检索结果-内蒙古大学图书馆

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Ramaiah, Mangayarkarasi Padma, Adla Vishnukumar, Ravula Rahamathulla, Mohemmed Yousuf Chithanuru, Vasavi Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350372120

In the age of smart era, usage of IoT devices is inevitable. As the number of IoT devices increases, the amount of data they generate also increases, which in turn leads to security breaches. Continuous monitoring through SDN is the appropriate solution to mitigate security breaches. SDN introduces a new architecture where the control plane operates independently of the data plane. While this design allows applications in the base plane to interact with network components via the controller, it also creates security concerns. An attacker could exploit vulnerabilities in the control plane, potentially leading to significant data breaches. Amid a lot of research in various venues to address the security aspects of SDN, a simple and robust Intrusion detection system is necessary for the current context. Hence, a hybrid-wrapped enabled feature selection RF-RFE has been included in determining the highly influential features upon the derived features and a fine-tuned machine learning-based model to detect the anomalies at the earliest possible in the context of SDN has been trained and tested on SDN-IoT dataset. The tested results reveal that RF-based RF-RFE-SDNIoT-NIDS obtained 99% of its binary and multi-classification accuracy using minimal features compared to other machine learning models. © 2024 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Face Recognition Based Attendance Management System Using Deep Learning Method 2

Face Recognition Based Attendance Management System Using De...

引用

2nd International Conference on Emerging Trends in information technology and engineering, ic-ETITE 2024

作者： Angulakshmi, M. Susithra, V. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (数字)9798350328202

ISBN: (纸本)9798350328202

Deep learning and transfer learning are extremely important in the internet sector and the health care industry. Face recognition technology is essential in practically every industry in our digital age. Several improvements have been made to automatic facial recognition (AFR) technology in an ever-changing world. Managing the daily student attendance system is made simple with Smart attendance with Real-Time Face Recognition. In the proposed method, Images of the students in class are used to construct a dataset. Both Face detection and recognition are performed using the Multitask Convolution Neural Network algorithm. The data will be uploaded after the face is recognition. The proposed method compared with Haar Cascade Convolution Neural Network Classification method and other few methods. The proposed method produced better resultcompared to other methods © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enhancing Video Protection: A Reversible Digital Watermarking approach using Swin features and Arnold Transform enabled Multi-Aggregation Model 3

Enhancing Video Protection: A Reversible Digital Watermarkin...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Dilip, Mali Satish Agilandeeswari, L. Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350372120

Nowadays, the widespread internet technology brings out rapid advancement in the use of videos for sharing huge amounts of secret data. Conversely, the privacy of transmitted digital content is jeopardized by digital image processing techniques that are capable of producing flawless image or video duplication. Moreover, providing security to digital records in the form of videos is a highly challenging task, which requires a fusion-based watermarking technique to protect the data from illegitimate access and fraudulent usage. In this investigation, a tiny Swin and Arnold Transform-enabled Multi-aggregation model was introduced to protect video based on digital watermarking characteristics at a very low computational cost. Here, the Swin-T features are extracted from the input video, over which the Arnold transform and multi-aggregation model is developed in two phases. The best embedding location is identified by using multi aggregation model initially at the embedding phase and the inverse Arnold transform for secret image (VIT Logo) embedding in a binary embedding location to obtain the embedded video. The secret image is extracted from the attacked embedded video using the Arnold transform-multi-aggregation model in the extraction phase. The developed data-hiding technique is also evaluated to compute the robustness using the evaluation parameters. The simulation results reveal that the developed scheme achieved Peak-Signal-to-Noise Ratio (PSNR) and Similarity Index Measure (SSIM) values of 64.57 ∼dB and 0.9993 respectively. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Enhancing Alzheimer's Disease Detection with Chaotic Moth Flame Optimization Algorithm: A Feature Selection Approach

Enhancing Alzheimer's Disease Detection with Chaotic Moth Fl...

引用

2024 IEEE International Conference on Emerging Technologies in computer science for Interdisciplinary Applications, ICETCS 2024

作者： Sabari Vasan, S. Jayalakshmi, P. Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350372502

Advances in medical science have led to a better understanding of Alzheimer's disease (AD), as shown by the clear description of AD using numerical, medical and MRI architectural imagery details. Early diagnosis of AD is possible using clinical data in addition its presence can be identified with huge correctness. Still, managing the massive and broadening AD data record is seemly an issue and utilising the unrefined data record unless removing redundant and duplicate data can significantly impact prediction or classification accuracy. Therefore, this research proposes an improved memetic metaheuristic behavioural founded feature selection framework called chaotic moth flame optimization algorithm (CMFOA). The suggested framework of MFO incorporates chaotic mapping to boost the search process, distinguishing it from the traditional form. CMFOA outperforms Ant colony optimization (ACO) and Firefly algorithm (FFA) in terms of ease, variable reduction, optimal efficiency, quick implementation, and rapid computing, resulting in improved subsets of characteristics for AD prediction. The study utilized the Alzheimer's disease neuroimaging initiative (ADNI) dataset to ascertain potential characteristics implicated in the diagnosis of Alzheimer's disease. The performance of the three feature subset selection approaches was validated using a deep neural network (DNN).The results demonstrated that CMFOA outperformed the other models in terms of accuracy. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Supportive particle swarm optimization with time-conscious scheduling (SPSO-TCS) algorithm in cloud computing for optimized load balancing

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 192-198页

作者： Menaka, M. Sendhil Kumar, K.S. School of Computer Science and Engineering Vellore Institute of Technology Vellore632014 India

Task scheduling for virtual machines (VMs) has shown to be essential for the effective development of cloud computing at the lowest cost and fastest turnaround time. A number of research gaps about job schedule optimization are included in the current paper. A thorough analysis of the data generated by this activity is essential to resolving the resource allocation mechanism of the cloud architecture. To fully utilize virtual machines with a similar weight distribution, a strategy-oriented mixed support and load balancing structure has been developed in this work. To minimize make-span time and accomplish initial load balancing, the SPSO-TCS technique combines Time-Conscious Scheduling with Supportive Particle Swarm Optimization. Finding the optimal make span time minimization for each virtual environment is the aim of this stage. Its main objective is to discover the sequence of activities with the least computation time and to reduce the time required to finish each operation. Utilizing the hybrid idea leads to a decrease in makespan and the use of the least amount of energy. © 2024

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

A Study of Federated Learning with Internet of Things for Data Privacy and Security using Privacy Preserving Techniques

引用

Recent Patents on engineering 2024年第1期18卷 1-17页

作者： Shakeer, Shaik Mahamad Rajasekhara Babu, M. School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore India

To address the privacy concerns that arise from centralizing model training on a large number of IoT devices, a revolutionary new distributed learning framework called federated learning has been developed. This setup of devices works together to train models without compromising the security of individual data streams. To solve machine learning problems, a federated learning architecture relies on many clients working together through a central aggregator. To protect each device's privacy, we only access the training data at random. Because of its focus on decentralized processing and model transmission, federated learning considerably reduces systemic privacy risks and costs in comparison to conventional centralized machine learning systems. All client data is encrypted before being stored in a local database. Each user's device collects data locally for training during a federated learning session, and then uploads the final model to a centralized server. To provide a comprehensive assessment and inspire more research, this paper explores into the inner workings of federated learning from five different vantage points: data partitioning, privacy approaches, machine learning models, communication architectures, and system heterogeneity. Then, suggestions for further research are given, and a list is compiled of the most recent problems in federated learning. We conclude with an examination of the present applications of federated Learning knowledge. © 2024 Bentham science Publishers.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Deep Learning Techniques on Cyber Attacks on Cyber Physical systems

引用

SN computer science 2024年第7期5卷 891页

作者： Sagar, Maloth Vanmathi, C. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore 632014 India

Cyber-Physical systems (CPSs), which integrate control, computing, and communication, are considered as next-generation intelligent systems.A major concern in CPS is to ensure security. If security is not ensured, then it leads to both property damage and *** CPS is closely associated with real life, it is a hot research area in present security research. Nevertheless, cyber security issues are also raised. More efforts are still required for understanding CPS security from a more comprehensive perspective even though there are several studies on CPS *** identify and detect cyber security in CPS, numerous methods have been applied. The majority of recently published studies focused on Machine Learning (ML) techniques, with little attention paid to the development of Deep Learning (DL). Hence, the analysis of cyber security on CPS utilizing several algorithms of DL techniques is systematically *** appropriate cyber security risk levels and their corresponding detection and mitigation processesare determined. This study could augment the adaptability of the system of CPS data. Also, it could increase the generalization of the models of security attacks in CPS. Using DL algorithms is strongly recommended by most authors as a means to identify cyber security issues in *** CNN-centric LSTM, Deep Multi-architectural Approach, and DL-Meta classifier attained the highest accuracy in the detection rate of cyber security attacks in CPS when analogized with the other algorithms in DL techniques. Hence, for several critical systems in CPSs, the result renders clear guidelines to apply other regularization on DL techniques. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： CPS Cyber security Cyber-attack Cyber-attack detection Deep learning Risk analysis Security threats

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Deep Learning and Machine Learning Methods for Water Quality Prediction 3

A Comparison of Deep Learning and Machine Learning Methods f...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Srinivasa Gupta, N. Valarmathi, B. Hiwanj, Ishaan Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Information Technology School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798331527549

Predicting water quality is essential to preserving human health and environmental sustainability. Traditional water quality assessment methods often face scalability and real-time monitoring limitations. With accuracies of 62%, 72%, 83%, 69%, 63%, 66%, 71%, 63%, and 64%, respectively, the current techniques utilized were Logistic Regression, Decision Trees, Random Forest Regressor, Extreme Gradient Boosting, Naive Bayes, K-nearest neighbors, Support Vector Machine, AdaBoost, and Bagging [9]. This study addresses these challenges by leveraging Adaptive Synthetic Sampling (ADASYN) to balance the dataset and evaluating model performance on datasets of 5,000 and 10,000 entries per class. A robust dataset obtained from Kaggle was used, with five models – Long Short-Term Memory (LSTM), Feed Forward Neural Network (FFNN), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Random Forest – evaluated and compared. The proposed methods demonstrate significant improvements in accuracy, with XGBoost achieving the highest accuracy of 95.53%, followed by Random Forest at 93.98%. This work underscores the importance of advanced machine learning techniques in addressing the limitations of traditional methods, enhancing accuracy, scalability, and adaptability in water quality prediction. These findings contribute to advancing environmental monitoring and management practices with reliable, data-driven insights. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Prediction of Bandwidth of Metamaterial Antenna Using Pearson Kernel-Based Techniques

引用

computers, Materials & Continua 2024年第3期78卷 3449-3467页

作者： Sherly Alphonse S.Abinaya Sourabh Paul School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India School of Electronics Engineering Vellore Institute of TechnologyChennai600127India

The use of metamaterial enhances the performance of a specific class of antennas known as metamaterial *** radiation cost and quality factor of the antenna are influenced by the size of the *** antennas allow for the circumvention of the bandwidth restriction for small *** parameters have recently been predicted using machine learning algorithms in existing *** learning can take the place of the manual process of experimenting to find the ideal simulated antenna *** accuracy of the prediction will be primarily dependent on the model that is *** this paper,a novel method for forecasting the bandwidth of the metamaterial antenna is proposed,based on using the Pearson Kernel as a standard *** with these new approaches,this paper suggests a unique hypersphere-based normalization to normalize the values of the dataset attributes and a dimensionality reduction method based on the Pearson kernel to reduce the dimension.A novel algorithm for optimizing the parameters of Convolutional Neural Network(CNN)based on improved Bat Algorithm-based Optimization with Pearson Mutation(BAO-PM)is also presented in this *** prediction results of the proposed work are better when compared to the existing models in the literature.

关键词： Antenna pearson optimization bandwidth metamaterial

来源：评论

学校读者我要写书评

暂无评论

Dual strategy for single image denoising and generation using deep neural network

引用

Multimedia Tools and Applications 2025年第18期84卷 19255-19271页

作者： J, Ranjith Sarobin, Vergin Raja Bhargavi, Renta Chintala School of Computer Science and Engineering Vellore Institute of Technology Chennai India

Removing noise in the real-world scenario has been a daunting task in the field of natural language processing. Research has shown that Deep Neural Networks (DNN) have proven to be very useful in terms of noise generation in order to synthesize noise and clean image couples in order to train the deep denoiser architectures. In our work, we develop a method that denoises an image while dealing hand in hand with image generation tasks so as to facilitate the former and reduce the load on the denoiser. We use a probabilistic model by learning the joint distribution of the noisy and clean image couples. To be more specific, we use an approximation of the above-mentioned probabilistic distribution by using two different forms, one that can map clean images to noisy, hereafter referred to as the generator, and the vice versa, i.e., mapping a noisy image to a clean image hereafter referred to as the image denoiser. The advantage of this method is that as compared to traditional models where manual design of the images beforehand and deducing information on the noise assumption was critical, the learned probabilistic joint distribution now implicitly holds the required details related to the clean and noisy images. The main aim of the symmetric generator is to enhance the performance of the denoiser by generating synthetic noisy images from the same dataset itself. The evaluation of the denoiser was done using two evaluation metrics, peak signal to noise ratio (PSNR) and the structural similarity index (SSIM). The entire experiment was conducted using the publicly available Smartphone Image Denoising Dataset (SIDD). © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep 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：