检索结果-内蒙古大学图书馆

5th International conference on Green Energy, Environment, and Sustainable Development, GEESD 2024

作者： Fan, Ziming Yang, Jun Xun, Hua Co. Ltd. Inner Mongolia Power Research Institute Branch Inner Mongolia Hohhot010000 China

ISBN: (纸本)9781510683006

Due to the increasing degree of substation automation and intelligence and the promotion of unattended operation, the role of batteries is becoming more and more important. Battery life assessment methods usually rely on physical models and experimental data. However, due to the complexity and high cost of the experimental process, as well as the complexity of the model and the limitations of the hypothesis, these methods are often limited. By collecting a large number of battery operation data, machine learning and statistical analysis techniques are used to construct a prediction model, so as to more accurately evaluate the battery life and improve the evaluation efficiency. © 2024 SPIE.

关键词： Batteries data modeling Power grids Performance modeling Mathematical optimization data processing Reliability Education and training Mathematical modeling Systems modeling

来源：评论

学校读者我要写书评

暂无评论

Does COVID-19 Pandemic Motivate Privacy Self-Disclosure in Mobile Fintech Transactions? A Privacy-Calculus-Based Dual-Stage SEM-ANN analysis

引用

IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT 2024年 71卷 2986-3000页

作者： Yuan, Yun-Peng Tan, Garry Wei-Han Ooi, Keng-Boon UCSI Univ UCSI Grad Business Sch Kuala Lumpur 56000 Malaysia Nanchang Inst Technol Sch Finance & Econ Nanchang 330029 Jiangxi Peoples R China Yunnan Normal Univ Sch Econ & Management Kunming 650092 Yunnan Peoples R China Chang Jung Christian Univ Coll Management Tainan 711301 Taiwan

The emergence of mobile financial technology (mobile fintech) services raises numerous public concerns regarding privacy issues;consequently, researchers in mobile technology acceptance have focused on consumers' privacy self-disclosure behaviors under the usual scenario. However, there is still a lack of understanding on how external influences, such as a public health crisis, affect consumers' privacy decision-making process. Therefore, in this article, we examine the effects of privacy- and pandemic-related antecedents on mobile fintech users' information self-disclosure behavior during the coronavirus disease 2019 pandemic. The present research adopts a self-administered questionnaire with 712 effective responses for data collection and a two-stage partial least squares-structural equation modeling-artificial neural network (PLS-SEM-ANN) approach to test the theoretical lens proposed. The results indicate that the significant structural paths in the model are consistent with the proposed hypotheses and existing literature. Surprisingly, face-to-face avoidance (FFA) does not significantly influence consumers' self-disclosure willingness. Infection severity and infection susceptibility were insignificant with FFA. The present research is the first to investigate consumers' privacy-related behavior via integrating the privacy-calculus framework with control agency theory. This research focuses on consumers' decision-making during the pandemic, explicitly highlighting the macroenvironment's role in influencing an individual's behavior.

关键词： Privacy Pandemics COVID-19 Decision making Appraisal Calculus Psychology Artificial neural network (ANN) control agency theory coronavirus disease 2019 (COVID-19) mobile commerce mobile financial technology partial least squares structural equation modeling privacy calculus

来源：评论

学校读者我要写书评

暂无评论

Program analysis for Adaptive data analysis

引用

PROCEEDINGS OF THE ACM ON PROGRAMMING LANGUAGES-PACMPL 2024年第PLDI期8卷 914-938页

作者： Liu, Jiawen Qu, Weihao Gaboardi, Marco Garg, Deepak Ullman, Jonathan Boston Univ Boston MA 02215 USA Monmouth Univ West Long Branch NJ USA MPI SWS Saarbrucken Germany Northeastern Univ Boston MA 02115 USA

data analyses are usually designed to identify some property of the population from which the data are drawn, generalizing beyond the specific data sample. For this reason, data analyses are often designed in a way that guarantees that they produce a low generalization error. That is, they are designed so that the result of a data analysis run on a sample data does not differ too much from the result one would achieve by running the analysis over the entire population. An adaptive data analysis can be seen as a process composed by multiple queries interrogating some data, where the choice of which query to run next may rely on the results of previous queries. The generalization error of each individual query/analysis can be controlled by using an array of well-established statistical techniques. However, when queries are arbitrarily composed, the different errors can propagate through the chain of different queries and bring to a high generalization error. To address this issue, data analysts are designing several techniques that not only guarantee bounds on the generalization errors of single queries, but that also guarantee bounds on the generalization error of the composed analyses. The choice of which of these techniques to use, often depends on the chain of queries that an adaptive data analysis can generate. In this work, we consider adaptive data analyses implemented as while-like programs and we design a program analysis which can help with identifying which technique to use to control their generalization errors. More specifically, we formalize the intuitive notion of adaptivity as a quantitative property of programs. We do this because the adaptivity level of a data analysis is a key measure to choose the right technique. Based on this definition, we design a program analysis for soundly approximating this quantity. The program analysis generates a representation of the data analysis as a weighted dependency graph, where the weight is an upper bound on the

关键词： Adaptive data analysis program analysis dependency graph

来源：评论

学校读者我要写书评

暂无评论

Research on Fault Diagnosis modeling Methods Driven by Route QAR data

Research on Fault Diagnosis Modeling Methods Driven by Route...

引用

2024 IEEE International conference on Sensing, Diagnostics, Prognostics, and control, SDPC 2024

作者： Fang, Yinlong Jin, Feng Yang, Nan Yang, Lu Zhang, Guigang Wang, Jian Beijing Institute of Technology Beijing China Institute of Automation Chinese Academy of Sciences Beijing China Shanghai Aircraft Customer Service Co. Ltd. Shanghai China

ISBN: (纸本)9798350388855

Diagnosing flight route faults based on QAR data is crucial for preventing flight accidents and reducing maintenance costs. This paper presents a method for diagnosing flight route faults using a Long Short-Term Memory Network and Decision tree algorithm (LSTM-DT). We used feature optimization algorithms to process the original QAR data, including rolling window operation and principal component analysis. The optimized features were then used to establish an LSTM anomaly detection model to identify abnormal points of the faulty route. We established a decision tree fault diagnosis model using these detected outliers to determine the corresponding fault types. When tested with real airline data, the fault diagnosis accuracy of this method reached 99.45%, confirming its effectiveness. © 2024 IEEE.

关键词： Aircraft accidents

来源：评论

学校读者我要写书评

暂无评论

A Comparative Review of Advanced Techniques for Financial Sentiment analysis 24

A Comparative Review of Advanced Techniques for Financial Se...

引用

International conference on modeling, Natural Language processing and Machine Learning (CMNM)

作者： Xiao, Weizhen Wuhan Univ Technol Wuhan 430081 Peoples R China

ISBN: (纸本)9798400709760

Financial sentiment analysis, the task of discerning market sentiment from financial texts, plays a crucial role in investment decisions, risk assessment, and understanding economic trends. Traditional sentiment analysis techniques have often faced limitations in handling the complexities and nuances of financial language. The advent of large language models (LLMs) has brought a paradigm shift in this field. With their remarkable ability to process and understand natural language, LLMs are enabling new approaches that increase the accuracy and sophistication of financial sentiment analysis. This paper provides a comparative overview of cutting-edge LLM-based techniques for financial sentiment analysis. We introduce a six-pronged classification framework covering data types, sentiment granularity, model architectures, training approaches, methodological focus, and evaluation metrics. This framework aims to provide a structured perspective for understanding recent research trends. Our analysis reveals several key developments in the field. We discuss the challenges and opportunities associated with advanced techniques, like Instruction-tuning approaches and Retrieval-augmented methods. While LLMs offer clear advantages, ensuring data quality, mitigating bias, enhancing model explainability, and scaling these models to real-world applications remain active research areas. This review offers investors and financial researchers a comprehensive guide to the evolving landscape of financial sentiment analysis, facilitating well-informed choices for different use cases and laying the groundwork for future research.

关键词： Financial Sentiment analysis Large Language Models (LLMs) FinBERT Retrieval-Augmentation Instruction-tuning

来源：评论

学校读者我要写书评

暂无评论

Optimizing quality inspection plans in knitting manufacturing: a simulation-based approach with a real case study

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2024年第3-4期131卷 1167-1184页

作者： Mecheri, Chakib Ouazene, Yassine Nguyen, Nhan-Quy Yalaoui, Farouk Scaglia, Thierry Gruss, Marie Univ Technol Troyes Comp Sci & Digital Soc Lab LIST3N 12 Rue Marie CurieCS 10004 F-42060 Troyes France Petit Bateau 115 Rue Lieutenant Pierre Murard F-10000 Troyes France Univ Technol Troyes Chaire Connected Innovat 12 Rue Marie CurieCS 10004 F-42060 Troyes France

This paper introduces a simulation-based approach to enhance quality defect detection in a prominent French textile company's manufacturing process. The production workflow is initially simulated and analyzed to identify key parameters influencing defect creation and detection. After assessing the existing control process using performance metrics, a novel Inspection Quality Plan (IQP) is formulated. To validate the effectiveness of the proposed IQP, a simulation model is developed and calibrated to mirror real-world conditions. This model, initially validated against the current solution, acts as a benchmark for evaluating predefined scenarios and determining optimal configurations. The implemented scenario, tested in the workshop under authentic conditions, results in a remarkable 42% improvement in defect detection within the knitting process. The positive outcomes are meticulously examined and discussed. This study, employing a holistic approach that integrates simulation modeling, performance evaluation, and real-world deployment, establishes an optimized strategy for enhancing defect detection in the textile industry. It underscores the effectiveness of the proposed IQP, showcasing significant improvements observed in practical settings based on a simulation model.

关键词： Quality improvement Quality control Inspection quality plans data analysis Discrete event simulation Textile industry Knitting process

来源：评论

学校读者我要写书评

暂无评论

FModal: A Flexible Body Dynamics modeling Pipeline for Guidance and control

FModal: A Flexible Body Dynamics Modeling Pipeline for Guida...

引用

IEEE Aerospace conference

作者： Leake, Carl Jain, Abhinandan CALTECH Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA

ISBN: (纸本)9781665490320

This article describes the FModal tool that has been designed to bridge the gap between the structural dynamics and guidance and control domains to facilitate the development and use of high-fidelity flexible body dynamics models. FModal streamlines the process of generating modal data-including residual vectors and modal integral terms-from component NASTRAN structural dynamics models. The data generation process can be tailored to meet simulation fidelity and performance needs. FModal's output is a portable HDF5 file with hierarchical, well-organized, and labeled data that can be used to automate, simplify, and speed up the creation of flexible multibody dynamics models-resulting in faster design iterations and reduced costs. This paper uses an interface between FModal and the DARTS flexible multibody dynamics tool to carry out several numerical studies to exercise and validate the FModal pipeline.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Optimization of optical spectroscopy classification algorithms for limited data scenarios in the food industry: Tomato sauce samples case

引用

FOOD control 2025年 167卷

作者： Moises, Ander Gracia Pascual, Ignacio Vitoria de la Casa, Amaia Avedillo Perez, Maria Moreno Gonzalez, Jose Javier Imas Ruiz-Zamarreno, Carlos Pyroistech SL C Tajonar 22 Pamplona 31006 NA Spain Univ Publ Navarra Dept Elect Elect & Commun Engn Campus Arrosadia Pamplona 31006 NA Spain Univ Publ Navarra Inst Smart Cities ISC Pamplona 31006 NA Spain

This study addresses the problem of training deep learning models with limited datasets, a significant challenge in sectors like medical imaging and food quality analysis. To tackle this issue, generative adversarial networks (GANs) will be employed to augment the available data and improve model performance. An innovative approach is introduced here, integrating semi-supervised learning and generative modeling to maximize the use of small datasets in developing robust models. The method involves reversing the conventional distribution of training and testing data to focus on model evaluation and generalization from limited samples. Wasserstein GANs (WGANs) and Semi-Supervised GANs (SGANs), are utilized to supplement datasets with synthetic but realistic examples, enhancing the training process in scenarios of data scarcity. These techniques are applied in the context of visible reflectance spectroscopy to analyze tomato sauces, demonstrating the method's effectiveness in non-invasively assessing key quality parameters such as oil content, degrees Brix, and pH. The results show significant improvements in model performance metrics: for %Oil content, overall accuracy increased from 0.47 to 0.66;for degrees Bx, it rose from 0.65 to 0.71;and for pH measurement, accuracy improved from 0.43 to 0.62. These outcomes highlight the model's improved capability to generalize and maintain accuracy with limited data.

关键词： Visible reflectance spectroscopy Food quality control pH Oil content Generative adversarial networks Semi-supervised learning (degrees)Brix

来源：评论

学校读者我要写书评

暂无评论

Conjugated Polymer process Ontology and Experimental data Repository for Organic Field-Effect Transistors

引用

CHEMISTRY OF MATERIALS 2023年第21期35卷 8816-8826页

作者： Liu, Aaron L. Lee, Myeongyeon Venkatesh, Rahul Bonsu, Jessica A. Volkovinsky, Ron Meredith, J. Carson Reichmanis, Elsa Grover, Martha A. Georgia Inst Technol Sch Chem & Biomol Engn Atlanta GA 30332 USA Lehigh Univ Dept Chem & Biomol Engn Bethlehem PA 18015 USA

Polymer-based semiconductors and organic electronics encapsulate a significant research thrust for informatics-driven materials development. However, device measurements are described by a complex array of design and parameter choices, many of which are sparsely reported. For example, the mobility of a polymer-based organic field-effect transistor (OFET) may vary by several orders of magnitude for a given polymer as a plethora of parameters related to solution processing, interface design/surface treatment, thin-film deposition, postprocessing, and measurement settings have a profound effect on the value of the final measurement. Incomplete contextual, experimental details hamper the availability of reusable data applicable for data-driven optimization, modeling (e.g., machine learning), and analysis of new organic devices. To curate organic device databases that contain reproducible and findable, accessible, interoperable, and reusable (FAIR) experimental data records, data ontologies that fully describe sample provenance and process history are required. However, standards for generating such process ontologies are not widely adopted for experimental materials domains. In this work, we design and implement an object-relational database for storing experimental records of OFETs. A data structure is generated by drawing on an international standard for batch process control (ISA-88) to facilitate the design. We then mobilize these representative data records, curated from the literature and laboratory experiments, to enable data-driven learning of process-structure-property relationships. The work presented herein opens the door for the broader adoption of data management practices and design standards for both the organic electronics and the wider materials community.

关键词： Conjugated polymers Deposition Materials Organic electronics Polymers

来源：评论

学校读者我要写书评

暂无评论

Deep-learning-driven intelligent tool wear identification of high-precision machining with multi-scale CNN-BiLSTM-GCN

引用

ADVANCED ENGINEERING INFORMATICS 2025年 65卷

作者： Xu, Zhicheng Zhang, Baolong Fan, Louis Luo Yan, Edward Hengzhou Li, Dongfang Zhao, Zejia Yip, Wai Sze To, Suet Hong Kong Polytech Univ Dept Ind & Syst Engn State Key Lab Ultraprecis Machining Technol Kowloon Hong Kong Peoples R China Shenzhen Univ Inst Semicond Mfg Res Coll Mechatron & Control Engn Shenzhen 518060 Guangdong Peoples R China

In high-precision machining, the inevitable tool wear will significantly affect the surface quality. Traditional tool wear modeling is complicated due to the complex mathematical reasoning process and the identification of numerous unknown parameters linked to the wear mechanism. data-driven modeling for tool wear prediction can avoid the above issues but suffers from high-cost and low-efficiency because of amounts of expensive tool consumption and time-consumed experiments for generating the training dataset. To fill this gap, this study proposed an innovative approach to accurately identifying tool wear in high-precision machining effortlessly. Firstly an unsupervised Modified Toeplitz Inverse Covariance Clustering (MTICC) algorithm was first proposed to objectively categorize tool wear phase from multi-channel time-series data to break through traditional manualexperience-based division, whose effectiveness was validated by the well-designed experiments. Then, a hybrid deep learning model with a multi-scale CNN-BiLSTM-GCN and cross-attention structures was developed to deeply extract spatial-temporal features from multi-channel signals by first considering the interdependencies of the sensor network for higher accuracy. After hyperparameters optimization, features importance analysis was conducted to identify the most important features, which are "X-force", "Y-force" and "Phase1 Active Power", and the hyperparameters importance quantitatively analyze the contribution of CNN, BiLSTM, and GCN modules, respectively. Through the comparative studies, the proposed multi-scale CNN-BiLSTM-GCN model performed better with a weighted average F1 score of 0.987 than other models. The proposed model was finally employed on the intelligent IoT platform and successfully achieved the real-time identification of tool wear in the HPM process.

关键词： Intelligent tool wear identification Unsupervised MTICC clustering Hybrid CNN-BiLSTM-GCN model High-precision machining

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：