检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language resources and Evaluation, LrEC-COLING 2024

作者： Zheng, Xiangping Wu, Bo Zhang, Alex X. Li, Wei College of Computer Science and Technology Harbin Engineering University China R&D and External Relations Department Xiangjiang Laboratory China Modeling and Emulation in E-Government National Engineering Laboratory China Harvest Fund Management Co. Ltd. China Qingdao Innovation and Development Base of Harbin Engineering University China

ISBN: (纸本)9782493814104

Session-based recommendation (SBr) is a challenging task that involves predicting a user's next item click based on their recent session history. Presently, many state-of-the-art methodologies employ graph neural networks to model item transitions. Notwithstanding their impressive performance, graph-based models encounter significant challenges when confronted with intricate session dependencies and data sparsity in real-world scenarios, ultimately constraining their capacity to enhance recommendation accuracy. In recognition of these challenges, we introduce an innovative methodology known as'Mssen,' which stands for Multi-collaborative self-supervised learning in hypergraph neural networks. Mssen is meticulously crafted to adeptly discern user intent. Our approach initiates by representing session-based data as a hypergraph, adeptly capturing intricate, high-order relationships. Subsequently, we employ self-supervised learning on item-session hypergraphs to mitigate the challenges of data sparsity, all without necessitating manual fine-tuning, extensive search, or domain-specific expertise in augmentation selection. Comprehensive experimental analyses conducted across multiple datasets consistently underscore the superior performance of our approach when compared to existing methodologies. © 2024 ELrA Language resource Association: CC BY-NC 4.0.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving robustness of GNN-based Anomaly detection by Graph Adversarial Training 30

Improving Robustness of GNN-based Anomaly Detection by Graph...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language resources and Evaluation, LrEC-COLING 2024

ISBN: (纸本)9782493814104

Graph neural networks (GNNs) play a fundamental role in anomaly detection, excelling at the identification of node anomalies by aggregating information from neighboring nodes. Nonetheless, they exhibit vulnerability to attacks, with even minor alterations in the graph structure or node attributes resulting in substantial performance degradation. To address this critical challenge, we introduce an innovative mechanism for graph adversarial training, meticulously designed to bolster GNN-based anomaly detection systems against potential poisoning attacks. This novel approach follows a two-step framework. (1) In the initial phase, we employ a Multiple-Objective Generative Adversarial Attack (MO-GAA), which focuses on generating feature modifications and inducing structural disruptions within the graph. Its primary objective is to mimic the adversarial behavior of potential attackers on the anomaly detection graph, with the explicit intention of confounding the anomaly detector. (2) In the subsequent stage, we introduce Purification-Based Adversarial Attack defense (PB-AAd), a method specifically designed to rectify any contamination and restore the integrity of the graph. The central aim of PB-AAd is to counteract the destructive actions carried out by potential attackers. Our empirical findings, derived from extensive experiments conducted on four real-world anomaly detection datasets, serve to demonstrate how MO-GAA systematically disrupts the graph, compromising the effectiveness of GNN-based detectors, while PB-AAd effectively mitigates these adversarial actions, thereby enhancing the overall robustness of GNN-based anomaly detectors. © 2024 ELrA Language resource Association: CC BY-NC 4.0.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Sub-surface sinking effect of reinforcement particle in laser assisted machining of metal matrix composites

引用

CIrP Annals 2025年

作者： Mypati, Omkar Liao, Zhirong Zan, Shusong M'Saoubi, rachid Axinte, dragos Machining and Condition Monitoring Group Faculty of Engineering University of Nottingham United Kingdom R&D Materials and Technology Development Fagersta Sweden Division of Production and Materials Engineering Lund University Lund Sweden

Aluminium-based SiC particle-reinforced metal matrix composites are widely used in engineering applications due to their exceptional mechanical properties. However, their machining remains challenging due to the mismatch of material properties between the brittle SiC particles and the ductile aluminium matrix, causing tool wear and surface damage. To mitigate these issues, laser inverse problem scanning is utilised to strategically melt the top layer aluminium matrix, allowing the SiC particles to sink and promoting more ductile Al-matrix. The strategic hybrid laser milling approach optimises particle sinking, reduces tool wear and enhances surface integrity by minimising particle fracture, pullout and refining microstructure. © 2025 The Author(s)

关键词： Milling (machining)

来源：评论

学校读者我要写书评

暂无评论

Measurement and analysis of acoustic characteristics of panel type sensor arrays in an open water tank 24

Measurement and analysis of acoustic characteristics of pane...

引用

24th International Congress on Acoustics, ICA 2022

作者： Kim, Kyungseop Pyo, Seonghun Kwon, Byung-Jin Chang, Woosuk Lee, Jeong-Min Agency for Defense Development Maritime Technology Research Institute Korea Republic of LIG Nex1 Co. Ltd. Maritime R&D Lab. Korea Republic of

A new method is presented for acoustic measurement of a panel type sensor module in open water tank. The method utilizes the data from the hydrophones, which have in-plane three different positions, of the sensor module. It provides an estimation of the edge-diffracted pressure field as well as the sensor receiving field (incident/reflected pressure) for the finite-sized module. The method is applied on the synthetic and experimental data to confirm the validity. diffraction effects on the measurement of the acoustic characteristics are examined, and distribution characteristics of scattering sound field around panels according to sample size and composition of the panel materials are also analyzed. © ICA *** rights reserved

关键词： Acoustic measurement diffraction Panel

来源：评论

学校读者我要写书评

暂无评论

Hybrid Complex Proportional Assessment-Multi-objective Grey Wolf Optimizer for Biodiesel Process Optimization 1

引用

7th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Shanmugasundar, G. Chohan, Jasgurpreet Singh Kalita, Kanak Department of Mechanical Engineering Sri Sairam Institute of Technology Chennai600044 India Department of Mechanical Engineering and University Centre for Research & Development Chandigarh University Mohali140413 India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Jadara University Research Center Jadara University Irbid Jordan

ISBN: (数字)9783031733215

ISBN: (纸本)9783031733208

In this study, a hybrid COPrAS-MOGWO (Complex Proportional Assessment-Multi-Objective Grey Wolf Optimizer) optimization approach is proposed for optimizing biodiesel production. The performance of the MOGWO is compared with Non-dominated Sorting Genetic Algorithm II (NSGA-II). Optimization of biodiesel production from waste frying soybean oil through transesterification is considered as the case study to test the proposed algorithm. The research aims to minimize energy consumption and maximize reaction conversion and green chemistry balance simultaneously. results indicate that MOGWO outperforms NSGA-II in terms of computational time and solution quality. Furthermore, the same best compromise solution (BCS) is identified by COPrAS across different weight-based scenarios. By comparing the relative performance of NSGA-II and MOGWO, this study contributes valuable insights into multi-objective optimization in biodiesel production and provides guidance for researchers and practitioners in selecting appropriate optimization algorithms to improve the efficiency and sustainability of biodiesel production processes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Cleaner production

来源：评论

学校读者我要写书评

暂无评论

MErEC-MABAC Based-Parametric Optimization of Chemical Vapour deposition Process for diamond-Like Carbon Coatings 6th

MEREC-MABAC Based-Parametric Optimization of Chemical Vapour...

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Prabhukumar, Sellamuthu Chohan, Jasgurpeet Singh Kalita, Kanak Department of Mechanical Engineering Presidency University Bangalore India Department of Mechanical Engineering University Centre for Research and Development Chandigarh University Mohali India Department of Mechanical Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Avadi India

ISBN: (纸本)9783031501579

This research paper presents an application of the Multi-attributive Border Approximation Area Comparison (MABAC) method combined with the Method based on the removal Effects of Criteria (MErEC) for the parametric optimization of the Chemical Vapor deposition (CVd) process in diamond-like Carbon (dLC) coatings. A decision matrix is formulated using a case study from the literature. Four response parameters namely, Hardness (H), Young’s modulus (E), Coefficient of Friction (COF), and Wear rate (Wr) are considered. The weight allocation for these response parameters is calculated using five different methods, namely MErEC, mean weight (Mean), Standard deviation (Stdev), Entropy, and Criteria Importance Through Intercriteria Correlation (CrITIC) method. The MABAC method was employed to obtain the optimal parametric combination for the dLC coatings. results showed a clear superior combination of the CVd process parameters can be achieved using the MErEC-MABAC methodology. Thus, the study successfully demonstrates the effectiveness of the MErEC-MABAC-based approach for the simultaneous optimization of multiple responses in the CVd process for dLC coatings. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Coatings

来源：评论

学校读者我要写书评

暂无评论

Particle-based investigation of excipients stability: the effect of storage conditions on moisture content and swelling †

RSC Pharmaceutics

引用

rSC Pharmaceutics 2025年第2期2卷 369-386页

作者： Isra Ibrahim Mark Carroll Anas Almudahka James Mann Alexander Abbott Fredrik Winge Adrian davis Bart Hens Ibrahim Khadra daniel Markl Centre for Continuous Manufacturing and Advanced Crystallisation (CMAC) University of Strathclyde Glasgow UK daniel.markl@strath.ac.uk Strathclyde Institute of Pharmacy & Biomedical Sciences University of Strathclyde Glasgow UK Department of Pharmaceutics and Pharmaceutical Technology Yarmouk University Irbid Jordan Department of Pharmaceutics College of Pharmacy Kuwait University Kuwait Oral Product Development Pharmaceutical Technology & Development Operations AstraZeneca Macclesfield UK Oral Product Development Pharmaceutical Technology & Development Operations AstraZeneca Gothenburg Sweden Analytical R&D Pharmaceutical Sciences Small Molecules Pfizer R&D UK Ltd Sandwich UK Drug Product Design Pfizer Zaventem Belgium

Moisture sensitivity poses a challenge in formulating oral dosage forms, particularly when considering disintegrants’ swelling due to prior moisture exposure, impacting performance and physical stability. This study utilises dynamic vapour sorption to simulate real-world storage scenarios, investigating the equilibrium moisture content and dynamics of eight commonly used excipients in oral solid dosage forms. A model was developed to determine the kinetic rate constant of moisture sorption and desorption for different storage conditions. dynamic vapour sorption tests revealed that excipients with higher moisture-binding capacities showed slower equilibration to the target relative humidity (rH). Elevated temperatures accelerated the moisture sorption/desorption process for all excipients, reducing the equilibrated moisture content for most, except mannitol and lactose. Particle imaging over a 14-day accelerated storage period quantified swelling, indicating approximately 6% increase in particle diameter for croscarmellose sodium (CCS) and sodium starch glycolate (SSG), and a lesser 2.7% for microcrystalline cellulose (MCC), predominantly caused by the humidity. All excipients reached their swelling peak within the first day of storage, with permanent particle size enlargement for CCS and SSG, whereas MCC displayed a partial reversibility post-storage. Enhancing our understanding of excipients’ stability and interaction with moisture and the resulting particle swelling contributes to the rational design of oral solid dosage formulations and promotes a better understanding of their long-term physical stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of key atomic process of Metal-induced lateral crystallization from First-principles Calculations

Identification of key atomic process of Metal-induced latera...

引用

International Conference on Simulation of Semiconductor Processes and devices (SISPAd)

作者： Yutaro Ogawa Hikari Suzuki Masayasu Miyata Advanced Memory Development Center Memory Division Kioxia Corporation Yokohama Japan Core Technology Research Center Frontier Technology R&D Institute Kioxia Corporation Yokohama Japan

ISBN: (数字)9798331516352

ISBN: (纸本)9798331516369

In order to improve the efficiency of metal-induced lateral crystallization (MILC) using Ni, it is important to understand the fundamental mechanisms. In this study, the NiSi 2 /amorphous Si (a-Si) interface is appropriately modeled and the atom transfer behavior during the MILC process was explored by first-principles calculations. It is found that the overall picture of MILC mechanism can be effectively comprehended through three fundamental processes: (1) the formation of Ni vacancies at the a-Si interface, (2) the diffusion of Ni vacancies within the bulk NiSi2, and (3) the reconstruction of the c-Si interface. The trends under stress, observed in experiments, are explained by applying this mechanism to the MILC process.

关键词： Surface reconstruction Crystallization Market research Nickel Silicon Semiconductor process modeling Epitaxial growth Stress Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic Technique based Fault diagnosis for Electrical distribution Network

Fuzzy Logic Technique based Fault Diagnosis for Electrical D...

引用

Innovation in technology (INOCON), IEEE International Conference for

作者： Saurabh G. rana Shefali Talati Manish J. desai Department of Electrical Engineering Faculty of Technology and Engineering The Maharaja Sayajirao University Vadodara India Department of R&D Electrical Research and Development Association Vadodara India

The power system needs to operate reliably and efficiently, with the distribution system being a critical component. distribution systems are prone to faults and malfunctions for several reasons. These issues can have a significant impact on the power grid, but their effects can be minimized quickly and accurately through fault diagnostics. Electric utilities face an ongoing challenge in promptly and precisely identifying and locating faults in the distribution system. AI tools can be an efficient method for accurately identifying these faults. There are several possible diagnostic methods, such as fuzzy logic, ANN (artificial neural network), ANFIS (adaptive neuro-fuzzy inference system), support vector machines, genetic algorithms, and matching approaches. Each technique has its own advantages and disadvantages. The paper has employed fuzzy logic for fault detection, identification, and location. This paper includes the study of multiple faults on different buses. Also, the identification and location of multiple faults are included. The simulation and algorithm development have been carried out in MATLAB/Simulink. Thus, fault detection, identification, and location have been done through a fuzzy logic algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NLP-based Auto Generation of Graph database from Textual requirements

NLP-based Auto Generation of Graph Database from Textual Req...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Jagadish Shivamurthy Tarun Uppal deepti Vidyarthi Aeronautical Development Establishment Defence R&D Organization Bangalore India School of Computer Engineering and Mathematical Sciences Defence Institue of Advanced Technology Pune India

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

Natural Language (NL) continues to be the preferred medium of expression for requirements, especially for multi-disciplinary systems such as the Flight Control System (FCS) of an Aircraft. The importance of a precise and unambiguous understanding of requirements for the project's success is established beyond question. This aspect is further amplified in the case of a safety-critical system such as FCS. UML diagrams from use case to activity to sequence diagrams are used to understand and analyze the requirements. While these diagrams have immense value, Graph databases add new benefits for analyzing and managing requirements. Graph databases are gaining popularity due to their simplicity, scalability, and benefits of visualization. In this paper, we propose an NLP-based method for auto-generating a graph database for textual requirements. We explore the benefits of representing requirements as a graph database that complements the other diagrams and fills a few gaps, specifically in requirements allocation, identification of interdependencies, and change management. Though we use the Neo4j graph database management system and Cypher query language, the concepts are generic. The proposed approach for auto-generation works on requirements expressed in the EArS (Easy Approach to requirementsSyntax) template. However, it can be extended for other templates or free-flowing text.

关键词： Visualization Scalability Unified modeling language Natural languages Ear database systems Visual databases

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：