检索结果-内蒙古大学图书馆

Surface Defects Detection of Cylindrical High-Precision Industrial Parts Based on Deep Learning Algorithms: A Review

引用

Operations Research Forum 2024年第3期5卷 58页

作者： Wei, Li Solihin, Mahmud Iwan Saruchi, Sarah ‘Atifah Astuti, Winda Hong, Lim Wei Kit, Ang Chun School of Computer Science and Technology (School of Software) Guangxi University of Science and Technology Guangxi 545006 China Faculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur 56000 Malaysia Faculty of Manufacturing and Mechatronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia Computer Engineering Department Automotive and Robotics Engineering Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia

High-precision cylindrical parts are critical components across various industries including aerospace, automotive, and manufacturing. Since these parts play a pivotal role in the performance and safety of the systems they are integrated into, they are often subject to stringent quality control measures. Defects on the interior and exterior wall surfaces of these cylindrical parts can severely undermine their function, leading to degraded performance, increased wear, and even catastrophic failures in extreme cases. This article aims to comprehensively summarize the task definition, challenges, mainstream methods, public datasets, evaluation metrics, and other aspects of surface defect detection for high-precision cylindrical parts, in order to help researchers quickly grasp this field. Specifically, the background and characteristics of industrial defect detection are first introduced. Owing to the unique geometric features of cylindrical part surfaces, algorithms and equipment for image data acquisition used in surface defect detection are elaborated in detail. This article presents an extensive overview of state-of-the-art surface defect detection techniques designed for high-precision cylindrical components, all rooted in deep learning. The methods are systematically classified into three main categories: fully supervised, unsupervised, and alternative approaches, based on their data labeling strategies. Additionally, the paper conducts a comprehensive analysis within each category, shedding light on their unique strengths, limitations, and practical use cases. Concluding the discussion, the paper provides insights into future development trends and potential research directions in this field that will lead to manufacturing innovation. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Anomaly detection computer vision Deep learning Defect detection High-precision cylindrical parts Image processing Optical illumination

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Informal Persian Texts Using Embedding Informal words and Attention-Based LSTM Network 8

Sentiment Analysis of Informal Persian Texts Using Embedding...

引用

8th Iranian Joint Congress on Fuzzy and Intelligent Systems, CFIS 2020

作者： Karrabi, Mohammad Oskooie, Leila Bakhtiar, Mohsen Farahani, Mohammad Monsefi, Reza Ferdowsi University of Mashhad Faculty of Engineering Mashhad Iran Iran University of Science and Technology Department of Computer Computer Engineering Department Tehran Iran Tehran Iran Islamic Azad Arak Branch Department of Computer Engineering Tehran Iran Ferdowsi University of Mashhad Faculty of Engineering Mashhad Iran

ISBN: (纸本)9781728173016

The massive volume of comments on websites and social networks has made it possible to raise awareness of people's beliefs and preferences regarding products and services on a large scale. For this purpose, sentiment analysis, which refers to the determination of the sentiment of texts, has been proposed as an intelligent solution. From a methodological point of view, the recent combination of words embedding and deep neural networks (DNNs) has become an effective approach for sentiment analysis. In Persian studies, formal corpuses such as Wikipedia dumps have been used for word embedding. The fundamental difference between formal and informal texts means that the vectors derived from formal texts in informal contexts such as social networks do not result in desirable accuracy. To overcome this drawback, in this paper, we provide a large integrated text corpus of several different sources of informal comments and we also utilize the Fasttext as the word embedding algorithm. In this research, we use Attention-based LSTM, which has been shown to perform more effectively compared to the similar methods in sentiment analysis for the English language. The proposed method is evaluated on the two Persian 'Taaghche' and 'Filimo' datasets collected in this paper. The experiments on the two Persian datasets prove that utilizing informal vectors in sentiment analysis and applying the attention model improves the prediction accuracy of the DNN in the sentiment analysis of Persian texts. © 2020 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Off-Shelf Deep Learning Architectures as Feature Extractor in CT COVID-19 Classification

Off-Shelf Deep Learning Architectures as Feature Extractor i...

引用

2022 International Conference on Emerging Trends in Computing and engineering Applications, ETCEA 2022

作者： El-Messiry, Haythem University of Science and Technology of Fujairah College of Engineering and Technology Fujairah United Arab Emirates Ainsham University Faculty of Computer and Information Science Departement of Computer Science Egypt

ISBN: (纸本)9781665477093

Recently the chest imaging plays an important role in COVID-19 diagnosis compared to laboratory diagnosis such as RT-PCR. This paper investigates a robust algorithm to detect infected COVID-19 patients using computed tomography scans. The proposed algorithm utilizes a deep learning approach through applying an off shelf pretrained neural network to extract a feature map matrix from the first layer of convolutional neural network, which preserve the basic features related to geometry structures. Later the trained features are classified using a machine learning classifier as support vector machine algorithm to classify the tested images into two classes infected against not infected. The investigated algorithm was trained and tested using two open-source datasets. The results were experimented using five general pretrained off shelf CNN architectures, the performance of the pretrained algorithm was measured and evaluated for the extracted image features with popular five pretrained CNN and classification accuracy 90%. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Creating granular learning object towards reusability of Learning Object in e-learning context

Creating granular learning object towards reusability of Lea...

引用

2011 International Conference on Electrical engineering and Informatics, ICEEI 2011

作者： Noor, Siti Fadzilah Mat Yusof, Norazah Hashim, Siti Zaiton Mohd School of Information Technology Faculty of Technology and Information Science National University of Malaysia Malaysia Software Engineering Department Faculty of Computer Science and Information System University Technology of Malaysia Malaysia

ISBN: (纸本)9781457707520

Learning Object (LO) is one of the main research topics in the e-learning community in the recent years, and most researchers pay attention to the issue of Learning Object Reusability. The most obvious motivation is the economic interest of reusing learning material instead of repeatedly authoring it. In this paper we present the process of creating granular learning object for enabling the reusing of LO in e-Learning context. Reusability requires the LO to be in a fine-grain form because raw media elements are often much easier to reuse then aggregate assemblies. In other words, as the LO size decreases (lower granularity), its potential for reuse increases. A prototype of learning objects repository that contain granular LO has been developed to show the process of granularizing LO. Each of existing LO will be extracted into granular element with the metadata and the system generated unique id for each LO based on its identifier (URL of LO) and save automatically the metadata contain in the LO. These metadata will be used for searching and retrieval process of the granule LO. © 2011 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Performance of distributed coordination function for serving IoT applications 3

Performance of distributed coordination function for serving...

引用

3rd International Conference on Smart City Innovation, ICSCI 2020

作者： Harwahyu, R. Cheng, R.G. Sari, R.F. Department of Electrical Engineering Faculty of Engineering Universitas Indonesia Indonesia Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taiwan

The Internet of Things (IoT) interconnects "things"and autonomously exchanges data between them. It is expected that there are more than seven billion of connections interconnected by low-power wide-area (LPWA) networks to support IoT services before 2025. Several LPWA technologies are gaining popularity recently, such as LoRa and NB-IoT. Despite of their advertised advantages over conventional technologies such as low power, long range, and cheap module, several studies and field tests shows that they cannot communicate in long-range, the DIY supporting modules are not really power efficient, and the development are rather expensive. While commercial IoT networks have yet to be widely deployed, many smart connected devices use WiFi-based connectivity. This motivates us to study and evaluate the performance of WiFi's medium access protocol for this new use case of IoT. In the experiment, our proposed analytical model is evaluated against a custom-made Monte Carlo simulation. The result shows that our model is accurate in estimating the system performance in term of normalized throughput. © Published under licence by IOP Publishing Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An adaptive fuzzy logic controller by sliding mode control method for DC/DC converter

An adaptive fuzzy logic controller by sliding mode control m...

引用

Sixth International Conference on Power Electronics and Drive Systems, PEDS 200

作者： Khaehintung, Noppadol Kunakorn, Anatawat Aorpimai, Manop Sirisuk, Phaophak Dept. of Electrical Engineering Faculty of Engineering King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand Dept. of Control and Instrumentation Engineering Mahanakorn University of Technology Bangkok Thailand Dept. of Computer Engineering Faculty of Engineering Mahanakorn University of Technology Bangkok Thailand

ISBN: (纸本)0780392965

This paper presents the design of an adaptive fuzzy logic controller for DC/DC buck converters. The proposed controller uses a sliding mode control mechanism to improve the performance of a conventional buck converter. Despite of the nonlinear behavior of the converter, the performance of the closed-loop control system can be considerably improved compared to the results gained from other previously proposed schemes, such as the adaptive fuzzy logic controller by back propagation algorithm. This claim is obviously shown by the simulation and experimental results both in regulating and tracking modes. © 2005 IEEE.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Evaluating ML Algorithm precision over indoor thermal comfort through comparison of popular metrics 10

Evaluating ML Algorithm precision over indoor thermal comfor...

引用

10th International Conference on Modern Power Systems, MPS 2023

作者： Zanaj, Elma Balliu, Lorena Krasniqi, Bujar Basha, Gledis Polytechnic University of Tirana Faculty of Technology of Information Tirana Albania University of Prishtina Faculty of Electrical and Computer Engineering Kosovo Prishtina Serbia

ISBN: (纸本)9798350326826

Predicting the temperature in indoor spaces is essential for upholding cozy living and working conditions as well as for assuring the security and preservation of delicate tools and materials. This parameter's forecast beforehand can aid in reducing hazards, enhancing operations, and improving energy efficiency. In this paper, data retrieved from sensors, positioned within a particular building, has been simulated through three machine learning ML models. Machine Learnings (ML) become a potent tool for temperature prediction based on historical data, weather patterns, and other related elements in recent years. We evaluated the performance of three machine learning (ML) models using a train and test dataset. This paper focuses on identifying the best model selection comparing the three chosen models. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Fake News Types and Detection Models on Social Media A State-of-the-Art Survey 12th

Fake News Types and Detection Models on Social Media A State...

引用

12th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2020

作者： Collins, Botambu Hoang, Dinh Tuyen Nguyen, Ngoc Thanh Hwang, Dosam Department of Computer Engineering Yeungnam University Gyeongsan-si Korea Republic of Faculty of Computer Science and Management Wroclaw University of Science and Technology Wroclaw Poland Faculty of Engineering and Information Technology Quang Binh University Đồng Hới Viet Nam

ISBN: (纸本)9789811533792

Fake news has gained prominence since the 2016 US presidential election as well as the Brexit referendum. Fake news has abused not only the press but also the democratic rules. Therefore, the need to restrict and eliminate it becomes inevitable. The popularity of fake news on social media has made people unwilling to engage in sharing positive news for fear that the information is false. The main problem with fake news is how quickly it spreads to social media. In this paper, we introduced an overview of the various models in detecting fake news such as Machine learning, Natural Language Processing, Crowd-sourced techniques, Expert fact-checker, as well as Hybrid Expert-Machine. We also do reviews of different types of fake news, which is an essential criterion for detecting fake news. Our findings show that detecting fake news is a challenging but workable task. The techniques that combine people and machines bring very satisfactory results. We also study about open issues of fake news, then propose some potential research tasks for future works. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Implementing an AODV-Like Routing Protocol at Layer 2 for *** 802.11-Based Wireless Networks

Implementing an AODV-Like Routing Protocol at Layer 2 for **...

引用

2011 Chinese Control and Decision Conference（CCDC）

作者： Ngoc Minh Le Hoang Hong Nam Trinh Minh Duc Department of Systems ＆ Networking Faculty of Computer Science ＆ Computer EngineeringHo Chi Minh City University of Technology

ISBN: (纸本)9781424487363

Routing protocols play an important role in adhoc *** routing protocol AODV has been implemented on different *** AODV implementations operate,roughly speaking,at layer 3 of the OSI Reference Model,and have several *** have experimented with an implementation of an AODV-like routing protocol at layer 2 to show that such disadvantages can be avoided.

关键词： ad-hoc wireless networks network protocols 802.11s

来源：评论

学校读者我要写书评

暂无评论

Performance Investigation of Photovoltaic Panel under Cotton Dust Environment: Insights from Statistical Analysis

Performance Investigation of Photovoltaic Panel under Cotton...

引用

2023 International Conference on Emerging Power Technologies, ICEPT 2023

作者： Ali, Basit Khan, Muhammad Faisal Ishaque, Kashif Graduate School of Engineering Sciences & Information Technology Hamdard University Faculty of Engineering Sciences & Technology Karachi Pakistan Hamdard University Faculty of Engineering Sciences & Technology Department of Electrical Engineering Karachi Pakistan Muhammad Ali Jinnah University Department of Electrical and Computer Engineering Karachi Pakistan

ISBN: (纸本)9798350301014

The use of solar photovoltaic (PV) systems as a renewable source is gaining popularity as a means of reducing greenhouse gas emissions and meeting energy demand. However, losses associated with solar PV systems remain a challenge. In this study relationship between the average power output of a solar PV system in clean and cotton dust configurations using linear regression analysis is investigated. The data is being collected over a period of 12 days, with daily measurements of 8 hours of the average power output in both configurations. Based on the t-test, it is found that the average power output in the cotton dust configuration was significantly lower than that in the clean configuration. Linear regression analysis verified that the power output of the system decreased over time in both configurations. The coefficient of determination for the clean model is 0.1905 and the R-squared value for the cotton dust model is 0.8436. These outcomes highlight the importance of considering the effects of cotton dust growth on the performance of solar PV systems and the potential for improved maintenance strategies to overcome the related losses. © 2023 IEEE.

关键词： Solar panels

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

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

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：