检索结果-内蒙古大学图书馆

2nd International Conference on Machine Learning and Intelligent Systems engineering, MLISE 2022

作者： Li, Bin Ren, Fuji Ni, Hongjun Kang, Xin Lv, Shuaishuai Hao, Zhuangzhuang Tokushima University Faculty Of Engineering Tokushima Japan Nantong University School Of Mechanical Engineering Nantong China University Of Electronic Science And Technology School Of Computer Science And Engineering Chengdu China

ISBN: (数字)9781665492461

ISBN: (纸本)9781665492461

In the field of industrial defect detection based on machine learning, small and unbalanced number of sample data has been a challenge to the defect classification task. In this paper, the number of aluminum profile defect pictures is increased by digital image processing methods such as rotation and flipping. Then, a VGG16 network is pre-trained on ImageNet dataset, in which the weights of feature extraction modules are transferred to the classification task of surface defects of aluminum profile. Furthermore, the classification modules of VGG16 are structurally fine-tuned, the number of neurons in the second and third fully connected layers of which is adjusted to 256 and 10 respectively. The experimental results show that the classification accuracy of 10 types of aluminum profile surface defects reaches 98.47%, and the training process is stable without any obvious overfitting phenomenon. Our results suggest that the proposed method for aluminum profile surface defect classification is smooth in feature transferring and structural fine-tuning and renders reliable results in defect classification. © 2022 IEEE.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection and Segmentation Using Deep Learning Models 6

Brain Tumor Detection and Segmentation Using Deep Learning M...

引用

6th World Symposium on Artificial Intelligence, WSAI 2024

作者： Abiodun, Moses Kazeem Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Aworinde, Halleluyah Tinuoye, George Imoize, Agbotiname Lucky Li, Chun-Ta Lee, Cheng-Chi Landmark University Department of Computer Science Kwara State Omu-Aran Nigeria Bowen University Department of Computer Science Osun State Iwo Nigeria University of Ilorin Department of Computer Science Kwara State Ilorin Nigeria University of Lagos Faculty of Engineering Department of Electrical and Electronics Engineering Akoka Nigeria Fu Jen Catholic University Bachelor's Program of Artificial Intelligence and Information Security New Taipei City Taiwan Fu Jen Catholic University Department of Library and Information Science New Taipei City Taiwan

ISBN: (纸本)9798350374162

This study focuses on brain tumor detection and segmentation using Convolutional Neural Networks (CNN) with architectures of Fully Convolutional Net-work (FCN) and VGG16. The dataset imported for this study consists of brain MRI images, which were preprocessed to improve the overall image resolution. Data augmentation techniques were applied to heighten the variability and volume of the training data. For feature extraction, CNN models were utilized, specifically the VGG16 architectures. This model was trained on a preprocessed dataset to learn the important features associated with the presence of brain tumor. Image segmentation was performed to precisely outline and identify the tumor region within the brain images. FCN architecture was employed for this task, which allowed pixel-level classification of tumor regions. Finally, image classification was carried out to group brain images based on the absence or presence of a tumor. The trained models were evaluated using accuracy, precision, recall and F1score as the performance metrics. The results of the study demonstrated promising outcomes, achieving an accuracy score of 93% and a precision, recall and f1score ranging from 75% to 100% based on the specific type of tumor enlisted. This indicates that the developed CNN models, with the FCN and VGG16 architectures, effectively detect and segment brain tumors from MRI images. The findings of this study contribute to the field of medical image analysis and gives a foundation for further research and development in brain tumor diagnosis and treatment. The study recommends the use of more deep learning algorithms for the process of detecting brain tumors. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Structural RC computer aided intelligent analysis and computational performance via experimental investigations

引用

Structural engineering and Mechanics 2024年第3期90卷 253-261页

作者： Huang, Y.C. Lulios, TuMuli Chang, Chu-Ho Noor, M. Nasir Shao, Jen-Chung Chiu, Chien-Liang Lee, Tsair-Fwu Wang, Renata Information Technology Faculty Duy Tân University 254 Nguyen Van Linh Danang Viet Nam Princess Margaret Hospital Funafuti Island Private Mail Bag Tuvalu College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan College of Maritime National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Medical Physics and Informatics Laboratory of Electronics Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Information and Research Center of China 1/9 Road: 2 Block: D Section: 15 Dhaka1216 Bangladesh

This research explores a new finite element model for the free vibration analysis of bi-directional functionally graded (BDFG) beams. The model is based on an efficient higher-order shear deformation beam theory that incorporates a trigonometric warping function for both transverse shear deformation and stress to guarantee traction-free boundary conditions without the necessity of shear correction factors. The proposed two-node beam element has three degrees of freedom per node, and the inter-element continuity is retained using both C1 and C0 continuities for kinematics variables. In addition, the mechanical properties of the (BDFG) beam vary gradually and smoothly in both the in-plane and out-of-plane beam’s directions according to an exponential power-law distribution. The highly elevated performance of the developed model is shown by comparing it to conceptual frameworks and solution procedures. Detailed numerical investigations are also conducted to examine the impact of boundary conditions, the bi-directional gradient indices, and the slenderness ratio on the free vibration response of BDFG beams. The suggested finite element beam model is an excellent potential tool for the design and the mechanical behavior estimation of BDFG structures. © 2024 Techno-Press, Ltd.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Efficient Forgery Detection Approaches for Digital Color Images

引用

computers, Materials & Continua 2022年第5期71卷 3257-3276页

作者： Amira Baumy Abeer D.Algarni Mahmoud Abdalla Walid El-Shafai Fathi E.Abd El-Samie Naglaa F.Soliman Department of Communications High Institute for Engineering and TechnologyAl-Obour Obour CityEgypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadhSaudi Arabia Department of Electronics and Communications Engineering Faculty of EngineeringZagazig UniversityZagazigSharqia44519Egypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenoufia32952Egypt Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia

This paper is concerned with a vital topic in image processing:color image forgery detection. The development of computing capabilitieshas led to a breakthrough in hacking and forgery attacks on signal, image,and data communicated over networks. Hence, there is an urgent need fordeveloping efficient image forgery detection algorithms. Two main types offorgery are considered in this paper: splicing and copy-move. Splicing isperformed by inserting a part of an image into another image. On the otherhand, copy-move forgery is performed by copying a part of the image intoanother position in the same image. The proposed approach for splicingdetection is based on the assumption that illumination between the originaland tampered images is different. To detect the difference between the originaland tampered images, the homomorphic transform separates the illuminationcomponent from the reflectance component. The illumination histogramderivative is used for detecting the difference in illumination, and henceforgery detection is accomplished. Prior to performing the forgery detectionprocess, some pre-processing techniques, including histogram equalization,histogram matching, high-pass filtering, homomorphic enhancement, andsingle image super-resolution, are introduced to reinforce the details andchanges between the original and embedded sections. The proposed approachfor copy-move forgery detection is performed with the Speeded Up RobustFeatures (SURF) algorithm, which extracts feature points and feature vectors. Searching for the copied partition is accomplished through matchingwith Euclidian distance and hierarchical clustering. In addition, some preprocessing methods are used with the SURF algorithm, such as histogramequalization and single-mage super-resolution. Simulation results proved thefeasibility and the robustness of the pre-processing step in homomorphicdetection and SURF detection algorithms for splicing and copy-move forgerydetection, respectively.

关键词： Image forgery splicing algorithm copy-move algorithm histogram matching homomorphic enhancement SISR SURF

来源：评论

学校读者我要写书评

暂无评论

Performance enhancement of text-independent speaker recognition in noisy and reverberation conditions using Radon transform with deep learning

引用

International Journal of Speech Technology 2022年第3期25卷 679-687页

作者： El-Moneim, Samia Abd El-Mordy, Eman Abd Nassar, M.A. Dessouky, Moawad I. Ismail, Nabil A. El-Fishawy, Adel S. El-Dolil, Sami El-Dokany, Ibrahim M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt High Institute of Engineering and Technology Tanta Egypt Department of Computer Science and Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Automatic Speaker Recognition (ASR) in mismatched conditions is a challenging task, since robust feature extraction and classification techniques are required. Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) is an efficient network that can learn to recognize speakers, text-independently, when the recording circumstances are similar. Unfortunately, when the recording circumstances differ, its performance degrades. In this paper, Radon projection of the spectrograms of speech signals is implemented to get the features, since Radon Transform (RT) has less sensitivity to noise and reverberation conditions. The Radon projection is implemented on the spectrograms of speech signals, and then 2-D Discrete Cosine Transform (DCT) is computed. This technique improves the system recognition accuracy, text-independently with less sensitivity to noise and reverberation effects. The ASR system performance with the proposed features is compared to that of the system that depends on Mel Frequency Cepstral Coefficients (MFCCs) and spectrum features. For noisy utterances at 25 dB, the recognition rate with the proposed feature reaches 80%, while it is 27% and 28% with MFCCs and spectrum, respectively. For reverberant speech, the recognition rate reaches 80.67% with the proposed features, while it reaches 54% and 62.67% with the MFCCs and spectrum, respectively. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Ethical Decision-Making for the Inside of Autonomous Buses Moral Dilemmas

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5153-5166页

作者： Huang, Zijie Wu, Yulei Tempini, Niccolo Tang, Haina University of Exeter Faculty of Environment Science and Economy Department of Computer Science ExeterEX4 4QJ United Kingdom University of Bristol Faculty of Engineering Bristol Digital Futures Institute BristolBS8 1UB United Kingdom University of Exeter Faculty of Humanities Arts and Social Sciences Department of Sociology Philosophy and Anthropology ExeterEX4 4RJ United Kingdom University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China

The emergence of moral dilemmas inside autonomous buses can lead to unpredictable consequences for maneuver and amplify potential harms to passengers onboard. However, most existing approaches solely focus on ensuring ethical decision-making in scenarios outside of vehicles. To ensure ethical decision-making for autonomous buses when moral dilemmas occur inside, there are many urgent challenges that need to be addressed. First, the noncommensurability of ethical values presents difficulties in designing quantifiable environments and decision-making models. Moreover, ethical dilemmas involve multiple conflicting objectives, often necessitating the consideration of multiple moral theories to comprehensively evaluate different perspectives. Additionally, accurately representing these dilemmas and identifying optimal solutions that address conflicting objectives poses further challenges. This article proposes a general ethical decision-making system to handle ethical dilemmas inside autonomous buses. The system's design adheres to multiple ethical principles, and it comprises two stages: 1) develop a generative adversarial network (GAN) based human-value-aligned data collection scheme to gather representative moral values and generate comprehensive moral scenarios, which address the incommensurable ethical metrics issue;and 2) propose an ethical compliant multiobjective thresholded lexicographic Deep Q-learning method to ensure optimal policies that satisfy multiple ethical objectives. In a case study of autonomous bus route planning, our system outperforms benchmarks in showing a greater number and more evenly distributed policies in the Pareto Front and a 27% increase in coverage rate. Extensive experiments against nonethical systems show superior outcomes in convergence, average reward and cost. Finally, user studies demonstrate the system's accuracy and usability. © 2020 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Soliton Solutions for Coupled Nonlinear Generalized Zakharov Equations with Anti-cubic Nonlinearity Using Various Techniques

引用

International Journal of Applied and Computational Mathematics 2024年第1期10卷 1-30页

作者： AlQahtani, Salman A. Alngar, Mohamed E. M. New Emerging Technologies and 5G Network and Beyond Research Chair Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Basic Science Department Faculty of Computers and Artificial Intelligence Modern University for Technology and Information Cairo 11585 Egypt

This study introduces novel exact solutions for the coupled nonlinear generalized Zakharov equations with anti-cubic nonlinearity. Utilizing a variety of mathematical approaches, including the extended trial function method, the rational exp (-ψ(ξ))-expansion method, and three well-known auxiliary equation methods, a spectrum of solutions is derived. These solutions encompass dark solitons, bright solitons, singular solitons, Jacobi elliptic functions, periodic waves, and rational solutions. The unique contribution lies in the use of a phase variable θ(ξ) instead of a phase constant, providing fresh insights into wave behavior. A comparative analysis underscores the originality of the derived solutions, setting this work apart from prior studies. These findings advance our understanding of nonlinear dynamics and mathematical modeling, with potential applications in various domains. © 2023, The Author(s), under exclusive licence to Springer Nature India Private Limited.

关键词： Coupled nonlinear generalized Zakharov equations Extended trial function method Rational exp(- ψ(ξ))-expansion method Soliton solutions Three famous auxiliary equation methods

来源：评论

学校读者我要写书评

暂无评论

Application of Convolution Neural Network for Plastics Waste Management Using TensorFlow 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Saputro, Immanuela Puspasari Sanger, Junaidy Budi Adrian, Angelia Melani Mokorisa, Gilberth Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta11480 Indonesia Informatics Engineering Faculty of Engineering Universitas Katolik De La Salle Manado Manado95000 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Nowadays, plastic waste has become a global problem. Plastic waste can be found in the land, oceans, rivers, and even soil sediments. This problem has motivated various countries to overcome environmental pollution, especially plastic waste primarily through recycling programs. Plastic waste that is still good can be recycled into handicrafts or sold at the waste bank according to the current selling price. However, the waste management officer encountered difficulties classifying plastic waste since there are many forms of waste. Recently, a deep learning-based method, namely The Convolutional Neural Network (CNN), has been widely used for image processing tasks. In this study, we developed a mobile-based application by employing the CNN Algorithm to identify and classify plastic waste. The application will recognize and classify recyclable plastic waste such as plastic bags, plastic bottles, shampoo bottles, etc. There were 156 images collected manually by a smartphone camera and Google Image. All images are converted into jpg format with the size of 300 × 300 pixels. The dataset was divided into two parts, 106 images for data training and 50 images for data testing. From the experimental result, the model obtained an accuracy of 86%. Moreover, there are features to view price lists and tutorials for handicrafts from plastic waste. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Development in Flutter and its Widgits

Hybrid Development in Flutter and its Widgits

引用

2022 International Conference on Cyber Resilience, ICCR 2022

作者： Sharma, Swati Khare, Shanu Unival, Vaibhav Verma, Sahil Chandigarh University Department of Computer Science Punjab Gharuan India Uttaranchal University Dehradun248007 India Faculty of Computer Science and Engineering Sgt University Gurugram122505 India

ISBN: (纸本)9781665461221

The development of Cross-platform mobile applications is a goal of every client in today's world. Engineers are forced to build the same system multiple times for different OS (operating systems). Google provides a solution by introducing Flutter. It is an open-source SDK for improving high performance and the most reliable mobile apps for apps like iOS, Android, Linux, web and windows. It provides feature of timely compiling using a computer code that includes integration during the execution of the program in working time instead of previous practice. Typically, this includes byte-code translation known as source code to machine code, which is done continuously. Ahead of time integration includes advanced programming language such as C or C ++ [17]. Flutter provides different frameworks, widgets that makes it easy to use and implement code. In this Research paper we are gone discuss about flutter and about its widgets. © 2022 IEEE.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

Optimized Phishing Detection with Recurrent Neural Network and Whale Optimizer Algorithm

引用

computers, Materials & Continua 2024年第9期80卷 4895-4916页

作者： Brij Bhooshan Gupta Akshat Gaurav Razaz Waheeb Attar Varsha Arya Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPuneMaharashtra411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India Ronin Institute MontclairNJ 07043USA Management Department College of Business AdministrationPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Business Administration Asia UniversityTaichung413Taiwan Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)HomantinHong KongChina

Phishing attacks present a persistent and evolving threat in the cybersecurity land-scape,necessitating the development of more sophisticated detection *** machine learning approaches to phishing detection have relied heavily on feature engineering and have often fallen short in adapting to the dynamically changing patterns of phishingUniformResource Locator(URLs).Addressing these challenge,we introduce a framework that integrates the sequential data processing strengths of a Recurrent Neural Network(RNN)with the hyperparameter optimization prowess of theWhale Optimization Algorithm(WOA).Ourmodel capitalizes on an extensive Kaggle dataset,featuring over 11,000 URLs,each delineated by 30 *** WOA’s hyperparameter optimization enhances the RNN’s performance,evidenced by a meticulous validation *** results,encapsulated in precision,recall,and F1-score metrics,surpass baseline models,achieving an overall accuracy of 92%.This study not only demonstrates the RNN’s proficiency in learning complex patterns but also underscores the WOA’s effectiveness in refining machine learning models for the critical task of phishing detection.

关键词： Phishing detection Recurrent Neural Network(RNN) Whale Optimization Algorithm(WOA) cybersecurity machine learning optimization

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：