检索结果-内蒙古大学图书馆

Active disturbance reduction scheme for descriptor semi-Markovian jump systems with nonlinear uncertainties

The European Physical Journal Special Topics 2024年 1-13页

作者： Mohanapriya, S. Harshavarthini, S. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Bengaluru India Department of Mathematics School of Advanced Sciences Vellore Institute of Technology Chennai India

By using an active disturbance reduction strategy, the current study addresses the tracking problem of descriptor semi-Markovian jump systems against unknown nonlinear uncertainties (UNC) and aperiodic disturbances. In contrast to previous studies, the improved equivalent-input-disturbance (IEID) estimator is merged with the generalized modified repetitive control (GMRC) rule. To do this, initially, the state-space model of GMRC is proposed. Then, the composite IEID estimator-based GMRC is designed to regulate UNC and disturbances and ensures desired output tracking performance of the proposed model. By constructing augmented Lyapunov–Krasovskii functional, sufficient conditions are presented to guarantee mean-square asymptotic admissibility of closed-loop dynamics in terms of linear matrix inequalities. Finally, the dynamics of DC motor structure with two modes are validated with derived sufficient conditions. The simulation and comparison results confirmed the better tracking performances over the existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recent Advancements in Hyperspectral Face Recognition: A Review 13

Recent Advancements in Hyperspectral Face Recognition: A Rev...

引用

13th International Conference on computing Communication and Networking Technologies, ICCCNT 2022

作者： Das, Samiran Chatterjee, Sujoy JIS University Centre for Data Science JIS Institute for Advanced Studies and Research Kolkata India Amity University Department of Computer Science and Engineering Kolkata India

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

The increasing demand for high-accuracy face recognition methods and the rapid advancement in instrumentation has made hyperspectral face recognition a viable alternative to traditional face recognition. The high-security biometric application scenarios, which demand high accuracy of recognition are switching to hyperspectral imaging due to its robustness against spoofing, illumination, pose variation, etc. The hundreds of visible and near infrared (NIR) images contained in a hyperspectral face cube provide sufficient information content, leading to more accurate recognition. However, the gigantic volume of information and the computational challenges call for efficient learning strategies for the recognition task. Researchers have introduced several feature extraction, supervised learning, deep learning, and pattern recognition approaches to carry out face recognition from hyperspectral face cubes. This work summarized the state-of-the-art approaches for hyperspectral face recognition in detail and highlight their pros and cons. The work also discusses future directions and challenges in this domain. © 2022 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Detection of Selfish Nodes based on Node Energy in Mobile Adhoc Networks - MANETs 1

Detection of Selfish Nodes based on Node Energy in Mobile Ad...

引用

1st IEEE International Conference on Automation, computing and Renewable Systems, ICACRS 2022

作者： Sarumathi, R. Jayalakshmi, V. VISTAS Chennai India Dept. of Computer Science RajeswariVedhachalam Govt. Arts College Chengalpet India School of Computing Sciences Vels Institute of Science Technology and Advanced Studies VISTAS Chennai India

ISBN: (纸本)9781665460842

One of the most essential self-configuring and independent wireless networks is the MANET. MANET employs a large number of intermediate nodes to exchange information without the need for any centralized infrastructure. However, some nodes act in a selfish manner, utilizing the network's resources solely for their own benefit and refusing to share with the surrounding nodes. Mobile ad hoc network security is a critical factor that is widely accepted. Selfish nodes are the primary problem of MANET. In a MANET, nodes that are only interested in themselves do not involve in the process of packet forwarding. A node can be identified as selfish or malicious due to some misbehavior reasons. Selfishness on the part of network nodes may be a factor in the low delivery ratio of packets and data loss. A high end-to-end delay is caused by node failure in a MANET network. To study the selfish node attack, a malicious selfish node is put into the network, and a trust-based algorithm for the selfish node attack is also *** order to discover a solution to this issue, we have developed an algorithm called SNRM for the detection of selfish nodes. The routing protocol usedin this paper for analysis is AODV. Using a simulation tool, PDR and end-to-end delay are evaluated and compared. © 2022 IEEE

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Drug Discovery: Predicting Drug-Protein Binding Affinities using Graph Convolutional Networks 5

Machine Learning for Drug Discovery: Predicting Drug-Protein...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Radhamahendran, S. Dogra, Akriti Mendhe, Dinesh Tilak Babu, S.B.G. Dixit, Shriniket Singh, Surya Pratap Vels Institute of Science Technology and Advanced Studies School of Life Sciences Department of Bioinformatics Chennai Pallavaram India Manav Rachna Dental College Department of Oral & Maxillofacial Surgery Haryana Faridabad India State University of New Jersey Computer and Information Research Scientist Office of Research Computing Rutgers New BrunswickNJ United States Aditya Engineering College Department of ECE Surampalem India Vellore Institute of Technology School of Computer Science Engineering Tamil Nadu Vellore India UPUMS Department of Multi-Disciplinary Research Unit UP Etawah India

ISBN: (纸本)9798350351378

Determining the potential interactions between ligands and proteins is a crucial first step in developing new drugs. Graph BAR, our novel prediction model, makes accurate guesses about the strength of ligand-protein bindings by means of a graph convolutional neural network. When compared to graph convolutional neural networks, standard convolutional neural network models are more resource and time intensive to manage. The interaction between proteins and ligands is shown via a network consisting of many adjacency meshes. The atomic distances dictate the alterations to these matrices. Additionally, the atomic properties can be shown in a feature matrix. Using the PDBbind datasets, we verified the functionality of graph convolution and evaluated Graph BAR's ability to forecast the binding strengths of proteins and ligands. In order to maximize The model's performance was improved by utilizing ways for adding additional input, which took advantage of the processing capability of graph convolutional neural networks. Graph BAR's predictions appear to have potential for use in drug creation due to its great accuracy and quickness. The results of our research suggest that Graph Convolutional Networks have the potential to expedite the discovery of new medications by properly predicting the interactions between pharmaceuticals and proteins. © 2024 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition for Protecting Sensitive Data using Hybrid CNN

Named Entity Recognition for Protecting Sensitive Data using...

引用

International Conference on Smart Systems and Inventive Technology (ICSSIT)

作者： Sheela Gowr. P Kumar. N Department of Computer science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India

Named entity recognition is a natural language processing technique that effectively recognizes and categorizes named entities in a document. The named entity recognition helps to bring out dynamic information about a document or gather critical data to store in a database. Deep learning helps to develop over time, while NLP examines the structure and standards of language and produces an automated system that can discern meaning from text. Mining the essential entities in a text helps identify related data, which is vital when functioning with enormous datasets. The proposed system has a feature that can retrieve and identify sensitive data such as PAN numbers, bank account numbers, and Aadhar numbers from unstructured text data.. The proposed model is designed using Hybrid CNN and it attains 95% F1-Score, 97.5% precision, and 98.3% recall.

关键词： Deep learning Training Radio frequency Databases Data security Forestry Predictive models

来源：评论

学校读者我要写书评

暂无评论

Enhancing Chest X-ray Pathology Prediction through Data-Driven Approaches and Transfer Learning

引用

Procedia computer science 2025年 258卷 3447-3456页

作者： Rekha R. Nair Kishore S Tina Babu Vishnu Vilashini S Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University Bengaluru India Department of Computer Applications Nitte (Deemed to be University) Nitte Institute of Professional Education Mangalore India Analyst Capgemini Bellandur Karnataka India

Chest X-ray pathology prediction play a very important role in early disease detection, enabling timely intervention and improving patient outcomes. This project undertakes a comprehensive exploration of medical imaging analysis, focusing on chest X-rays for pathological identification. Starting this inquiry is thorough getting of information and exploratory information assessment (EDA), which demonstrates the significant elements of the dataset’s people, disease characteristics, and intrinsic predicaments. By making use of sophisticated image processing techniques, the study uses a Super-Resolution Convolutional Neural Network (SRCNN) in refining the resolution of chest X-ray scans, leading to improvement in diagnostic accuracy. Dealing with natural data imbalance found in medical data sets, this project proposed a new method by including a weighted loss function during training. Thus designed, this system allows the model to practically learn from uneven class distributions ensuring strong efficiency throughout different pathologies. The neural architecture for chest X-ray classification is built upon transfer learning principles, utilizing pretrained ResNet18, Alex net, Custom Neural Network models. The models are designed to meet the characteristics of the medical dataset in particular way, having replaced last fully connected layer with one that gives outputs across 14 different pathologies for predictions. The training process involves fine-tuning the models with a meticulously crafted weighted loss function and adaptive learning rate schedules, ensuring optimal convergence.

关键词： MQ2 Sensor NodeMCU Data Logging Analytics Real-time Alerts

来源：评论

学校读者我要写书评

暂无评论

A Trust Secure Attacker Detection with Upgraded Deep Learning-Assistance for SDN Networks

A Trust Secure Attacker Detection with Upgraded Deep Learnin...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： M. Sabarish A.S. Arunachalam Department of Computer Science Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai Tamilnadu

Software Defined Networking (SDN) technologies may be used to properly identify and monitor network security vulnerabilities brought about by the emergence of programmable features. SDN is a real possibility for modernizing internet network architecture. Due to its centralized nature, SDN architecture increases the frequency of assaults. Providing safety for the SDN is crucial. SDN has made it possible to improve the efficiency and adaptability of network security. In this study, we propose a system for security, energy savings, and intrusion detection based on Deep Learning Trust Secure Attacker Detection (IDLTSAD). There are a lot of benefits to using IDLTSAD, the most notable of which are increased network longevity and safety. Our cryptographic security solution was designed to be used in conjunction with SDN's encryption approach. Our approach is safe since we introduced an attribute-based encryption (ABE) mechanism. We compared the MLTSAD, DLTSAD, or EMLTSAD models to our IDLTSAD technique and ran a battery of experiments to see how each one fared in terms of energy efficiency, packet delivery rate, latency, and overall network longevity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Alzheimer's Disease Classification using Transfer Learning and Data Augmentation

Deep Learning-Based Alzheimer's Disease Classification using...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Deva Anand P. Sheela Gowr S. Logesh S. M. Anand Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India

Alzheimer's disease is a pressing healthcare concern worldwide, highlighting the importance of early and accurate detection. Deep learning models, particularly those utilizing transfer learning, have shown promise for AD classification. This research study explores the effectiveness of transfer learning in training models based on deep learning for the classification of Alzheimer's condition. We trained several transfer models using DenseNet121, InceptionV3, Xception, and ResNet101. Based on performance evaluation, InceptionV3 was selected as the base model, outperforming in comparison to the accuracy of the other models. To enhance the accuracy of the InceptionV3 base model, we added capacity, tuned hyperparameters using Keras tuner, and utilized data augmentation techniques. The final model was trained on the Kaggle Alzheimer's Dataset, consisting of 4 classes of images, and achieving an AUC value of 87%. Our research demonstrates that transfer learning and other data augmentation approaches are useful in improving the accuracy of deep learning models for the categorization of Alzheimer's condition. This research has practical implications for improving public health outcomes, facilitating timely intervention and effective treatment. It contributes to the development of more accurate diagnostic tools for AD and can help address the challenges associated with this disease.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling and Clustering of Parabolic Granular Data

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3728-3742页

作者： Tang, Yiming Gao, Jianwei Pedrycz, Witold Hu, Xianghui Xi, Lei Ren, Fuji Hu, Min Hefei University of Technology Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei230601 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6R 2V4 Canada Hefei University of Technology School of Computer and Information Hefei230601 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Polish Academy of Sciences Systems Research Institute Warsaw00-901 Poland Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Southeast University School of Computer Science and Engineering Nanjing211189 China University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China

At present, there exist some problems in granular clustering methods, such as lack of nonlinear membership description and global optimization of granular data boundaries. To address these issues, in this study, revolving around the parabolic granular data, we propose an overall architecture for parabolic granular modeling and clustering. To begin with, novel coverage and specificity functions are established, and then a parabolic granular data structure is proposed. The fuzzy c-means (FCM) algorithm is used to obtain the numeric prototypes, and then particle swarm optimization (PSO) is introduced to construct the parabolic granular data from the global perspective under the guidance of principle of justifiable granularity (PJG). Combining the advantages of FCM and PSO, we propose the parabolic granular modeling and optimization (PGMO) method. Moreover, we put forward attribute weights and sample weights as well as a distance measure induced by the Gaussian kernel similarity, and then come up with the algorithm of weighted kernel fuzzy clustering for parabolic granularity (WKFC-PG). In addition, the assessment mechanism of parabolic granular clustering is discussed. In summary, we set up an overall architecture including parabolic granular modeling, clustering, and assessment. Finally, comparative experiments on artificial, UCI, and high-dimensional datasets validate that our overall architecture delivers a good improvement over previous strategies. The parameter analysis and time complexity are also given for WKFC-PG. In contrast with related granular clustering algorithms, it is observed that WKFC-PG performs better than other granular clustering algorithms and has superior stability in handling outliers, especially on high-dimensional datasets. © 2020 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Web Based Cyber Attack Detection for Industrial System (PLC) Using Deep Learning

Web Based Cyber Attack Detection for Industrial System (PLC)...

引用

Advances in computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： A. Yasir Kalaivani Kathirvelu M. K. Arif Department of Computer Science and Engineering School of Engineering Vels Institute of Science Technology and Advanced Studies Chennai Tamil Nadu India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Web apps are frequently targeted by cyber-attacks due to their network access and security flaws. Instances of attacks targeting online applications might pose significant risks. The issue of cyber security continues to pose a significant barrier in Industry 5.0 scenarios, since cyber-attacks have the potential to result in severe outcomes such as production disruptions, data breaches, and even physical injuries. In order to tackle this difficulty, this study suggests a novel deep-learning approach for identifying web-based assaults in the context of Industry 5.0. The investigation explores transformer models, which are methods used in deep learning, for their capacity to accurately classify attacks and detect unusual behavior. The results of this research demonstrated the higher performance of the suggested transformer-based system, surpassing earlier methods in terms of accuracy, precision, and recall. Deep learning plays a crucial role in effectively tackling cyber security issues in Industry 5.0 settings.

关键词： Deep learning Instruments Production Transformers Robustness Security Fifth Industrial Revolution

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：