检索结果-内蒙古大学图书馆

Landslide hazard zonation using advanced machine learning algorithms based on statistical models (Case study: Sarvabad, Iran)

引用

EARTH SCIENCE INFORMATICS 2025年第2期18卷 1-19页

作者： Rastkhadiv, Himan Motamedvaziri, Baharak Javadi, Seyed Akbar Ahmadi, Hassan Islamic Azad Univ Dept Nat Engn Sci & Res Branch Tehran Iran Univ Tehran Dept Reclamat Arid & Mt Reg Karaj Iran

Effectively reducing damages and making decisions on land development policies can be achieved identifying areas that are at high risk. Thus, the aim of the current research is to explore the risk of landslides zonation in Sarvabad by use of advanced machine learning algorithms based on statistical models. At the present research, landslide hazard zonation was conducted by use of hybrid algorithms, including Frequency Ratio-random forest (FR-RF), Frequency Ratio-Support Vector Machine (FR-SVM), Weight of Evidence-random forest (WoE-RF), and Weight of Evidence-Support Vector Machine (Woe-SVM). First, the point shape files of 166 landslides in Sarvabad, prepared by the Natural Resource Departmens of Kurdistan State, considered as the inventory of landslides map. The data from the landslide points was split into training sets comprising 70% and validation sets comprising 30%. To achieve to conduct the landslides hazard zone, a sum of 16 items were used that are as follows: slope, aspect, elevation, distance to the stream, distance to the road, river density, distance to the fault, fault density, roadway density, precipitation, land utilization, Normalized Difference Vegetation Index (NDVI), lithology, earthquake, Stream Power Index (SPI), and topographic wetness index (TWI). Finally, the performance of the models was evaluated using the ROC curve. Among the FR-RF, WoE-RF, FR-SVM, and WoE-SVM models, the FR-RF model accounted for the most high performance. In the end, it can be concluded that obtaining an accurate and reasonable spatial prediction map can help managers and urban planners identify zones susceptible to landslide occurrence so that they can manage the potential crises of landslide-prone zones.

关键词： Landslide random forest algorithm Support vector machine algorithm Sarvabad

来源：评论

学校读者我要写书评

暂无评论

Personalized Motion Scheme Generation System Design for Motion Software Based on Cloud Computing

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2025年第2期16卷 1186-1197页

作者： Duan, Jinkai Inner Mongolia Tech Coll Construct Dept Publ Courses Hohhot 010070 Peoples R China

The increase of national attention has also promoted the growth of the scale of sports health industry. However, for ordinary people who lack professional knowledge, intuitive data cannot make correct sports planning. Therefore, aiming at the problem that it is difficult for ordinary people to make correct exercise plan according to intuitive data, a personalized exercise plan generation system based on cloud computing is proposed. By analyzing the user's movement and physical data, the system uses cloud computing resources and machine learning algorithms to provide customized exercise recommendations for users. The key innovation of the research is the combination of improved random forest algorithm and reinforcement learning, while improving the performance of the algorithm on unbalanced sample sets. The results indicated that the accuracy of the improved random forest was 0.985 higher than that of the precision weighted random forest. The research algorithm was 9.04% higher on average than the original random forest algorithm and 2.71% higher than the accuracy weighted random forest algorithm. In terms of the accuracy of personalized motion scheme generation of motion software, the improved algorithm reached 95.05% at most, and its recall rate reached 83.46% at most. Compared with the existing sports software solutions, the research system can generate personalized sports programs more accurately, promote the development of the sports health industry and improve the national physical health level. The system can provide users with personalized sports suggestions, and utilize the powerful computing power of cloud computing to realize real-time processing and analysis of large-scale user data, providing users with timely sports feedback and suggestions.

关键词： Cloud computing sports random forest algorithm personalization system

来源：评论

学校读者我要写书评

暂无评论

A prediction method of purchasing intention of e-commerce consumers in network marketing

引用

International Journal of Business Intelligence and Data Mining 2025年第1-2期26卷 161-173页

作者： Da, Hongyan Department of Applied Foreign Languages Ma An Shan Technical College Maanshan243000 China

In order to improve the accuracy of prediction results, a prediction method of purchasing intention of e-commerce consumers in network marketing is proposed. Firstly, collect consumer related data, standardise and handle outliers to eliminate dimensional differences between data. Secondly, a logistic regression algorithm is used to extract and select consumer features related to purchase intention, revealing consumers’ purchasing preferences. Finally, based on the feature extraction results, a random forest algorithm is used to predict purchase intention. Gini impurity and information gain are used as splitting criteria to construct multiple decision trees, and the prediction results of all decision trees are synthesised by voting or averaging to obtain the final prediction result. The experimental results show that the root mean square error of the proposed method is relatively low, with the highest normalised information value reaching 0.89, indicating that it can accurately reflect consumers’ purchasing intention. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： e-commerce logistic regression algorithm network marketing purchase intention random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Investigation of forest fluvial geomorphological parameters through geospatial and machine learning approach for efficient watershed management

引用

GEOMORPHOLOGY 2025年 471卷

作者： Ponnuchakkammal, P. Raviraj, A. Kumar, D. Suresh Kannan, Balaji Sumathi, C. S. Boomiraj, K. Tamil Nadu Agr Univ Dept Soil & Water Conservat Engn AEC & RI Coimbatore 641003 India Tamil Nadu Agr Univ AEC & RI Coimbatore 641003 India Tamil Nadu Agr Univ Ctr Agr & Rural Dev Studies Coimbatore 641003 India Tamil Nadu Agr Univ Dept Phys Sci & Informat Technol AEC & RI Coimbatore 641003 India Tamil Nadu Agr Univ Dept Environm Sci Coimbatore 641003 India

forest watersheds, as providers of ecosystem services, are becoming increasingly vulnerable due to climate change. Urgent investigation and management of watershed parameters that are prioritized by sub-watersheds are necessary. This study provides a holistic view of the forest watershed by investigating fluvial geomorphological descriptions, land use land cover changes, Sediment parameter for better management of watershed. These factors were significantly influencing the watershed's capacity to store water, runoff, infiltration capacity, peak flow, susceptibility to erosion and landslides, etc. Morphometric analysis, Hypsometric analysis, random forest algorithm, Composite Intensity Mapping Unit, Principal Component Analysis methods were utilized for the computation, extraction of watershed parameters to construct Compound parameter as a basis for watershed ranking. In this case of investigation, The Kundha River Sub-watershed with 160 km2 of catchment area of Upper Bhavani River Basin in Tamil Nadu, South India was investigated. It has 14 sub-watersheds (KSW1-KSW14) with elevation variation about 1618 to 2623 m above Mean Sea Level. The KSW14 & KSW11 are more vulnerable to soil erosion due to high basin relief. The Kundha Sub-watershed is characterized by features such as 47 % of the total area having steep slopes, 50 % of the total area belonging to the Hydrologic Soil Group (HSG) A, an 11 % reduction in the vegetation class over a five-year period, and a very high Sediment Yield Index value. The much- influenced parameters viz., vegetation class, stream frequency, drainage density and Sediment Yield Index were detected and there are strongly recommended for the prioritization of any identical forest watersheds. According to the investigation, the area of 10.09 km2 including KSW11 required instantaneous implementation of catchment area treatment measures to conserve natural resources and to ensure the water security.

关键词： Fluvial Geomorphology Google Earth Engine Kundha Sub-watershed Principal Component Analysis random forest algorithm Sediment Yield Index

来源：评论

学校读者我要写书评

暂无评论

Novel Approach for Generating the Key of Stream Cipher System Using random forest Data Mining algorithm 6

Novel Approach for Generating the Key of Stream Cipher Syste...

引用

Sixth International Conference on Developments in eSystems Engineering (DeSE)

作者： Ali, Samaher Hussein Univ Babylon Fac Informat Technol Dept Informat Network Hilla 00964 Iraq

ISBN: (纸本)9781479952649

Key generator is part of the stream cipher system that is responsible for generating a long random sequence of binary bits key that used in ciphering and deciphering processes. Therefore, key generator is the heart of the stream cipher system. A system with traditional key generating techniques such as using the feedback shift register is vulnerable to cypher attacks which render it to be ineffective and insecure. A suggested novel method to overcome this problem is to use a random forest-Data Mining (RF-DM) algorithm. It incorporates using new types of linear and nonlinear functions to mix the plain text with the key in the encryption process and the cipher text with the reverse key in the decryption process. The method is successful in satisfying the secrecy goal of the stream cipher system because it uses two types of dual randomization to baffle the attacker or cryptanalysist. By mathematical logic and prove by experiments, we generate the key successfully by encrypting messages of different sizes. This proves the ablity to generated the unique key for each message based on its length without repeating the key in most cases. In addition, by combining the use of the random forest data mining technique as the randomizating principle in the ciperhing process makes it exteremely difficult for any attacker because the attacker does not have access or understanding of the not only the technique used but also the process to decipher. The result from our experiment shows that the longer the number of the message size, the longer is the length of the generated key, which determines its strength and hence, its complexity to break by brute force.

关键词： random forest algorithm data mining stream cipher key generator linear and nonlinear functions security attacks cryptanalysis

来源：评论

学校读者我要写书评

暂无评论

An Early Intelligent Detection Method for Well Leakage Based on the Adaptive Fusion of Multi-Drilling Parameter Trends 30th

An Early Intelligent Detection Method for Well Leakage Based...

引用

30th International Conference on Computational and Experimental Engineering and Sciences

作者： Wang, Biao Li, Jun Yang, Hongwei Guo, Boyun Chen, Kangping Zhan, Jiahao Zhang, Geng Long, Zhenyu Chen, Wang China Univ Petr Coll Artificial Intelligence Beijing Peoples R China China Univ Petr Beijing Karamay Xinjiang Peoples R China Univ Louisiana Lafayette Lafayette LA USA Arizona State Univ Tempe AZ USA

ISBN: (纸本)9783031816758;9783031816734;9783031816727

Well leakage accidents occur frequently during drilling operations in ultra-deep oil and gas wells, which may lead to serious safety hazards if not detected promptly. Therefore, early intelligent detection of well leakage is critical to ensure drilling safety. To address the issues of the scarcity of well leakage data samples and the differences in the response patterns of drilling parameters under different drilling conditions, this study proposes an early intelligent detection method for well leakage based on the adaptive fusion of multi-drilling parameter trends. First, an intelligent recognition model for drilling conditions was built using the random forest algorithm (RF). Secondly, by eliminating the influence of drilling conditions on the feature parameters of well leakage and combining the trend values of multi-drilling parameters, an adaptive calculation method for the Leakage Risk Coefficient (LRC) is constructed. Finally, the effectiveness of this method was verified by testing on measured well leakage data. The research results show that the accuracy of the intelligent recognition model for drilling conditions reaches 97.9%, which can be used to optimize well leakage feature parameters. This method is less affected by changes in drilling conditions and parameters, making it applicable throughout the entire drilling process. It can issue an early warning signal for well leakage 16 min earlier than the mud pit gain method, providing valuable time to take appropriate measures.

关键词： Well leakage Early intelligent detection Drilling conditions random forest algorithm Well leakage risk coefficient

来源：评论

学校读者我要写书评

暂无评论

Design of Hybrid Approach for Cloud Resource Allocation Using Genetic algorithms and ML Techniques 8th

Design of Hybrid Approach for Cloud Resource Allocation Usin...

引用

8th International Conference on Microelectronics Electromagnetics and Telecommunications, ICMEET 2023

作者： Talhar, Nitin R. Gaikwad, D.P. AISSMS College of Engineering Maharashtra Pune India Savitribai Phule Pune University Pune India

ISBN: (纸本)9789819784219

This paper introduces a novel approach to optimizing cloud resource allocation using genetic algorithms and machine learning. The goal is to reduce costs while meeting service-level agreement (SLA) requirements. It combines genetic algorithms for real-time optimization and neural networks for predicting future resource needs. Testing on a cloud simulation platform shows it outperforms existing methods in cost-effectiveness and SLA compliance. The hybrid approach combines "NSGA-II and SPEA2" with supervised learning, leveraging their strengths to overcome individual weaknesses. These algorithms enable efficient solution selection, and supervised learning predicts fitness values for new solutions, enhancing optimization speed and accuracy for complex multi-objective challenges. This approach is versatile and can be applied in various cloud computing applications, improving resource allocation efficiency and reducing expenses. It consistently outperforms traditional resource allocation strategies. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cloud computing Fitness function Genetic algorithm Heuristic-based algorithm NSGA-II random forest algorithm Resource allocation SPEA2 Supervised learning Workload prediction

来源：评论

学校读者我要写书评

暂无评论

Risk attitudes and private disability insurance holdings

引用

JOURNAL OF ECONOMICS AND FINANCE 2025年第1期49卷 23-44页

作者： Giannikos, Christos I. Kakolyris, Andreas Suen, Tin Shan CUNY Baruch Coll 55 Lexington Ave New York NY 10010 USA CUNY Grad Ctr 55 Lexington Ave New York NY 10010 USA Kean Univ Coll Business & Publ Management 1000 Morris Ave Union NJ 07083 USA

This study identifies several factors that affect the demand for disability insurance (DI), such as wealth, health, financial literacy, and self-reported willingness to take financial risks, using a logit model and a random forest algorithm. While the role of risk aversion in insurance ownership is well established within theoretical insurance models, the empirical literature is still inconclusive. We provide evidence based on the Survey of Consumer Finances that willingness to take financial risks similar to wealth, health, and financial literacy is positively associated with the ownership of private DI. Furthermore, the literature has not explored multivariate risk attitudes in this framework. We thus employ indices of multivariate risk attitudes within a theoretical DI model. Our empirical results on private DI, in conjunction with the theoretical model we present, allow us to test hypotheses regarding multivariate household preferences and reject the hypothesis of correlation-neutral preferences on wealth and health.

关键词： Disability Insurance Risk Tolerance Financial Literacy Multivariate risk attitudes random forest algorithm Underinsurance Index of Cross-Prudence in Health G22 D14 G52 I1 G53 G41

来源：评论

学校读者我要写书评

暂无评论

Improving Deep Learning Performance Using random forest HTM Cortical Learning algorithm 1

Improving Deep Learning Performance Using Random Forest HTM ...

引用

1st International Workshop on Deep and Representation Learning (IWDRL)

作者： Abbas, Mohamed AbdElhamid Delta Univ Sci & Technol Fac Engn Dept Comp & Commun Gamasa City Egypt

ISBN: (纸本)9781538650837

Deep Learning is an artificial intelligence function that imitates the mechanisms of the human mind in processing records and developing shapes to be used in selection construction. The objective of the paper is to improve the performance of the deep learning using a proposed algorithm called RFHTMC. This proposed algorithm is a merged version from random forest and HTM Cortical Learning algorithm. The methodology for improving the performance of Deep Learning depends on the concept of minimizing the mean absolute percentage error which is an indication of the high performance of the forecastprocedure. In addition to the overlap duty cycle which its high percentage is an indication of the speed of the processing operation of the classifier. The outcomes depict that the proposed set of rules reduces the absolute percent errors by using half of the value. And increase the percentage of the overlap duty cycle with 15%.

关键词： Deep learning random forest algorithm HTM algorithm mean absolute percentage error duty cycle

来源：评论

学校读者我要写书评

暂无评论

Life prediction of battery based on random forest optimized by genetic algorithm

Life prediction of battery based on random forest optimized ...

引用

IEEE International Conference on Prognostics and Health Management (ICPHM)

作者： Li Cailian Zhang Chun Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China

ISBN: (数字)9781728162867

ISBN: (纸本)9781728162867

When the random forest algorithm is used for battery life prediction, the prediction result is unstable, and it is difficult to ensure the accuracy of the model. In view of the above problems, this study proposes to use genetic algorithms to optimize the random forest prediction model. While ensuring the prediction accuracy, the depth and number of decision trees in the random forest are optimized, and the optimal combination of decision tree depth and number is used Life prediction. Using the lithium-ion battery data published by NASA to conduct simulation experiments and evaluate the prediction performance of the model, and then compare with the prediction results of the random forest prediction model and lasso prediction model.

关键词： random forest algorithm lithium-ion battery life prediction genetic algorithm

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：