检索结果-内蒙古大学图书馆

Deep Learning Classification of Concrete Crack Images using Pre-trained AlexNet and GoogleNet Models

Deep Learning Classification of Concrete Crack Images using ...

2024 International Conference on Control and Automation, Electronics, robotics, Internet of Things, and Artificial Intelligence, CERIA 2024

作者： Jusman, Yessi Tyassari, Wikan Nadia, Liza Kurniawati, Ranti Yossa Sura, H. Nusaiba, Dzulfikar Firza Universitas Muhammadiyah Yogyakarta Center of Artificial Intelligence and Robotics Studies Department of Electrical Engineering Faculty of Engineering D.I. Yogyakarta Indonesia Pauh Faculty of Electrical Engineering and Technology 02600 Malaysia Universitas Muhammadiyah Yogyakarta Department of Electrical Engineering Faculty of Engineering D.I. Yogyakarta Indonesia

ISBN: (纸本)9798331511166

Cracking in concrete walls is a common issue in construction, often leading to structural weakening. Such damage can significantly impact both maintenance and repair costs. Concrete wall damage can be categorized in various ways, and detecting these cracks is crucial for timely intervention. This study employed deep learning neural networks to accelerate and simplify the detection and classification of concrete crack images. Two deep learning models, AlexNet and GoogleNet, were trained to classify cracks according to three categories: severe cracks (class 1), fine cracks (class 2), and normal concrete (class 3), using a total of 10,601 concrete images. Among the models, GoogleNet performed than AlexNet. The average performance for GoogleNet is 94.04% for accuracy, 91.96% for precision, 91.97% for recall, 95.39% for specificity, and 91.77% for F-score. However, despite having a lower accuracy than GoogleNet, AlexNet exhibited faster training times, which may be advantageous in certain applications where processing speed is prioritized over precision. These results demonstrate that while GoogleNet provides higher accuracy, AlexNet offers a more time-efficient solution. © 2024 IEEE.

关键词： AlexNet Concrete Crack Deep learning GoogleNet

来源：评论

学校读者我要写书评

暂无评论

Basis change, projection, and relative linear algebra tricks in signal and image processing 27

Basis change, projection, and relative linear algebra tricks...

引用

27th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2024

作者： Dabrowski, Adam Poznań University of Technology Faculty of Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Division of Signal Processing and Electronic Systems Jana Pawla II 24 Poznań60-965 Poland

ISBN: (纸本)9788362065486

In this tutorial some basic linear algebra problems: basis change and projection, are discussed together with examples of their applications in signal and image processing. In typical linear algebra university courses perpendicular projections are only discussed. However, in image processing, for defining various color spaces, we need non-perpendicular projections. That is why this is the key problem in this tutorial. © 2024 Division of Signal Processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Digital Manufacturing Pilot Study for Stepping Towards Mixed Reality Applications in Tertiary Education 30

Digital Manufacturing Pilot Study for Stepping Towards Mixed...

引用

30th ISTE International Conference on Transdisciplinary engineering: Leveraging Transdisciplinary engineering in a Changing and Connected World, TE 2023

作者： Ulmeanu, Mihaela-Elena Dijmǎrescu, Manuela-Roxana Abaza, Bogdan-Felician Szuder, Andrei Doicin, Cristian-Vasile Faculty of Industrial Engineering and Robotics University Politehnica of Bucharest Splaiul Independenţei 313 Bucharest Romania

ISBN: (纸本)9781643684406

Digital manufacturing is a comprehensive approach which includes the integration of information technology and automation into the entire product lifecycle, from design and engineering to production, logistics, and customer service. In education, mixed reality can be used to create interactive educational experiences. It has the potential to revolutionize the way products are designed, manufactured, and maintained in the digital manufacturing industry. One of the key-ways mixed reality can be used in digital manufacturing is by providing a more immersive and interactive design experience. Engineers and designers can use mixed reality to create virtual prototypes of their products and test them in a realistic, 3D environment. This can help identify potential issues early in the design process before they become costly to fix. The current paper explores the process of testing and selecting specific applications from a digital manufacturing university level course to be designed and integrated into mixed reality scenarios. Within the framework of an Erasmus+ funded project, the authors designed a Digital Manufacturing course which was implemented over 15 hours of face-to-face activities. Based on participant feedback and assessment of trainers the main areas of content were identified for further development into mixed reality applications. The paper presents one mixed reality application and pinpoints future areas of improvement and development into immersive environments for tertiary education. © 2023 The Authors.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control for Systems with Limited State Variables

引用

Russian Electrical engineering 2023年第2期94卷 77-83页

作者： Bogdanov, A.N. Anuchin, A.S. Demidova, G.L. Department of Electric Drive Moscow Power Engineering Institute Moscow111250 Russia Faculty of Control System and Robotics ITMO University St. Petersburg197101 Russia

Abstract: Model predictive control are actively used in industry in high-power electric drives, in which it is permissible to use expensive programmable logic matrices that provide calculations with a prediction horizon of up to ten epochs and a forecast tree of several million variants. However, the computing power of microcontrollers is not enough to implement such systems in a low-power electric drive. The development of microcontrollers is following the path of increasing not only computing power, but also memory, which makes it possible to implement model predictive control systems in practice using lookup table methods for calculating control actions for all combinations of state variables and control actions. The paper shows the possibility of designing control with prediction for two types of electric drives—a DC electric drive and a switched reluctance electric drive—as objects with a small number of state variables, which allows one to fit the precalculated lookup tables of control actions in the memory of the microcontroller. Studies on mathematical models have shown that model predictive control with a finite control set and a single prediction horizon has disadvantages due to variable switching frequency, and control with a continuous control set implemented by the lookup table method allows one to perform control calculations immediately before the start of the next pulse width modulation period, reducing the algorithm execution time by hundreds of times. © 2023, Allerton Press, Inc.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The Design of a Triple-Band H-and Dual C-Shaped Planar Dipole Antenna for a Drone Application

引用

Progress In Electromagnetics Research C 2023年 134卷 103-117页

作者： Naktong, Watcharaphon Ruengwaree, Amnoiy Sakulchat, Suwat Promput, Sommart Department of Telecommunications Engineering Faculty of Engineering and Technology Rajamangala University of Technology Isan Nakhon Ratchasima30000 Thailand Department of Electronics and Telecommunication Engineering Faculty of Engineering Rajamangala University of Technology Thanyaburi Pathum Thani12110 Thailand Department of Electrical Engineering Faculty of Engineering and Architecture Rajamangala University of Technology Suvarnabhumi Phranakhon Si Ayutthaya13000 Thailand Department of Mechatronics and Robotics Engineering School of Engineering and Innovation Rajamangala University of Technology Tawan-ok Chonburi 20110 Thailand

This paper presents the study of an H-and dual C-shaped planar dipole antenna by adding and etching technique for the triple-band of drone operating frequencies. Tuning the frequency range was performed to cover the VOR standard of 108–118 MHz, GS standard of 328.6–335.4 MHz, and the DME standard of 962–1,231 MHz. The antenna structure was fabricated on a PCB of FR4 with a dielectric constant (Εr ) of 4.4 and thickness (h) of 1.6 mm (material with low cost, compact size, and easy to use). The reflection coefficient (S11) results of the simulation and measurement were in good agreement, which demonstrated the bandwidth frequencies of resonance frequency at 112 MHz (106– 118 MHz), 331.50 MHz (323–401 MHz), and 1,087.50 MHz (920–1,301 MHz). The antenna gains were 1.73, 3.43, and 6.31 dBi, respectively, and the antenna radiation pattern was omnidirectional when it was used with H-plane. It was found in experiment that the proposed antenna could be installed in a drone with sending and receiving signals fittingly as desired. Furthermore, the proposed antenna is lightweight at just 0.4 kg, less than the original drone antenna (1.8 kg), and it does not require changing the antenna in each frequency range. © 2023, Electromagnetics Academy. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Identify the objective parameters of direct communication between PLC and MS SQL server 24

Identify the objective parameters of direct communication be...

引用

24th International Carpathian Control Conference, ICCC 2023

作者： Flaga, Stanislaw Majcher, Maciej AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Department of Process Control Krakow Poland

ISBN: (纸本)9798350310221

When building digital twins of existing technical solutions, we need a large amount of data on the parameters of their operation under various conditions. The source of data on the values of process variables at the lowest level is control devices - most often PLCs. There are many ways to acquire the qualities of process variables available from the PLC level. Increasingly, OPC UA is replacing the OPC model, and the OPC UA server is increasingly a functionality of the PLC CPU. The Industrial Internet of Things IIoT is used in companies moving toward Factory 4.0. Data from controllers can be acquired using high-level languages such as C++, C# or Python. Libraries often made available under an open-source license are used for this. For example, you can find commercial libraries for communication between PLCs of selected manufacturers and MySQL servers. Siemens provides a library for communication between S7-1200/1500 controllers and MS SQL server. The author has yet to find an exhaustive analysis of such a solution. In the literature, there need to be more studies of experiments describing the performance of query generation and execution and the impact of the library on PLC performance. The article presents the results of an experimental study of this issue. © 2023 IEEE.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Research study of image classification algorithms based on Convolutional Neural Networks 24

Research study of image classification algorithms based on C...

引用

24th International Carpathian Control Conference, ICCC 2023

作者： Nawrocka, Agata Nawrocki, Marcin Kot, Andrzej AGH University of Science and Technology Faculty of Mechanical Engineering and Robotics Department of Process Control Krakow Poland

ISBN: (纸本)9798350310221

The beginning of the paper introduces the idea of neural networks by presenting the neuron models and artificial neural networks. Next, the flow of operations used in the development of convolutional neural networks is presented, as well as an overview of popular architectures used in model development. After introducing the theoretical issues, a project using the EfficientNet architecture to recognize medical images taken by MRI is presented. The project describes: the selection and parameters of the MRI image database representing different types of brain tumors, the process of implementation and appropriate modification of the EfficientNet architecture used to classify images, the presentation of the results of learning the convolutional neural network and the images that highlight on the basis of which area the convolutional neural network classifies images. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of BrainMRI: AI-Assisted Healthcare Framework for the Smart Cities

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 1843-1856页

作者： Walid El-Shafai Randa Ali Ahmed Sedik Taha El-Sayed Taha Mohammed Abd-Elnaby Fathi E.Abd El-Samie Department Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenoufia32952Egypt Department of ROBOTICS and Intelligent Machines Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikhEgypt Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

The use of intelligent machines to work and react like humans is vital in emerging smart ***-aided analysis of complex and huge MRI(Mag-netic Resonance Imaging)scans is very important in healthcare *** AI(Artiﬁcial Intelligence)driven healthcare applications,tumor detection is one of the contemporary researchﬁelds that have become attractive to *** are several modalities of imaging performed on the brain for the pur-pose of tumor *** paper offers a deep learning approach for detecting brain tumors from MR(Magnetic Resonance)images based on changes in the division of the training and testing data and the structure of the CNN(Convolu-tional Neural Network)*** proposed approach is carried out on a brain tumor dataset from the National Centre of Image-Guided Therapy,including about 4700 MRI images of ten brain tumor cases with both normal and abnormal *** dataset is divided into test,and train subsets with a ratio of the training set to the validation set of 70:*** main contribution of this paper is introdu-cing an optimum deep learning structure of CNN *** simulation results are obtained for 50 epochs in the training *** simulation results reveal that the optimum CNN architecture consists of four layers.

关键词： Healthcare smart cities clinical automation CNN machine learning brain tumor medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

INNOVATIVE Y-SHAPED STENT FABRICATION: A LEAP FORWARD IN BIFURCATION LESION TREATMENT

INNOVATIVE Y-SHAPED STENT FABRICATION: A LEAP FORWARD IN BIF...

引用

ASME 2024 International Mechanical engineering Congress and Exposition, IMECE 2024

作者： Gharaie, Saleh Zolfagharian, Ali Moghadam, Amir Ali Amiri School of Engineering Faculty of Science Engineering and Built Environment Deakin University Burwood Australia Dept. of Robotics & Mechatronics Engineering Kennesaw State University AtlantaGA United States

ISBN: (纸本)9780791888629

This study introduces a novel method for fabricating Yshaped stents from Nitinol sheets, aimed at addressing clinical needs more effectively than current braided designs. Stents play a crucial role in treating narrowed blood vessels, but conventional methods often result in high bending resistance and increased risk of in-stent restenosis (ISR). The proposed method allows for precise control over the stent's flexibility and mesh density, overcoming the limitations of braiding techniques. A complex Y-shaped stent design was developed and subjected to extensive mechanical testing, including tensile, bending, and crush resistance tests, and finite element analysis (FEA). The results demonstrated that the developed stent exhibited superior flexibility, lower bending resistance, and high structural integrity under various load conditions. The stent's performance was benchmarked against a commercially available Y-shaped stent, showing comparable or improved mechanical properties. This innovative approach enhances the mechanical performance of Yshaped stents and also opens new possibilities for design customization, potentially improving clinical outcomes and reducing complications associated with stent implantation. Copyright © 2024 by ASME.

关键词： Tensile testing

来源：评论

学校读者我要写书评

暂无评论

Camera-based light source localization for precise luminous intensity measurement of airport lamps 27

Camera-based light source localization for precise luminous ...

引用

27th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2024

作者： Podbucki, Kacper Marciniak, Tomasz Poznan University of Technology Faculty of Automatic Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Division of Electronic Systems and Signal Processing Jana Pawla II 24 Poznań60-965 Poland

ISBN: (纸本)9788362065486

Measuring luminous intensity using electronic sensors requires their precise positioning. In the case of mobile measurement platforms, it is important to detect the light source and thus determine the correct direction of movement of the measuring device. This article presents research on a solution for the initial detection of glowing airport lamps based on camera images. The impact of the selection of parameters and image processing methods on the prepared data set was assessed. The histogram filtration method was introduced to improve the effectiveness of airport lamp localization. The proposed solution was investigated in different weather and daytime conditions. The overall accuracy of the proposed solution is more than 90%. © 2024 Division of Signal Processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Image enhancement

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：