检索结果-内蒙古大学图书馆

Using evolutionary algorithms and group method of data handling ANN for prediction of the viscosity MWCNT-ZnO /oil SAE 50 nano-lubricant

引用

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER 2025年 163卷

作者： Liu, Zuozhi Ali, Ali B. M. Hussein, Rasha Abed Singh, Narinderjit Singh Sawaran Al-Bahrani, Mohammed Abdullaeva, Barno Saeidlou, Salman Salahshour, Soheil Esmaeili, Sh. Guizhou Univ Finance & Econ Sch Math & Stat Guiyang 550025 Guizhou Peoples R China Univ Warith Al Anbiyaa Coll Engn Air Conditioning Engn Dept Karbala Iraq Al Manara Coll Med Sci Dept Dent Amarah Maysan Iraq INTI Int Univ Fac Data Sci & Informat Technol Nilai 71800 Malaysia Al Mustaqbal Univ Dept Chem Engn & Petr Ind Babylon 51001 Iraq Tashkent State Pedag Univ Dept Math & Informat Technol Sci Affairs Tashkent Uzbekistan Canterbury Christ Church Univ Sch Engn Technol & Design Mech Mat Engn Canterbury CT1 1QU Kent England Istanbul Okan Univ Fac Engn & Nat Sci Istanbul Turkiye Bahcesehir Univ Fac Engn & Nat Sci Istanbul Turkiye Piri Reis Univ Fac Sci & Letters Istanbul Turkiye Shabihsazan Ati Pars Fast Comp Ctr Tehran Iran

This study looked at ANNs' ability to predict the rheological properties of MWCNT-ZNO / Oil SAE 50 nano lubricant. Five artificial intelligence algorithms-Group Method of Data Handling (GMDH), Extreme Gradient Boosting (XGBoost), Multivariate Adaptive Regression Splines (MARS), Support vector machine (SVM), and Multilayer Perceptron (MLP)-were employed in this work to forecast this nanofluid. The most optimum objective function (mu nf) as an output is the foundation of algorithms used in artificial intelligence. This capacity is developed so that the values predicted by ANN were more consistent with the laboratory numbers by combining GMDH with the metaheuristic approach. This combination enables the metaheuristic algorithm to optimize the evaluation indices and get the predicted data closer to the experimental data by using the GMDH activation parameters as input. For optimization, three metaheuristic algorithms are used, and the combination of GMDH and MOGWO produced the best results. Ultimately, the finest condition that could be achieved is found to have the following input data values: share rate (gamma), temperature (T), and solid volume fraction (phi): 0.0625 %, 50 degrees C, and 5499.6783 s-1 correspondingly.

关键词： Nano-lubricant Meta-heuristic artificial intelligence algorithms Metaheuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

A Review of Reliability Assessment and Lifetime Prediction Methods for Electrical Machine Insulation Under Thermal Aging

引用

ENERGIES 2025年第3期18卷 576-576页

作者： Zhang, Jian Wang, Jiajin Li, Hongbo Zhang, Qin He, Xiangning Meng, Cui Huang, Xiaoyan Fang, Youtong Wu, Jianwei Zhejiang Univ State Key Lab Fluid Power & Mechatron Syst Hangzhou 310027 Peoples R China Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China Zhejiang Guoli Secur Technol Co Ltd Hangzhou 310059 Peoples R China Zhejiang Univ Sch Mech Engn Hangzhou 310027 Peoples R China

The thermal aging of insulation systems in electrical machines is a critical factor influencing their reliability and lifetime, particularly in modern high-performance electrical equipment. However, evaluating and predicting insulation lifetime under thermal aging poses significant challenges due to the complex aging mechanisms. Thermal aging not only leads to the degradation of macroscopic properties such as dielectric strength and breakdown voltage but also causes progressive changes in the microstructure, making the correlation between aging stress and aging indicators fundamental for lifetime evaluation and prediction. This review first summarizes the performance indicators reflecting insulation thermal aging. Subsequently, it systematically reviews current methods for reliability assessment and lifetime prediction in the thermal aging process of electrical machine insulation, with a focus on the application of different modeling approaches such as physics-of-failure (PoF) models, data-driven models, and stochastic process models in insulation lifetime modeling. The theoretical foundations, modeling processes, advantages, and limitations of each method are discussed. In particular, PoF-based models provide an in-depth understanding of degradation mechanisms to predict lifetime, but the major challenge remains in dealing with complex failure mechanisms that are not well understood. Data-driven methods, such as artificial intelligence or curve-fitting techniques, offer precise predictions of complex nonlinear relationships. However, their dependence on high-quality data and the lack of interpretability remain limiting factors. Stochastic process models, based on Wiener or Gamma processes, exhibit clear advantages in addressing the randomness and uncertainty in degradation processes, but their applicability in real-world complex operating conditions requires further research and validation. Furthermore, the potential applications of thermal lifetime models, such as

关键词： thermal aging physics of failure artificial intelligence algorithms curve-fitting technologies stochastic process application of insulation lifetime model

来源：评论

学校读者我要写书评

暂无评论

Spillovers, Bottlenecks, and More Invention After Invention

引用

IEEE MICRO 2025年第1期45卷 101-103页

作者： Greenstein, Shane Harvard Sch Business Boston MA 02163 USA

来源：评论

学校读者我要写书评

暂无评论

Urban flood management from the lens of social media data using machine learning algorithms

引用

JOURNAL OF HYDROLOGY 2025年 653卷

作者： Boota, Muhammad Waseem Soomro, Shan-e-hyder Xu, Jikun Ahmad, Muhammad Irshad Xia, Haoming Qin, Yaochen Idrees, Muhammad Bilal Ahmad, Naseem Yan, Chaode Yousaf, Ayesha Ning, Xiaoju Henan Univ Coll Geog & Environm Sci Kaifeng 475004 Peoples R China Henan Univ Henan Key Lab Earth Syst Observat & Modeling Kaifeng 475004 Peoples R China Henan Univ Minist Educ Key Lab Geospatial Technol Middle & Lower Yellow R Kaifeng 475004 Peoples R China Henan Univ Key Res Inst Yellow River Civilizat & Sustainable Kaifeng 475004 Peoples R China Henan Univ Collaborat Innovat Ctr Yellow River Civilizat Join Kaifeng 475004 Peoples R China China Three Gorges Univ Coll Hydraul & Environm Engn Yichang 443002 Peoples R China Zhengzhou Univ Sch Water Conservancy & Transportat Zhengzhou 450001 Peoples R China Zhengzhou Univ Business Sch Zhengzhou 450001 Peoples R China Dalian Univ Technol Fac Infrastruct Engn Dalian 116024 Peoples R China Univ Peshawar Natl Ctr Excellence Geol Peshawar 25000 Pakistan Henan Univ Technol Coll Mech & Elect Engn Zhengzhou 450052 Peoples R China Henan Univ Econ & Law Sch Resources & Environm Zhengzhou 450046 Peoples R China

Urban flooding (UFL) occurs frequently due to climatic variations and anthropogenic activities. Real-time information on the physical and emotional damage caused by UFL is critical for catastrophic emergency management, but methods to rapidly acquire such information are lacking. Social media promptly disseminates emergency information and has become a valuable source for real-time data with low acquisition cost and rich content. Here, we present a framework to rapidly categorize physical and emotional damage caused by UFL events using data scraped from Twitter and Facebook and machine-learning classification algorithms. To test our framework, we use a UFL event from August 2022 in the Swat Valley of Pakistan. First, we obtain data from Twitter and Facebook users worldwide. Second, we filter the data using deduplication and denoising. Last, we use a novel approach based on machine-learning algorithms to assess the physical and emotional damage caused by the flooding. We also explore the capacity for recovery by analyzing keyword frequencies indicative of floodinduced destruction. We observe that social media can be used to assess the extent of damage and the progress of the recovery process. We find that people in regions with more physical damage tend to be more emotionally affected. Also, government officials tend to disseminate positive information to mitigate public panic during flooding episodes, and students are more likely to express negative emotions. Our UFL disaster classification framework captures changes in the physical and emotional state of UFL-stricken areas in real time and can be leveraged by emergency responders during disaster management and recovery efforts and by managers to mitigate the impacts of future potential UFL disasters.

关键词： Urban floods Spatio-temporal variations Physical and emotional damage Empowerment artificial intelligence algorithms

来源：评论

学校读者我要写书评

暂无评论

Photonic platform coupled with machine learning algorithms to detect pyrolysis products of crack cocaine in saliva: A proof-of-concept animal study

引用

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2025年 329卷 125635页

作者： Santana-Melo, Igor Caixeta, Douglas Carvalho Aguiar, Emilia Maria Gomes Cardoso-Sousa, Leia Pacheco, Amanda Larissa Dias dos Santos, Yngrid Mickaelli Oliveira da Silva, Jefte Teixeira Santana, Antonio Euzebio Goulart Carneiro, Murillo Guimaraes de Castro, Olagide Wagner Sabino-Silva, Robinson Fed Univ Alagoas UFAL Inst Biol Sci & Hlth Ave Lourival de Melo Motakm 14Campus AC SimoesC BR-57072970 Maceio AL Brazil Fed Univ Uberlandia UFU Inst Biomed Sci ICBIM Innovat Ctr Salivary Diag & Nanotheranost Dept Physiol Ave Univ Fed Alagoas Campus Engn & Agrarian Sci Maceio AL Brazil Univ Fed Uberlandia Fac Comp Uberlandia MG Brazil

The non-invasive detection of crack/cocaine and other bioactive compounds from its pyrolysis in saliva can provide an alternative for drug analysis in forensic toxicology. Therefore, a highly sensitive, fast, reagent-free, and sustainable approach with a non-invasive specimen is relevant in public health. In this animal model study, we evaluated the effects of exposure to smoke crack cocaine on salivary flow, salivary gland weight, and salivary composition using Attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy. The exposure to crack cocaine was performed in an acrylic box apparatus with a burned activation of crack/cocaine 400 mg for 10 min for 14 consecutive days. Crack/cocaine exposure increased the salivary secretion without changes in parotid and submandibular weights. Hierarchical Clustering Analysis (HCA) was applied to depict subgrouping patterns in infrared spectra, and Principal components analysis (PCA) explained 83.2 % of the cumulative variance using 3 PCs. ATR-FTIR platforms were coupled to AdaBoost, artificial Neural Networks, Na & iuml;ve Bayes, Random Forest, and Support Vector Machine (SVM) algorithms tool to identify changes in the infrared salivary spectra of rats exposed to crack cocaine. The best classification of crack cocaine exposure using the salivary spectra was performed by Na & iuml;ve Bayes, presenting a sensitivity of 100 %, specificity of 80 %, and accuracy of 90 % between crack cocaine and control rats. The SHAP features of salivary infrared spectra mostly indicate the vibrational modes at 1331 cm- 1 and 2806 cm-1 , representing CH2 wagging commonly linked in lipids and C-H stretch often attributed to the CH2 or CH3 groups in lipid molecules, respectively, as the main responsible vibrational modes for crack cocaine exposure discrimination. In summary, the present pre-clinical findings indicate the potential of the ATR-FTIR platform coupled with machine learning to effectively detect changes in salivary in

关键词： Crack cocaine Flow salivary Screening tool ATR-FTIR artificial intelligence algorithms

来源：评论

学校读者我要写书评

暂无评论

Emerging strategies for addressing flood-damage modeling issues: A review

引用

INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION 2025年 116卷

作者： Redondo-Tilano, Sergio Andres Boucher, Marie-Amelie Lacey, Jay Univ Sherbrooke Dept Genie Civil & Genie Batiment Quebec City PQ Canada

Flood-damage models allow decision-makers to estimate potential flood impacts, yet they continue to face critical challenges that affect their accuracy. This review identifies and organizes these challenges, highlighting recent strategies proposed to address them. Key issues in flood-damage modeling include data scarcity, unquantified uncertainty, limited consideration of extended losses (e.g., secondary, intangible, and indirect damages), and limited model transferability. These issues can be caused by both data limitations and methodological choices and are also interconnected so they can influence each other. Strategies to overcome these issues fall into two categories: using alternative data sources other than historical damage records and enhancing existing models to deal with methodological gaps. Additionally, artificial intelligence (AI) algorithms, such as Random Forests and Bayesian networks, show promise in optimizing limited datasets and delivering more comprehensive damage estimates than traditional models. However, their performance remains inconsistent across different applications. This review emphasizes the need for future research to refine AI applications and improve damage data availability, aiming to develop more robust, transferable flood-damage models. By addressing these gaps, the review provides a framework to guide improvements in flood loss identification and estimation, benefiting government agencies, insurance sectors, and communities at risk.

关键词： Flood damages Uncertainty assessment Data scarcity Health impacts of floods Transferability Integrated flood risk management artificial intelligence algorithms

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal simulation of net ecosystem productivity in the Tibetan Plateau region using multi-scale data assimilation for terrestrial ecosystem process model

引用

AGRICULTURAL AND FOREST METEOROLOGY 2025年 366卷

作者： Ma, Changhui Duan, Si-Bo Xu, Cong Qin, Wenhua Wang, Feng He, Lei Chinese Acad Agr Sci State Key Lab Efficient Utilizat Arable Land China Inst Agr Resources & Reg Planning Beijing 100081 Peoples R China Lanzhou Univ Coll Earth & Environm Sci Lanzhou 730000 Gansu Peoples R China MNR Fourth Topog Surveying Team Harbin 150025 Peoples R China

Accurately elucidating the spatio-temporal pattern of net ecosystem productivity (NEP) in grasslands on the Tibetan Plateau (TP) is essential for understanding the feedback mechanisms of the carbon cycle to climate and grazing. Parameter localization through data assimilation for terrestrial ecosystem process model is the dominant approach to accurately simulate NEP. However, current studies calibrate ecosystem process model by grassland types, neglecting the spatial variation of model parameters within the same type. Consequently, the calibrated model struggles to characterize the spatially diverse ecological mechanisms. Therefore, we propose a multi-scale parameterization scheme for the CENTURY model, described as follows. (1) Calibrate model parameters in terms of grassland type by assimilating NEP observations from eddy covariance (EC) stations. (2) Migrate the grassland type-scale model to discrete pixels within prohibited pastures, then fine-tune the model parameters with strong spatial divergence and sensitivity by assimilating remotely sensed NPP data on a per-pixel basis;(3) Use ensemble learning algorithms to construct spatial interpolation models driven by environmental factors for discrete parameters. The results confirmed that the calibrated CENTURY model has higher spatial generalization performance compared to model calibrated using previous parameterization scheme. Specifically, the RMSE (R2) for NEP simulations at all EC stations was reduced from 10.18 g C m2 mo-1 (0.58) to 7.58 g C m2 mo-1 (0.72). The CENTURY model was employed in the Selinco region to generate spatio-temporal datasets of grassland NEP from 1980 to 2020, incorporating various grazing intensity scenarios. The following conclusions were drawn from the spatio-temporal analyses. (1) Regardless of grazing scenarios, almost all grasslands functioned as carbon sinks, exhibiting a significant annual increase of net sinks. (2) The annual net sink decreased significantly with altitude. (3) A

关键词： Carbon cycle Net ecosystem productivity Terrestrial ecosystem process model Data assimilation artificial intelligence algorithms Tibetan plateau

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing prosthetic hand control using non-invasive sensors and intelligent algorithms: A comprehensive review

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 123卷

作者： Shah, Gautam Sharma, Abhinav Joshi, Deepak Rathor, Ajit Singh Univ Petr & Energy Studies Sch Engn Dept Elect & Elect Engn Dehra Dun 248007 Uttarakhand India Indian Inst Technol Delhi Ctr Biomed Engn New Delhi 110016 India All India Inst Med Sci AIIMS Dept Biomed Engn New Delhi 110029 India

Over the last few years, there has been significant growth in neurological diseases which drastically affect a person's ability to perform everyday tasks, reducing their overall well-being. The development of wearable hand gesture interfaces to restore and augment hand function is a potential approach that facilitates natural human-machine interaction. This article presents a comprehensive review of recent advancements in prosthetic hand control using gesture recognition greatly aided by the incorporation of non-invasive sensors and the use of intelligent algorithms. Surface EMG, IMU, MMG, and FMG are some of the most prominent biosensors used to extract forearm muscle activity, while sensor fusion has shown significant improvement in identifying user intentions and assisting robotic hands in pattern recognition (PR). The extraction of significant signal information in myoelectric control is facilitated by feature engineering which involves manual extraction of features and feature learning that uses algorithms to automatically extract features from raw data. The conventional control techniques estimate a limited number of hand gestures, therefore artificial intelligence (AI) based intelligent algorithms were explored to predict a wide number of hand gestures with improved dexterity. This article also examines the effectiveness of sensor fusion, and intelligent algorithms and identifies recent trends and gaps which suggest new directions for research in gesture recognition for myoelectric prosthetic hand control systems.

关键词： Gesture recognition Non-invasive sensors Feature extraction Myoelectric control Prosthetic hand artificial intelligence algorithms

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based privacy-preserving technology to secure shared data in vehicular communication

引用

INTERNATIONAL JOURNAL OF COMMUNICATION NETWORKS AND DISTRIBUTED SYSTEMS 2025年第3期31卷 346-371页

作者： Slama, Omessaad Dhifallah, Walid Zidi, Salah Lloret, Jaime Alaya, Bechir Tarhouni, Mounira Univ Gabes Hatem Bettaher Lab IRESCOMATH Gabes 6029 Tunisia Univ Politecn Valencia Integrated Management Coastal Res Inst Valencia Spain Univ Gabes Hatem Bettaher Lab IResCoMath Gabes 6029 Tunisia Qassim Univ Coll Business & Econ Dept Management Informat Syst & Prod Management Buraydah 51452 Saudi Arabia

In vehicular ad-hoc networks (VANETs), securely exchanging sensitive data like misbehaviour detection models faces significant security and privacy hurdles. Our solution, machine learning model blockchain-based privacy-preserving (MBPP), combines Blockchain technology and advanced cryptography to tackle this. MBPP ensures data confidentiality and integrity while improving detection model reliability. It involves securely storing ML models on the blockchain using cryptographic hash functions. Our study meticulously evaluates transactional time and computational costs, vital for smooth blockchain transactions. This research not only presents a conceptual framework for blockchain use in VANETs but also offers insights into managing transactions via smart contracts, addressing VANETs' security and privacy challenges effectively.

关键词： blockchain smart contract computational costs artificial intelligence algorithms VANETs vehicular ad-hoc networks data sharing privacy preservation cryptography hash function

来源：评论

学校读者我要写书评

暂无评论

Evaluation method for asphalt pavement condition based on intelligent inspection technology

Evaluation method for asphalt pavement condition based on in...

引用

2024 International Conference on Smart Transportation and City Engineering, STCE 2024

作者： Ou, Jianxi Zhang, Jianqin Liu, Yi Xu, Shaozhuang School of Surveying and Urban Spatial Information Beijing University of Civil Engineering and Architecture Beijing China

ISBN: (纸本)9781510690585

With the rapid development of the transportation network, efficient and accurate asphalt pavement maintenance has become an urgent need. Traditional pavement condition evaluation methods are time-consuming, inefficient, and highly dependent on manual judgment and subjectivity, failing to meet the current needs for efficiency and precision in maintenance. This study proposes a rapid evaluation method for asphalt pavement condition based on lightweight intelligent inspection technology, aiming to utilize digital and artificial intelligence technologies to provide a scientific and efficient method for pavement maintenance evaluation. This method employs vehicle-mounted high-definition cameras as data collection tools without the need for fixed installations, combined with artificial intelligence algorithms to analyze pavement images, automatically identify pavement damage, and score conditions. Experimental results show that, compared to traditional evaluation methods, the method proposed in this study significantly improves evaluation efficiency, achieves a marked acceleration in the evaluation process, and ensures the objectivity and repeatability of the evaluation results. By applying lightweight intelligent inspection equipment, not only is the operational process simplified, but the flexibility and coverage of the evaluation work are also enhanced. This study provides new technical means for the rapid evaluation and maintenance of asphalt pavements. Future work will further optimize algorithms and system design, expand the application scope, with the aim of achieving broader practicality and effectiveness. © 2025 SPIE.

关键词： artificial intelligence algorithms Asphalt Pavement Intelligent Inspection Technology Lightweight Collection Equipment Rapid Evaluation Sustainable Development

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：