检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Advances in computing, Communication and Applied Informatics, ACCAI 2023

作者： Doshi, Nisarg Bhavsar, Sagar Rajeswari, D. Srinivasan, R. College of Engineering and Technology Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Tamil Nadu Kattankulathur603203 India College of Engineering and Technology Srm Institute of Science and Technology School of Computing Department of Computing Technologies Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798350315905

In dusty and hazzy circumstances, pictures caputured tend to be unclear. To tackle this challenge researchers have founded different image-dehazing approaches. Lately, high quality pictures which could be used to extract maximal data from autonomous systems are in great demand. In order to minimize the haze from the picture, this research study uses various deep learning (also known as DL) architectures to identify the information recovered and extract key details from the image. The research paper focuses on utilizing deep learning techniques to remove haze from clear *** first phase of the suggested architecture involves applying multiple pre-processing methods, including estimating the airlight, implementing contextual regularization and boundary constraints, as well as contrast enhancement techniques (CS, CLAHE, HE) and Image Fusion. The subsequent goal of this study is to pinpoint the optimal deep learning model that can produce clear images based on the resulting dehazed images. The quality of the dehazed images is evaluated by comparing them with clear images using metrics such as PSNR and SSIM. Experimental findings shows that Alex Net upon the implementation of pre-processing beats other state of the art techniques with regard to PSNR value and holds its own w.r.t SSIM values. © 2023 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Integrated Approach to Detect Cyberbullying Text:Mobile Device Forensics Data

引用

Computer Systems science & engineering 2022年第3期40卷 963-978页

作者： G.Maria Jones S.Godfrey Winster P.Valarmathie Department of Computer Science and Engineering Saveetha Engineering CollegeChennai602105India Department of Computer Science and Engineering School of ComputingSRM Institute of Science and TechnologyChengalpattu603203India Department of Information Technology Saveetha Engineering CollegeChennai602105India

Mobile devices and social networks provide communication opportunities among the young generation,which increases vulnerability and cybercrimes activities.A recent survey reports that cyberbullying and cyberstalking constitute a developing issue among *** paper focuses on cyberbullying detection in mobile phone text by retrieving with the help of an oxygen forensics *** describe the data collection using forensics technique and a corpus of suspicious activities like cyberbullying annotation from mobile phones and carry out a sequence of binary classification experiments to determine cyberbullying *** use forensics techniques,Machine Learning(ML),and Deep Learning(DL)algorithms to exploit suspicious patterns to help the forensics investigation where every evidence contributes to the *** on a real-time dataset reveal better results for the detection of cyberbullying *** Random Forest in ML approach produces 87%of accuracy without SMOTE technique,whereas the value of F1Score produces a good result with SMOTE *** LSTM has 92%of validation accuracy in the DL algorithm compared with Dense and BiLSTM algorithms.

关键词： Mobile forensics cyberbullying machine learning investigation model suspicious pattern

来源：评论

学校读者我要写书评

暂无评论

Comparison of Image Encryption Techniques Using Chaotic Maps and Conventional Cryptographic Techniques 2

Comparison of Image Encryption Techniques Using Chaotic Maps...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Varshney, Aanchal Routh, Pratyusha Sujatha, G. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Networking and Communications Tamil Nadu Chennai India

ISBN: (纸本)9798350328202

In past few years, there has been a great deal of research being done on chaos-based cryptosystems. Chaos-based cryptosystems like Arnold cats map can add security when employed with traditional public key cryptosystems like RSA or El-Gamal, despite the fact that these techniques are not standardized like AES, DES, RSA, etc. Although chaotic-map-based encryption techniques are frequently recommended for picture or video encryption because of their computational efficiency, standard encryption algorithms like DES, AES and RSA have traditionally been the preferred option. The encryption methods like chaos-based picture encryption and conventional cryptographic techniques like AES, DES and RSA are surveyed in this work. There is discussion of the great advancements in image encryption. The comparison is done on the basis of quality of image before and after encryption and decryption using various methods like Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM) and Mean Squared Error (MSE). The PSNR, MSE, and SSIM values of chaotic map-based cryptography don't perform well when compared to traditional methods like RSA, DES, and AES. Also the time complexities and the key sizes of all the algorithms have been compared. The conventional techniques consistently show nearly perfect values, highlighting their stronger security and reliability in data protection and encryption. In contrast, the chaotic map-based approaches fall short in terms of these metrics, indicating that the traditional methods are more effective in ensuring robust security. © 2024 IEEE.

关键词： computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Securing healthcare big data in industry 4.0: cryptography encryption with hybrid optimization algorithm for IoT applications

引用

Optical and Quantum Electronics 2024年第3期56卷 1-29页

作者： Goswami, Chandrashekhar Tamil Selvi, P. Sreenivas, Velagapudi Seetha, J. Kiran, Ajmeera Talasila, Vamsidhar Maithili, K. Department of Computer Science and Engineering School of Computing MIT ADT University Maharashtra Pune India School of Computing Science and Engineering Rajalakshmi Engineering College Mevalurkuppam India Department of Computer Science and Engineering SRK Institute of Technology Vijayawada (A.P) India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering MLR Institute of Technology Telangana Dundigal Hyderabad India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur Dist(A.P) India Department of CSE KG Reddy College of Engineering and Technology Telangana Chilukuru Village India

In recent years, the Internet of Things (IoT) has grown at an exponential rate, transforming the healthcare business and perhaps leading to the creation of healthcare big data. As a result, there is a requirement to safeguard data from being attacked in order to ensure secure data transfer through the network. Cryptography has been discovered to be a simple and efficient method for safeguarding healthcare big data. At the same time, in cryptography, the best key generation process is viewed as an optimization issue that may be addressed with meta-heuristic algorithms. As a result, the main focus of this research is on the investigation of health care data security in IoT using the ASS-JFO-DHEA model, which combines an innovative hybrid Artificial Shuffle Shepherd Integrated Jellyfish optimization (ASS-JFO) algorithm with Digital Homomorphism Elgamal Algorithm (DHEA) encryption for data security. MATLAB software is used to carry out the execution and experiments for this research. On different benchmark images from a healthcare dataset, the ASS-JFO-DHEA model is experimentally validated. The peak signal to noise ratio, root mean square error, encryption time, mean square error, and other metrics are used to assess the *** findings are compared and contrasted as a consequence of this execution, and a variety of encryption algorithms with their optimization techniques from the literature are recognized as having the most intense PSNR values, i.e., 74 dB, generated by the suggested approach. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Cryptography Healthcare Internet of things and cloud Optimization Security

来源：评论

学校读者我要写书评

暂无评论

Smart GPS Based Vehicle Speed Limit Controller on zone identification using Geo-Fencing Algorithm 3

Smart GPS Based Vehicle Speed Limit Controller on zone ident...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Upendra, Modem Reddy, Varun Safa, M. College of Engineering and Technology Srm Institute of Science and Technology School of Computing Department of Networking and Communications Kattankulathur Chennai603203 India

ISBN: (纸本)9798350381931

In light of growing concerns about road safety and the surge in traffic accidents, this project aspires to an Internet of Things smart GPS-based vehicle speed limit controller system. The primary objective is to elevate road safety by harnessing real-time data and automated control mechanisms to enforce speed limits, thereby diminishing incidents of speeding-related accidents. This project adopts a comprehensive approach, integrating both hardware and software components. Vehicle-mounted sensors, encompassing speed sensors and GPS receivers, continually gather real-time data on vehicle speed and location. Furthermore, road condition data is sourced from multiple outlets, such as weather stations and traffic cameras. This data is wirelessly transmitted to a central control unit, which processes and analyzes it. The control unit deploys machine learning algorithms to evaluate vehicle speed limits against predefined speed limits for specific road segments. Depending on this analysis, it transmits control signals back to the vehicle when necessary. These signals can encompass driver warnings, power limitations, or autonomous speed control. These methodologies collectively enabled the creation of an intelligent and adaptable GPS-based vehicle speed control system, offering the potential to significantly enhance road safety by dynamically enhancing road safety regulating vehicle speeds in different zones, ensuring the safety of people and drivers alike. The Smart GPS-based vehicle speed limit controller system has undergone successful development and testing, both in controlled environments and on public roads. The outcomes manifest a remarkable reduction in incidents of speeding and an enhanced adherence to speed limits, exhibiting an accuracy level exceeding 96%. In real-world scenarios, the system effectively mitigates speeding-related risks, leading to a substantial decline in traffic accidents. Its ability to adapt to changing road conditions and. Its scalability ren

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Two-step Runge–Kutta methods for Volterra integro-differential equations

引用

International Journal of Computer Mathematics 2024年第1期101卷 37-55页

作者： Wen, Jiao Huang, Chengming Guan, Hongbo College of Mathematics and Information Science Zhengzhou University of Light Industry Zhengzhou China School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan China

In this paper, we investigate two-step Runge–Kutta methods to solve Volterra integro-differential equations. Two-step Runge–Kutta methods increase the order of convergence in comparing the classical Runge–Kutta method without extra computational cost. First, the local order conditions and convergence theorem are derived. Then, stability properties of two-step Runge–Kutta methods corresponding to the basic and convolution test equations are analysed. Furthermore, one-stage method with order four and two-stage method with order six are constructed and we plot the stability regions. Numerical examples are presented to confirm the theoretical analyses. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enhanced Machine Learning Models for Predictive Maintenance in Industrial IoT 2

Cloud-Enhanced Machine Learning Models for Predictive Mainte...

引用

2nd IEEE International Conference on Trends in Quantum computing and Emerging Business Technologies, TQCEBT 2024

作者： Usharani, R. Sivagami, V.M. Saravanan, K. Pushparani, S. Rekha, K. Sashi Department of Computational Intelligence School of Computing Faculty of Engineering and Technology Srm Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Information Technology Sri Venkateswara College of Engineering Sriperumbudur Tamil Nadu Chennai India Department of Artificial Intelligence and Data Science Care College of Engineering Tamil Nadu Trichy India Department of Computer Science and Engineering Meenakshi College of Engineering Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India

ISBN: (纸本)9798350384277

This study examines the implementation and impact of Cloud-Enhanced Machine Learning Models in the realm of Predictive Maintenance within Industrial Internet of Things (IIoT) settings. Emphasizing the integration of cloud computing with machine learning, the research focuses on how this synergy improves the accuracy and efficiency of maintenance predictions in industrial environments. Key metrics evaluated include prediction accuracy, operational efficiency, cost savings, and reduction in equipment downtime. The study demonstrates a significant increase in prediction accuracy, from 65% to 88%, attributed to the advanced data processing and analytical capabilities of cloud-enhanced machine learning. Operational efficiency saw marked improvements, with a 50% reduction in response times and a 25% increase in maintenance scheduling efficiency, leading to a 20% rise in asset utilization rates. Financially, the implementation led to a 37% reduction in annual maintenance costs and a 40% decrease in both the cost per downtime incident and long-term repair expenses. Most notably, the study recorded a 62.5% reduction in both the duration and frequency of downtime incidents. These results highlight the transformative potential of integrating cloud computing and machine learning in IIoT for predictive maintenance, showcasing significant advancements in predictive accuracy, operational efficiency, cost-effectiveness, and overall reduction in downtime. The study underscores the critical role of technological innovation in advancing industrial maintenance strategies, leading to more proactive, efficient, and economically viable operations. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

SAMIC: Segment Anything Model for Integrated Circuit Image Analysis

SAMIC: Segment Anything Model for Integrated Circuit Image A...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Ng, Yong-Jian Tee, Yee-Yang Cheng, Deruo Gwee, Bah-Hwee College of Computing and Data Science Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350350821

Circuit annotation is crucial in analyzing integrated circuit (IC) images for hardware assurance. While deep learning algorithms perform well in circuit annotation, they are highly reliant on labeled training data, which are extremely costly to obtain. The Segment Anything Model (SAM) excels in segmenting natural images but performs sub-optimally on IC images due to the domain gap between IC images and natural images. In this paper, we introduce SAMI C which extends the application of SAM for effective annotation of IC images. We curated an extensive dataset of IC images from four different devices and developed a novel training methodology for SAM models in IC image segmentation. Our experiments show that SAMIC outperforms the original SAM model by 36.78 % and improves accuracy by 6.35 % compared to the second-best technique. © 2024 IEEE.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Enhanced Detection and Characterization of Pulmonary Nodules 4

Deep Learning for Enhanced Detection and Characterization of...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Lavanya, G. Muthulakshmi, M. Latha, Manohar Keerthinathan, A. Vishal Krishh, P. Sulthana, Sheba Meghana, Meka Kavya Uma Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India Amrita School of Computing Department of Electronics and Communication Engineering Amrita Vishwa Vidyapeetham Chennai India Rajalakshmi Engineering College Department of Electronics and Communication Engineering India

ISBN: (纸本)9798350349900

This study aims to develop, an effective customized Convolutional Neural Network model that can accurately identify areas on CT scans that have lung nodules and those that do not. The study utilizes two datasets, the LUNA-16 dataset for training and the IQ-OTH/NCCD dataset for testing. Additionally, we employ a U-Net model for precise lung nodule segmentation. This segmentation approach aimed to achieve a comprehensive characterization of nodules based on their spatial characteristics. The testing phase involves evaluating the performance of our trained models on the IQ-OTH/NCCD dataset, particularly focusing on localizing nodules in malignant cases. Overall, the research highlights the effectiveness of deep learning in early detection and diagnosis of lung cancer. This work contributes to improving the accuracy and reliability of automated pulmonary nodule detection systems, with a focus on identifying nodules in patients with suspected malignancies. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Fire detection method based on improved DETR 4

Fire detection method based on improved DETR

引用

4th International Symposium on AI, ISAI 2024

作者： Ge, Ruize Hu, Xiaoyin Xiao, Duo Zhejiang University College of Contral Science and Engineering China Hangzhou City University School of Information and Electrical Engineering Hangzhou China Hangzhou City University Hangzhou School of Computer and Computing Science China

ISBN: (纸本)9798350342482

Fire, as a type of disaster, poses a significant threat to both life and property safety. Therefore, timely and accurate detection of fire occurrences is of utmost importance. However, current fire detection methods that rely on traditional sensors suffer from limitations such as a high false alarm rate and extended response time. In this manuscript, we propose a novel fire detection method based on an enhanced version of DETR that leverages flame detection. Our approach entails several key modifications. Firstly, we replace the bounding box loss function of the original DETR with the alpha-CIoU loss function. This substitution enhances the accuracy and efficiency of our fire detection method. Secondly, we introduce relative position encoding to replace the sine-cosine position encoding in the transformer module. This adjustment aims to improve the model's ability to capture spatial relationships between flame instances, resulting in more precise detection outcomes. Furthermore, we incorporate multiscale features by modifying the backbone of DETR. This addition enables our algorithm to effectively handle variations in flame sizes and appearances, contributing to improved detection performance across different fire scenarios. Finally, we apply gradient clipping to the DETR optimizer to stabilize the training process and mitigate the potential issue of exploding gradients. To evaluate our proposed method, we train and test the model using a self-generated dataset specifically tailored for flame detection. Experimental results indicate that our improved DETR algorithm achieves an average accuracy of 92.27%, which represents a substantial 3.81% enhancement over the original DETR. Moreover, through ablation experiments, we demonstrate the effectiveness of each individual improvement in our approach. © 2024 IEEE.

关键词： Premixed flames

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：