检索结果-内蒙古大学图书馆

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Phaneendra Kumar, B.L.N. Vaddi, Radhesyam Manoharan, Prabukumar K L Deemed to Be University Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram India Velagapudi Ramakrishna Siddhartha Engineering College Department of Inforamtion Technology Vijayawada India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350325799

The high volume and replication of data in hyperspectral images results in improper classification. This paper addresses a non-linear spectral feature extraction using Local Linear Embeddings in which graph-based structures are utilized. The representative features are then trained for smoothed features using a spatial filter. The extracted spatial features are then trained for classification using a nonlinear version of Support Vector Machine. The proposed model is tested on two datasets: Indian Pines & Pavia. Proposed approach is tested with well-known dimensionality reduction techniques. The reported Overall Accuracy is 92.33% & 98.21% on Indian Pines & Pavia respectively and outperformed well. The algorithm is used for hyperspectral change detection. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Real-Time Water Quality Tracking and Alert System with IoT Integration 3

Real-Time Water Quality Tracking and Alert System with IoT I...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Mohan Kumar, Ch. Munaga, Masthan Siva Krishna Kolli, Chandra Sekhar Maddila, Suresh Kumar Koneru Lakshmaiah Education Foundation Department of Computer Science & Engineering Guntur District Andhra Pradesh Vaddeswaram India Aditya College of Engineering and Technology Department of Information Technology Andhra Pradesh Surampalem India Shri Vishnu Engineering College for Women Department of Information Technology Andhra Pradesh Bhimavaram India School of Computing Gandhi Institute of Technology and Management Department of Computer Science Andhra Pradesh Visakhapatnam India

ISBN: (纸本)9798350322842

Water is an essential resource for all living beings, and given the limited availability of natural resources, it is crucial to use water efficiently. Monitoring and analysing water quality parameters have become imperative in today's scenario to ensure good health and prevent excessive usage and wastage of water. The traditional approach of manually collecting water samples from different sources and sending them to research labs for analysis is neither feasible nor cost-effective. Moreover,frequent manual sampling and analysis could be more practical. IoT technology can be leveraged to monitor and alert people in real time about water quality in specific areas. The proposed system comprises sensors to measure essential water characteristics in real time, enabling decision-making without external intervention. The system can control all the critical parameters to ensure accurate measurements, and the readings can be stored in a cloud environment for future analysis. This proposed system can be used for real-time water quality analysis. © 2023 IEEE.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

Perioperative Anesthesia Data: Visualization, Effects, Analysis with Artificial Intelligence 4

Perioperative Anesthesia Data: Visualization, Effects, Analy...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Liu, Xiaoxiao McGrath, Sean Flanagan, Colin Lei, Yiming Zeng, Liaoyuan Electronic and Computer Engineering University of Limerick Limerick Ireland School of Mathematics and Information HeBei University HeBei China Mobile Digital Hospital System School of Electronics Peking University Ministry of Education Engineering Research Center Beijing China University of Electronic Science and Technology of China Department of Information and Communication Engineering Chengdu China

ISBN: (纸本)9798350360721

A comprehensive understanding of physiological data is essential for anesthesiologists to monitor and maintain the health of surgical patients. Understanding anesthetic signals is essential to improve over the past ten decades to comprehend a variety of diseases, ensure the safety of patients, and accelerate their recovery. We identified and summarized four themes of artificial intelligence (AI) research in anesthesia: applications of AI in anesthesiology, signals monitored in different anesthesia stages, commonly monitored signs, and data standardization. The effect of various AI technologies on data analysis was studied, and the types, functions, sensors, characteristics, and intelligent analysis of physiological signals monitored during anesthesia are presented in this article. AI influences anesthesia practices in many ways, including preoperative data evaluation, anesthetic depth monitoring, and postoperative event prediction. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Classification of Unbalanced Data Based on Bayesian Optimal Neural Network Model

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1427-1440页

作者： Ye, Li-Zhu Alkawaz, Mohammed Hazim Johar, Md Gapar Md School of Information Technology and Engineering Guangzhou College of Commerce Guangzhou511363 China School of Graduate Studies Management and Science University 40100 Shah Alam Selangor Malaysia Department of Computer Science College of Education for Pure Science University of Mosul Mosul41002 Iraq Software Engineering and Digital Innovation Center Management and Science University Shah Alam40100 Malaysia

Aiming at the unbalanced problem of big data classification, this paper proposes a classification method of unbalanced data on the ground of Bayesian optimal neural network model. The method firstly uses Optimized Graph Convolutional Network (OGCN) network to carry out message passing mechanism in data graph, designs neural network model with self-attention pooling and mean maximization pooling, and then uses Bayes optimization to update the posterior probability of optimization function by constantly updating the probability model and evaluating the objective function. Effectively solve the problem of speed and optimal solution of hyperparameter optimization in the neural network model. Secondly, the model is used for data set training to obtain the weight of the entire network. Secondly, the unbalanced data is mixed sampling to reduce the number of negative samples. Finally, the capability of the model was verified on the CiteSeer dataset. Experimental results showed that the accuracy rate, accuracy rate and recall rate of the proposed algorithm were 0.974, 0.982 and 0.973, respectively, which effectively improved the accuracy rate, accuracy rate and recall rate of unbalanced data classification compared with other algorithms. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

An Optimal Deep Learning for Cooperative Intelligent Transportation System

引用

computers, Materials & Continua 2022年第7期72卷 19-35页

作者： K.Lakshmi Srinivas Nagineni E.Laxmi Lydia A.Francis Saviour Devaraj Sachi Nandan Mohanty Irina V.Pustokhina Denis A.Pustokhin Department of Computer Science and Engineering Periyar Maniammai Institute of Science&TechnologyThanjavur613403India Department of Computer Science and Engineering KG Reddy College of Engineering and TechnologyTelangana500075India Department of Computer Science and Engineering Vignan’s Institute of Information Technology(Autonomous)Visakhapatnam530049India Department of Computer Science and Engineering Kalasalingam Academy of Research and EducationKrishnankoil626128India Department of Computer Engineering College of Engineering PunePuneMaharashtra411005India Department of Entrepreneurship and Logistics Plekhanov Russian University of EconomicsMoscow117997Russia Department of Logistics State University of ManagementMoscow109542Russia

Cooperative Intelligent Transport System(C-ITS)plays a vital role in the future road traffic management system.A vital element of C-ITS comprises vehicles,road side units,and traffic command centers,which produce a massive quantity of data comprising both mobility and service-related *** the extraction of meaningful and related details out of the generated data,data science acts as an essential part of the upcoming C-ITS *** the same time,prediction of short-term traffic flow is highly essential to manage the traffic *** to the rapid increase in the amount of traffic data,deep learning(DL)models are widely employed,which uses a non-parametric approach for dealing with traffic flow *** paper focuses on the design of intelligent deep learning based short-termtraffic flow prediction(IDL-STFLP)model for C-ITS that assists the people in various ways,namely optimization of signal timing by traffic signal controllers,travelers being able to adapt and alter their routes,and so *** presented IDLSTFLP model operates on two main stages namely vehicle counting and traffic flow *** IDL-STFLP model employs the Fully Convolutional Redundant Counting(FCRC)based vehicle count *** addition,deep belief network(DBN)model is applied for the prediction of short-term traffic *** further improve the performance of the DBN in traffic flow prediction,it will be optimized by Quantum-behaved bat algorithm(QBA)which optimizes the tunable parameters of *** results based on benchmark dataset show that the presented method can count vehicles and predict traffic flowin real-time with amaximumperformance under dissimilar environmental situations.

关键词： Cooperative intelligent transportation systems traffic flow prediction deep belief network deep learning vehicle counting

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Pre-trained ResNet and DenseNet Models for the Detection of Diabetic Macular Edema 2

Comparative Analysis of Pre-trained ResNet and DenseNet Mode...

引用

2nd International Conference on Artificial Intelligence, Computational Electronics and Communication System, AICECS 2023

作者： Pavithra, K.C. Kumar, Preetham Geetha, M. Bhandary, Sulatha V Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Ophthalmology Kasturba Medical College Manipal Manipal Academy of Higher Education Manipal India

A major setback in Deep Learning (DL) is that a huge amount of data is essential to render the trained model more generalizable. Constructing a higher-order model based on insufficient data has a detrimental effect on testing performance. Transfer Learning (TL) involves less training data than conventional DL approaches and offers superior decision support. Healthcare datasets of reasonable sizes are generally inappropriate for training DL models. A promising solution to the issue would be to use TL methods for the classification of medical image datasets. This paper aims at the training and evaluation of six variants of pre-trained ResNet and three variants of pre-trained DenseNet models for Diabetic Macular Edema (DME) classification employing a public retinal Optical Coherence Tomography (OCT) image dataset. Among the ResNet implementations, ResNet101V2 has delivered the highest accuracy value of 95%. And among the DenseNet implementations, DenseNet201 has yielded an exceptional classification accuracy of 99%. As all three DenseNet versions, along with the ResNet101V2 version, have produced noticeably good results (accuracy values greater than 95%), they can be used to screen the retinal OCT images of DME patients. © Published under licence by IOP Publishing Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Exploring Non-convex Optimization in Sparse Signal Recovery: A Comparative Study of Non-convex Dantzig Selector and LASSO 1

引用

5th International Conference on Advances in information Communication technology and Computing, AICTC 2024

作者： Devadas, Raghavendra M. Hiremani, Vani Sharma, Aditi Venugopal, Anita Ichangi, Raghavendra M. Kulkarni, Naveen Pavithra, N. Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Pune India Department of IT Unit Dhofar University Muscat Oman Sphoorthy Engineering College Nadargul Hyderabad India School of Engineering Dayananda Sagar University Kanakapura Road Bangalore India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (数字)9789819761036

ISBN: (纸本)9789819761029

Sparse signal recovery, lying at the core of signal processing and machine learning, has been traditionally attacked with convex optimization approaches such as LASSO and the Dantzig Selector. This paper investigates the field of non-convex optimization for sparse signal recovery, particularly comparing non-convex variants of Dantzig Selector and LASSO. A motivating choice of non-convex penalties may thus capture more complicated structures in sparse signals, offering a flexible framework for modeling complex sparsity patterns. Evaluate the performance of a non-convex Dantzig Selector in comparison with a non-convex variant of LASSO and investigate the sensitivity of the parameters in both methods. The non-convex Dantzig Selector introduces Huber loss, whereas the non-convex LASSO introduces a square root penalty. The performance metrics include sparsity and accuracy of recovered signals. The comparison between those methods in different scenarios gives the relative merits, adding up to the discussion on what methods to use for the reconstruction of signals. The study finds that the non-convex Dantzig Selector is of the final sparsity of the order of 10%, basically selecting only 10% of the variables. Contrarily, the non-convex LASSO is of about 90% sparsity, selecting about 90% of the variables. Finally, the non-convex LASSO has final accuracy closer to 1 with low prediction error, while the non-convex Dantzig Selector has final accuracy closer to 0.6, pointing to the reality of higher prediction error. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Origins to Innovations: A Comprehensive Journey Into Artificial Intelligence's Future Application

Origins to Innovations: A Comprehensive Journey Into Artific...

引用

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Saraswat, Shivam Mehra, Ritika Gurpreet Yuvaraj, K. Karthigaikumar, P. Wankhede, D.S. Department of Civil Engineering School of Engineering & Technology K. R. Mangalam University Haryana Gurugram India School of Engineering and Computer Dev Bhoomi Uttarakhand University Uttarakhand 248007 India Department of Computer Applications Invertis University Uttar Pradesh Bareilly India Department of Computer Science Karpagam Academy of Higher Education Coimbatore India Department of Electronics and Communication Engineering Karpagam College of Engineering Coimbatore India Vishwakarma Institute of Information Technology Pune India

ISBN: (纸本)9798350355338

In the contemporary era characterized by the proliferation of extensive data sets and the advent of Industry 4.0, artificial intelligence (AI) emerges as a prominent catalyst for economic growth. It assumes a pivotal role in facilitating the integration of advanced technologies like bitcoin, virtualization, the Internet of Things (IoT), and graphics processors, hence fostering innovation and development. In this scholarly essay, a comprehensive examination of artificial intelligence (AI) and learning methodologies spanning the years 1961 to 2018 is conducted. Through an extensive examination of AI, encompassing various aspects such as causal factors, practical systems, fundamental machine learning, commercial achievements, and current advancements, this investigation serves as a highly valuable resource for both academic scholars and industry experts. There is a substantial number of challenges associated with artificial intelligence (AI). However, it is undeniable that AI has seen significant advancements, emerging as an innovative and transformative tool across all domains and applications. © 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

An Analysis of Web Security Measures for Protecting Wireless Networks from Malicious Attack 3

An Analysis of Web Security Measures for Protecting Wireless...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Balaji, N.V. Senthamilselvan, K. Dhabliya, Dharmesh Mishra, Dinesh Saxena, Manish Akhtar, Md. Amir Khusru Karpagam Academy of Higher Education Department of Computer Science Coimbatore641021 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai India Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India Mangalayatan University Department of Computer Science Jabalpur India Himalayan University Department of Computer Science Itanagar India Usha Martin University Department of Coputing & Information Technology Ranchi India

ISBN: (纸本)9798350319125

This technical abstract is an analysis of internet security features for shielding Wi-Fi networks from malicious assaults. The main objective of this evaluation is to perceive the best security features for defensive a wireless community, and to determine which of the net protection alternatives are the best and within your means. The evaluation makes use of each quantitative and qualitative studies methods to degree different factors which includes cost, inconvenience, implementation complexity, and safety warranty. After an extensive assessment of the present net protection alternatives, its miles concluded that a combination of encryption, authentication, firewalls, access control lists, and antivirus/anti-malware software is the maximum efficient approach for preserving a wireless community secure from malicious assaults. Furthermore, the most excellent security features depend upon the size, complexity, and price range of the corporation, and ought to be tailor-made to fulfill the precise needs of the employer. © 2023 IEEE.

关键词： community corporation determine evaluation maximum

来源：评论

学校读者我要写书评

暂无评论

Leakage-Resilient Anonymous Multi-Receiver Outsourced Revocable Certificateless Encryption 5

Leakage-Resilient Anonymous Multi-Receiver Outsourced Revoca...

引用

5th International Conference on computer Communication and the Internet, ICCCI 2023

作者： Tseng, Yuh-Min Chien, Hung-Yu Hung, Ruo-Wei Tsai, Tung-Tso National Changhua University of Education Department of Mathematics Changhua Taiwan National Chinan University Department of Information Management Nantou Taiwan Chaoyang University of Technology Department of Computer Science and Information Engineering Taichung Taiwan National Taiwan Ocean University Department of Computer Science and Engineering Keelung Taiwan

ISBN: (纸本)9798350326956

To reduce the complexity of managing certificates in public-key infrastructure (PKI)-based public key systems (PKI-PKS) and solve the key escrow issue in identity (ID)-based public-key systems (ID-PKS), certificateless public-key systems (CL-PKS) are proposed and play an important role in public-key cryptography. But, a CL-PKS setting should consider the revocation issue to revoke intruded members so that a revocable certificateless public-key setting (RCL-PKS) is used to resolve this issue. Recently, side-channel attacks have been realized and endangered the existing cryptographic schemes/protocols. Fortunately, the research of leakage-resilient cryptographic schemes/protocols resisting such attacks have attracted the attention of cryptologists. Indeed, several leakage-resilient certificateless encryption (LR-CLE) schemes have been proposed. However, these LR-CLE schemes have some deficiencies. In the paper, the first leakage-resilient anonymous multi-receiver outsourced revocable certificateless encryption (LRAMR-ORCLE) scheme is proposed. As compared with several previous schemes, the proposed scheme possesses several merits: (1) The revocation functionality is performed by an outsourced revocation authority;(2) It guards against side-channel attacks and possesses leakage-resilient property;(3) An authorized receiver's identity is anonymous for other receivers;(4) It is a secure one-to-many encryption scheme. © 2023 IEEE.

关键词： Side channel attack

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：