检索结果-内蒙古大学图书馆

6th International Conference on Power and Energy Technology, ICPET 2024

作者： Su, Zhao-Gang Chen, Sheng-Jie Li, Yu-Fei Chen, Liang Kou, Caixia Cai, Zhi Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China Institute of Applied Mathematics Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China College of Sciences Beijing University of Posts and Telecommunications Beijing China Beijing Key Laboratory of Research and System Evaluation of Power Dispatching Automation Technology China Electric Power Research Institute Beijing China

ISBN: (纸本)9798350375855

The unit commitment (UC) problem has been extensively researched in the literature, which is typically formulated as a mixed integer programming (MIP) problem. However, current studies lack effective methods to identify potential UC problem structures within a general MIP problem, making it challenging to leverage well-established valid inequalities for UC problems to accelerate the solution process. In this paper, we present a novel detection method that automatically identifies UC structures within an MIP problem by analyzing the relationships between variables and constraints. Moreover, we enhance the MIP formulation by incorporating three well-studied classes of valid inequalities as cutting planes, based on the identified UC structures. Our experiments demonstrate that our proposed UC detection method greatly improves computational efficacy of a standard MIP solver compared to the default setting. © 2024 IEEE.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Detecting Leaf Diseases Using Centralized CNN'S with Efficient R-CNN and Mask R-CNN

Detecting Leaf Diseases Using Centralized CNN'S with Efficie...

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： Pongiannan R K Samudra Banerjee Poornima P U Brindha R Richard Pravin A Franklin J Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur India Department of Computational intelligence SRM Institute of Science and Technology Kattankulathur India Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Kattankulathur India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510039

Plant diseases have emerged as a significant concern, as they can drastically reduce both the quality and quantity of agricultural products. The research aims to identify plant leaf infections early on, enabling timely treatment to prevent the spread of diseases to other plants. The objective is to determine the severity of leaf diseases, allowing for targeted treatment based on the level of severity. Additionally, the severity of leaf diseases can help predict crop losses. This work is to improve the accuracy of leaf detection and measurement of morphological traits by Region Convolutional Neural Network (RCNN), Network namely state of the Mask region art. Experimental results verify that our automated approach effectively segments leaves from different plant families. Measured leaves of comparable size have an average relative error of about 4.6 percent for leaf length and approximately 5.7 percent for leaf width when compared to manual measurements by expert ecologists and botanists.

关键词： Plant diseases Accuracy Measurement uncertainty Neural networks Length measurement Size measurement Prediction algorithms Convolutional neural networks Standards Diseases

来源：评论

学校读者我要写书评

暂无评论

Evidence for validity and reliability of a research-based assessment instrument on measurement uncertainty

引用

Physical Review Physics Education Research 2024年第2期20卷 020125页

作者： Gayle Geschwind Michael Vignal Marcos D. Caballero H. J. Lewandowski National Institute of Standards and Technology and the University of Colorado Boulder Colorado 80309 USA Department of Physics Department of Physics and Astronomy and CREATE for STEM Institute Department of Computational Mathematics Science and Engineering Department of Physics and Center for Computing in Science Education

The Survey of Physics Reasoning on Uncertainty Concepts in Experiments (SPRUCE) was designed to measure students’ proficiency with measurement uncertainty concepts and practices across ten different assessment objectives to help facilitate the improvement of laboratory instruction focused on this important topic. To ensure the reliability and validity of this assessment, we conducted a comprehensive statistical analysis using classical test theory. This analysis includes an evaluation of the test as a whole, as well as an in-depth examination of individual items and assessment objectives. We make use of a previously reported on scoring scheme involving pairing items with assessment objectives, creating a new unit for statistical analysis referred to as a “couplet.” The findings from our analysis provide evidence for the reliability and validity of SPRUCE as an assessment tool for undergraduate physics labs. This increases both instructors’ and researchers’ confidence in using SPRUCE for measuring students’ proficiency with measurement uncertainty concepts and practices to ultimately improve laboratory instruction. Additionally, our results using couplets and assessment objectives demonstrate how these can be used with traditional classic test theory analysis.

关键词： Assessment Research methodology

来源：评论

学校读者我要写书评

暂无评论

Optimal convergence in finite element semi-discrete error analysis of the Doyle-Fuller-Newman model beyond 1D with a novel projection operator

arXiv

引用

arXiv 2024年

作者： Xu, Shu Cao, Liqun School of Mathematical Sciences Peking University Beijing100871 China Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China LSEC NCMIS Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

We present a finite element semi-discrete error analysis for the Doyle-Fuller-Newman model, which is the most popular model for lithium-ion batteries. Central to our approach is a novel projection operator designed for the pseudo-(N+1)-dimensional equation, offering a powerful tool for multiscale equation analysis. Our results bridge a gap in the analysis for dimensions 2 ≤N ≤3 and achieve optimal convergence rates of h+(∆r)2. Additionally, we perform a detailed numerical verification, marking the first such validation in this context. By avoiding the change of variables, our error analysis can also be extended beyond isothermal conditions. Copyright © 2024, The Authors. All rights reserved.

关键词： Discrete element methods

来源：评论

学校读者我要写书评

暂无评论

Secure Data Reduplication System with Efficient and Reliable Multi-Key Management in Cloud Storage 3

Secure Data Reduplication System with Efficient and Reliable...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Jayaram, B. Suguna, T. Fairooz, Shaik Arul Selvam, P. Vimal, S. Rmk Engineering College Department of Computer Science and Business Systems Tamil Nadu Kavaraipettai India Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Malla Reddy Engineering College Department of Cse -AIML Telangana Secunderabad India Hindusthan College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350336238

Malicious hackers may compromise hundreds or millions of machines with little effort, allowing them to shut down networks, steal sensitive data, and compromise critical infrastructure. Data is stolen and used for malicious purposes by hackers who exploit security flaws in the network. And the sophisticated technology they use, like the bucks they do, are continually feeding them the information they needed, not just once. Moreover, even if Internet firewalls have improved, cybercrime has been on the rise. Then, we have a long way to go before we approach the limit, what with all the different kinds of cloud server devices that can connect to the internet nowadays. It's certain that in the future, little devices, no matter how helpful they are really in our everyday lives, will become the preferred tool of villains. In this research, we offer a novel security technique for protecting sensitive data on cloud servers. This intelligent cloud server was protected from any hacking with the aid of this algorithm. The system's output was measured against those of pre-existing algorithms. More than 96% of inputs are authenticated by the proposed technique, while password cracking operations are reduced by about 3%. The source code security management is improved to 99% and the updating issues for various devices entries is reduced 0.02%, and further the privacy breach is reduced up to 0.32%. Hence the proposed method was more secured from cyber security issues. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Aquaculture Practices: IoT and Deep Learning-based Remote Monitoring for Sustainable Fish Farming 5

Revolutionizing Aquaculture Practices: IoT and Deep Learning...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Chelladurai, S. Prince Shiny, G.Susan Jeevitha, S.V. Swapna, P. Pavithra, R. Arulraj, S. Srm Institute of Science and Technology Faculty of Engineering and Technology School of Computing Department of Computational Intelligence Chennai Kattankulathur India Sethu institute of Technology Department of information technology Kariapatti Virudhunagar Tamil Nadu Pulloor626115 India Bannari Amman Institute of Technology Department of information technology Erode India Velammal college of engineering and technology Department of Cse Madurai India Rathinam Technical Campus Department of Ece Coimbatore India

ISBN: (纸本)9798331504403

Aquaculture plays a vital role in meeting the growing demand for seafood while addressing sustainability concerns in fisheries. To optimize fish growth and ensure efficient resource utilization an innovative IoT and Deep Learning-based remote monitoring system is proposed tailored for aquaculture operations. Our system integrates sensor technology, IOT connectivity, and Deep Learning algorithms to provide real-time monitoring and control of key environmental parameters such as water temperature, pH levels, oxygen concentration, and feeding behavior. By leveraging a network of sensors deployed in aquaculture facilities, our system collects and analyzes environmental data to optimize aquaculture practices and ensure optimal conditions for fish growth. Through a user-friendly interface accessible via web or mobile applications, aqua-culturists can remotely monitor the status of their facilities and adjust operational parameters as needed. Additionally, our system utilizes Deep Learning algorithms to analyze historical data and predict optimal feeding schedules, thereby enhancing feed efficiency and fish growth rates. Field trials demonstrate the effectiveness of our IOT and Deep Learning-based monitoring system in improving fish health and productivity while reducing environmental impacts and operational costs. Our findings highlight the potential of IoT and Deep Learning technologies in revolutionizing aquaculture practices, promoting sustainability, and enhancing food security in fisheries © 2024 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Sequential infinite-dimensional Bayesian optimal experimental design with derivative-informed latent attention neural operator

arXiv

引用

arXiv 2024年

作者： Go, Jinwoo Chen, Peng School of Computational Science and Engineering College of Computing Georgia Institute of Technology 756 West Peachtree Street Northwest AtlantaGA30308 United States

We develop a new computational framework to solve sequential Bayesian optimal experimental design (SBOED) problems constrained by large-scale partial differential equations with infinite-dimensional random parameters. We propose an adaptive terminal formulation of the optimality criteria for SBOED to achieve adaptive global optimality. We also establish an equivalent optimization formulation to achieve computational simplicity enabled by Laplace and low-rank approximations of the posterior. To accelerate the solution of the SBOED problem, we develop a derivative-informed latent attention neural operator (LANO), a new neural network surrogate model that leverages (1) derivative-informed dimension reduction for latent encoding, (2) an attention mechanism to capture the dynamics in the latent space, (3) an efficient training in the latent space augmented by projected Jacobian, which collectively leads to an efficient, accurate, and scalable surrogate in computing not only the parameter-to-observable (PtO) maps but also their Jacobians. We further develop the formulation for the computation of the MAP points, the eigenpairs, and the sampling from posterior by LANO in the reduced spaces and use these computations to solve the SBOED problem. We demonstrate the superior accuracy of LANO compared to two other neural architectures and the high accuracy of LANO compared to the finite element method (FEM) for the computation of MAP points and eigenvalues in solving the SBOED problem with application to the experimental design of the time to take MRI images in monitoring tumor growth. We show that the proposed computational framework achieves an amortized 180× speedup. © 2024, CC BY-SA.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based Species Reciprocal System for Partridge 1st

A Deep Learning Based Species Reciprocal System for Partridg...

引用

1st International Conference on Deep sciences for computing and Communications, IconDeepCom 2022

作者： Aswini, J. Gayathri, A. Revathi, A. Vinoth Kumar, L. Affiliated to Anna University Chennai India Chennai India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Department of Information Technology R.M.K Engineering College RSM Nagar Chennai India

ISBN: (纸本)9783031276217

Bird watching is a form of wildlife observation of birds which is a recreational activity. Bird watchers make use of bird books to know about the birds. To provide handy tool to birdwatchers and to admire the splendor of birds, to recognize bird species a web based Convolutional Neural Network is used to help out users. Avifauna species images were used to localize major features in the image and it is learnt by a convolutional neural network (CNN)s. To distill the shapes and colors of the object granularities then to balance the distribution of bird species, circumscribed region of interest is performed. Then, for feature extraction convolutional neural network (CNN) is used. Finally, activation function softmax is applied on the resulting class probabilities. To identify picture uploaded by users, the erudite parameters of bird features were used. Instead of training from scratch, the concept of transfer learning is used in which pre-trained models (VGG16, Xception, ResNet, etc.) are used. Here two of these models are used namely ResNet50 and VGG16. Among these two models ResNet50 have provided better accuracy. Transfer learning helps us to increase the classification accuracy. Hence, materialization of deep learning algorithms has resulted in highly intricate cognitive for computer vision & image recognition. The deep learning model uses CNN framework for bird image classification. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

FedHZone: Federated Learning Based Hazardous Zone Detection Using Internet of Drone Things

FedHZone: Federated Learning Based Hazardous Zone Detection ...

引用

2024 IEEE International Conference on Communications, computing, Cybersecurity and Informatics, CCCI 2024

作者： Biswas, Payel De, Debashis Obaidat, Mohammad S. Hazra, Arnab Sadoun, Balqies Jogesh Chandra Chaudhuri College Department of Computer Science Kolkata India Maulana Abul Kalam Azad University of Technology Centre of Mobile Cloud Computing Department of Computer Science and Engineering West Bengal WB Nadia India School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China School of Computing SRM University Department of Computational Intelligence SRM Nagar TN Kattankulathur603203 India School of Engineering The Amity University UP Noida201301 India Dr. Sudhir Chandra sur Institute of Technology & Sports Complex Department of Computer Science and Engineering Kolkata India College of Engineering Al Balqa ' Applied University Al-Salt19117 Jordan

ISBN: (纸本)9798350349832

Air pollution can affect human health, so it is necessary to predict the air quality index (AQI) in advance. In this work, air quality data collected by the Internet of Drone Things (IoDT) is predicted and analyzed to detect highly polluted zones using a distributed privacy-preserving federated learning (FL) approach. Air quality data for a particular zone is collected and then fed into a Long short-Term memory (LSTM) based model to predict the pollution level in local training. Global aggregation is done by an IoDT-mounted central server to aggregate the received models from the local IoDT level. Privacy-preserving FedHZone predicts and analyses the AQI values from the past time series dataset in a multi-drone environment. This work detects the most hazardous zone in a larger region of Jaipur, Rajasthan using real-Time data. The result shows FedHZone with stacked LSTM having ''2%-7% better accuracy than the vanilla LSTM-based model. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Quasiperiodic Symmetric Tilt FCC Grain Boundaries

arXiv

引用

arXiv 2024年

作者： Zou, Wenwen Zhang, Juan Xu, Jie Jiang, Kai Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China LSEC NCMIS Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

In this work, we investigate [110] symmetric tilt FCC grain boundaries (GBs) by a recently developed approach for quasiperiodic interfaces using the Landau-Brazovskii model. On special tilt angles associated with quadratic algebraic numbers, quasiperiodic GBs exhibit generalized Fibonacci substitution rules. The transition mechanism from quasiperiodic GBs to periodic GBs is explored through sphere offsets and spectral coalescence. We also propose an accurate method to calculate the GB energy for arbitrary tilt angle and analyze the factors affecting the GB energy. The revealing GB energy change is continue along with tilt angle except periodic GBs. © 2024, CC BY-NC-SA.

关键词： Grain boundaries

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：