检索结果-内蒙古大学图书馆

Machine Learning-Based Methods for Materials Inverse Design: A Review

computers, Materials & Continua 2025年第2期82卷 1463-1492页

作者： Yingli Liu Yuting Cui Haihe Zhou Sheng Lei Haibin Yuan Tao Shen Jiancheng Yin Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650093China Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and TechnologyKunming650500China Yunnan Tin Company Limited Tin Industry Branch Gejiu661000China Faculty of Materials Science and Engineering Kunming University of Science and TechnologyKunming650093China

Finding materials with specific properties is a hot topic in materials *** materials design relies on empirical and trial-and-error methods,requiring extensive experiments and time,resulting in high *** the development of physics,statistics,computer science,and other fields,machine learning offers opportunities for systematically discovering new *** through machine learning-based inverse design,machine learning algorithms analyze the mapping relationships between materials and their properties to find materials with desired *** paper first outlines the basic concepts of materials inverse design and the challenges faced by machine learning-based approaches to materials inverse ***,three main inverse design methods—exploration-based,model-based,and optimization-based—are analyzed in the context of different application ***,the applications of inverse design methods in alloys,optical materials,and acoustic materials are elaborated on,and the prospects for materials inverse design are *** authors hope to accelerate the discovery of new materials and provide new possibilities for advancing materials science and innovative design methods.

关键词： Materials inverse design machine learning target properties deep learning new materials discovery

来源：评论

学校读者我要写书评

暂无评论

Intelligent Farming: IoT-Powered System for Efficient Soil Condition Analysis 13

Intelligent Farming: IoT-Powered System for Efficient Soil C...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Sisodia, Ankur Vishnoi, Swati Sharma, Nandini Singh, Shiv Shanker Khenwar, Medha Gupta, Priyanka Gla University Department of Computer Engineering and Application Mathura India Banasthali Vidyapith Department of Computer Science Rajasthan India G.L. Bajaj Group of Institutions Department of Computer Science and Engineering Mathura India Sanskriti University Department of Computer Science and Engineering Mathura India

ISBN: (纸本)9798350380583

Smart farming technology allows farmers to control and analyse variables in real-time, helping them optimize crop growth and manage their operations more efficiently. The use of specialized sensors, data collection tools, and advanced analytics in Internet of Things (IoT) systems is helping to bridge the gap between physical farm conditions and digital monitoring. In this study, we aim to develop a system that monitors soil conditions to support smart farming. The system provides farmers with live data on key environmental factors, such as temperature, humidity, soil moisture, and soil temperature, to improve crop yield and product quality. The IoT setup for this intelligent farming solution includes components like the DHT11 and humidity sensors, a DS18B20 temperature probe, LDR, water pump, and a 12V LED strip, all controlled by a NodeMCU. When the system is activated, it continuously monitors soil and environmental conditions and sends this information to the cloud for real-time access. If the soil moisture falls below a set threshold, the system automatically triggers irrigation. Our experimental results show that this model improves decision-making for managing farming conditions. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Anti-Collusion Mechanism for Audio Signals Based on Pre-Adjustment 3

Anti-Collusion Mechanism for Audio Signals Based on Pre-Adju...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Shekhawat, Jyoti Khurana, Rashmi Vivekananda Global University Department of Computer Science Engineering Jaipur India Chandigarh School of Business Master of Computer Application Department of Computer Science Engineering Jhanjeri India

ISBN: (纸本)9798350399264

One of the most well-known and difficult attacks for audio transmissions that gravely infringes on copyright is collusion. The mixture attack by collaboration and other assaults, is too sophisticated for conventional defenses to handle. In this study, we propose by removing the perceived quality of a pre-adaptation process (PAP)-based strategy to collusion signals by removing the incentive for traitors to carry out covert attacks. The PAP signal is then produced by modifying the DCT coefficients in accordance with an adjustment matrix (AM) that has already been designed. The vigor of some frequency groups in the colluding signal will be lost or lowered when numerous PAP signals are averaged to produce it, which significantly lowers the colluded signal's perceptual quality. The suggested technique is resistant against hybrid as well as collusion assaults. Additionally, it is safe because the receiver won't receive access to the PAP secret keys. The suggested copyright protection technique may be further enhanced in terms of effectiveness by being integrated with other state-of-the-art watermarking algorithms. The proposed mechanism is superior, as demonstrated by theoretical analysis and experimental findings. © 2023 IEEE.

关键词： Copyrights

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm and Naïve Bayes-Based (GANB) Diabetes Mellitus Prediction System 1st

Genetic Algorithm and Naïve Bayes-Based (GANB) Diabetes Mel...

引用

1st International Conference on Microelectronics, Communication Systems, Machine Learning, and Internet of Things, MCMI 2020

作者： Yadav, Dharmveer Kumar Azad, Chandrashekhar Bala, Kanchan Sharma, Pradeep Kumar Kumar, Sujeet Computer Science and Engineering Katihar Engineering College Katihar India Computer Application Department Computer Science and Engineering NIT Jamshedpur India Sitamarhi Institute of Technology Sitamarhi India Computer Science and Engineering Katihar Engineering College Katihar India

ISBN: (纸本)9789811919053

Today, machine learning plays a significant role in the classification of healthcare conditions. Machine learning is the process of finding, discovering, and modeling massive amounts of data in order to identify unknown relationships and patterns that are useful to the decision makers. Medical data mining has begun to emerge exemplary, with the potential to discover interesting insights from medical domain datasets. These patterns may be used in the making of clinical decisions. In this research work, we proposed genetic algorithm and Naïve Bayes-based (GANB) diabetes mellitus prediction system. In which, genetic algorithm (GA) is used for feature selection and Naïve Bayes is used for prediction. The proposed system is trained using Pima Indian diabetes dataset (PIDD). The dataset is preprocessed using synthetic minority oversampling technique (SMOTE) for solving the issue of class imbalances. The effectiveness of the system is evaluated using classification accuracy (CA) and error. The simulation results show that the proposed GANB system achieves better accuracy as compared to the results of related earlier studies. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

HIJLI-JU-CLEF at MULTI-Fake-DetectiVE: Multimodal Fake News Detection Using Deep Learning Approach 8

HIJLI-JU-CLEF at MULTI-Fake-DetectiVE: Multimodal Fake News ...

引用

8th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop, EVALITA 2023

作者： Sarkar, Sandip Tudu, Nripen Das, Dipankar Department of Computer Science and Application Hijli College Kharagpur India Department of Computer Science and Engineering Jadavpur University Kolkata India

This report presents the progress made in developing a system for participation in a shared task called MULTI-Fake-DetectiVE Task 1, which aims to detect and verify fake news in a multimodal environment comprising both textual and visual elements. The task primarily revolves around automatically identifying fake news by analyzing the combined use of text and images. Our system is structured into three distinct modules. The initial module is responsible for extracting textual information from images. The second module serves as a translation component, enabling the analysis of non-English text by converting it into English. Lastly, the classification module utilizes the outputs from the previous modules to predict the appropriate classes, allowing for accurate differentiation between various types of content. Our objective is to create a system that can predict these labels. To achieve this, we extract information from both the image and the text, specifically focusing on English language text and translating any textual data into English. Subsequently, both sets of data are utilized to train a classification-based model, which aims to predict the aforementioned labels. We were able to obtain a Weighted Average F1-Score of 0.393 by implementing a Multi-head attention mechanism. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improving energy efficiency in scalable WSNs through IoT-driven approach

引用

International Journal of Information Technology (Singapore) 2025年 1-11页

作者： Singh, Omkar Kushwaha, Ajay Shriram Sharma, Col. Rahul Kumar, Lalit National Institute of Fashion Technology Bihar Patna India Department of Computer Science & Application Sharda School of Computing Sciences & Engineering Sharda University UP Greater Noida India School of Computer Science & Engineering ILM University Greater Noida India

A novel QoS-Driven Optimization for Energy-Efficient Clustering Routing (QDOEECR) protocol tailored for IoT-based Wireless Sensor Networks (WSNs), addressing the critical challenge of energy efficiency in sensor nodes with limited battery life. The protocol’s innovative approach lies in its advanced techniques for optimizing the selection of sub-sink nodes and identifying the optimal path to the sink node, ensuring improved adherence to Quality of Service (QoS) standards. Performance evaluations, conducted through MATLAB simulations, demonstrate the QDOEECR protocol's superior performance, achieving significant advancements over existing routing protocols. These include 30–35% reduction in end-to-end delay, 25–30% improvement in throughput, 35–40% decrease in energy consumption, 28–32% reduction in packet loss, and 32–38% extension in network lifetime. These results establish QDOEECR as a groundbreaking solution that not only enhances energy efficiency but also elevates network performance metrics beyond the capabilities of current state-of-the-art protocols like CBCCP, HCSM, and ZEAL. © Bharati Vidyapeeth's Institute of computer applications and Management 2025.

关键词： CBCCP HCSM IoT QDOEECR WSN ZEAL

来源：评论

学校读者我要写书评

暂无评论

DL-Based Somnolence Detection for Improved Driver Safety and Alertness Monitoring 5

DL-Based Somnolence Detection for Improved Driver Safety and...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Neeraja, Peddinti. Kumar, R.G. Kumar, M. Sunil Liyakat, Kazi Kutubuddin Sayyad Vani, M. Sowmya School of Computing Department of Computer Application AP Tirupathi India Siddharth Institute of Engineering & Technology Computer Science and Engineering AP Puttur India School of Computing Department of Computer Science and Engineering AP Tirupathi India Brahmdevdada Mane Institute of Technology Department of Computer Science and Engineering Maharashtra Solapur India

ISBN: (纸本)9798350383522

This abstract explores the utilization of deep learning for detecting driver somnolence, aiming to enhance driver safety and alertness monitoring. It investigates the integration of computer vision, physiological signals, and machine learning algorithms. Key considerations include real-time detection, accuracy, scalability, and driver intervention mechanisms. By leveraging deep learning techniques, effective driver somnolence detection systems can contribute to preventing accidents and promoting safer roads. © 2024 IEEE.

关键词： Convolution neural network deep learning Drowsiness detection transfer learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Bank Loan Approval with Artificial Intelligence 1

Predicting Bank Loan Approval with Artificial Intelligence

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Ratan, Raj Yadav, Sudeept Singh Malhotra, Ritika Kumar, Avneesh Galgotias University School of Computer Application and Technology Greater Noida India Galgotias University School of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350356816

In the contemporary financial landscape, banks play a crucial role in facilitating individuals and businesses with their monetary needs. Central to their operations is the assessment of borrower creditworthiness through loan approval processes, ensuring the security of loans extended. However, traditional manual assessment is not only time-consuming but also prone to human error. Therefore, there is an urgent need to develop an automated and reliable credit approval system. In this study, diverse machine learning calculations are compared to decide the ideal show for anticipating whether a bank ought to endrose a advance for a person. Employing a dataset gotten from Kaggle, diverse machine learning methods to a degree logistic reversion, decision trees, K-nearest neighbors (KNN), haphazard woodlands and neural networks are exploited. The animation of these models is evaluated handling measurements to a degree veracity, accuracy, review and F1 score. In particular, the influence of the model is improved by taking into account a number of factors that include the borrower's personal characteristics, such as tax liabilities, purpose of the loan, credit history, loan amount and home ownership, in addition to traditional checking account information. This holistic approach allows for a more accurate estimation of the likelihood of loan default. Furthermore, the logistic regression model proves to be the top performer with an impressive accuracy of 81.89%. Additionally, a trait importance analysis is performed to identify the variables that have the greatest impact on loan approval decisions. The results underline the superiority of ML models over conventional statistical approaches and illustrate their potential to significantly improve the accuracy of loan forecasting. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Identification of Age, Plumage, and Sex of Bird Species Using Pre-Trained Deep Convolutional Neural Network 2

Identification of Age, Plumage, and Sex of Bird Species Usin...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Banerjee, Sourik Gupta, Richa Pandian, J. Arun Saranya, S. Mariappan, L. Thanga Vellore Institute of Technology Department of Computer Application Vellore India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India K.Ramakrishnan College of Engineering Department of Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350306415

The research aims to identify the age, plumage, and sex of bird species using standard Pre-trained Deep Convolutional Neural Networks (Pre-DCNNs). The proposed work involves collecting various bird images, which are then used for training and validating the pre-trained DCNNs. The dataset contains 200 images of four bird species. The dataset was split into twelve labeled classes of images based on age, plumage, and sex. The standard image manipulation techniques such as cropping, flipping, mirroring, rotating, shearing, and skewing were used as image augmentation techniques to increase the size of the proposed dataset. The proposed data is preprocessed, including feature extraction and data cleaning, to ensure the performance of the Pre-Trained DCNNs. The Pre-Trained DCNNs were trained on 90% of the dataset to recognize patterns in bird images. The accuracy of the pre-trained DCNNs was evaluated using metrics such as classification accuracy. The research acknowledged the advantages and limitations of the standard Pre-Trained DCNNs on the age, plumage, and sex of birds using the images. Also, it compares the performance of the Pre-Trained DCNNs on the proposed bird species image dataset. © 2024 IEEE.

关键词： Bird Plumage Identification Bird Species Identification Deep Convolutional Neural Networks Image Augmentation Pre-trained networks

来源：评论

学校读者我要写书评

暂无评论

An Integrated Security VANET Algorithm for Threat Mitigation and Performance Improvement Using Machine Learning

引用

SN computer science 2024年第8期5卷 1089页

作者： Khanna, Heena Kumar, Mukesh Bhardwaj, Vivek School of Computer Application Lovely Professional University Punjab Phagwara 144411 India Department of Computer Application Chandigarh School of Business Chandigarh Group of Colleges Jhanjeri Punjab Mohali 140307 India School of Computer Science and Engineering Manipal University Jaipur Jaipur 303007 India

Vehicular Ad-Hoc Networks (VANETs) have emerged as a captivating field of research due to the escalating number of vehicles on the road in recent years. Ensuring a secure Intelligent Transportation System (ITS) is imperative for passenger and driver safety. However, the dynamic nature of VANETs presents challenges for real-time implementation. This study proposes an enhanced security algorithm tailored for VANETs, adept at mitigating threats such as Denial of Service Attacks (DoS), Sybil, and Replay attacks. The proposed method employs an Enhanced K-Means approach to form clusters for diverse attacks, coupled with a hybrid technique utilizing Support Vector Machine (SVM) and Feed-forward backpropagation for classifier accuracy assessment which incorporates firefly algorithm for optimization. The findings demonstrate notable enhancements in terms of Throughput, Jitter, True Detection Rate, and Packet Delivery Ratio (PDR). Lastly, we delineate future directions and identify open issues for further investigation. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： DoS Machine learning Security Support vector machine VANET

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：