检索结果-内蒙古大学图书馆

Data Science Meets Ziegler-Natta Catalysis to Design High-Performance Lewis Bases for Isotactic Polypropylene Production

引用

ACS CATALYSIS 2025年第10期15卷 8185-8193页

作者： Zhang, Ziyun Falivene, Laura Takasao, Gentoku Morini, Giampiero Mignogna, Alessandro Cavallo, Luigi King Abdullah Univ Sci & Technol KAUST Phys Sci & Engn Div Thuwal 239556900 Saudi Arabia Univ Salerno Dept Chem & Biol I-84084 Fisciano Italy Basell Poliolefine Italia G Natta Res Ctr LyondellBasell I-44122 Ferrara Italy

In this study, we harness data science to design carbamate esters (CEs) as donors in Ziegler-Natta catalysis. Using a small yet insightful data set of 18 patented CEs, we developed a multivariate linear regression (MLR) model incorporating key electronic and steric descriptors to predict polymerization yields. Rigorous validation demonstrated the model's robustness and predictive power, enabling its application in the discovery of higher performing CEs. In the initial optimization cycle, the model guided the design of 10 CEs, which were synthesized and tested, successfully confirming the predictions. A second optimization cycle fine-tuned the most promising CE from cycle 1, leading to the discovery of a highly efficient CE with a yield of 108 kg polymer/g catalyst, marking a 30% improvement over the best performing CE in our initial data set. This work underscores the transformative role of data science in industrial catalyst design, offering a powerful alternative to traditional trial-and-error and density functional theory approaches while accelerating innovation.

关键词： Ziegler-Natta catalysis propene polymerization isotactic polypropylene catalyst design datascience multivariate linear regression

来源：评论

学校读者我要写书评

暂无评论

Quantifying the relationship between landscape patterns and ecosystem services along the Urban-rural gradient

引用

LANDSCAPE AND ECOLOGICAL ENGINEERING 2023年第3期19卷 531-547页

作者： Abdollahi, Sedighe Ildoromi, Alireza Salmanmahini, Abdolrassoul Fakheran, Sima Kulczyk, Sylwia Malayer Univ Fac Nat Resources & Environm Dept Environm Sci & Engn Malayer Iran Malayer Univ Fac Nat Resources & Environm Nat Engn Dept Malayer Iran Gorgan Univ Agr Sci & Nat Resources Fac Fisheries & Environm Dept Environm Sci Gorgan Iran Isfahan Univ Technol Fac Nat Resources Dept Environm Esfahan Iran Univ Warsaw Fac Geog & Reg Studies Dept Tourism Geog & Recreat Krakowskie Przedmiescie 30 PL-00927 Warsaw Poland

Landscape characteristics can be described using statistical metrics of the structure and spatial arrangement of land use types that may also affect the ecological and functional processes of ecosystems. Hence, understanding the relationship between these variables and the functional indicators of ecosystems is a priority in evaluating benefits obtained from ecosystems and land uses/covers. The present study aimed to investigate and model the relationship between the composition and configuration of two land-use classes, the green covers, and human-infrastructure and ecosystem services, using a spatial-statistical approach. Upon quantifying three ecosystem services, including aesthetic, recreational, and noise reduction services, the relationship between these services and the composition and configuration metrics of land use classes were evaluated using multivariate linear regression models. The results showed a significant correlation between the composition and configuration of green infrastructure and the ecosystem services supply. The percentage of the landscape, class area, number of patches, fractal dimension, shape index, and aggregation index metrics had the most significant contribution to explaining the ecosystem services variations in both land use categories. Comparing models for ecosystem services in the two land use classes showed that both models had relatively similar performance and accuracy in explaining the ecosystem services variations. The results can provide a practical framework for planning land use, based on the landscape ecology concepts.

关键词： Noise reduction service Landscape patterns Land use planning multivariate linear regression Iran

来源：评论

学校读者我要写书评

暂无评论

A Method for Estimating Fish Biomass Based on Underwater Binocular Vision 36

A Method for Estimating Fish Biomass Based on Underwater Bin...

引用

36th Chinese Control and Decision Conference (CCDC)

作者： Gao, Zhaozhi Jiang, Wenxin Man, Xiangnan Zheng, Rong Ma, Xin Shandong Univ Sch Control Sci & Engn Jinan Peoples R China Shandong Marine Grp LTD Jinan Peoples R China

ISBN: (纸本)9798350387780;9798350387797

This paper presents an underwater binocular vision-based fish biomass estimation method using instance segmentation and 3D reconstruction. To validate the system's effectiveness in aquaculture environments and the accuracy of measurement results, three datasets are proposed in experimental and breeding settings. These datasets are respectively used for training and validation of the instance segmentation network;dimension estimation;and mass fitting and estimation. In this work, we introduce pyramid squeeze attention and triple attention in the backbone of instance segmentation network to enhance segmentation accuracy. In the context of free-swimming conditions, where fish often assume non-orthogonal positions relative to the camera's optical axis and exhibit non-linear body shapes, we introduce a stereo disparity map optimization method. This method generates smooth and accurate point cloud and triangular mesh of fish targets, allowing for the estimation of fish fork length and body width based on 3D information. The LAR is also used to estimate the mass by taking the fork length and body width as independent variables.

关键词： instance segmentation 3D reconstruction multivariate linear regression dimension and mass estimation

来源：评论

学校读者我要写书评

暂无评论

Simulation and Evaluation Method of a Survival Equipment System Based on DQN 24

Simulation and Evaluation Method of a Survival Equipment Sys...

引用

International Conference on Algorithms, Software Engineering, and Network Security (ASENS)

作者： Zhang, Qichen Ni, Bin Qian, Li Pan, Zhigang Air Force Logist Acad Xuzhou 221000 Jiangsu Peoples R China

ISBN: (纸本)9798400709784

When distressed pilots crash into the sea, they confronted with a significantly more complex and harsh survival environment, and the survival equipment plays a crucial role in ensuring the pilot's survival. Due to the intricate nature of the survival equipment system, coupled with the dynamic and multifaceted usage conditions, conventional performance evaluation methods fall short in providing effective assessments. In the context of pilots in distress at sea, this paper presents a simulation-based evaluation method for survival equipment systems using Deep Q-Networks (DQN). Firstly, an analysis of the potential environmental scenarios and situations that distressed pilots may encounter at sea is conducted. Using an agent-based approach, a simulation environment is developed, encompassing various circumstances that distressed pilots may face. Secondly, the DQN model is employed as an intelligent decision agent to simulate the decision-making processes of distressed pilots in different situations. Finally, the DQN model is trained within the simulation environment to converge towards the optimal strategy. Through testing in various environmental scenarios, the efficacy of the DQN model's decisions is validated. Subsequently, extensive simulation data is collected, and a multivariate linear regression analysis is employed to investigate the impact of different survival equipment items on the survival of distressed pilots at sea. This approach offers an effective framework for the evaluation of survival equipment system performance.

关键词： Deep Q Network Agent-Based Simulation Rescue equipment system Performance evaluation multivariate linear regression

来源：评论

学校读者我要写书评

暂无评论

Determination of the effective utilization coefficient of irrigation water based on geographically weighted regression

引用

Frontiers of Earth Science 2022年第2期16卷 401-410页

作者： Rui SHI Gaoxu WANG Xuan ZHANG Yi XU Yongxiang WU Wei WU College of Hydrology and Water Resource Hohai UniversityNanjing 210098China State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering Nanjing 210029China Hydrology and Water Resources Department Nanjing Hydraulic Research InstituteNanjing 210029China

This study uses geographically weighted regression to determine the spatial distribution of the effective utilization coefficient of irrigation water in Zhejiang Province,China,owing to the influences of spatial attributes on the irrigation *** sample set of this study comprised 165 agricultural test sites.A multivariate linear regression model and a geographically weighted regression model were established using the effective utilization coefficient of agricultural irrigation water as the dependent variable in addition to a suite of independent variables,including the actual irrigation area,the percentage of farmland using water-saving irrigation,the type of irrigation area,the net water consumption per mu,the water intake method,the terrain slope,and the soil field *** revealed a positive spatial correlation and noticeable agglomeration features in the effective utilization coefficient of irrigation water in Zhejiang *** geographically weighted regression model performed better in terms of fit and prediction accuracy than the multivariate linear regression *** obtained findings confirm the suitability of the geographically weighted regression model for determining the spatial distribution of the effective utilization coefficient of irrigation water in Zhejiang,and offer a new approach on a regional scale.

关键词： effective utilization coefficient of irrigation water spatial autocorrelation multivariate linear regression geographically weighted regression

来源：评论

学校读者我要写书评

暂无评论

Patterns of species diversity and its determinants in a temperate deciduous broad-leaved forest

引用

Forest Ecosystems 2022年第5期9卷 647-656页

作者： Rui He Man Hu Hang Shi Quan Zhou Xiao Shu Kerong Zhang Quanfa Zhang Haishan Dang Key Laboratory of Aquatic Botany and Watershed Ecology Wuhan Botanical GardenChinese Academy of SciencesWuhan430074China University of Chinese Academy of Sciences Beijing100049China

Biodiversity conservation has long been a subject of extreme interest to community ecologists,with a particular focus on exploring the underlying causes of species diversity based on niche and neutral *** study aims to identify the potential determinants of species diversity in a deciduous broad-leaved forest in the transitional region from subtropical to temperate climate in *** collected woody plant data and environmental variables in a fully mapped 25-ha permanent forest plot,partitioned the beta-diversity into local contributions(LCBD)and species contributions(SCBD),and then applied multivariate linear regression analysis to test the effects of biotic and abiotic factors on alpha-diversity,LCBD,and *** used variation partitioning in combination with environmental variables and spatial distance to determine the contribution of environment-related variations versus spatial *** results showed that the indices of alpha-diversity(i.e.,species abundance and richness)were positively correlated with soil available phosphorus(P)and negatively with *** the betadiversity,environment and space together explained nearly half of the variations in community *** 60%of the variation of LCBD in the understory layer,40%in the substory layer,and 29%in the canopy layer were jointly explained by topographic,soil and biological variables,with biotic factors playing a dominant role in determining the *** abundance accounted for a large proportion of the variations in SCBD in each vertical stratum,and niche position(NP)was the ecological trait that significantly affected the variations in SCBD in the substory and canopy *** findings help to gain better understanding on how species diversity in forest ecosystem responds to environmental conditions and how it is influenced by biotic factors and ecological traits of species.

关键词： Alpha-diversity Beta-diversity Vertical strata multivariate linear regression

来源：评论

学校读者我要写书评

暂无评论

Measurement Invariance Investigation for Performance of Deep Learning Architectures

引用

IEEE ACCESS 2022年 10卷 78070-78087页

作者： Chen, Dewang Lu, Yuqi Hsu, Chih-Yu Fujian Univ Technol Sch Transportat Fuzhou 350118 Fujian Peoples R China Fuzhou Univ Coll Comp & Data Sci Fuzhou 350108 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Fujian Univ Technol Intelligent Transportat Syst Res Ctr Fuzhou 350118 Fujian Peoples R China Fujian Univ Technol Sch Comp Sci & Math Fuzhou 350118 Fujian Peoples R China

Models can be compared against each other. Such comparison helps to find strengths and weaknesses of different approaches and gives additional possibilities for model validation. Multi-class classification is a classification task where each image is assigned to one and only one label. Confusion matrix, Precision, Recall, and F1 Score are popular performance metrics. The common sense is that the performance of any architecture is dependent on the sizes of data set. The goodness of the architecture of deep learning models for different data sets is critical issue. This paper implements Pearson correlation coefficient and the multivariate linear regression method to assess the accuracy of deep learning architectures with five performance indicators. The five performance indicators are training loss rate, robustness, training time, number of model parameters and computation complexity. There are five image datasets used to test four deep learning models: Alexnet, GoogLeNet, ResNet, MobileNet to obtain the values of accuracy and other five indicators. The most important contribution of the article is to show that the accuracy indicator related to training loss rate and training time indicators are not dependent on the selection of the data group. According to the definition of Measurement Invariance (MI), the measurement invariance is demonstrated by the linear regression analysis and inner product of the unit normal vector of the linear regression planes.

关键词： Convolutional neural networks Training Licenses Predictive models Diseases Deep learning Neural networks Deep learning model multivariate linear regression Pearson correlation coefficient measurement invariance performance indicators

来源：评论

学校读者我要写书评

暂无评论

Efficient approach for modeling substrate integrated waveguides

引用

MICROWAVE AND OPTICAL TECHNOLOGY LETTERS 2022年第10期64卷 1719-1725页

作者： Liu, Yuanzhi Mu, Hongyu Yagoub, Mustapha C. E. Bai, Guo Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON K1N 6N5 Canada Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu Peoples R China Southwest Jiaotong Univ Inst Electromagnet Chengdu Peoples R China

In this letter, a highly accurate surrogate model of substrate integrated waveguide (SIW) is proposed. This model allows designers to design SIW structures more efficiently compared to existing complex and CPU-intensive fine approaches. Based on the multivariate linear regression technique, an accurate equation linking the physical parameters of the proposed surrogate but simple model to the fine but complex model was obtained. The accuracy and efficiency of the proposed modeling procedure were demonstrated through a practical design example.

关键词： fine mode machine learning multivariate linear regression SIW surrogate model

来源：评论

学校读者我要写书评

暂无评论

Research and Prediction Based on Multiple linear regression and Machine Learning 3

Research and Prediction Based on Multiple Linear Regression ...

引用

3rd IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2024

作者： Liang, Yunzhen Wang, Shufei Ma, Xiaoxuan South China University of Technology Guangzhou China

ISBN: (纸本)9798350380989

In this paper, a multivariate linear regression model is built for prediction based on SBPE Dataset by drawing heat maps to select relevant features. All 80% of the data is used as a training set. The remaining 20% was divided into 5 variants as a test set. The accuracy of the model in estimating the predicted and true values of the different variables was calculated by comparing their RMSE and R2 scores. The results show that the precision is different between the different variables. In addition, this paper discusses whether the predictions of the same sailboat are affected by the region and whether they vary significantly across sailboat types within the same region. © 2024 IEEE.

关键词： machine learning multivariate linear regression regional impact

来源：评论

学校读者我要写书评

暂无评论

Effects of the stochastic and deterministic movements in the optimization processes

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GA...

引用

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY 2022年第2期37卷 949-965页

作者： Seyyarer, Ebubekir Karci, Ali Ates, Abdullah Van Yuzuncu Yil Univ Dept Comp Programming TR-65080 Van Turkey Inonu Univ Dept Comp Engn TR-44000 Malatya Turkey

In this study, a linear function representing the iris data set is obtained by making use of the MLR model. SGD, Momentum, Adagrad, RMSProp, Adadelta and Adam optimization algorithms are used to find the optimum values of coefficients of this function. An initialization method with initial population is recommended for these coefficients, which are generally initialized with a fixed or random value in MLRs. IAE, ITAE, MSE and ISE error functions are used as objective functions in the MLR model used. Initial populations of the methods are developed by using a proposed deterministic and classical stochastic initialization methods between upper and lower bounds. The method that are initialized stochasticaly is run several times as seen in literature and the mean values are calculated. On the other hand, the application that is initialized deterministic is only run once. According to the results of deterministic and stochastic initialization methods, it is observed that the coefficients and iteration numbers obtained in both applications are close to each other. Despite very high temporal gain is achieved from the application that is initialized deterministic. As a result of the comparisons, the linear model obtained with Adadelta and MSE reaches the result in the shortest time.

关键词： Deterministic initial population stochastic initial population multivariate linear regression optimization algorithms iris data set

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：