检索结果-内蒙古大学图书馆

2024 Laser science, LS 2024

作者： Xu, Yuan Liu, Jiangnan Singh, Anshuman Tsai, Cheng-Chia Malek, Stephanie C. Shin, Walter Jin Wu, Jiahao Zhu, Freddie Liu, David Yu, Nanfang Mi, Zetian Soltani, Mohammad Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Raytheon BBN Technologies CambridgeMA02138 United States

We fabricated GaN metasurfaces doped with InGaN quantum dots by templated molecular beam epitaxy (MBE) that support tunable high Q-factor quasi-bound states in the continuum (q-BICs) and demonstrated efficient optical... 详细信息

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Domination based graph neural networks

引用

International Journal of computers and Applications 2024年第11期46卷 998-1005页

作者： Meybodi, Mohsen Alambardar Safari, Mahdi Davoodijam, Ensieh Department of Applied Mathematics and Computer Science Faculty of Mathematics and Statistics University of Isfahan Isfahan Iran Department of Software Engineering University of Kashan Kashan Iran

Graph Neural Networks (GNNs) have emerged as a widely used and effective method across various domains for learning from graph data. Despite the abundance of GNN variants, many struggle with effectively propagating messages over long distances. This paper introduces a novel hierarchical message passing framework for graph learning, specifically designed to address the challenge of long-distance message propagation in graphs. By constructing smaller graphs from the main graph using the concept of domination, a fundamental principle in graph theory, we facilitate more efficient message passing within each subgraph. Subsequently, we employ a Graph Attention Network (GAT) to aggregate these features and propagate them to distant nodes across the graph. Experimental results on standard node classification datasets validate that the proposed architecture achieves performance comparable to or better than conventional GNNs. Additionally, our model consistently performs better on graphs with missing edges. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Prognostic Kalman Filter Based Bayesian Learning Model for Data Accuracy Prediction

引用

computers, Materials & Continua 2022年第7期72卷 243-259页

作者： S.Karthik Robin Singh Bhadoria Jeong Gon Lee Arun Kumar Sivaraman Sovan Samanta A.Balasundaram Brijesh Kumar Chaurasia S.Ashokkumar Department of ECE College of Engineering and TechnologySRM Institute of Science and TechnologyVadapalaniChennai600026India Department of CSE Birla Institute of Applied Sciences(BIAS)BhimtalUttarakhand263136India Division of Applied Mathematics Wonkwang University460Iksan-DaeroIksan-SiJeonbuk54538Korea School of Computer Science and Engineering Vellore Institute of Technology(VIT)Chennai600127India Department of Mathematics Tamralipta MahavidyalayaWest Bengal721636India School of Computer Science and Engineering Center for Cyber Physical SystemsVellore Institute of Technology(VIT)Chennai600127India Indian Institute of Information Technology(IIIT) LucknowUttar Pradesh226002India Department of Computer Science and Engineering Saveetha School of EngineeringSIMATSChennai602105India

Data is always a crucial issue of concern especially during its prediction and computation in digital *** paper exactly helps in providing efficient learning mechanism for accurate predictability and reducing redundant data *** also discusses the Bayesian analysis that finds the conditional probability of at least two parametric based predictions for the *** paper presents a method for improving the performance of Bayesian classification using the combination of Kalman Filter and *** method is applied on a small dataset just for establishing the fact that the proposed algorithm can reduce the time for computing the clusters from *** proposed Bayesian learning probabilistic model is used to check the statistical noise and other inaccuracies using unknown *** scenario is being implemented using efficient machine learning algorithm to perpetuate the Bayesian probabilistic *** also demonstrates the generative function forKalman-filer based prediction model and its *** paper implements the algorithm using open source platform of Python and efficiently integrates all different modules to piece of code via Common Platform Enumeration(CPE)for Python.

关键词： Bayesian learning model kalman filter machine learning data accuracy prediction

来源：评论

学校读者我要写书评

暂无评论

Hesitant Bi-fuzzy Dombi Operator Based Group Decision-making Approach for Electric Vehicle Selection

引用

Process Integration and Optimization for Sustainability 2025年 1-35页

作者： Golui, S. Das, Bidyut Mahapatra, G.S. Mahapatra, B.S. Department of Engineering Sciences and Humanities Siliguri Institute of Technology Siliguri734009 India Department of Applied Mathematics Maulana Abul Kalam Azad University of Technology Haringhata741249 India Department of Master of Computer Applications Siliguri Institute of Technology Siliguri734009 India Department of Mathematics National Institute of Technology Puducherry Karaikal609609 India School of Applied Science and Humanities Haldia Institute of Technology Haldia721657 India

Electric vehicles (EVs) are one of the sustainable modes of transportation that can reduce the air pollution caused by fossil fuel-powered automobiles. The literature overlooks non-technical criteria, including environmental considerations and social responsibility in the EV selection process, which may navigate the adoption of EVs. This study addresses the EV selection process in the hesitant bi-fuzzy context, considering technical and non-technical EV features. A multi-criteria group decision-making approach is developed to evaluate EVs utilizing a modified hesitant bi-fuzzy COmbinative Distance-based Assessment technique. This study proposes a novel hesitant bi-fuzzy Dombi weighted average operator to integrate the decision maker’s opinions with their weightage. The proposed approach incorporates the importance of the criteria evaluated by the method based on the removal effects of criteria and hesitant information in Euclidean and Taxicab metrics to produce the ranking sequence of EVs. The Python code for the suggested group decision-making model is provided to rationalize the computational process. This study highlights the relative importance of charging time, price, and range compared to the remaining features in selecting EVs. The study’s findings indicate that the technical features of an EV are still a primary consideration for the customers. These findings will assist policymakers and EV industry stakeholders in making decisions to focus on EV modification. A comparative analysis with the existing decision-making models encompasses the applicability of the proposed technique. In contrast, the sensitivity analysis demonstrates the suggested approach’s robustness through the alteration in decision makers’ s preferences, internal parameters, and criteria importance to assess their impact on the final rankings of EVs. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

A Novel Perspective on Brain Tumor Classification Using Hybrid Algorithm

A Novel Perspective on Brain Tumor Classification Using Hybr...

引用

2023 International Conference on computer, Electronics and Electrical engineering and their Applications, IC2E3 2023

作者： Jayanthi, R. Christinal, A. Hepzibah Hephzibah, R. Shekinah, T. Bajaj, Chandrajit Chandy, D. Abraham Karunya University Department of Mathematics Coimbatore India Loyola - Icam College of Engineering and Technology Department of Computer Science and Engineering Chennai India University of Texas Computational Applied Mathematics Chair in Visualization Austin United States Karunya University Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798350338003

Brain tumor classification is a critical task in medical imaging, where the early and accurate detection of brain tumors is crucial for patient treatment and survival. In recent years, Machine Learning techniques have emerged as a promising approach for automated brain tumor classification. In this paper, we investigate the performance of three ML classifiers - Support Vector Machine, Naïve Bayes, and an ensemble of SVM and Naïve Bayes - for the two-class classification of brain tumor data into a tumor and no tumor classes. Our experiments demonstrate that the ensemble of SVM and Naïve Bayes classifier achieved an accuracy of 97% outperforming the other classifiers. These results indicate that our ensemble classifier can be a powerful tool for the accurate and efficient classification of brain tumor data, potentially leading to improved patient outcomes. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Development of Virtual Reality Platform through Human computer Interaction using Artificial Intelligence 3

Development of Virtual Reality Platform through Human Comput...

引用

3rd International Conference on applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Saranya, S. Channarayapriya, B. Harshavardhini, U. Nandhini, A.Sunitha Revathi, J. Venkatesan, R. New Horizon College of Engineering Department of Computer Science and Engineering Bangalore India Vel Tech Multi Tech Dr.Rangarajan Dr Sakunthala Engineering College Deparment of Information Technology Chennai India Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India Kongu Engineering College Department of Mathematics Erode India Bannari Amman Institute of Technology Deparment of Information Technology Erode India

ISBN: (纸本)9798350375190

The development of a virtual reality platform through human-computer interaction (HCI) is obtained using deep learning with a genetic algorithm. The human-computer interaction forms a bridge between users and the VR system. This helps in providing a natural interaction experience to the users. Deep learning techniques help in obtaining the realistic nature of the physical world in the virtual platform. The personalized experiences are obtained using the integration of deep learning with VR platforms. The optimization algorithm helps in achieving user interaction in a real-time platform. The adaptive learning helps in increasing the overall immersion with a user-friendly interface. The VR development process is done using a genetic algorithm. This helps to evolve and optimize themselves within the period of time. This helps the VR platform to iteratively improve its performance and complete design through adopting successful combinations of various parameters. The proposed approach helps the VR system to evolve towards an optimal condition. This helps to satisfy the various needs and preferences of the users. Thus the proposed system helps in obtaining adaptive and intelligent virtual environments. This helps in overcoming various challenges in designing immersive VR experiences with personalized digital environments. © 2024 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Military Decoys for the Digital Age

Military Decoys for the Digital Age

引用

MILCOM, Military Communications Conference

作者： Stefan Tschimben Isabella Bates Rucha Khairnar Joanna Crosby James H. Curry Keith D. Gremban Aerospace Engineering University of Colorado Boulder Applied Mathematics and Computer Science University of Colorado Boulder Applied Mathematics University of Colorado Boulder LLC RDMPierce

ISBN: (数字)9798350374230

ISBN: (纸本)9798350374247

The rapid proliferation of smartphones over the last decades presents new challenges for military communication and commanders. Besides dealing with device and application vulnerabilities, the intentional and unintentional information transmitted by every device can reveal important information about troop locations and movements. This research seeks to address some of these challenges by using decoys to increase operational security. Using Wi-Fi data from the University of Colorado Boulder as a surrogate for cellular data and using models generated with Nonnegative Matrix Factorization (NMF), three Wi-Fi decoys are deployed at three locations across campus to simulate network activity from a military scenario. By populating alternate locations with decoy devices to mimic real activity, this research shows how NMF can be used to create models that can effectively be translated into real network activity to obfuscate real operations. This enhances operational security by dispersing network signatures and confusing adversarial detection.

关键词： Military communication Information age Data models Security Wireless fidelity Smart phones

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Nature-Inspired Algorithms for Task Assignment Problem 5th

Comparative Analysis of Nature-Inspired Algorithms for Tas...

引用

5th International Conference on Trends in Computational and Cognitive engineering, TCCE 2023

作者： Mishra, Pawan Pooja Jolly Tripathi, Shashi Prakash Upadhyay, Kamal Kishor Department of Electronics and Communication Engineering University of Allahabad Uttar Pradesh Prayagraj India Department of Applied Mathematics and Computer Science Liverpool John Moores University Liverpool United Kingdom Department of Electronics and Communication Engineering JSS Academy of Technical Education Noida India

ISBN: (纸本)9789819719228

In modern task assignment scenarios, the effective allocation of tasks to individuals with suitable skill levels is crucial to ensure efficient execution and resource utilization. This research addresses the problem of task assignment optimization, focusing on minimizing the discrepancy between the assigned skill levels of individuals and the required skill levels for each task. In this research, a comprehensive comparative analysis of nature-inspired algorithms applied to the TAP, to iteratively refine task assignments and improve skill matching. Nature-inspired algorithms (NIA) draw inspiration from biological and ecological processes, mimicking patterns observed in nature to solve complex problems. This study investigates four prominent nature-inspired algorithms: Jaya algorithm and Ant Colony Optimization (ACO) algorithm from Swarm Intelligence, genetic algorithm (GA), and Differential evolution from Evolutionary algorithm. These NIA approaches demonstrate its potential to provide practical solutions to complex task assignment challenges by mitigating skill mismatches and fostering efficient task execution. The significance of this research lies in its applicability to real-world scenarios such as project management, workforce scheduling, and resource allocation. By optimizing task assignments based on skill levels, organizations can enhance productivity, minimize skill wastage, and improve resource utilization. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Intelligent recognition system for viewpoint variations on gait and speech using CNN-CapsNet

引用

International Journal of Intelligent Computing and Cybernetics 2022年第3期15卷 363-382页

作者： G.Merlin Linda N.V.S.Sree Rathna Lakshmi N.Senthil Murugan Rajendra Prasad Mahapatra V.Muthukumaran M.Sivaram Department of Computer Science and Engineering SRM Institute of Science and Technology–Vadapalani CampusChennaiIndia Department of Electronics and Communication Engineering Agni College of TechnologyChennaiIndia School of Computer Science and Engineering VIT-AP UniversityAmaravatiIndia Department of Computer Science and Engineering SRM Institute of Science and TechnologyGhaziabadIndia Department of Mathematics School of Applied SciencesREVA UniversityBangaloreIndia Faculty of Information Technology Ton Duc Thang UniversityHo Chi Minh CityVietnam

Purpose-The paper aims to introduce an intelligent recognition system for viewpoint variations of gait and *** proposes a convolutional neural network-based capsule network(CNN-CapsNet)model and outlining the performance of the system in recognition of gait and speech *** proposed intelligent system mainly focuses on relative spatial hierarchies between gait features in the entities of the image due to translational invariances in sub-sampling and speech ***/methodology/approach-This proposed work CNN-CapsNet is mainly used for automatic learning of feature representations based on CNNand used capsule vectors as neurons to encode all the spatial information of an image by adapting equal variances to change in *** proposed study will resolve the discrepancies caused by cofactors and gait recognition between opinions based on a model of ***-This research work provides recognition of signal,biometric-based gait recognition and sound/speech *** evaluations are conducted on three aspects of scenarios,namely fixed-view,cross-view and multi-view *** main parameters for recognition of gait are speed,change in clothes,subjects walking with carrying object and intensity of *** limitations/implications-The proposed CNN-CapsNet has some limitations when considering for detecting the walking targets from surveillance videos considering multimodal fusion approaches using hardware sensor *** can also act as a pre-requisite tool to analyze,identify,detect and verify the malware *** implications-This research work includes for detecting the walking targets from surveillance videos considering multimodal fusion approaches using hardware sensor *** can also act as a pre-requisite tool to analyze,identify,detect and verify the malware ***/value-This proposed research work proves to be performing better for the recognition of gait and speech when

关键词： Intelligent system Gait recognition Convolutional neural network Deep learning Capsule network Viewpoint variations

来源：评论

学校读者我要写书评

暂无评论

Security framework for IoT and deep belief network-based healthcare system using blockchain technology

引用

International Journal of Electronic Business 2022年第3期17卷 226-243页

作者： Nagarajan, Senthil Murugan Anandhan, Prathik Muthukumaran, V. Uma, K. Kumaran, U. School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Mathematics School of Applied Sciences REVA University Bengaluru India School of Advance Sciences Vellore Institute of Technology Vellore India Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

Nowadays, the computerisation and information systems need very fast, easier and secure data analysis models. So, blockchain technology and deep learning concepts play important roles for data security and analysis in field of healthcare applications. Blockchain technology has optimal reliability in various sectors like healthcare, security, information management, smart home, etc. In this paper, blockchain technology is used for the healthcare system to provide a secure and reliable data transmission. Furthermore, IoT-based wearable devices are used to collect the data from the patients. Moreover, deep belief network (DBN) is proposed to classify the obtained data in order to predict the type of disease or problems of the patients. The experimental results shows that the proposed framework and classification model abruptly outperforms when compared with other existing techniques. The efficiency of the proposed framework is analysed based on the performance metrics like throughput and latency. The obtained loss ratio for the proposed model seems very less of 0.0126 when compared with other existing techniques like MLP, SVM, ANN, and CNN. The accuracy obtained for the proposed DBN classifier is above 95% for the increase in the number of patients. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Internet of things

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：