检索结果-内蒙古大学图书馆

5th International Conference on Circuits, Control, Communication and computing, I4C 2024

作者： Satya Balaji, Bandaru Rohan Varma, Alluri Jayanth Ashwini, K. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331528539

With the development of advanced communication ensuring the secure transmission of images has become more and more important. This research suggests a novel approach for digital image encryption and decryption that combines Linear Feedback Shift Register (LFSR) encryption, recursive image splitting and shuffling in order to increase security. Test image is divided into blocks and each block is encrypted using a different LFSR key. The encrypted blocks are then joined to create a single encrypted image that is ready to be sent. The receiver uses a machine learning model that has been pre-trained to identify the specific LFSR key used for each block after breaking the image back up into its component blocks. This allows for precise decryption. The viability of the encryption process is assessed using entropy analysis, histogram comparison and pixel relationship etc. The results show that the encrypted images have a notable disruption of spatial relationships, a high degree of unpredictability, and significant interference with spatial relations. Furthermore, evaluation is done on the performance of multiple Support Vector Machine (SVM) models with different kernel functions. The results indicate that the SVM with a radial basis function (RBF) kernel performs best in terms of key identification accuracy. This thorough analysis demonstrates the suggested encryption method's resilience and its potential for safe image transfer across a range of applications. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Facial Grid Environment for Vitiligo Detection: A Deep Reinforcement Learning Perspective 2

Facial Grid Environment for Vitiligo Detection: A Deep Reinf...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Adwayan, P.C. Anfas Hassan, V. Suresh, Navneeth Nisha, K.S. Sha, Akhbar Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350360523

This research addresses the challenging task of vitiligo detection within facial images through the lens of Deep Reinforcement Learning (DRL). Leveraging the Skin Disease dataset from Kaggle, our study focuses on the integration of three distinct convolutional neural network architectures - ResNet, VGG, and EfficientNet - within the DRL framework. Facial landmarks, crucial for spatial awareness, were extracted using OpenCV as a preprocessing step. The DRL agent navigates through a grid overlaying facial images, with states corresponding to grid cells, to reach the vitiligo-affected region and maximize cumulative rewards. Analysis of the models revealed ResNet's superior stability in the loss curve, indicative of its effective feature learning. The classification accuracy further reinforced ResNet's prominence, reaching an impressive 97%, outperforming VGG (94.5%) and EfficientNet (95.3%). While VGG and EfficientNet demonstrated competitive performances, ResNet's robustness and accuracy position it as the preferred architecture for vitiligo detection in facial images. This study contributes to the burgeoning field of dermatological diagnostics by showcasing the efficacy of DRL and different CNN architectures in automating vitiligo detection. The findings not only advance our understanding of the interplay between deep learning and dermatology but also lay the foundation for more accurate and efficient models in the broader landscape of skin disorder identification. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted Internet of Vehicles over Licensed and Unlicensed Spectrum: Architecture, Intelligent Resource Management, and Challenges

引用

IEEE Internet of Things Magazine 2023年第3期6卷 78-84页

作者： Su, Yuhan Liwang, Minghui Chen, Zhong Wang, Xianbin School of Electronic Science and Engineering Xiamen University China School of Informatics Xiamen University China Western University Department of Electrical and Computer Engineering London Canada

Benefited from their flexibility and on-demand deployment capability, unmanned aerial vehicles (UAVs) have emerged as critical aerial communication platforms in future Internet of Vehicles (IoV). However, limited spectrum resources can lead to unsatisfying data rate of IoV, which thus incur large latency, especially under congested IoV network conditions. Although UAVs and road side units (RSUs) can work within the same spectrum and increase spectral efficiency, mutual interference becomes unavoidable. To this end, this article develops a heterogeneous network architecture, in which a UAV-assisted IoV system coexists with a Wi-Fi system: the RSUs can properly occupy unlicensed spectrum to increase the capacity of the UAV-assisted IoV system while mitigating interference, without affecting the performance of the Wi-Fi system. A case study of resource management over licensed and unlicensed spectrum is investigated under the proposed architecture, where time and power are jointly optimized to maximize the sum user satisfaction of the system. We further provide an intelligent solution to tackle the problem in the considered case study. Simulations demonstrate that our proposed case can efficiently improve the sum user satisfaction of the system. Key challenges and opportunities for UAV-assisted IoV over licensed and unlicensed spectrum are discussed, while recommendable future research directions are investigated. © 2018 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of the Dynamic Source Routing Protocol with Packet Numbering for Efficient Route Discovery, Improved Packet Delivery and Routing Optimization in Dynamic Network Scenarios 13

Design and Implementation of the Dynamic Source Routing Prot...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Kannan, Srinidhi Suryamritha, M. Balaji, Varshini Rajesh, M. Sreevidya, B. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350305463

Dynamic Source Routing (DSR) protocol is mostly used in the wireless mesh network, where all the nodes are in a mesh topology, it is also used in Mobile ad-hoc Networks (MANETs). As it is in mesh topology that the communication can be directly established between the nodes or utilizing intermediate nodes. The proposed work mainly focuses on the necessary modifications to be made in the DSR protocol that is to add extra information to the packet format - a Packet Number, which is assigned when the packet is sent. This is verified by simulating a wireless network using network simulator NS2. © 2024 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based Approach for Estimating Object Interactions in Surveillance Video Synopsis 2

A Graph-Based Approach for Estimating Object Interactions in...

引用

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

作者： Sood, Varnika Ray, Santosh Kumar Mahato, Kiran Kumar Sidharth, A.V. Namitha, Kalakunnath Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350328202

Video synopsis is a technique that condenses surveillance videos into compact equivalent videos. The objective of this paper is to identify and group related moving objects (also referred to as tubes) in a video using a graph-based video synopsis method. To do this, we first develop an interaction matrix to determine the degree of pairwise interaction between the tubes. A tube-set generation graph is then suggested as a way to combine linked tubes into a single tube set. Publicly available video datasets have been utilized by us to demonstrate the effectiveness of our method. Our technique has come up with another way of video synopsis;that is, focusing on the context of the original movie and picking out important details. This makes it a reliable surveillance approach as it greatly improves security efficiency through fast and accurate compression of videos. Moreover, our method grounded in graph preservation eases our understanding of what connects various elements in a film or video. © 2024 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Shallow-Sec: Malware Detection in Real-Time Devices using Feature Weightage and Shallow Learning Models 5

Shallow-Sec: Malware Detection in Real-Time Devices using Fe...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Priyanka, Panaganti Udhayakumar Deepak, K. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350379945

In the domain of mobile security, particularly in APK (Android Application Package) malware detection, ensuring robust threat identification is critical for safeguarding user devices and sensitive data. This study addresses the need for a reliable Mobile Intrusion Detection System (MIDS) by harnessing advanced machine learning techniques. We advocate for employing tested models such as Logistic Regression, Decision Tree, and XGBClassifier, alongside the top-performing Random Forest (RF) model, which achieved an impressive accuracy of ninety-eight-point six percent. To enhance model performance, we utilize feature selection techniques like Recursive Feature Elimination (RFE) and hyperparameter optimization. The datasets chosen for training and evaluation, including real-world malicious and benign APKs, yield accuracies around ninety five percent. Furthermore, diverse APK datasets, including benchmarks and real-time streams, are used for rigorous testing. By leveraging optimized models and features, our study ensures exceptional performance in detecting various forms of APK malware, thus fortifying the reliability and efficacy of MIDS in real-world scenarios. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

An Incremental Naive Bayes Learner for Real-time Health Prediction 2

An Incremental Naive Bayes Learner for Real-time Health Pred...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Appasani, Deepthi Bokkisam, Charan Sai Surendran, Simi Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

Healthcare monitoring systems have improved with the Internet of Things and machine learning prediction models. Traditional batch machine-learning approaches cannot generate an effective model since most data will be continuous and real-time. Real-time medical data processing is challenging since the entire data is unavailable during prediction. Here, a continuous model adaptation based on incremental learning is demanded. The development of such a system can significantly improve patient outcomes and reduce healthcare costs. This paper proposes an Incremental Naive Bayes Learner that can handle concept drifts in data. The algorithm keeps a sliding window of data constantly updated as new data is added. The adaptive window size determines how much data is used to train the model at any given time. After processing each chunk of data, the algorithm calculates the model's accuracy. The system detects a concept drift and dynamically updates the training set if the accuracy drops below a predefined threshold. We conducted a comparative evaluation of state-of-the-art batch and incremental learning algorithms on different medical datasets, demonstrating the impact of incremental learning. The results demonstrate the effectiveness of our approach: the Agrawal dataset achieved the highest accuracy at 66.6%, followed by Dialysis at 61.6%, while Liver and HCC achieved 50% and 58.3% accuracy, respectively. This approach ensures a sustained high level of accuracy in healthcare monitoring systems over time, even amidst concept drift. © 2024 Elsevier B.V.. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Parser for TINY Language 8

Parser for TINY Language

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Priya, Ch. Durga Raju, Ch. Vikram Daniel, A. Issac Patel, G. Rishik Belwal, Meena Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer science and Engineering Bangalore India

ISBN: (纸本)9798331505462

This study provides a novel method to generate a compiler, which translates a program using TINY language. TINY language is a simple programming language which is designed to understand the basic concepts of compiler. A compiler is a type of program which is designed to convert the code written in high-level language into machine language that is understandable by the computer. The procedure for building a parser requires various sub-tasks, there are a list of operations that include parsing or splitting the code into tokens, checking's the code's syntax using grammar rules, understanding, interpreting and optimizing the provided code and generating the execution-ready code by the performance of last assembling. In order to face the challenges of compiler construction, which includes rule-based complex grammar, error handling, and fast tokenization, the python programming language is implemented for developing pyLexer(tokenization) and pyParsing (syntactic analysis) libraries. Lexer is used for matching regular expressions to return corresponding tokens(lexemes), while parser is supposed to check whether the given syntax is according to the grammar rules or not through recursion. Web application is created for this using Streamlit, which provides users with many useful features like text rendering capability, error highlighting and code suggestions. © 2024 IEEE.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Visual Error Detection System (VEDS) Leveraging Convolutional Neural Networks for Early Detection of Ocular Abnormalities to Mitigate Vision-Related Complications

Design and Development of Visual Error Detection System (VED...

引用

2024 International Conference on Computational Intelligence and computing Applications, ICCICA 2024

作者： Krishna, Kaivaram Sivarama Deepak Kumar, Bommala Reddy, Morumpalli Deekshith Saketh, Ch. Sreevidya, B. Rajesh, M. Amrita School Of Computing Department Of Computer Science And Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350306446

Ocular disorders are one of the severe eye disease The proposed system is to design and develop an automated system which captures the patient's eye image and uses the benefits of Convolutional Neural Networks (CNN) to predict whether the patient suffers from ocular eye disorders or not. The functionality integrates MongoDB database administration with a visual error detection system. The model is employed in a web-based platform that enhances the usefulness of MongoDB overall by utilizing convolutional neural networks (CNN) to interface with it smoothly. The CNN was selected based on its accuracy and trained on several datasets that included around 5000 photos for each category of eye illness from reputable databases including Eye Recognition, IDRiD, and HRF. Instant eye deployment is possible with the user-friendly website while retinal pictures load. Integration with MongoDB enhances user experience, saves and retrieves diagnostic data, and manages data better. Numerous outcomes supported the model's efficacy and indicated a significant advancement in the early diagnosis and treatment of ocular disorders. © 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

Compressive Sensing Based Image Compression-Encryption Scheme Using Triangular Series and Novel Chaotic Map 3

Compressive Sensing Based Image Compression-Encryption Schem...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Sai, Kolagani Yeshwanth Ashwini, K. Karthik, Vadde Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331518592

In recent years communication through image has evolved so much that we must make sure that secret message stages should not be leaked. Hence the use of compression-encryption algorithms is of utmost necessity. In this paper, we present a unique chaotic map and encryption algorithm that can provide a robust yet efficient method for securing digital images against unauthorized access. The proposed encryption scheme begins by employing the triangular series to rearrange the pixel values of the input image. For the encryption process to offer a high level of security, a chaotic map is designed to display desirable qualities like ergodicity, unpredictability, and sensitivity to the initial key values. image compression through the Compressive sensing approach because of its lightweight implementation and suitability for resource-constrained environments like real-time image processing applications and Internet of Things devices. To prove the robustness of the chaotic map and encryption algorithm, many quantitative evaluation metrics such as entropy, correlation, bifurcation etc are used. © 2024 IEEE.

关键词： Image compression

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：