检索结果-内蒙古大学图书馆

Prediction of Geopolymer Concrete Compressive Strength Using Convolutional Neural Networks

computer Modeling in Engineering & Sciences 2024年第5期139卷 1455-1486页

作者： Kolli Ramujee Pooja Sadula Golla Madhu Sandeep Kautish Abdulaziz S.Almazyad Guojiang Xiong Ali Wagdy Mohamed Department of Civil Engineering VNR Vignana Jyothi Institute of Engineering and TechnologyHyderabadTelangana500090India Department of Information Technology VNR Vignana Jyothi Institute of Engineering and TechnologyHyderabadTelangana500090India Department of Computer Science LBEF Campus(Asia Pacific University of Technology&InnovationMalaysia)Kathmandu44600Nepal Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia Guizhou Key Laboratory of Intelligent Technology in Power System College of Electrical EngineeringGuizhou UniversityGuiyang550025China Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research Center Applied Science Private UniversityAmmanJordan

Geopolymer concrete emerges as a promising avenue for sustainable development and offers an effective solution to environmental *** attributes as a non-toxic,low-carbon,and economical substitute for conventional cement concrete,coupled with its elevated compressive strength and reduced shrinkage properties,position it as a pivotal material for diverse applications spanning from architectural structures to transportation *** this context,this study sets out the task of using machine learning(ML)algorithms to increase the accuracy and interpretability of predicting the compressive strength of geopolymer concrete in the civil engineering *** achieve this goal,a new approach using convolutional neural networks(CNNs)has been *** study focuses on creating a comprehensive dataset consisting of compositional and strength parameters of 162 geopolymer concrete mixes,all containing Class F fly *** selection of optimal input parameters is guided by two distinct *** first criterion leverages insights garnered from previous research on the influence of individual features on compressive *** second criterion scrutinizes the impact of these features within the model’s predictive *** to enhancing the CNN model’s performance is the meticulous determination of the optimal *** a systematic trial-and-error process,the study ascertains the ideal number of epochs for data division and the optimal value of k for k-fold cross-validation—a technique vital to the model’s *** model’s predictive prowess is rigorously assessed via a suite of performance metrics and comprehensive score ***,the model’s adaptability is gauged by integrating a secondary dataset into its predictive framework,facilitating a comparative evaluation against conventional prediction *** unravel the intricacies of the CNN model’s learning trajectory,a loss plot is deployed to elucidate its learning rat

关键词： Class F fly ash compressive strength geopolymer concrete prediction deep learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Design and beam dynamics study of a magnet system for an 11 MeV superconducting isochronous cyclotron

引用

Nuclear Science and Techniques 2025年第6期 193-202页

作者： Pan-Pan Zheng Xiang-Hui Wang Zi-Feng He Yue Wu Zhi-Min Dai Wei-Shi Wan School of Physical Science and Technology ShanghaiTech University Shanghai Institute of Applied Physics Chinese Academy of Sciences School of Computer Engineering Wefang University

In recent years, due to the scarcity of domestic radioisotopes, the Chinese government has strongly supported the development of dedicated radioisotope production facilities. This paper presents conceptual design simulations of an 11 MeV, 50 μA,H-compact superconducting cyclotron for radioisotope production. This paper focuses primarily on four aspects: magnet system design, central region configuration, beam dynamics analysis, and extraction system design. This paper outlines the cyclotron's primary parameters and key steps in the development process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tool for Game Plot Line Visualization for Designers, Testers and Players 1

引用

20th International Conference on Cooperative Design, Visualization and Engineering, CDVE 2023

作者： Nowak, Leszek Grabska-Gradzińska, Iwona Palacz, Wojciech Grabska, Ewa Guzik, Maria Department of Information Technologies Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Krakow Poland Department of Games Technology Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Krakow Poland Department of Design and Computer Graphics Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Krakow Poland Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Krakow Poland

ISBN: (数字)9783031438158

ISBN: (纸本)9783031438141

This paper presents a tool for automatic and interactive visualization of game plots, which can be used to check whether the designers’ work meets the constraints of the world, to help testers control played game story paths. The referential designers’ game plots can be imported from any flowchart diagrams as an XML file and the actual gameplay variant is generated on the fly and applied to the original design based on detected common diagram points. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

CSLP: Collaborative Solution to Long-Tail Problem and Popularity Bias in Sequential Recommendation

CSLP: Collaborative Solution to Long-Tail Problem and Popula...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Huang, Yan Yang, Zhenyu Hu, Wenyue Xu, Baojie Zhang, Zhibo Jinan250353 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan250353 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan250353 China

ISBN: (纸本)9781665410205

Sequential Recommender Systems (SRS), leveraging the temporal information from users' behaviors, have noticeably improved user experience against traditional systems. However, these behaviors often follow long-tail distribution, making the systems biased towards popular items (i.e., popularity bias). Moreover, popularity bias would amplify the neglect of long-tail recommendations, thereby sharpening the long-tail problem. Previous researches usually address these challenges independently, focusing on reducing the over-recommendation of popular items or enhancing the representation quality of tail items. Indeed, it is possible to incorporate their merits to achieve the best of both worlds. Thus, we propose a novel and unified framework, named Collaborative Solution to Long tailed problem and Popularity bias (CSLP), to tackle both the long-tail problem and popularity bias simultaneously. To achieve this, we first introduce a representation enhancement module featuring dual generators to enhance user and item representations, particularly for those in the tail. On the other hand, a debiasing module incorporating an Inverse Propensity Score (IPS) with a clipping strategy is introduced to further alleviate the popularity bias. Specifically, this clipping strategy demonstrates a clear decrease in the original IPS method's variance, effectively improving the recommendation for stability and accuracy. Experiments on three widely-used datasets show CSLP's effectiveness in solving both issues. CSLP surpasses all baselines (traditional, popularity bias, and long-tail problem) in overall performance, significantly enhancing recommendation accuracy for both tail users and items, and achieving a more balanced ratio of recommendations between popular and tail items. Code is available at https://***/Echohuangyan/CSLP. © 2024 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Enabled Future Wireless Electric Vehicles with Multi-Model Learning and Decision Making Models

引用

Tsinghua Science and technology 2024年第6期29卷 1776-1784页

作者： Gajula Ramesh Anil Kumar Budati Shayla Islam Louai A.Maghrabi Abdullah Al-Atwai Department of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering&TechnologyHyderabad 500090India Institute of Computer Science and Digital Innovation(ICSDI) UCSI UniversityKuala Lumpur 56000Malaysia also with Department of ECE KoneruLakshmaiah Education FoundationHyderabad 500090India ICSDI UCSI UniversityKuala Lumpur 56000Malaysia Department of Software Engineering College of EngineeringUniversity of Business and TechnologyJeddah 21448Kingdom of Saudi Arabia Department of Computer Science Applied CollegeUniversity of TabukTabuk 47512Kingdom of Saudi Arabia

In the contemporary era,driverless vehicles are a reality due to the proliferation of distributed technologies,sensing technologies,and Machine to Machine(M2M)***,the emergence of deep learning techniques provides more scope in controlling and making such vehicles energy *** existing methods,it is understood that there have been many approaches found to automate safe driving in autonomous and electric vehicles and also their energy ***,the models focus on different aspects *** is need for a comprehensive framework that exploits multiple deep learning models in order to have better control using Artificial Intelligence(AI)on autonomous driving and energy *** this end,we propose an AI-based framework for autonomous electric vehicles with multi-model learning and decision *** focuses on both safe driving in highway scenarios and energy *** deep learning based framework is realized with many models used for localization,path planning at high level,path planning at low level,reinforcement learning,transfer learning,power control,and speed *** reinforcement learning,state-action-feedback play important role in decision *** simulation implementation reveals that the efficiency of the AI-based approach towards safe driving of autonomous electric vehicle gives better performance than that of the normal electric vehicles.

关键词： wireless vehicles deep learning multi-model learning reinforcement learning Artificial Intelligence(Al)

来源：评论

学校读者我要写书评

暂无评论

Consensus MPC-Based hierarchical control of Islanded AC Microgrid 3

Consensus MPC-Based hierarchical control of Islanded AC Micr...

引用

3rd International Conference on Communication, Computing and Digital Systems, C-CODE 2023

作者： Khan, Zawar Aamir, Muhammad Pak-Austria Fachhochschule: Institute of Applied Sciences and Technology Electrical & Computer Engineering Department Haripur Pakistan

ISBN: (纸本)9798350332391

In this paper, the consensus model predictive control (MPC)-based hierarchical control scheme is presented for the primary and secondary layers of an islanded AC microgrid (MG). The secondary control is designed on the tracker consensus method, in this way a distributed controller in collaboration with the finite time observer will set the referenced values of voltage magnitude and frequency by significantly speeding up the method of synchronous convergence. Furthermore, the primary control has been implemented for each DG separately and comprises Finite Control Set-Model Predictive control (FCS-MPC), and droops control. FCS-MPC regulates PCC reference voltages for each DG unit. Droop Control regulates power exchange within and among DG units. In the proposed hierarchical control approach, information sharing is accomplished by a neighbouring node creating a sparse communication network while fully eliminating the requirement for a centralized controller. The controller effectiveness have been validated against unbalanced load, transients, and load plug-and-play capabilities. The simulation result shows that MG operates effectively using FCS-MPC for parallel inverters of DG units, and the consensus algorithm based distributed secondary controller in MG effectively delivers the anticipated power, voltage, and frequency. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Design of 5G Multi-Frequency Antenna Based on Multi-Objective Sequential Domain Patching

引用

Progress In Electromagnetics Research C 2024年 145卷 53-61页

作者： Zhu, Wenjian Chen, Jiayi Hu, Panshi Song, Zhi Xue, Yanbing School of Automation and Electrical Engineering Dalian Jiaotong University China School of Computer and Communication Engineering Dalian Jiaotong University Applied Basic Research Project of Liaoning Science and Technology Department Dalian116028 China

This paper introduces a 5G multi-frequency antenna design method based on multi-objective sequential domain patching. By etching helical metamaterials on radiation patches and loading asymmetric electric-inductive-capacitive metamaterials on the transmission line side, the antenna structure is designed and optimized using electromagnetic simulation software, HFSS, and MATLAB. The resulting multi-frequency antenna operates across multiple frequency bands: n1, n41, 3.5G, and 4.9G. To ensure antenna performance and radiation efficiency, the antenna multi-frequency bands are precisely controlled. The experimental results show that the error between each operating frequency band and target frequency bands of the antenna is within 7.2%. Compared with conventional antenna design methods, the use of metamaterials and intelligent algorithms to optimize the structural parameters and loading positions of metamaterials can improve antenna performance while shortening the design cycle. Overall, this research offers novel insights into the design of 5G high-performance antennas. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Metamaterials

来源：评论

学校读者我要写书评

暂无评论

AYUsearch: a repository to facilitate the biochemical understanding of natural products-derived chemical substances

引用

Current Science 2024年第6期126卷 706-713页

作者： Tilwani, Komal Patel, Abhishek Patel, Ghanshyam Rahevar, Mrugendra Dave, Gayatri P.D. Patel Institute of Applied Sciences Changa 388 421 India U & P U Patel Department of Computer Engineering Charotar University of Science and Technology Changa 388 421 India

Ayurveda - a traditional Indian medicinal (TIM) practice advocates a lifestyle regimen utilizing natural products to cure complex ailments. The famous Ayurveda classics, viz. Charak Samhita, Ashtanga Hridayam and Sushruta Samhita, elaborate on various plant and animal products, in which the descriptions are narrated in Sanskrit and often signified through a metaphor. The particulars are empirical and usually lack experimental evidence. Its efficacy needs to be ensured towards the gold standard of biomedical sciences. Indeed, an ordered catalogue on a natural product is quintessential to designing the validation strategies for TIM. We obtained evidence on 60 natural products with a mentioned history in Ayur-veda. For this, we manually curated a list of natural products-derived molecules (NDMs). Next, they were sorted into universally accepted chemical identifiers and processed into SDF formats. The 1004 gene targets were identified for 636 NDMs through molecular and reverse docking studies. Subsequently, the functional annotation of differentially expressed genes using KEGG pathways and Gene Ontology analysis unravelled the role of the scrutinized ligands on cell functions. AYUsearch (database) is an attempt to redefine the in-formation embedded in Ayurveda, where the biological role of natural chemical products is decoded through network pharmacology. © (2024), (Indian Academy of Sciences). All Rights Reserved.

关键词： Gene Ontology

来源：评论

学校读者我要写书评

暂无评论

HPML-CVD: Hyperparameter Tuned Machine Learning Model to Predict Cardiovascular Disease

引用

Biomedical Materials and Devices 2025年 1-15页

作者： Uddin, Nazim Hossain, Md. Sahadat Mahmud, Md. Zulfiker Ferdous, Rebina Talukder, Md. Alamin Department of Information and Communication Technology Chandpur Science and Technology University Chandpur Bangladesh Department of Computer Science and Engineering Jagannath University Dhaka Bangladesh Basic and Applied Research on Jute Project Bangladesh Jute Research Institute Dhaka 1207 Bangladesh Department of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka Bangladesh

Cardiovascular disease (CVD) remains a significant global health concern, necessitating early detection and accurate prediction for effective intervention. Machine learning (ML) offers a data-driven approach to analyzing patient data, identifying complex patterns, and predicting CVD risk factors such as blood pressure, cholesterol, and genetic predispositions. This study employs the Heart Disease UCI dataset, comprising 303 cases and 14 attributes, to develop predictive ML models. A comprehensive feature engineering approach was applied, including Chi-Square feature selection, where the 10 most influential features were identified to enhance model performance. After feature selection, hyperparameter tuning was performed to optimize five classifiers: Random Forest, K-Nearest Neighbors, Decision Tree, Support Vector Machine, and Logistic Regression. The results indicate significant improvements in accuracy after feature engineering and fine-tuning, with the Random Forest classifier achieving the highest accuracy of 93.41%, outperforming previous work on the same dataset by 3.41%, followed by SVM at 91.21%. These findings underscore the potential of ML in early CVD prediction, emphasizing its role in proactive risk management and healthcare. The integration of ML-driven CVD risk assessment paves the way for personalized healthcare, benefiting both patients and medical professionals by facilitating early intervention, improving patient outcomes, and optimizing healthcare resource allocation. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Cardiovascular disease Cleveland dataset Heart disease prediction Logistic regression Machine learning

来源：评论

学校读者我要写书评

暂无评论

IMAN: An Adaptive Network for Robust NPC Mortality Prediction with Missing Modalities

IMAN: An Adaptive Network for Robust NPC Mortality Predictio...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Huo, Yejing Huang, Guoheng Cheng, Lianglun He, Jianbin Chen, Xuhang Yuan, Xiaochen Zhong, Guo Pun, Chi-Man Guangdong University of Technology School of Computer Science and Technology China Huizhou University School of Computer Science and Engineering China University of Macau Department of Computer and Information Science China Macao Polytechnic University Faculty of Applied Sciences China Guangdong University of Foreign Studies School of Information Science and Technology China

ISBN: (纸本)9798350386226

Accurate prediction of mortality in nasopharyngeal carcinoma (NPC), a complex malignancy particularly challenging in advanced stages, is crucial for optimizing treatment strategies and improving patient outcomes. However, this predictive process is often compromised by the high-dimensional and heterogeneous nature of NPC-related data, coupled with the pervasive issue of incomplete multi-modal data, manifesting as missing radiological images or incomplete diagnostic reports. Traditional machine learning approaches suffer significant performance degradation when faced with such incomplete data, as they fail to effectively handle the high-dimensionality and intricate correlations across modalities. Even advanced multi-modal learning techniques like Transformers struggle to maintain robust performance in the presence of missing modalities, as they lack specialized mechanisms to adaptively integrate and align the diverse data types, while also capturing nuanced patterns and contextual relationships within the complex NPC data. To address these problem, we introduce IMAN: an adaptive network for robust NPC mortality prediction with missing modalities. IMAN features three integrated modules: the Dynamic Cross-Modal Calibration (DCMC) module employs adaptive, learnable parameters to scale and align medical images and field data;the Spatial-Contextual Attention Integration (SCAI) module enhances traditional Transformers by incorporating positional information within the self-attention mechanism, improving multi-modal feature integration;and the Context-Aware Feature Acquisition (CAFA) module adjusts convolution kernel positions through learnable offsets, allowing for adaptive feature capture across various scales and orientations in medical image modalities. Extensive experiments on our proprietary NPC dataset demonstrate IMAN's robustness and high predictive accuracy, even with missing data. Compared to existing methods, IMAN consistently outperforms in scenarios with incom

关键词： Patient treatment

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：