检索结果-内蒙古大学图书馆

Run time dynamic digital twins and dynamic digital twins networks

Future Generation Computer Systems 2025年 172卷

作者： Alexander Vodyaho Radhakrishnan Delhibabu Dmitry I. Ignatov Nataly Zhukova Department of Computer Science and Engineering Saint Petersburg Electrotechnical University ‘LETI’ (ETU) St. Petersburg 197376 Russia School of Computing Science and Engineering (SCOPE) Vellore Institute of Technology Vellore 632014 India Computer Science Faculty School of Data Analysis and Artificial Intelligence HSE University Moscow 109028 Russia St. Petersburg Federal Research Center of the Russian Academy of Sciences St. Petersburg 199178 Russia

Digital twins are widely used for building various types of cyber–physical systems. There are a huge number of publications devoted to the use of digital twins in production systems. Much less attention is paid to the issues of building runtime digital twins. The article describes an approach to building complex distributed cyber–physical systems with a high level of architectural dynamics built on fog and edge computing platforms based on the use of digital twins. The issues of implementing runtime digital twins and distributed systems of runtime digital twins are considered. The requirements to runtime digital twins are defined. Typical problem statements for constructing and maintaining a runtime digital twin system are formulated. A reference architecture of a dynamic runtime digital twin is proposed, which includes a model of the observed system (or the object) and a model processor. The dynamic model of the observed and managed system is considered as a key element of the digital twin. Possible approaches to the synthesis of built-in models of runtime digital twins are discussed. Examples of using the proposed approach to solve practical problems are given. The described approach may be of interest to specialists involved in research and development of various types of information systems implemented on Internet of Things platforms, such as smart cities, smart transport, medical information systems, etc. It is proposed to conduct further research and development in the areas of creating human digital twins.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure multimedia communication: advanced asymmetric key authentication with grayscale visual cryptography

引用

Mathematical Biosciences and Engineering 2024年第3期21卷 4762-4778页

作者： Liu, Tao Vairagar, Shubhangi Adagale, Sushadevi Karthick, T. Karunya, Catherine Esther Blesswin, A. John Mary, G. Selva Tianjin Sino-German University of Applied Sciences Tianjin300350 China Department of Artificial Intelligence and Data Science Dr. D. Y. Patil Institute of Technology Pimpri Pune411018 India Department of Computer Engineering KJEI's Trinity Academy of Engineering Pune411048 India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur603203 India Computer Science and Engineering School of Computing SRM Institute of Science and Technology Kattankulathur603203 India Directorate of Learning and Development SRM Institute of Science and Technology Kattankulathur603203 India

The secure authentication of user data is crucial in various sectors, including digital banking, medical applications and e-governance, especially for images. Secure communication protects against data tampering and forgery, thereby bolstering the foundation for informed decision-making, whether managing traffic, enhancing public safety, or monitoring environmental conditions. Conventional visual cryptographic protocols offer solutions, particularly for color images, though they grapple with challenges such as high computational demands and reliance on multiple cover images. Additionally, they often require third-party authorization to verify the image integrity. On the other hand, visual cryptography offers a streamlined approach. It divides images into shares, where each pixel represented uniquely, thus allowing visual decryption without complex computations. The optimized multi-tiered authentication protocol (OMTAP), which is integrated with the visual sharing scheme (VSS), takes secure image sharing to the next level. It reduces share count, prioritizes image fidelity and transmission security, and introduces the self-verification of decrypted image integrity through asymmetric key matrix generators, thus eliminating external validation. Rigorous testing has confirmed OMTAP's robustness and broad applicability, thereby ensuring that decrypted images maintain their quality with a peak signal-to-noise ratio (PSNR) of 40 dB and full integrity at the receiver's end. © 2024 American institute of Mathematical sciences. All rights reserved.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

Twitter-Based Early Depression Detection Through Machine Learning 4th

Twitter-Based Early Depression Detection Through Machine Lea...

引用

4th International Conference on Advances in Computational science and Engineering, ICACSE 2023

作者： Ting, Kee Hui Majid, Mazlina Abdul Ibrahim, Ashraf Osman Faculty of Computing Universiti Malaysia Pahang Al-Sultan Abdullah Pekan Pahang Malaysia Creative Advanced Machine Intelligence Research Centre Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Sabah Malaysia Centre for Artificial Intelligence & Data Science Universiti Malaysia Pahang Al-Sultan Abdullah Pekan Pahang Malaysia

ISBN: (纸本)9789819729760

Depression, a prevalent mental health disorder, significantly affects individuals’ quality of life, emphasizing the critical need for early detection and intervention to ensure successful treatment. However, conventional methods for early depression detection have limitations that can impact accuracy and effectiveness. The proposed research advocates integrating technology to overcome these challenges, explicitly leveraging social media and machine learning. The focus is on detecting early signs of depression in Twitter users. A dataset of tweet texts is gathered and employed in machine learning classifiers, including Naïve Bayes, Logistic Regression, and Support Vector Machine (SVM). The research aims to identify the most effective algorithm for depression detection by comparing testing results and determining the classifier with the highest accuracy level. This contributes to achieving Sustainable Development Goal 3 (SDG3) by enhancing individuals’ quality of life. The result proved that the Support Vector Machine (Linear Support Vector Classifier) is best performed with the highest accuracy value of 90.57% among the three tested classification models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

A Mathematical Model to Minimize the Total Cultivation Cost of Sugarcane 11th

A Mathematical Model to Minimize the Total Cultivation Cost ...

引用

11th International Conference on Soft computing for Problem Solving, SocProS 2022

作者： Kumar, Sumit Pant, Millie Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Roorkee Uttarakhand Roorkee India Mehta Family School for Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Uttarakhand Roorkee India

ISBN: (纸本)9789811965241

In the present study, a non-linear mathematical model is proposed to minimize the total expenditure made on sugarcane cultivation. The objective here is to optimize the costs involved in transportation, cultivation, and management of the deterioration of sugarcane. The optimization tools used are Differential Evolution (DE) and Particle Swarm Optimization (PSO). Further, the model is validated by comparing the actual expenditure of sugarcane cultivation with results obtained by PSO and DE, which indicates that the application of optimization methods may help in reducing the expenditure made on sugarcane cultivation. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Efficiency Assessment of an institute Through Parallel Network data Envelopment Analysis 11th

Efficiency Assessment of an Institute Through Parallel Netwo...

引用

11th International Conference on Soft computing for Problem Solving, SocProS 2022

作者： Kumar, Atul Panwar, Ankita Pant, Millie Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Roorkee Roorkee247667 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Roorkee247667 India

ISBN: (纸本)9789811965241

Conventional data envelopment analysis (DEA) is a non-parametric approach to examine the efficiency of similar decision-making units (DMUs) as a whole system without considering its internal structure, i.e., the system is considered as a black box. Therefore, a network DEA (NDEA) is needed to study the internal structure of a system. By allowing for the measurement of individual components, an NDEA model can reveal inefficiencies that a traditional DEA ignores. In this study, we use the parallel network DEA to calculate the efficiency of a higher education institute with 19 decision-making units (DMUs) using two parallel processes (teaching and research) and compare it with the conventional DEA, CCR model through a numerical example. The main advantages of the parallel NDEA model are (i) to identify which DMUs are inefficient and make necessary adjustments, and (ii) the parallel DEA model has a lower efficiency score than the traditional DEA model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A generalized software reliability prediction model for module based software incorporating testing effort with cost model

引用

Life Cycle Reliability and Safety Engineering 2024年第4期13卷 419-436页

作者： Yadav, Akshay Kumar Srivastava, Shilpa Pant, Millie Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Roorkee 247001 India Christ University Karnataka Bengaluru 560029 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee 247667 India

As software innovation has advanced, it has been noted that the testing effort function (TEF) is one of the key factors influencing the improvement of software reliability. This paper presents a simplified model which incorporates the testing effort for the reliability growth of a software. A closed form solution has been derived for the reliability of the software. This study examines the impact of testing efforts on a software reliability model based on NHPP. The sensitivity analysis has been made available to investigate how the created model's system parameters affect the cost function, mean value function, and software’s reliability. The parameters of the model have been estimated using the non-linear least square estimation (MLE) method in MATLAB software. Additionally, a warranty cost model is constructed to assess the optimal release policy for the software. The general form of the reliability expression involves elliptic integrals, which can be computed easily through a software like Mathematica. We have derived analytical solutions for reliability pertaining to several particular cases. Optimal release time for the software product has been calculated for some particular cost-sets. Goodness of fit curves have been plotted to compare the proposed model with some well-known existing SRGMs. Numerical illustrations are provided to bolster the analytical outcomes. © The Author(s), under exclusive licence to Society for Reliability and Safety (SRESA) 2024.

关键词： Maximum likelihood estimation (MLE) Non-homogeneous Poisson process (NHPP) Optimal release time (ORT) Software reliability growth model (SRGM) Testing effort function (TEF) Warranty cost model

来源：评论

学校读者我要写书评

暂无评论

Multi-View Dynamic Kernelized Evidential Clustering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第12期11卷 2435-2450页

作者： Jinyi Xu Zuowei Zhang Ze Lin Yixiang Chen Weiping Ding the Software Engineering Institute East China Normal UniversityShanghai 200062 Shanghai Key Laboratory of Trustworthy Computing East China Normal UniversityShanghai 200062China IEEE the School of Automation Northwestern Polytechnical UniversityXi’an 710072China the School of Artificial Intelligence and Computer Science Nantong UniversityNantong 226019 the Faculty of Data Science City University of MacaoMacao 999078China

It is challenging to cluster multi-view data in which the clusters have overlapping *** multi-view clustering methods often misclassify the indistinguishable objects in overlapping areas by forcing them into single clusters,increasing clustering *** solution,the multi-view dynamic kernelized evidential clustering method(MvDKE),addresses this by assigning these objects to meta-clusters,a union of several related singleton clusters,effectively capturing the local imprecision in overlapping *** offers two main advantages:firstly,it significantly reduces computational complexity through a dynamic framework for evidential clustering,and secondly,it adeptly handles non-spherical data using kernel techniques within its objective *** on various datasets confirm MvDKE's superior ability to accurately characterize the local imprecision in multi-view non-spherical data,achieving better efficiency and outperforming existing methods in overall performance.

关键词： Evidential clustering imprecision characterizing kernel technique multi-view clustering

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Disease Identification in Cassava Plants Using RGB Imaging 6th

Deep Learning for Disease Identification in Cassava Plants U...

引用

6th International Conference on Recent Innovations in computing, ICRIC 2023

作者： Sutar, Shivam Mohite, Snehal Kamble, Tushar Kolhar, Shrikrishna Jagtap, Jayant Shastri, Rajveer Joshi, Shubham Vidya Pratishthan’s Kamalnayan Bajaj Institute of Engineering and Technology Maharashtra Baramati India Maharashtra Pune India Marik Institute of Computing Artificial Intelligence Robotics and Cybernetics NIMS University Rajasthan Jaipur303121 India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Maharashtra Pune411037 India

ISBN: (纸本)9789819778614

Agriculture is the most critical sector in the world economy. Food security and consistent food supply are the key challenges due to rapid growth in the world population and crop diseases. Crop yield gets significantly hampered due to diseases attacking large crop fields. The precise classification of plant diseases is essential to provide appropriate pesticide supplements. This study applies deep learning (DL) models to identify diseases in cassava plants using red–green–blue (RGB) images. Three models, namely Xception-net, MobileNetV2, and EfficientNetB0, are trained and evaluated on the cassava disease dataset publicly available on Kaggle. Since the dataset is imbalanced, five-fold cross-validation is used to check the consistency of the results. Transfer learning and random weight initialization were used for model training. The Xception-net is the clear winner among the three models, with an accuracy of 87.8% using transfer learning, 81.33% using random weight initialization, and 85% average accuracy using five-fold cross-validation. Further, this work is extended to develop web and mobile applications with DL models deployed at the backend to predict plant diseases from input images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Adversarial mutual information learning for network embedding 29

Adversarial mutual information learning for network embeddin...

引用

29th International Joint Conference on artificial intelligence, IJCAI 2020

作者： He, Dongxiao Zhai, Lu Li, Zhigang Yang, Liang Jin, Di Huang, Yuxiao Yu, Philip S. College of Intelligence and Computing Tianjin University Tianjin China School of Artificial Intelligence Hebei University of Technology Tianjin China Data Science George Washington University WashingtonDC United States Department of Computer Science University of Illinois at Chicago ChicagoIL United States Institute for Data Science Tsinghua University Beijing China

ISBN: (纸本)9780999241165

Network embedding which is to learn a low dimensional representation of nodes in a network has been used in many network analysis tasks. Some network embedding methods, including those based on generative adversarial networks (GAN) (a promising deep learning technique), have been proposed recently. Existing GAN-based methods typically use GAN to learn a Gaussian distribution as a priori for network embedding. However, this strategy makes it difficult to distinguish the node representation from Gaussian distribution. Moreover, it does not make full use of the essential advantage of GAN (that is to adversarially learn the representation mechanism rather than the representation itself), leading to compromised performance of the method. To address this problem, we propose to use the adversarial idea on the representation mechanism, i.e. on the encoding mechanism under the framework of autoencoder. Specifically, we use the mutual information between node attributes and embedding as a reasonable alternative of this encoding mechanism (which is much easier to track). Additionally, we introduce another mapping mechanism (which is based on GAN) as a competitor into the adversarial learning system. A range of empirical results demonstrate the effectiveness of this new approach. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Temporal Structural Probability Network for Weather Prediction

Temporal Structural Probability Network for Weather Predicti...

引用

2023 International Conference on Sustainable computing and Smart Systems, ICSCSS 2023

作者： Veeramani, R. Sathya Bama, B. Deeptha, R. Ishwarya, M.V. Karthikeyan, U. Srm Institute of Science and Technology Ramapuram Department of Information Technology Chennai India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Chennai India Srm Institute of Science and Technology Kattankulathur Department of Computing Technologies Chennai India

ISBN: (纸本)9798350333602

A large number of people and assets are destroyed each year as a result of severe weather, such as cyclones, lightning, storm, or rain. Scientists are developing machine learning approaches that can help forecasters better anticipate these catastrophes by better understanding the underlying mechanisms and generating more accurate empirical models. Temporal structural probability networks have been significantly improved in this research, allowing for autonomous discovery of spatiotemporal correlations and the capacity to learn with any form. Prediction of thunderstorms in Texas and aero plane instability in the United States are the focus of the evaluations of suggested method. As part of the work discussion on how to assess the effectiveness of a machine learning algorithm in the context of severe weather, the system give a collection of instructions cultured for given machine learning techniques and talk about how to implement the proposed strategy. © 2023 IEEE.

关键词： Storms

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：