检索结果-内蒙古大学图书馆

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Kumar, Dubasi Pavan Bhadula, Shuchi Al-Farouni, Mohammed Varshney, Neeraj Sharma, Vishal Saraswat, Manish National Institute Of Technology Integrated Master Of Science Mathematics Department Of Mathematics Patna India Graphic Era Deemed To Be University Department Of Computer Science & Engineering Dehradun India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Gla University Department Of Computer Engineering And Applications Mathura India Lovely Professional University Phagwara India Lloyd Institute Of Engineering & Technology Greater Noida India

ISBN: (纸本)9798350366846

This investigation explores the viability of four noticeable models, specifically Pix2Pix, Neural Style Transfer (NST), Fast Neural Style Transfer (FastNST), and CycleGAN, within the space of aesthetic style exchange. The think about envelops a fastidious assessment of these models, investigating their capabilities in generating outwardly engaging and elaborately reliable pictures. Through broad tests and quantitative evaluations, Pix2Pix developed as a strong choice, accomplishing a Crest Signal-to-Noise Ratio (PSNR) of 26.78 dB, a Basic Likeness List (SSIM) of 0.832, and a Fréchet Initiation Separate (FID) of 54.21. NST, exceeding expectations in style devotion, achieved a PSNR of 29.45 dB, an SSIM of 0.905, and an FID of 72.03. FastNST, known for its real-time preparation, illustrated an adjusted execution with a PSNR of 28.12 dB, an SSIM of 0.892, and an FID of 68.54. CycleGAN, outlined for unpaired picture interpretation, accomplished a PSNR of 27.65 dB, an SSIM of 0.874, and an FID of 63.72. The results give profitable experiences into the comparative qualities and weaknesses of these models, educating their appropriateness in different artistic assignments. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Approaches to Secure Mobile Devices in Wireless Networks 15

Exploring the Approaches to Secure Mobile Devices in Wireles...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Pandian, Rajesh Garima Jayadurga, R. Karnik, Madhuri P. Grover, Madhur Naval, Preeti Karnataka Bangalore India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Master of Business Administration Prince Shri Venkateshwara Padmavathy Engineering College Chennai127 India Department of Computer Engineering Vishwakarma Institute of Technology Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350370249

This paper explores various approaches used to relaxed mobile devices from intrusions in wireless networks. The contemporary strategies contemporary security, inclusive of encryption, authentication and authorization strategies, is discussed in detail. The advantages and downsides latest approach are mentioned to decide the satisfactory technique for mobile tool safety. Furthermore, numerous emerging security measures such as the ones primarily based on biometrics and context-consciousness are evaluated and compared. The abilities and obstacles trendy method are analyzed relative to these options. These research paper goals to discover new possibilities for security contemporary cell devices in Wi-Fi networks for reinforcing relaxed facts transactions and conversation. The paper outlines the contribution contemporary security methods to enhance the security degree cutting-edge cellular devices, and suggest effective strategies to defend towards capability security threats. Similarly, the paper will offer an in-depth survey present day security technology and their implementation challenges in the wireless domestic community surroundings. ©2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Dynamic Trust Management in IoT Networks using Reputation-Based Systems

Dynamic Trust Management in IoT Networks using Reputation-Ba...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Naidu, D J Samatha Jain, Upma Shruthi, S. Rao, K. B. V. Brahma Iqbal, Syed Mohammad Uzair Natrayan, L. Annamacharya Pg College of Computer Studies Department of Master of Computer Applications India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Bms Institute of Technology and Management Department of Artificial Intelligence and Machine Learning Bengaluru India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering India Symbiosis Law School Department of Law Pune India Simats Saveetha School of Engineering Department of Mechanical Engineering India

ISBN: (纸本)9798350375442

The Internet of Things (IoT) enables intelligent data exchange across many kinds of interconnected devices in a diverse and unpredictable physical setting. The Internet of Things (IoT) network used in this study is a cluster-based sensor network that includes a base station and an application server that offers various services in a cloud setting. In this setting, assaults may occur in both device-to-device and user-to-device communication. For pervasive devices with limited resources, the use of conventional encryption techniques to address this problem is not practical. In addition, the majority of current trust-based security solutions either address the user level or the devices level. Therefore, this study aims to tackle environment-specific security concerns at the device and user levels in light of the environment's inherent dynamic and dispersed nature. This research explored the usage of a Trust Based Security Framework (TBSF) and Reputation Based Systems in the Internet of Things (IoT) to accurately describe the actions of devices and users. Fuzzy logic was used to calculate both the device trust and the user trust. A trust-based access control system, secure cluster head selection, and safe routing were all built using these trust values. At first, the security of device-to-device communication was addressed by the design and effective implementation of the Trust Aware Device Access Control System (TADACS). © 2024 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Smart Auto Image Captioning Using LSTM and Densenet Network 6

Smart Auto Image Captioning Using LSTM and Densenet Network

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Arumugam, M. Vijayakumar, P. Siddharrth, G.M. Rohini, J. Karthikeyan, A. Rohith Bhat, C. Kongu Engineering College Department of Computer Technology - PG Perundurai India Kongu Engineering College Department of Master of Computer Applications Tamil Nadu Perundurai638060 India Erode Sengunthar Engineering College Department of Computer Science and Engineering Thuduppathi638057 India PSNA College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul624622 India Saveetha School of Engineering Department of Computer Science and Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (纸本)9798350304480

The integration of semantic attention increase photo captioning ability. The premise underlying semantic attention-based techniques is that the model should prioritize words or qualities with high semantic value. Prior studies focused on the attribute detector and the captioning network as distinct entities. This hampers the best use of semantic data. Image captioning is the computational process of producing accurate written descriptions of an image's or video's visual content. Captioning images makes it easier to construct contextualized interpretations, allowing people to situate photographs within a larger context. Using photo captions can be useful in a variety of contexts, such as conducting research with an unlabeled image collection or attempting to identify. previously unknown patterns. Subtitles added to the photos using a Deep Learning Model. Recent advances in the fields of deep learning and natural language processing have made it much easier to generate captions for input photographs. This study will use neural networks to generate image captions on their own. The Long Short-Term Memory (LSTM) model, a type of recurrent neural network, used as an encoder, together with a pre-trained lexicon and visual attributes. This enables the extraction of image data and the generation of captions. © 2023 IEEE.

关键词： Deep Learning Model Densenet Network Long Short-Term Memory Remote Sensing

来源：评论

学校读者我要写书评

暂无评论

Prediction of Traffic Accidents Using Deep Learning Ensemble Model

Prediction of Traffic Accidents Using Deep Learning Ensemble...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Sekhar, G Soma Mahadik, Shubhangi Ramana, Attili Venkata Chandra Shaker Reddy, Pundru Pughazendi, N. Asif, S. Computer Science and Engineering Vardhaman College of Engineering Telangana Hyderabad India Bharati Vidyapeeth's Institute of Management & Information Technology Master of Computer Applications Navi Mumbai India Hyderabad India SR University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Computer Science and Engineering Panimalar Engineering College Tamil Nadu Chennai India Marri Laxman Reddy Institute of Technology and Management CSE-Data Science Telangana Hyderabad India

ISBN: (纸本)9798350319200

Because of the widespread negative effects that traffic accidents can have on people's lives, the study of how to assess and anticipate them using cutting-edge technology is an important area of study. The research of traffic accidents has traditionally relied on data made public by traffic-entities and road-police forces. However, with the advent of social-media, researchers now have access to detailed, real-time data on road accidents occurring across a region, allowing for more comprehensive analyses that take into account previously unreported incidents. This paper uses an ensemble-Deep-Learning(EDL) strategy made up of Gated-Recurrent Units(GRUs) and Convolutional-Neural-Networks(CNNs) to offer a model to forecast traffic accidents utilizing data mined from social-media and the open web. The acquired results are compared to those of published baseline methods and other researchers. The outcomes are encouraging, showing that the proposed EDL approach outperforms the conventional models and other DL approaches published in the literature when applied to the problem setting. Authorities in charge of preventing accidents on the roads can use the data generated by the program. © 2023 IEEE.

关键词： DL ML risk prediction traffic accident traffic accidents

来源：评论

学校读者我要写书评

暂无评论

Unified hybrid quantum classical neural network framework for detecting distributed denial of service and Android mobile malware attacks

引用

EPJ Quantum technology 2025年第1期12卷 1-29页

作者： S, Sridevi B, Indira S, Geetha S, Balachandran Kar, Gorkem Kharbanda, Shangirne School of Computer Science and Engineering Vellore Institute of Technology Chennai India Central Library Hindustan Institute of Technology and Science Chennai India Computer Science & Cybersecurity University of Central Missouri Warrensburg USA Master of Engg Gina Cody School of Engineering and Computer Science Concordia Institute for Information Systems Engineering Montreal Canada

The rise of advanced networking and mobile technologies has improved flexibility in Software Defined Networking (SDN) management and mobile ecosystems but it has also introduced vulnerabilities like Distributed Denial of Service (DDoS) attacks and Android malware. In this research, we propose a Hybrid Quantum Classical Neural Network (HQCNN) framework that operates with a Dressed Quantum Circuit (DQC) to achieve efficient detection and classification of threats. The input pipeline of the HQCNN integrates Wavelet Transforms based feature pre-processing, Convolutional Neural Network based feature extraction, Linear Discriminant Analysis (LDA) for dimensionality reduction, and quantum layers for enhanced classification with less computational complexity. Experiments were conducted on the SDN DDoS Attack Dataset and the CCCS-CIC-AndMal2020 Static Dataset. Two different model variants were devised for binary and multiclass classification problems addressing various cybersecurity issues. The binary HQCNN model for SDN-based DDoS detection was implemented on AWS Braket’s real Quantum Processing Unit (QPU), achieving 99.86% accuracy, 99.85% precision, 100% recall, and a 99.88% F1-score, thereby outperforming the classical Convolutional Neural Network (CNN). The multiclass HQCNN, on the other hand, attains accuracy of 93.56%, 94.38%, and 95.13% on the 15-class, 14-class, and 12-class versions of CCCS-CIC-AndMal2020 Static, respectively, hence outperforms all existing methods. These results show that HQCNN is efficient, scalable, and very much applicable in cybersecurity, validating its real-world use effectiveness applicability in threat detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Milling Force Prediction of Titanium Alloy Based on Support Vector Machine and Ant Colony Optimization

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2021年第2期48卷 1-12页

作者： Zhang, Xiaoxia Yu, Ziqiao Hu, Yinyin Yang, Jiao A Professor of School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan11041 China A Master Student of School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China

Milling force prediction of titanium alloy plays an important role in titanium alloy milling process. In the article, the milling process of titanium alloy materials is analyzed, and this material quality is affected directly by the milling force. Support vector machine (SVM) has shown prominent performance for many real-world problems. However, SVM computational complexity increases, as the number of samples increases. How to effectively apply it to massive datasets is still a serious challenge. Although there are some literatures on parameter optimization techniques of SVM regression, the performance of this model still needs to be further studied and improved. We present a new milling force predicting model, namely ACO&SVM, which integrate SVM regression with ACO algorithm to enhance the prediction accuracy of milling force for mill process of titanium alloy. The primary innovation feature of hybrid model is to apply the ACO to automatically determine parameters of SVM regression model. In addition, as being applied to discrete optimization, to solve continuous optimization problems, ACO algorithm needs to transform continuous variables into discrete ones by discretizing of continuous variables. The results have shown that proposed ACO&SVM model yields better prediction accuracy, and thus it can be widely applied to the fields of material processing optimization. © 2021. All Rights Reserved.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Driven - Pest Classification and Sustainable Agriculture 3

Deep Learning Driven - Pest Classification and Sustainable A...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Kumar, M. Sirish Usha, R. Reddy, B. Rama Kantha Ramachandra, S. Prakash, P. Jaya Swetha, B. Mohan Babu University School of Computing Dept. of Data Science India Madanapalle Institute of Technology and Science Madanapalle India Sri Venkateswara College of Engineering Tirupati India Mother Theresa Institute of Engineering and Technology Palamaner India Sri Venkateswara College of Engineering Department of It Tirupati India Mohan Babu University Dept. of Master of Computer Applications India

ISBN: (纸本)9798331509675

This study introduces a system designed to identify pests in crops and classify them as either beneficial or harmful. The project begins by providing a comprehensive overview of various pest identification methods, analyzing their strengths and limitations. To address the problem, a categorization approach is proposed that incorporates convolutional neural networks (CNN) to build the pest identification and classification model. The model was trained using a dataset containing images of different pest species. Extensive testing was conducted on a large dataset, and the system's performance was validated against multiple traditional classification models. The proposed framework achieved a classification accuracy of 90%, outperforming conventional methods. This research highlights agriculture's vital role in the economy and underscores the potential of advanced technologies in supporting sustainable farming practices. © 2025 IEEE.

关键词： Agriculture Sustainability Classification Accuracy Classification Model Convolutional Neural Network (CNN) Pest Classification

来源：评论

学校读者我要写书评

暂无评论

Hybrid Convolutional Neural Networks for Enhanced Detection of Mango Leaf Diseases 6

Hybrid Convolutional Neural Networks for Enhanced Detection ...

引用

6th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2024

作者： Porna, Shweta Bhattacharjee Kabir, Md. Firoz Rana, Md. Imran Chowdhury Sajol, Md. Saiful Islam Roy, Tonmoy Khan, Mohammad Aman Ullah Adnan, Md. Al Bhavani, Girigula Durga Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh Master's in Information Technology University of the Cumberlands United States Bachelor of Business Administration International American university Los Angeles CA United States Louisiana State University Department of Computer Science and Engineering LA United States Data Analytics & Information Systems Utah State University Logan United States Brac University School of Data and Sciences Department of Computer Science and Engineering Dhaka1212 Bangladesh Noakhali Science And Technology University Bsc in software engineering Bangladesh Andhra Pradesh Amaravati522237 India

ISBN: (纸本)9798331505790

The classification of mango leaf diseases is critical for effective disease management and ensuring high-quality yields in mango cultivation. This paper presents a comprehensive study on using deep learning techniques to classify various mango leaf diseases, leveraging convolutional neural networks (CNNs) and hybrid models. A total of 7,524 images were used in our study. These included 4,000 training samples and 3,524 testing samples. The images were split into eight groups, which were powdery mildew, cutting weevil, anthracnose, bacterial canker, sooty mold, gall midge, healthy, and die back. The suggested method starts with feature extraction using VGG19 and MobileNetB1, then classification using both standalone models (ResNet50V2 + EfficientNetB1 and VGG16 + MobileNetB1). We employed data augmentation techniques like random brightness adjustment, rotation, and flipping to enhance the robustness of the model. We conducted hyperparameter tuning using hyperband and Bayesian optimization to optimize the model's performance. Experimental results demonstrate that the hybrid models achieved superior performance, with ResNet50V2 and EfficientNetB1 attaining a perfect accuracy of 100 % on the test set. These findings highlight the potential of deep learning techniques to improve the accuracy and reliability of mango leaf disease diagnosis, contributing significantly to the advancement of precision agriculture. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Identification and Segmentation of Polyp Using Deep Learning Approaches 4

Identification and Segmentation of Polyp Using Deep Learning...

引用

4th IEEE Asian Conference on Innovation in technology, ASIANCON 2024

作者： Yaligar, Suman Kallur, Shanta S. Patil, Vijeeta Thotad, Puneeth N. K. L. E. Institute of Technology Dept. of Computer Science and Engineering Hubballi India Visvesvaraya Technological University Belagavi India K. L. E. Institute of Technology Dept. of Master of Computer Applications Hubballi India

ISBN: (纸本)9798350354218

Colorectal cancer (CRC) is a major health problem, and accurate detection of polyps plays a major role in its prevention and treatment. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had issues capturing global context and lacked robustness to complex scenarios. With the rise in deep learning, more and more rigorous segmentation of medical images dependent on deep learning networks have emerged, making significant progress in this field. This paper aims to develop an efficient model for polyp detection and segmentation using machine learning techniques. The model will assist clinicians in accurately locating and segmenting polyp regions, which will help in the prevention and treatment of CRC. The work will first review traditional methods that are dependent manually on extracted features and deep segmentation algorithms, then detail benchmark datasets relevant for the topic. The two datasets Kvasir-SEG and CVC-ClinicDB are used for implementation. Specifically, we carried out a comprehensive evaluation of recent deep learning CNN methods. The model gave an accuracy with Pranet method of about 99% in polyp segmentation and identification respectively. © 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

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：