiral extrapolation to tune the simulated pion and kaon masses to the physical ones. From the results with various analyses, the systematic error of the form factor at the zero momentum transfer is estimated. The value of |Vus| is determined using our result, and is compared with those using the previous calculations and also those determined through the kaon leptonic decay process. Copyright © 2024, The Authors. All rights reserved.

关键词： Momentum transfer

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：