检索结果-内蒙古大学图书馆

Adaptive sail fish optimizer based optimized region selection for robust video steganography

International Journal of Information Technology (Singapore) 2025年第4期17卷 2417-2427页

作者： Babu, J. Suresh Niranjana, G. Ramana, Kadiyala Department of Computing Science & Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur Chengalpattu India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chengalpattu India Department of Artificial Intelligence and Data Science Chaitanya Bharathi Institute of Technology (Autonomous) Hyderabad India

Securing data transmission in a digital era is a difficult one due to the broad application of the Internet, personal computers, and mobile phones for communication. Traditional video steganography techniques sometimes fail to identify the best pixels for encoding hidden data, resulting in lowerquality and robustness. To solve this issue, this article proposes an innovative steganography technique that improves the security and quality of data hiding. The proposed method takes cover video and secret images as input. The Structural Similarity Index Measurement (SSIM) first collects key frames from the input video. The adaptive sailfish optimizer (ASFO) is then used to find the best regions within these keyframes to insert the secret data in. To improve security, the discrete wavelet transform (DWT) is applied to the specified region, and the LL band is used for the hiding process. The secret image is encrypted by Adaptive elliptical curve cryptography (AECC) and transformed to binary bits, which then get embedded in the chosen band. This method leads to the construction of a stego-video. The extraction procedure is repeated using the same approach, which ensures secure and robust data transmission. Performance metrics, including PSNR, BER, NAE, TAF, and NC are analyzed to compare each method's efficacy. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： Adaptive elliptical curve cryptography And stego-video Discrete wavelet transform Structural similarity index measurement Video steganography

来源：评论

学校读者我要写书评

暂无评论

Leveraging HPC with GAN-CNN Integration for Enhanced Tuberculosis Detection using Synthetic Image Generation 3

Leveraging HPC with GAN-CNN Integration for Enhanced Tubercu...

引用

3rd International Conference on Automation, computing and Renewable Systems, ICACRS 2024

作者： Manasa, Pokala Veeramalla, Vaishnavi Vanusha, D. Vathana, D. Robinsha, Delsi S. Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India

ISBN: (纸本)9798331532420

Tuberculosis (TB) remains a significant global health challenge, especially in remote areas with limited medical resources. Early and accurate diagnosis is crucial to control its spread. This project harnesses high-performance computing (HPC) to address two key issues: managing unreliable medical data and improving TB diagnosis. Given the imbalance between healthy and TB-affected samples, Generative Adversarial Networks (GANs) are used to generate synthetic images, enriching the dataset and making it more diverse. This helps train Convolutional Neural Networks (CNNs), which are highly effective in medical image analysis. By leveraging HPC, we accelerate the training of CNNs on large, augmented datasets, significantly reducing processing time while maintaining accuracy. This system improves TB detection by combining GAN-enhanced data and CNN models, enabling faster and more reliable diagnosis. © 2024 IEEE.

关键词： X ray apparatus

来源：评论

学校读者我要写书评

暂无评论

Enhancing sarcasm detection through grasshopper optimization with deep learning based sentiment analysis on social media

引用

International Journal of Information Technology (Singapore) 2025年第3期17卷 1785-1791页

作者： Srinu, Nidamanuri Sivaraman, K. Sriram, M. School of Computing Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai 600073 India

Detecting sarcasm in social media presents challenges in natural language processing (NLP) due to the informal language, contextual complexities, and nuanced expression of sentiment. Integrating sentiment analysis (SA) with sarcasm detection enhances the understanding of text meaning. Deep learning (DL), utilizing neural networks to grasp lexical and contextual features, offers a method for sarcasm detection. However, current DL-based sarcasm detection methods often overlook sentiment semantics, a crucial aspect for improving detection outcomes. Therefore, this study develops a new sarcasm detection using grasshopper optimization algorithm with DL (SD-GOADL) technique. The SD-GOADL technique aims to explore the patterns that exist in social media data and detect sarcasm. To obtain this, the SD-GOADL technique undergoes data pre-processing and Glove based word embedding technique. Next, the classification of sarcasm takes place using deep belief network (DBN) system. For enhancing the detection results of the DBN approach, the SD-GOADL technique uses GOA for hyperparameter selection process. The stimulation outcome of the SD-GOADL technique is tested on a sarcasm dataset and the results highlight the significant performance of the SD-GOADL technique compared to recent models. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： Deep learning Grasshopper optimization algorithm Natural language processing Sarcasm detection Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Cognition2Vocation: meta-learning via ConvNets and continuous transformers

引用

Neural computing and Applications 2024年第21期36卷 12935-12950页

作者： Kamran, Sara Hosseini, Saeid Esmailzadeh, Sayna Kangavari, Mohammad Reza Hua, Wen School of Computer Engineering Iran University of Science and Technology Tehran Iran Faculty of Computing and Information Technology Sohar University Sohar Oman Department of Computing The Hong Kong Polytechnic University Hong Kong

Estimating the suitability of individuals for a vocation via leveraging the knowledge within cognitive factors comes with numerous applications: employment resourcing, occupation counseling, and workload management. Accordingly, the enterprises aim to hire the most suitable person from a massive array of similar applicants, maximizing performance and minimizing the gap between strategic indicators and predefined targets. While cognitive factors signify the best-suited person from similarly skilled workers, inferring pertinent latent cues from noisy and growing social network contents is time-intensive. To tackle the challenges involved, we propose a framework that, on the one hand, extends influential features based on the correlations between cognitive cues and, on the other hand, leverages a novel continuous transformer to mitigate the overlapping and approximation issues in discrete modeling. Rather than relying on discrete patterns that may evolve frequently, we use continuous elements that include not only numerous aggregating components but also sense minor irregular fluctuations. In a hybrid manner, we fuse multiple base models to transfer a higher representation to the meta-learning unit, agglomerating outputs from gradient boosters and the ConvNets. The experimental results show that our proposed framework can outperform trending vocation estimation methods by 1.36% in F1-Score and approximately 1% in accuracy. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Sybil Assault Detection in VANET with Efficient Network Analysis

Sybil Assault Detection in VANET with Efficient Network Anal...

引用

2024 MIT Art, Design and Technology school of computing International Conference, MITADTSoCiCon 2024

作者： Mukherjee Mathur, Shubhra Jadhav, Nagesh Gupta, Ravindra Design and Technology University Pune Sarvepalli Radakrishnan University School of Computing MIT Art Department of Computer Science and Engineering Bhopal India Design and Technology University School of Computing MIT Art Department of Computer Science and Engineering Pune India Sarvepalli Radakrishnan University School of Computing Department of Computer Science and Engineering Bhopal India

ISBN: (纸本)9798350362879

A developing technology that can be highly helpful for both intelligent transportation services and safety and security is the Automobile ad hoc network, or VANET. Nevertheless because of the great mobility and wireless connection of cars, there are numerous security risks that jeopardize people's safety and security when driving. The Sybil assault, in which the perpetrator makes up a false identity to obtain significant influence within the network and delay certain services and manipulate others by fictitious voting, is one of the main security issues. People can avoid being duped by an attacker or falling into traps when attacks are detected early. This study describes two methods for detecting Sybil attacks: the first uses the Poisson Distribution Method in order to forecast traffic on the street, whereas the latter examines network efficiency for packet delivery ratio (PDR) in both benign additionally malicious environments. According to the simulation's findings, PDR lowers the number of fictitious cars in the network. Our method is straightforward and efficient because it doesn't involve a lot of computational overhead and doesn't breach users' privacy concerns. © 2024 IEEE.

关键词： Poisson distribution

来源：评论

学校读者我要写书评

暂无评论

Enhancing Asthma Diagnosis Through Machine Learning: A Stacking Ensemble Approach 1

Enhancing Asthma Diagnosis Through Machine Learning: A Stack...

引用

1st International Conference for Women in computing, InCoWoCo 2024

作者： Goel, Manas Gupta, Manya Jothikumar, C. Shanmugam, S. Ashokkumar, C. School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Computing Technologies Chennai603203 India

ISBN: (纸本)9798331518943

Asthma diagnosis remains a major clinical concern since it has diverse symptoms and is caused by various contributory causes. Machine learning was applied in this study to solve these complications in order to analyze such a broad dataset of 2,392 patients with the capture of important variables such as demographics, environmental exposures, allergies, medical history, and clinical indicators. Several machine learning models were implemented, including those such as Random Forest, XGBoost, Decision Tree, LGBM, CatBoost, and AdaBoost. Next, the stacking ensemble strategy was taken to further optimize predictive performance, using the Random Forest model meta-classifier. Our approach proves that stable ensemble learning takes place with an amazing 97% accuracy rate when it comes to difficult clinical data. Recall, precision, and F1-score represent some of the most important measures for model performance evaluation. These results might point out the machine learning potential in improving asthma diagnosis accuracy and might be helpful for a doctor in coping with this complicated disease. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 1-14页

作者： Tan, Mingkui Chen, Guohao Wu, Jiaxiang Zhang, Yifan Chen, Yaofo Zhao, Peilin Niu, Shuaicheng South China University of Technology School of Software Engineering China Pazhou Laboratory Guangzhou China XVERSE China National University of Singapore School of Computing Singapore Tencent AI Lab China Nanyang Technological University College of Computing and Data Science Singapore

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important when the test environment changes frequently. Although some recent attempts have been made to handle this task, we still face two key challenges: 1) prior methods have to perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications;2) while existing TTA solutions can significantly improve the test performance on out-of-distribution data, they often suffer from severe performance degradation on in-distribution data after TTA (known as catastrophic forgetting). To this end, we have proposed an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples for test-time entropy minimization. To alleviate forgetting, EATA introduces a Fisher regularizer estimated from test samples to constrain important model parameters from drastic changes. However, in EATA, the adopted entropy loss consistently assigns higher confidence to predictions even when the samples are underlying uncertain, leading to overconfident predictions that underestimate the data uncertainty. To tackle this, we further propose EATA with Calibration (EATA-C) to separately exploit the reducible model uncertainty and the inherent data uncertainty for calibrated TTA. Specifically, we compare the divergence between predictions from the full network and its sub-networks to measure the reducible model uncertainty, on which we propose a test-time uncertainty reduction strategy with divergence minimization loss to encourage consistent predictions instead of overconfident ones. To further re-calibrate predicting confidence on different samples, we utilize the disagreement among predicted labels as an indicator of the data uncertainty. Based on this, we devise a min-max entropy

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

YOLOv4-Powered Traffic Intelligence: From Detection to Optimization

YOLOv4-Powered Traffic Intelligence: From Detection to Optim...

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Sanjiv, Sinha Tharunn, E. Baskar, M. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Computing Technologies Chennai Kattankulathur India

ISBN: (纸本)9798350382693

The Traffic Analysis System utilizes machine learning for real-time traffic insights at a junction. It provides instant stats like vehicle count, density, and FPS, while summarizing average vehicle crossings, densities, stop times, and identifying peak minutes. Machine learning techniques include object detection, tracking, and lane segmentation. The system offers a user-friendly interface with graphical representations, aiding traffic management decisions. It not only ensures efficient traffic control but also allows for predictive analytics and potential integration with traffic light systems for adaptive signal adjustments. Continuous model training and future enhancements promise improved accuracy and adaptability to evolving traffic scenarios. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Integrated Approach To Mitigating Systemic Cyber Risk In Autonomous Electric Vehicles 100

An Integrated Approach To Mitigating Systemic Cyber Risk In ...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Mamun, Quazi Pan, Zhenni Shimamoto, Shigeru Charles Sturt University School of Computing Mathematics and Engineering Australia Waseda University Global Center for Science and Engineering Faculty of Science and Engineering Japan Waseda University School of Fundamental Science and Engineering Faculty of Science and Engineering Japan

ISBN: (纸本)9798331517786

Integrating autonomous vehicles (AVs) within our transportation ecosystem presents exciting possibilities and introduces intricate challenges. Systemic failures due to cyberattacks on AVs could have far-reaching consequences, impacting safety and financial stability. This paper emphasizes the interdependence of stakeholders, particularly within the financial and insurance sectors. We propose a proactive approach, focusing on three objectives: (1) Systemic Risk Mitigation, (2) Premortem Analysis with a focus on cascading failures, and (3) Integration of Cybersecurity Standards tailored for autonomous electric vehicles (EVs). By addressing EV-specific vulnerabilities in charging infrastructure and telematics systems, we aim to significantly enhance the security of safety-critical cyber-physical systems, strengthen the resilience of interconnected industries, and contribute to broader economic stability. © 2024 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Survey on the Evolution of Bootkits Attack and Defense Techniques

引用

China Communications 2024年第1期21卷 102-130页

作者： Yilin Zhou Guojun Peng Zichuan Li Side Liu Key Laboratory of Aerospace Information Security and Trust Computing Ministry of EducationWuhan 430072China School of Cyber Science and Engineering Wuhan UniversityWuhan 430072China

According to the boot process of modern computer systems,whoever boots first will gain control *** advantage of this feature,a malicious code called bootkit can hijack the control before the OS bootloader and bypass security mechanisms in boot *** makes bootkits difficult to detect or clean up *** the improvement of security mechanisms and the emergence of UEFI,the attack and defense techniques for bootkits have constantly been *** first introduce two boot modes of modern computer systems and present an attack model of bootkits by some sophistical *** we discuss some classic attack techniques used by bootkits from their initial appearance to the present on two axes,including boot mode axis and attack phase ***,we evaluate the race to the bottom of the system and the evolution process between bootkits and security *** last,we present the possible future direction for bootkits in the context of continuous improvement of OS and firmware security mechanisms.

关键词： bootkit hook legacy BIOS security mechanisms UEFI

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：