检索结果-内蒙古大学图书馆

第十届（2018）金融风险与公司金融国际研讨会

作者： Ge Lin Commercial College Xinxiang University

Green credit is a special form of *** it is advocated by the state,it also has a high financial *** the existing financial risk assessment methods are not well ***,the random forest algorithm is applied to the credit risk assessment process,in order to construct a comprehensive evaluation index ***,the model test is carried out in the high pollution *** is found that the new model is not only highly targeted,but also more accurate and efficient.

关键词： random forest algorithm Green-credit risk Heavy pollution industry Green credit policy

来源：评论

学校读者我要写书评

暂无评论

Electronic Health Record (EHR) System Development for Study on EHR Data-based Early Prediction of Diabetes Using Machine Learning algorithms

引用

Open Bioinformatics Journal 2023年 16卷

作者： Jagadamba, G. Shashidhar, R. Gururaj, H.L. Vinayakumar, Ravi Meshari, Almeshari Yasser, Alzamil Department of Information Science and Engineering Siddaganaga Institute of Technology Karnataka Tumakuru 57210 India Department of Electronics and Communication Engineering JSS Science and Technology University Karnataka Mysuru 570006 India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal 576104 India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Diagnostic Radiology College of Applied Medical Sciences University of Ha'il Ha'il Saudi Arabia

Aims: This research work aims to develop an interoperable electronic health record (EHR) system to aid the early detection of diabetes by the use of Machine Learning (ML) algorithms. A decision support system developed using many ML algorithms results in optimizing the decision in preventive care in the health information system. Methods: The proposed system consisted of two models. The first model included interoperable EHR system development using a precise database structure. The second module comprised of data extraction from the EHR system, data cleaning, and data processing and prediction. For testing and training, about 1080 patients’ health record was considered. Among 1080, 1000 records were from the Kaggle dataset, and 80 records were demographic information from patients who visited our health center of Siddaganga organization for a regular checkup or during emergencies. The demographic information was collected from the proposed EHR system. Results: The proposed system was tested for the interoperability nature of the EHR system and accuracy in diabetic disease prediction using the proposed decision support system. The proposed EHR system development was tested for interoperability by random updations from various systems maintained in the laboratory. Each system acted like the admin system of different hospitals. The EHR system was tested for handling the load and interoperability by considering user view status, system matching with the real world, consistency in data updations, security etc. However, in the prediction phase, diabetes prediction was concentrated. The features considered were not randomly chosen;however, the features were those prescribed by a doctor who insisted that the features were sufficient for initial prediction. The reports collected from the doctors revealed several features they considered before giving the test details. The proposed system dataset was split into test and train datasets with eight proper features taken as inpu

关键词： Artificial intelligence Classification Diabetic prediction Electronic health record (EHR) Electronic medical record (EMR) Healthcare Machine learning random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Using online student interactions to predict performance in a first-year computing science course

引用

TECHNOLOGY PEDAGOGY AND EDUCATION 2022年第4期31卷 451-469页

作者： Goundar, Sam Deb, Arpana Lal, Goel Naseem, Mohammed Univ South Pacific Sch Comp & Informat Sci Suva Fiji

Student performance is a critical factor in determining a university's reputation because it has a negative effect on student retention. Students who do not perform well in a course are more likely to drop out from their programmes before graduating. Many students who enrol in Computing Science programmes struggle to find success because it is considered a difficult discipline. In this study, a sample of 918 observations were selected containing demographic and academic information about students enrolled in a first-year undergraduate Computing Science course at a university. Classification algorithms such as Decision Tree, random forest, Naive Bayes and Support Vector Machine were used to build predictive models to determine whether a student will pass or fail the course. The results showed the random forest algorithms are capable of producing better predictive performance compared with traditional Decision Tree algorithms.

关键词： Predictive analytics data mining classification algorithms random forest algorithm decision trees

来源：评论

学校读者我要写书评

暂无评论

Development of machine learning-based reference evapotranspiration model for the semi-arid region of Punjab, India

引用

JOURNAL OF AGRICULTURE AND FOOD RESEARCH 2023年 13卷

作者： Das, Susanta Baweja, Samanpreet Kaur Raheja, Amina Gill, Kulwinder Kaur Sharda, Rakesh PAU Dept Soil & Water Engn Ludhiana 141004 Punjab India Dept Ctr Commun & Int Linkages PAU Ludhiana 141004 Punjab India

Evapotranspiration (ET) is a critical element of the hydrological cycle, and its proper assessment is essential for irrigation scheduling, agricultural and hydro-meteorological studies, and water budget estimation. It is computed for most applications as a product of reference crop evapotranspiration (ET0) and crop coefficient, notably using the well-known two-step method. Accurate predictions of reference evapotranspiration (ET0) using limited meteorological inputs are critical in data-constrained circumstances. Due to the unavailability and heterogeneity of broad parameters of the FAO PM method, it becomes a major constraint for accurately estimating ET0. To overcome the complexity of calculation, the present study was focused on developing a random forest-based (RF) ET0 model to estimate the crop ET for the semi-arid region of northwest India. The RF-based model was developed by focusing on the easily available data at the farm level. For comparative study existing models like Hargreaves-Samani, Modified Penman and modified Hargreaves-Samani were used to estimate the ET0. The models' calibration and validation were done using meteorological data collected from the weather station of Punjab Agricultural University for 21 years (1990-2010) and nine years (2011-2019), respectively, and the FAO PM model was taken as a standard. The mean absolute error (MAE) and root-mean-square error (RMSE) were found to be least as 0.95 mm/d and 1.32 mm/d, respectively for the developed RF model, with an r(2) value of 0.92. The seasonal ET0 estimated by modified Hargreaves-Samani (MHS) and RF were found as 498.3, 482.1 mm in rabi season and 755, 744.8 mm in kharif season respectively, whereas the annual ET0 was 1380.2 and 1355.7 mm respectively. The predicted ET0 values by RF-based model were used for irrigation scheduling of two growing seasons (2020-2021) of maize and wheat crops. The outcome of the field trial also demonstrates that there was no appreciable yield drop in the crop

关键词： Reference evapotranspiration random forest algorithm FAO PM Hargreaves-Samani model Modified Hargreaves-Samani model Irrigation scheduling

来源：评论

学校读者我要写书评

暂无评论

An optimized ensemble model for predicting average localization error of wireless sensor networks

引用

Decision Analytics Journal 2024年 12卷

作者： Nti, Isaac Kofi Rout, Sidharth Sankar Yeboah, Jones School of Information Technology University of Cincinnati 2600 Clifton Ave Cincinnati 45221 OH United States

Wireless sensor networks (WSNs) are widely utilized in various applications due to their compact size, cost-effectiveness, and ease of deployment. Nonetheless, one of the biggest problems in WSNs is getting a reasonable estimate of the average location error of a node at the setup in the least amount of time. Wireless sensor networks can undergo changes over time due to various external and internal factors, such as environmental conditions, network congestion, hardware failures, or software updates. When these changes occur, the network may require redesigning, which can incur significant expenses. Traditional WSNs approaches, on the other hand, have been explicitly programmed, which makes it hard for networks to respond dynamically. Therefore, machine learning (ML) techniques can be used to respond appropriately in such scenarios. In this work, we proposed an optimized ML ensemble model for (i) identifying the critical network parameters for node localization when setting up wireless sensor networks with the accuracy needed in a short amount of time and (ii) predicting the average localization error of wireless sensor networks. We used the random forest algorithm with optimized hyperparameters from different optimization techniques to predict average localization error (ALE) using independent features like node density, anchor ratio, transmission range, and iterations. © 2024 The Author(s)

关键词： Average localization error prediction Machine learning Node localization Optimized hyperparameters random forest algorithm Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Above and belowground woody-biomass and carbon stock estimations at Kunzila watershed, Northwest Ethiopia

引用

TREES forestS AND PEOPLE 2022年 7卷

作者： Shiferaw, Hailu Kassawmar, Tibebu Zeleke, Gete Addis Ababa Univ Water & Land Resource Ctr POB 8707 Addis Ababa Ethiopia

Woody-biomass is an important indicator for good vegetation cover, and a healthy environment that provides ecosystems services such as supplying, provisioning, regulating, esthetic, and cultural values. Moreover, woody-biomass stores a very good amount of carbon dioxide as about fifty percent of living organisms are built from carbon. The objective of this study is to estimate the above and belowground woody biomass and carbon stock of Kunzila watershed, Northwest Ethiopia as a piece of baseline information so as to gage the changes after the intervention. The watershed covers about 11,200 ha of land with undulating topographic landscapes. More than 230 sample plots of 30 m by 30 m were surveyed and every woody plant (shrub/bush and tree) was measured. Allometric equations were applied to calculate biomass and carbon stock potential at the plot level. The random forest algorithm was applied to upscale plot values to watershed level. The results indicate that Kunzila watershed offers maximum biomass of 1,756(+/- 249) Mt year(-1)/watershed and corresponding carbon dioxide equivalent (CO(2)e) of 3,022(+/- 429) Mt C year(-1) /watershed with the current vegetation status;while the average woody biomass and CO(2)e were estimated about 244(+/- 249) Mt ha(-1) year(-1) and 425(+/- 429) Mt C ha(-1) year(-1), respectively. These results indicate that there are high variabilities among different ecosystem types and also the watershed generally offers below its potential. However, there is a high potential to achieve up to triples of biomass and CO(2)e by implementing recommended intervention plans developed out of the current study. The current approach using machine learning algorithm to upscale from sample plot-level to watershed scale is a very good one and can be applied to other watersheds at scale.

关键词： Allometric equation Carbon stock CO(2)e Ethiopia Kunzila watershed random forest algorithm Woody biomass

来源：评论

学校读者我要写书评

暂无评论

Impact of Eucalyptus plantations on ecosystem services in the Upper Blue Nile basin of Ethiopia

引用

ENVIRONMENTAL AND SUSTAINABILITY INDICATORS 2024年 22卷

作者： Yimam, Abdurohman Mekuriaw, Asnake Assefa, Dessie Bewket, Woldeamlak Addis Ababa Univ Dept Geog & Environm Studies Addis Ababa Ethiopia Debre Birhan Univ Dept Geog & Environm Studies Debre Birhan Ethiopia Bahir Dar Univ Dept Nat Resources Management Bahir Dar Ethiopia Univ Nat Resources & Life Sci Inst Forest Ecol Vienna Austria

In the Northern highlands of Ethiopia, Eucalyptus plantations have been widely established since the 1970s. However, there have been debates and concerns about the impact of these plantations on ecosystem services. Therefore, the study aimed to assess the impact of monoculture Eucalyptus plantations on ecosystem service values (ESVs) in the upper Blue Nile part of Ethiopia. We used Landsat satellite images (captured in 1993, 2004, 2014, and 2023) for land use/cover assessment. The images were classified using the random forest (RF) algorithm in the R open-source software. For ecosystem services valuation, we used the benefit transfer method, which allowed us to estimate ESVs by applying both global and local value transfer coefficients. The results show a significant expansion of Eucalyptus plantations, with the highest net change (180%) between 1991 and 2023. The estimated global ESVs ranged from US$206 million in 1991 to US$208 million in 2023, with croplands contributing the largest share (75%). However, specific ESVs related to nutrient cycling, habitat refuge, pollination, and culture declined due to decreasing ESVs of forest land, shrub land, and grazing land over the study period (1991-2023). In addition, ESVs associated with food production declined in the latter period (2014-2023) due to the conversion of croplands into Eucalyptus plantations and shrub lands. This study highlights the need for informed decision-making in land use systems, considering the trade-off between increasing productivity and the loss of other ecosystem functions and services.

关键词： Land use/cover dynamics Benefit transfer Global value transfer coefficient Landsat satellite images random forest algorithm Ecosystem service value

来源：评论

学校读者我要写书评

暂无评论

Evaluating the performance of multi-temporal synthetic-aperture radar imagery in land-cover mapping using a forward stepwise selection approach

引用

REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT 2023年 30卷

作者： Mucsi, Laszlo Bui, Dang Hung Univ Szeged Dept Geoinformat Phys & Environm Geog Egyet str 2 H-6722 Szeged Hungary Ind Univ Ho Chi Minh City Inst Environm Sci Engn & Management Nguyen Bao str 12 Ho Chi Minh City 700000 Vietnam

Radar images are a supplement or alternative to optical images, especially in tropical regions where cloud cover is a challenge. The present study evaluated the performance of using multitemporal synthetic-aperture radar images in land-cover mapping in Binh Duong province, Vietnam. Two experimental cases were investigated: Case 1 used only multi-temporal radar images, whereas Case 2 used a combination of multi-temporal radar images and one optical image. A set of 24 Sentinel-1 images and one Landsat-8 image acquired in 2020 were processed. A forward stepwise selection approach based on a random forest algorithm and a six-class classification scheme were used to determine the best combination of images. In Case 1, the 16-date combination gained the best result with an overall accuracy (OA) of 76.6%. Considering the trade-off between efficiency and cost, the seven-date combination (OA = 76.1%) could be the optimal integration. Compared to using single-date radar images, the OA in Case 1 was improved by 9.5%, and the producer's and user's accuracies were improved by 4.68%-33.33%. Meanwhile, in Case 2, the combination of one optical and seven radar images gave the best result (OA = 83.7%). It had at least 7.1% higher OA than Case 1. However, its OA was at least 2.4% lower, and the producer's and user's accuracies of most classes were reduced when compared to using only a single Landsat8 image. Overall, the findings of this study confirmed the effectiveness of using multi-temporal radar images in land-cover mapping. However, the effectiveness of the combination of radar and optical images needs further elucidation.

关键词： Land-cover mapping Multi-temporal Synthetic-aperture radar imagery random forest algorithm Forward stepwise selection

来源：评论

学校读者我要写书评

暂无评论

A new in-form and role-based Deep Player Performance Index for player evaluation in T20 Cricket

引用

Decision Analytics Journal 2022年 2卷

作者： Deep Prakash, C. Verma, Sanjay Information Systems Department Indian Institute of Management Ahmedabad Vastrapur Ahmedabad 380015 India

Sports analytics has benefited immensely from the growth and popularity of Machine Learning algorithms. Machine Learning and Data Mining advances have enabled sports analysts to evaluate a player's performance more effectively. A review of existing literature on player performance evaluation methods shows the need to develop a new performance evaluation index for Twenty20 (T20) Cricket. We propose a Deep Player Performance Index (DPPI) to evaluate a T20 Cricket player based on batting and bowling strengths. DPPI captures a player's current form and role in the team. DPPI serves a dual purpose. First, it enables sports fans and researchers to compare players playing a similar role in different teams. Second, the aggregated DPPI values of players playing at different positions in a team give the approximate team strength. To build DPPI, we first modify the existing Fédération Internationale de Football Association (FIFA) player performance evaluation guidelines. We then use the modified guidelines in the context of T20 Cricket. We propose DPPI based on K-Means clustering and random forest algorithm and compare our results with the existing player performance evaluation indexes for the Indian Premier League (IPL) 2019 season. Our empirical results show that DPPI captures a player's batting and bowling strength better than other indexes. Thus, DPPI serves as a helpful index for fantasy Cricket users, Cricket fans, coaches, and managers to gain better insights into a player's performance. © 2022 The Author(s)

关键词： Data mining K-Means clustering Machine learning Player performance evaluation random forest algorithm Sports analytics

来源：评论

学校读者我要写书评

暂无评论

Financial support for unmet need for personal assistance with daily activities: Implications from China's long-term care insurance pilots

引用

FINANCE RESEARCH LETTERS 2022年 45卷 1-8页

作者： Kang, Lili Zhao, Guangchuan Inner Mongolia Med Univ Sch Hlth Management Hohhot Peoples R China Nanjing Univ Finance & Econ Sch Publ Adm Nanjing 210023 Peoples R China Nanjing Univ Finance & Econ Jiangsu Inst Social Secur Nanjing 210023 Peoples R China Inner Mongolia Med Univ Sch Hlth Management Jinshan Econ Dev Zone Hohhot Inner Mongolia Peoples R China

This study investigates the association between income and unmet need for personal assistance with daily activities and introduces four policy options for financial support for the unmet need, particularly the public long-term care insurance (LTCI) system. Using the logit model and random forest algorithm, we find that household income is a significant contributing factor to unmet need. Moreover, we find that older adults in the low-income group have a higher level of unmet needs. China's policy experimentation shows that financial support can be provided in the policy arrangements of LTCI financing with low individual contributions and benefits with a high reimbursement rate.

关键词： Financial support Personal assistance Long-term care insurance random forest 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：