检索结果-内蒙古大学图书馆

A Multimodal learning model based on a QSPR approach for the estimation of RON, MON and CN, for any C, H, O hydrocarbons

引用

FUEL 2025年 381卷

作者： Bounaceur, Roda Barthelemy, Nicolas Delort, Nicolas Herbinet, Olivier Battin-Leclerc, Frederique Univ Lorraine CNRS LRGP F-54001 Nancy France

With the increasing demand for alternative fuels and the use of biomass as feedstock for fuel production, a wider range of oxygenated hydrocarbons as fuel additives needs to be considered. Consequently, the development of robust methods for predicting criteria such as Research Octane Number (RON), Motor Octane Number (MON), and Cetane Number (CN) will play a crucial role in characterizing novel fuels. In this paper, we propose a robust deep-learning model based on a Quantitative Structure-Property Relationship (QSPR) approach for estimating RON, MON, and CN of any C, H, and O molecules. We developed a multimodal learning model that combines two types of data, using an Artificial Neural Network (ANN) as the foundation. The Mordred algorithm was used to determine 457 descriptors to characterize hydrocarbons. These numerical values represent the first type of data considered in this study. To account for the effects of mesomerism or chirality in molecules, the InChIKey notation was used. This 27- character notation represents the second type of data, treated as text data. To encode these textual variables into numeric data, we employed a Word Embedding method. The predictions from the final model were successfully tested against a large set of experimental data and compared with those from five recent learning models-GNN, ANN, GPR, DLMO, and PIGNN-found in the literature. The GNN (Graph Neural Networks) model relies on the molecular architecture, the ANN (Artificial Neural Networks) model is based on a limited number of chemical groups, while the GPR (Gaussian Process Regression) model is primarily based on Joback groups. The two most recent methodologies, DLMO (Deep learning Mixing Operator) and PIGNN (Physics-Informed Graph Neural Network), utilize more sophisticated algorithms. Full comparisons and multiple tests demonstrate the very robust and predictive capabilities of our newly proposed multimodal learning model. The prediction tool is available via a web page at

关键词： RON MON CN Research Octane Number Motor Octane Number Cetane Number learning model Artificial Neural Network QSPR Molecular descriptors

来源：评论

学校读者我要写书评

暂无评论

Overcoming the spiritual emptiness of students in the modern era through the integration of Al-Ghazali's human concepts in the Islamic religious education learning model

引用

COGENT EDUCATION 2025年第1期12卷

作者： Jenuri Faqihuddin, Achmad Suresman, Edi Abdullah, Mulyana Univ Pendidikan Indonesia Ilmu Pendidikan Agama Islam Bandung Indonesia

This study examines the integration of Al-Ghazali's human concepts into the Islamic Religious Education (IRE) learning model to address spiritual emptiness among students in contemporary educational contexts. A mixed-methods approach was employed, combining qualitative interviews with 10 IRE lecturers and quantitative pretest-posttest data from students. Qualitative findings revealed that current IRE models are too theoretical, insufficiently relevant to modern life, and lack focus on deep spiritual experiences. Based on these findings, a new learning model was developed, integrating Al-Ghazali's concepts of Nafs (self), Qalb (heart), Ruh (spirit), and 'Aql (intellect), aimed at fostering holistic spiritual development in students. Quantitative results showed a significant improvement in students' spiritual understanding, with an N-Gain score of 0.85, indicating the model's effectiveness in enhancing knowledge and engagement. This research suggests that the IRE learning model should prioritize not only academic rigor but also spiritual growth, addressing the need for a more holistic approach to education that aligns with modern spiritual and intellectual demands. The implications of these findings underscore the necessity of adapting learning models to bridge the spiritual gap prevalent in contemporary education. Further studies are needed to explore the long-term impact and challenges of implementing this model across diverse educational settings.

关键词： Spiritual Al-Ghazali learning model islamic religious education

来源：评论

学校读者我要写书评

暂无评论

Open-world multi-modal machine learning decision model based on uncertain data analysis for fetal heart diagnosis

引用

INFORMATION SCIENCES 2025年 701卷

作者： Zhu, Guosong Qin, Zhen Xiong, Hu Kumari, Saru Alenazi, Mohammed J. F. Guo, Yingkun Chen, Chien-Ming Univ Elect Sci & Technol China Network & Data Secur Key Lab Sichuan Prov Chengdu 610054 Sichuan Peoples R China Chaudhary Charan Singh Univ Dept Math Meerut Uttar Pradesh India Lovely Profess Univ Sch Chem Engn & Phys Sci Phagwara 144411 Punjab India King Saud Univ Coll Comp & Informat Sci Dept Comp Engn Riyadh 11451 Saudi Arabia Sichuan Univ West China Second Univ Hosp Dept Radiol Chengdu Peoples R China Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Nanjing Peoples R China

Machine learning-generated diagnostic decision for fetal heart screening can assist doctors in diagnosing fetal conditions more quickly and accurately. However, due to the uncertainties in fetal heart data, there has always been a gap in the generation of fetal heart diagnostic decision. To address the modal uncertainty and potential incompleteness of fetal heart data, a novel open-world machine learning framework for fetal heart diagnostic decisions is proposed, which involves deep analysis across text, image and audio modalities to thoroughly explain uncertain and incomplete data, accurately diagnose conditions, and depict key screening locations. It further integrates an efficient cardiac ultrasound diagnosis network that provides precise prompts for cardiac views and disease categories, to address the generic issues of low accuracy in multi-task, multi-category complex classification and poor robustness to incomplete images faced by existing medical diagnostic decision methods. The diagnostic content generation network of the framework is finetuned on medicine and healthcare big data to generate decision text, collaboratively diagnosing conditions with heart images and audios, possessing the capability to reconstruct incomplete fetal heart images and guide focus on key locations.

关键词： Condition diagnosis and multi-modal data analysis Fetal heart screening Robust open-world multi-modal machine learning model Medical report generation

来源：评论

学校读者我要写书评

暂无评论

Crowd Congestion Forecasting Framework Using Ensemble learning model and Decision Making Algorithm: Umrah Use Case

引用

IEEE ACCESS 2024年 12卷 67453-67469页

作者： Derhab, Abdelouahid Mohiuddin, Irfan Halboob, Waleed Almuhtadi, Jalal King Saud Univ Ctr Excellence Informat Assurance CoEIA Riyadh 11451 Saudi Arabia King Saud Univ Coll Comp & Informat Sci Riyadh 11461 Saudi Arabia

Forecasting crowd congestion is a critical aspect of crowd management, particularly in dynamic and densely populated areas, such as urban centers, events, or pilgrimage sites. In this paper, we proposed the first crowd congestion forecasting framework for the pilgrimage of Umrah. We addressed the crowd congestion forecasting problem by clustering the crowd flow trajectory in Masjid Al-Haram (Great Mosque) in the city of Makkah into six zones. The framework consists of two main components: 1) Ensemble forecasting model that aims at forecasting the crowd density of Masjid Al-Haram and its six zones, and 2) decision making algorithm that aims at keeping the crowd density at an acceptable level, and recommends updating the crowd flows when the forecasted crowd density exceeds the crowd density threshold. We built the ensemble learning model in three phases. In the first phase, we selected and evaluated different learning base models, including ARIMA, Sequence to Sequence (Seq2Seq) learning, M-1D-CNN-LSTM, and DeepSTN. In the second phase, the best three models, which performed well in the first phase, are selected to build the stacked ensemble model. The latter is validated using the walk-forward technique in the third phase. To evaluate the framework, we built a crowd dataset based on two temporal properties: 1) hourly context and 2) daily context. We evaluated the three phases of the ensemble forecasting model. In the first phase, DeepSTN performs the best by achieving a Mean Absolute Error (MAE) of 0.281. The results also indicate that DeepSTN is the best fit for five zones, and one variant of Seq2Seq, named Seq2Seq2b is the best fit for one zone under Mean Square Error (MSE) and Root Mean Squared Error (RMSE). Under MAE, DeepSTN and Seq2Seq2b, each of which is the best choice for three zones. In the second phase, the stacked ensemble achieves a MAE of 0.257. In the third phase, the stacked ensemble model is validated using the walk forward technique, which allows to

关键词： Crowd congestion crowd density decision making forecasting learning model Umrah

来源：评论

学校读者我要写书评

暂无评论

Intelligent learning model-based skill learning and strategy optimization in robot grinding and polishing

引用

Science China(Technological Sciences) 2022年第9期65卷 1957-1974页

作者： CHEN Chen WANG Yu GAO ZhiTao PENG FangYu TANG XiaoWei YAN Rong ZHANG YuKui School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China

With the rapid advancement of manufacturing in China,robot machining technology has become a popular research *** increasing number of robots are currently being used to perform complex tasks during manual operation,e.g.,the grinding of large components using multi-robot systems and robot teleoperation in dangerous environments,and machining conditions have evolved from a single open mode to a multisystem closed *** the environment is constantly changing with multiple systems interacting with each other,traditional methods,such as mechanism modeling and programming are no longer *** learning models,such as deep learning,transfer learning,reinforcement learning,and imitation learning,have been widely used;thus,skill learning and strategy optimization have become the focus of research on robot *** learning in robot machining can use robotic flexibility to learn skills under unknown working conditions,and machining strategy research can optimize processing quality under complex working ***,skill learning and strategy optimization combined with an intelligent learning model demonstrate excellent performance for data characteristics learning,multisystem transformation,and environment perception,thus compensating for the shortcomings of the traditional research *** paper summarizes the state-of-the-art in skill learning and strategy optimization research from the perspectives of feature processing,skill learning,strategy,and model optimization of robot grinding and polishing,in which deep learning,transfer learning,reinforcement learning,and imitation learning models are integrated into skill learning and strategy optimization during robot grinding and ***,this paper describes future development trends in skill learning and strategy optimization based on an intelligent learning model in the system knowledge transfer and nonstructural environment autonomous processing.

关键词： learning model robot grinding polishing feature processing skill learning strategy optimization

来源：评论

学校读者我要写书评

暂无评论

learning model IN SCHOOL OF VOCATIONAL STUDIES

LEARNING MODEL IN SCHOOL OF VOCATIONAL STUDIES

引用

8th International Scientific Conference on Modern Management of Mine Producing, Geology and Environmental Protection

作者： Yildirim, Osman Bal, Pervin Istanbul Kultur Univ Sch Vocat Studies Istanbul Turkey Bogazici Dersanesi Yeni Bogazici Egitim Kurumlari Istanbul Turkey

ISBN: (纸本)9789549181814

In this research, it is aimed to determine which individual and environmental characteristics affecting training. Instead of both types of evaluation models, to be proactive, the evaluation of training mentioned in this research is focused on how training affects individuals. To this end, in this thesis the factors affecting to the training effectiveness were examined in regard of trainee perspectives. According to the research results, it is revealed that mostly related to the training effectiveness are respectively: trainer's consideration of employees' learning styles, employees motivation to attend the training, employee's organizational affective commitment and employee's belief that the training will add value to his/her career.

关键词： learning model vocational studies training effectiveness

来源：评论

学校读者我要写书评

暂无评论

Cognitive machine learning model for network information safety

引用

SAFETY SCIENCE 2019年 118卷 435-441页

作者： Bi, Xinwen Shi, Xiaodan Zhang, Zeliang Beihua Univ Sch Comp Sci & Technol Jilin Jilin Peoples R China

The problem of network information security has resulted in a significant increase in economic losses, resulting in an increase in the energy loss of learning resource scheduling in situational cognitive learning networks. In order to improve the scheduling ability of learning resources in networks, a situational cognitive learning model based on network information security is proposed. Considering the limitation of data packet delay in attenuation channel, the link equilibrium configuration condition of learning resource scheduling output is obtained. Based on this, a situational cognitive learning network security situation assessment model is constructed to reflect the security situation in learning scheduling system and the degree of harm to the system. Based on the inertia weight of learning resources output, the data flow model of learning resources in situational cognitive learning network is constructed, and the sharing security settings of situational cognitive learning network resources are realized by combining the network security situation assessment model. Optimize the cognitive learning mode network, select the candidate nodes that meet the conditions as Sink nodes, and take the initial energy of the nodes as the constraint index, carry out the learning path planning of Situational Cognition under network information security, realize the optimization of learning resource scheduling, and complete the construction of situational cognitive learning mode. The simulation results show that this method is applied to secure scheduling of learning resources in situational cognitive learning network, can reduce the energy consumption of network nodes, improve the survival probability of situational cognitive learning nodes, maximize the benefits of balanced control of learning resources, reduce economic losses and optimize the situational cognitive learning model.

关键词： Network information security Situational cognition learning model Resource scheduling Equilibrium

来源：评论

学校读者我要写书评

暂无评论

An associative memory-based learning model with an efficient hardware implementation in FPGA

引用

EXPERT SYSTEMS WITH APPLICATIONS 2011年第4期38卷 3499-3513页

作者： Ahmadi, Ali Mattausch, Hans Juergen Abedin, M. Anwarul Saeidi, Mahmoud Koide, Tetsushi Khajeh Nasir Univ Technol Elect & Comp Coll Tehran Iran Hiroshima Univ Res Inst Nanodevice & Bio Syst RNBS Higashihiroshima 724 Japan Educ & Res Inst Informat & Commun Technol Tehran Iran Dhaka Univ Engn & Technol Dept Elect & Elect Engn Dhaka Bangladesh

In this paper we propose a learning model based on a short- and long-term memory and a ranking mechanism which manages the transition of reference vectors between the two memories. Furthermore, an optimization algorithm is used to adjust the reference vectors components as well as their distribution. continuously. Comparing to other learning models like neural networks, the main advantage of the proposed model is that a pre-training phase is unnecessary and it has a hardware-friendly structure which makes it implementable by an efficient LSI architecture without requiring a large amount of resources. A prototype system is implemented on an FPGA platform and tested with real data of handwritten and printed English characters delivering satisfactory classification results. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： FPGA Handwritten characters Hardware prototyping learning model Machine learning

来源：评论

学校读者我要写书评

暂无评论

Nonlinear model predictive controller design based on learning model for turbocharged gasoline engine of passenger vehicle

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2018年 109卷 74-88页

作者： Hu, Yunfeng Chen, Huan Wang, Ping Chen, Hong Ren, Luquan Jilin Univ State Key Lab Automot Simulat & Control Changchun 130012 Jilin Peoples R China Jilin Univ Dept Control Sci & Engn Changchun 130025 Jilin Peoples R China Jilin Univ Minist Educ Key Lab Bion Engn Changchun 130025 Jilin Peoples R China

In this paper, a neural-network-based nonlinear model predictive control (NMPC) scheme is investigated to realize coordinated control over the throttle and wastegate of a turbocharged gasoline engine of a passenger vehicle. First, due to the presence of MAPs and the complex structure of the turbocharged engine, establishing a mechanism model for controller design is very complicated. Benefiting from a large amount of experimental data, a predictive model is learned by a neural network to predict the future dynamics of the engine air-path system, and the accuracy of this model is verified. Second, to address the system constraints and coupling, a nonlinear model predictive controller is proposed to track the desired intake manifold pressure and boost pressure for meeting the engine torque demand. Third, quantum-behaved particle swarm optimization (QPSO) is applied for optimization of the NMPC objective function to obtain a more accurate solution. Finally, the performance of the control system is tested using the commercial simulation software AMESim. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Turbocharged gasoline engine control model predictive control learning model Neural network Quantum-behaved particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

The proposition of Possibilistic sigmoid features and the Shannon-Hanman transform classifier along with the pervasive learning model for the classification of brain tumor using MRI

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第17期81卷 23913-23939页

作者： Asthana, Pallavi Hanmandlu, Madasu Vashisth, Sharda NorthCap Univ EECE Dept Gurugram Haryana India MVSR Engn Coll CSE Dept Hyderabad India

As part of developing a computer-aided diagnosis system for the early detection/classification of brain tumors, this paper presents an Information set-based sigmoid features and a classifier using MR images. A set of information values constituting an Information set springs forth on fitting a membership function to a set of information source (attribute) values, the sum of which gives the certainty/uncertainty in the attribute values to a class, say, the pixel intensities in an MRI to a disease class. This certainty/uncertainty representation is not attempted in the existing methods, thus failing to produce efficient features. To this end, Hanman-Anirban (HA), Mamta-Hanman (MH), and Possibilistic Renyi entropy functions are employed including the pervasive membership function in the generation of four types of sigmoid features. The pervasive Information set results from the use of pervasive membership function that is a combination of the membership function and non-membership function. Furthermore, the Shannon-Hanman Transform classifier is formulated using the t-norm of error vectors between the training and test feature vectors, and its parameters are learned through the Pervasive learning model. The proposed system comprising features, classifier, and the learning model is tested on two Brain MRI's datasets. The t-norm based fusion of two features has also been experimented. The Shannon-Hanman Transform classifier along with the Pervasive learning model is found to outperform the other classifiers in the literature with the highest accuracy of 99.51% for the two-class classification with a fusion of two features and 99.09% for the three-class classification with a sigmoid MH feature.

关键词： Brain tumor Classification learning model Feature extraction Shannon-Hanman transform classifier

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：