检索结果-内蒙古大学图书馆

China Semiconductor Technology International conference (CSTIC)

作者： Lin Du Biqiu Liu Yu Zhang Kailin Ren Yang Xu Yanpeng Chen Yuyang Bian School of Microelectronic Shanghai University China Advanced Module Technology Dept. Shanghai Huali Integrated Circuit Corp. China

ISBN: (数字)9798331513351

ISBN: (纸本)9798331513368

In the AA (Active Area) dry etching process at the 28 nm node, the accuracy of the OCD measurement model is significantly constrained by the uncertainty of TEM slice data. Experimental data indicate that the range of three TEM slice depths at the Center-Middle-Edge points within the same STI measurement mark reaches 12.6%, highlighting the risk of model bias stemming from anomalous TEM data in the traditional modeling process. If such data noise is not effectively mitigated, it will directly increase the OCD prediction error for trench depth and critical dimensions (CD), jeopardizing the reliability of process monitoring. This study proposes a dualthreshold collaborative optimization strategy for the OCD modeling stage: employing Cook's distance $\left( {{D_i} > \fracmodeling{n}} \right)$ to identify influential TEM data and combining standardized residuals (|r i |>2) to filter out outliers, thereby enhancing the model's generalization capability. Based on the 28 nm process dataset, the OCD prediction RMSE of trench depth and CD in the optimized model is reduced to 21.3%, and the sensitivity to TEM fluctuations within the same measurement mark is decreased by 34%. To facilitate the rapid implementation of this method by measurement personnel, an open-source Python analysis tool has been developed, which can automatically perform outlier diagnosis, model iterative optimization, and visualization report generation, significantly streamlining the process of constructing high-precision OCD models for AA etching process control.

关键词： process monitoring Optical filters Semiconductor device measurement Sensitivity Current measurement process control Optical variables measurement data models Semiconductor process modeling Optimization

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction of Sequence data Based on LSTM and its Application to Fault Diagnosis of Industrial process 11

Feature Extraction of Sequence Data Based on LSTM and its Ap...

引用

11th IEEE data Driven control and Learning Systems conference, DDCLS 2022

作者： Yang, Xiaojun Wan, Chuan Zhang, Tongshuai Xiong, Zhihua Tsinghua University Department of Automation Beijing100084 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

data with sequential relationships such as text, speech, and sensor data, belong to sequence data. Many deep learning models are proposed to extract features and learn inherent information among the sequence data. We investigate the similarities and differences of the modeling methods of sequence data in various fields, and then use deep learning neural network to build a model for the fault diagnosis of sequence data in process industry. Long-short-term memory (LSTM) network and feature extraction of contrastive predictive coding (CPC) are used in this paper for building deep learning models. CPC can learn representations of data, and LSTM can learn the information contained in sequence data. For application to fault diagnosis, the whole model combining CPC and LSTM can appropriately distinguish normal data from various fault data. Experiments on the Tennessee-Eastman process show that the LSTM model combining with proper feature extraction methods can improve the performance of fault diagnosis. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Reduced order modeling of spray drying

引用

IFAC-PapersOnLine 2025年第1期59卷 145-150页

作者： A. Lepsien A. Schaum Department of Process Analytics University of Hohenheim Stuttgart Germany Computational Science Hub University of Hohenheim Stuttgart Germany

Spray drying is a common a technique in process engineering, involving analysis tasks for large-scale multiphysics mechanisms, typically addressed using Computational Fluid Dynamics (CFD) software based on Finite Element Method (FEM) simulation. To enable e.g. real-time control schemes to take into account spatio-temporal behavior, efficient Reduced Order Models (ROMs) need to be identified, which in the best case retain physical information and interpretability as much as possible. In this paper, this problem is approached for a simplified two-dimensional spray dryer CFD model. Two different versions of Dynamic Mode Decomposition with control (DMDc) are compared, namely (i) a direct application of DMDc to snapshot data for temperature and humidity profiles, including droplet populations as moving and distributed inputs, and (ii) an adaptation exploring structure preservation based on the physical insight to the underlying mechanisms. It turns out that for the presented case study the structure preserving DMDc yields improved results.

关键词： Model order reduction eDMDc Spray drying Structure preservation

来源：评论

学校读者我要写书评

暂无评论

Method of Successive Approximations for Optimal control under Uncertainty of Initial data: An Interval Approach

Method of Successive Approximations for Optimal Control unde...

引用

International conference on control Systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Sofia Mustafina Elvira Gizzatova Tatiana Mikhaylova Department of Mathematical and Computer Modeling Ufa University of Science and Technology Ufa Russia

ISBN: (数字)9798331532178

ISBN: (纸本)9798331532185

This article discusses the development of an interval algorithm based on the method of successive approximations for solving optimal control problems under uncertainty of initial data. To achieve this goal, interval analysis methods are applied, allowing for the consideration of variations in system parameters. A numerical implementation of the algorithm is provided, along with a description of a computational experiment using a model example. The results demonstrate that the proposed method can construct confidence intervals for the solutions to the optimal control problem, making it useful for practical applications in situations with uncertainty in initial parameters.

关键词： Uncertainty Computational modeling Decision making Optimal control process control Approximation algorithms Mathematical models Energy efficiency Numerical models Reliability

来源：评论

学校读者我要写书评

暂无评论

Visualizing the Cosmos: A Novel Method for Text Recombination with Space News 22nd

Visualizing the Cosmos: A Novel Method for Text Recombinatio...

引用

22nd Mexican International conference on Artificial Intelligence (MICAI)

作者： Zhiyenbekov, Zhalgas Omirbekova, Zhanar Mutanov, Galymkair Tasbolatov, Madiyar Kazakh British Tech Univ Sch Informat Technol & Engn Alma Ata 050000 Kazakhstan Al Farabi Kazakh Natl Univ Affiliat Dept Comp Sci Alma Ata 050000 Kazakhstan Inst Informat & Computat Technol Alma Ata 050000 Kazakhstan

ISBN: (纸本)9783031476396;9783031476402

As the volume of data continues to surge, researchers are confronted with the challenge of extracting meaningful insights from this wealth of information. Despite rapid advancements in Natural Language processing (NLP) techniques in the AI industry, there remain gaps and opportunities for further exploration, particularly in the realm of data recombination techniques and methods. This paper proposes a novel text recombination method to facilitate the generation of recombined words from a given text. The process commences with a 'stanza' model, which identifies and compiles Named Entity Recognitions (NERs) into a list. These NERs are then cross-referenced with Wikipedia pages to retrieve relevant information, thereby enhancing entity understanding and analysis. The ensuing step involves preprocessing the output text from the previous stage, generating a list of unique words while eliminating stop words. This preprocessing stage serves to remove noise and focus on meaningful words, laying the groundwork for more effective clustering. To enable clustering, we employ vector embeddings, representing words in a 2-dimensional space, rendering them suitable for clustering techniques. Notably, the proposed method further enhances results by re-clustering words after applying K-Means, thereby identifying the most fitting candidate words for recombination. Comparatively, this method outperforms large language models (LLMs) due to its incorporation of NER information, utilization of Wikipedia pages, and effective preprocessing techniques. Unlike LLMs, which operate as resource-intensive black boxes on static data, this method benefits from real-time information access and knowledge base updates. Furthermore, each stage of the process is visualized to control the progress correctly. Thus, due to the plots of word clusterization, the proposed text recombination approach showed positive results.

关键词： Named Entity Recognition word embeddings Principal Component analysis Natural Language processing

来源：评论

学校读者我要写书评

暂无评论

Automated Productivity Evaluation of Concreting Works: The Example of Concrete Pillar Production

Automated Productivity Evaluation of Concreting Works: The E...

引用

International conference on Construction Logistics, Equipment, and Robotics, CLEaR 2023

作者： Pfitzner, Fabian Schlenger, Jonas Borrmann, André Chair of Computational Modeling and Simulation Technical University of Munich Munich Germany Leonhard Obermeyer Center TUM Center of Digital Methods for the Built Environment Munich Germany

ISBN: (纸本)9783031440205

Site schedules are usually developed by the rule of thumb based on the experience of on-site managers. While this approach can be suitable for smaller job sites, it is challenging to make good decisions for larger projects. Planning errors can result in massive delays and increasing costs. Significant improvements in other industries showed that data-driven productivity analysis of past processes advances the planning and execution of current and future projects. However, in the Architecture, Engineering & Construction (AEC) domain, automated productivity analysis of the construction phase has barely been investigated. To overcome this deficiency, this paper presents a first approach for multi-level productivity analysis of shell constructions. We discuss several state-of-the-art vision-based technologies that serve as a foundation for large-scale evaluation of the progress on a construction site. A complete pipeline is introduced that uses different types of neural networks to extract productivity information from images at various levels of detail. The proposed workflow is demonstrated for the construction process of cast-in-place concrete pillars, implementing the first two layers. Finally, remaining challenges are discussed. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Advances in Machine Learning-driven Quality control within ERP Systems: A Comprehensive Survey 11

Advances in Machine Learning-driven Quality Control within E...

引用

11th IEEE International conference on Intelligent Computing and Information Systems, ICICIS 2023

作者： Qaddoori Aldoori, Shaymaa Ahmed Mabrouk, Mohamed Mahmoud, Abeer M. Cairo Egypt Faculty of Computer and Information Science Computer Science Department Cairo Egypt

ISBN: (纸本)9798350322101

Enterprise Resource Planning (ERP) systems have become essential instruments in contemporary corporate operations, offering significant benefits in process optimization and efficient data management. The assurance of quality and dependability in these intricate systems is of utmost significance given that errors or inconsistencies might yield extensive ramifications. This study highlights the importance of quality control within ERP systems, emphasizing the crucial role of accuracy and integrity in facilitating efficient decision-making processes and optimizing operational efficiency. This analysis explores the increasing importance of upholding ERP quality as firms become increasingly dependent on these systems to traverse intricate business environments. In addition, this study explores the capacity of machine learning to enhance quality control procedures. Machine learning techniques, owing to their ability to examine large datasets and identify subtle patterns, provide a transformative shift away from the traditional rule-based approaches. Machine learning enhances the capacity to anticipate problems, reduce interruptions, and maintain consistent operational performance by employing real-time anomaly detection, predictive modeling, and adaptation to shifting ERP settings. This study explores the complex confluence of technology and business imperatives, highlighting the transformative impact of the collaboration between machine learning and quality control on the evolution of ERP systems. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

4th International conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

4th International Conference on Numerical Computations: Theo...

引用

4th International conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

ISBN: (纸本)9783031812439

The proceedings contain 105 papers. The special focus in this conference is on Numerical Computations: Theory and Algorithms. The topics include: Resource Allocation via Bayesian Optimization: an Efficient Alternative to Semi-Bandit Feedback;multi-Objective and Multiple Information Source Optimization for Fair & Green Machine Learning;extended Optimal control Problem for Practical Application;explainable process Deviance Discovery with data-Efficient Deep Learning;line Search Stochastic Gradient Algorithm with A-priori Rule for Monitoring the control of the Variance;a Machine Learning Approach to Speed up the Solution of the Distributor’s Pallet Loading Problem;combined First- and Second-Order Directions for Deep Neural Networks Training;constrained Global Optimization by Smoothing;the Unreasonable Effectiveness of Optimal Transport Distance in the Design of Multi-Objective Evolutionary Optimization Algorithms;an Improved Modified Jaya Optimization Algorithm: Application to the Solution of Nonlinear Equation Systems;GPU Acceleration of the Enhanced Jaya Optimization Algorithm for Solving Large Systems of Nonlinear Equations;effective Resistance Based Community Detection in Complex Networks;a Comparison of Formulations for Aircraft Deconfliction;optimal Recombination Problem in Genetic Programming for Boolean Functions;heuristics with Local Improvements for Two-processor Scheduling Problem with Energy Constraint and Parallelization;numerical analysis of Optimal control of Assets and Liabilities by a Bank;optimal control for Stochastic Multi-agent Systems With the Use of Parallel Hybrid Genetic Algorithm;DC Optimization in Adversarial Sparse Support Vector Machine;A First-Order Optimality Condition in Nonsmooth Generalized Semi-infinite Programming (GSIP);miniaturisation of Binary Classifiers Through Sparse Neural Networks;Price Forecasting for Bitcoin: Linear Regression and SVM Approaches;inside the Box: 0–1 Linear Programming Under Interval Uncertainty;machine Learn

关键词：

来源：评论

学校读者我要写书评

暂无评论

4th International conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

4th International Conference on Numerical Computations: Theo...

引用

4th International conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

ISBN: (纸本)9783031812408

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistical Learning to Measure the Efficacy of Digital Surgical Workflows 3

Statistical Learning to Measure the Efficacy of Digital Surg...

引用

3rd IEEE International conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2024

作者： Santoriello, Vittorio D'Antò, Michela De Franciscis, Silvia Calderone, Danilo Cesarelli, Giuseppe Delrio, Paolo Romano, Maria Ponsiglione, Alfonso Maria University of Naples 'Federico II' Dept. Electrical Engineering Information Technology Naples Italy Istituto Nazionale Tumori-IRCCS Fondazione Pascale Unit of Building Design and Maintenance-Systems-Technologies Naples Italy Istituto Nazionale Tumori-IRCCS Fondazione Pascale Unit of Colorectal Surgical Oncology Naples Italy

ISBN: (纸本)9798350378009

The crisis facing many National Health Services, arising from economic resources, often limited, impacts their ability to integrate new technologies and meet citizens' healthcare demands. To tackle this challenge, optimizing existing resources, particularly in surgical activities, which require considerable effort, is necessary to improve operational efficiency. Standardizing surgical procedures represents a significant commitment to advancing healthcare equity, minimizing errors, and optimizing resources. This study investigates the standardization of surgical procedures, focusing on laparoscopic right hemicolectomy, given that colorectal cancer is the third most commonly diagnosed cancer. Comparative analyses were conducted among conventional, robotic, and Surgical process Institute (SPI) supported approaches. The performance of the different operative approaches in terms of surgical duration times (minutes) and lengths of hospital stay (days) was analyzed through a statistical learning approach. In particular, statistical analyses and regression modeling were conducted on 29 patients. The regression analysis showed that the intervention mode is confirmed to be the most significant predictor of intervention duration and length of stay. The results indicate that SPI-supported procedures exhibit more stability and less variability in intervention duration compared to the other two groups, reduced average surgical time durations compared to robotic surgeries, and shorter lengths of stay. Due to the size of the dataset, further data collection and analysis are needed to better evaluate the effect of standardization on surgical outcomes. Despite this, it is anticipated that greater use of standardization software, such as that offered by SPI, will increase the quality standards of interventions, allow for better resource management, and enhance patient satisfaction and safety. © 2024 IEEE.

关键词： Diseases

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：