检索结果-内蒙古大学图书馆

10th International Conference on Intelligent Computing (ICIC)

作者： Tang, Li Zhao, Zheng Zhang, Lei Zhang, Tao Gao, Shan Nankai Univ Minist Educ Key Lab Bioact Mat Coll Life Sci Tianjin 300071 Peoples R China Tianjin Univ Sch Comp Sci & Technol Tianjin 300072 Peoples R China Tianjin Univ Finance & Econ Informat Sci & Technol Dept Tianjin Peoples R China

ISBN: (纸本)9783319093307;9783319093291

The beta sheet, as one of the three common second form of regular secondary structure in proteins plays an important role in protein function. The best strands in a beta sheet can be classified into the outer or inner strands. Considering the protein primary sequences have determinant information to arrange the strands in the beta sheet topology, we introduce an approach by using the random forest algorithm to predict outer or inner arrangement of a beta strand. We use nine features to describe a strand based on the hydrophobicity, the hydrophilicity, the side-chain mass and other properties of the beta strands. The random forest classifiers reach the best prediction accuracy 89.45% with 10-fold cross-validation among five machine learning methods. This result demonstrates that there are significant differences between the outer beta strands and the inner ones in beta sheets. The finding in this study can be used to arrange beta strands in a beta sheet without any prior structure information. It can also help better understanding the mechanisms of protein beta sheet formation.

关键词： beta sheet beta strand protein secondary structure random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of compressive strength of nano-silica concrete by using random forest algorithm

引用

Asian Journal of Civil Engineering 2024年第7期25卷 5205-5213页

作者： Nigam, Mayank Verma, Manvendra Department of Civil Engineering GLA University Mathura India

The prediction of compressive strength in concrete is an important part of civil engineering because it influences structural design and durability. Recent improvements have brought nano-silica as an addition, improving concrete’s mechanical qualities. This study investigates the use of the random forest (RF) method to estimate the compressive strength of nano-silica concrete, taking advantage of its ability to manage complicated, non-linear interactions among factors. We used a large dataset with varying concentrations of nano-silica and other concrete mix components. Normalisation and feature selection were used as preprocessing techniques to improve the model’s performance. The RF model, which is known for its resilience and accuracy, was trained and verified, displaying better predictive performance than typical linear regression models. The results showed that the RF method could efficiently capture the subtle correlations between nano-silica content and compressive strength, resulting in accurate predictions over a wide range of concrete compositions. This prediction model is a vital tool for civil engineers, allowing for more precise and efficient design of nano-silica concrete mixtures, resulting in stronger and more durable projects. A complete dataset with varying concentrations of nano-silica and other concrete mix components was used. Preprocessing techniques, such as normalisation and feature selection, were used to improve the model's predicted accuracy. The RF model was trained and tested, demonstrating higher performance over established prediction methods like linear regression. The results showed that the RF algorithm could successfully forecast the compressive strength of nano-silica concrete while also capturing the complex interactions between the mix ingredients. This predictive capability is critical for civil engineers since it provides a powerful tool for creating concrete mixtures with improved performance characteristics. To summarise, inc

关键词： Concrete composites Machine learning techniques Mechanical properties Nano-silica concrete random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method of Photovoltaic Array Based on random forest algorithm 39

Fault Diagnosis Method of Photovoltaic Array Based on Random...

引用

39th Chinese Control Conference (CCC)

作者： Gong, Sizhe Wu, Xunhao Zhang, Ziwen Northeastern Univ Coll Informat Sci & Engn Shenyang 110000 Peoples R China

ISBN: (纸本)9789881563903

This paper proposes a fault diagnosis method for photovoltaic array based on random forest algorithm. The random forest algorithm used in this paper is based on classification regression tree (CART). And bootstrap sampling method was used to generate multiple training sets from the original training set, and random attributes were introduced in the training process to generate multiple CART trees. When troubleshooting, the final troubleshooting results are determined by voting according to the diagnosis results of each CART tree. By building a photovoltaic array model in Matlab/Simulink simulation module, use it to summarize the output characteristics of photovoltaic array in the common fault states (partial shading, abnormal component aging, open circuit, short circuit). And considering the main natural factors that affect the output of photovoltaic array, the open circuit voltage, short circuit current, maximum power point voltage, maximum power point current, environmental temperature and light irradiance were selected as the input parameters of the random forest algorithm. Then, a 2X2 small photovoltaic array experiment platform and a field data acquisition system were designed and built to collect data in order to further verify the feasibility of the random forest algorithm. The test results of random forest were compared with those of single CART decision tree, K nearest neighbor (KNN) and support vector machine (SVM) algorithms. The results showed that random forest could complete the fault diagnosis task of photovoltaic array better.

关键词： photovoltaic array fault diagnosis random forest algorithm Matlab/Simulink simulation photovoltaic array experimental platform

来源：评论

学校读者我要写书评

暂无评论

Vehicle Accident Foresight System using Bigdata Intelligent random forest algorithm 10

Vehicle Accident Foresight System using Bigdata Intelligent ...

引用

10th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)

作者： Aburas, Abdurazzag A. Eyono, Scott Naidoo, Omesan Univ KwaZulu Natal Dept Comp Engn Durban South Africa

ISBN: (数字)9781728109749

ISBN: (纸本)9781728109749

commercial vehicles are used to improve people life. One of the main concern is the safety of these commercial vehicle during accidents. This research paper presents the idea of a Vehicle Accident Foresight System (VAFS). Accident datasets for VAFS are based on actual vehicle accident datasets extracted from open-source datasets. VAFS aims to analyze past accident data using the random forest algorithm to predict future accidents. One thousand decision trees are used in implementation. The implemented prototype consists of a dashboard which can specify accident locations according to time, it can also identify the elements which contribute the most to accident severity. The prediction model of VAFS has a minimum accuracy of 69% and a maximum accuracy of 100%.

关键词： Vehicle accident Precognition insurance datasets random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Multilevel random forest algorithm in image recognition for various scientific applications

Multilevel Random forest algorithm in image recognition for ...

引用

73rd IEEE National Aerospace and Electronics Conference (NAECON)

作者： Karmakar, Sayantani Karmakar, Supriya Portland State Univ Portland OR 97207 USA SUNY Farmingdale State Coll Farmingdale NY 11735 USA

ISBN: (纸本)9781665448598

Artificial Intelligence (AI) is a field of research where researchers and scientists are trying to understand our nature and incorporate that understanding in the machine and computer to serve our society. Machine learning (ML) is another aspect of AI. Several algorithms are inverted, modified and updated to characterize the understanding of the nature and implement intelligence artificially within the machine. One major challenge of AI is to understand the object. The first identification of an object is visual information. There are several mechanisms and algorithms to identify an object. Every algorithm has some pros and cons. Among these algorithms, decision tree and random forest algorithm, which is a combination of decision tree algorithms, can play a very effective role. This work shows the application of the multilevel random forest algorithm (MRFA) which is a modified application of the random forest algorithm is introduced for image classification.

关键词： Artificial Intelligence (AI) Image classification Decision tree random forest algorithm Multilevel random forest algorithm (MRFA) Machine Learning (ML)

来源：评论

学校读者我要写书评

暂无评论

Student course grade prediction using the random forest algorithm: Analysis of predictors' importance

引用

TRENDS IN NEUROSCIENCE AND EDUCATION 2023年 33卷 100214页

作者： Nachouki, Mirna Mohamed, Elfadil A. Mehdi, Riyadh Abou Naaj, Mahmoud Ajman Univ Artificial Intelligence Res Ctr AIRC Dept Informat Technol Ajman U Arab Emirates

Background: Universities need to find strategies for improving student retention rates. Predicting student academic performance enables institutions to identify underachievers and take appropriate actions to increase student completion and lower dropout rates. Method: In this work, we proposed a model based on random forest methodology to predict students' course performance using seven input predictors and find their relative importance in determining the course grade. Seven predictors were derived from transcripts and recorded data from 650 undergraduate computing students. Results: Our findings indicate that grade point average and high school score were the two most significant predictors of a course grade. The course category and class attendance percentage have equal importance. Course delivery mode does not have a significant effect. Conclusion: Our findings show that courses students at risk find challenging can be identified, and appropriate actions, procedures, and policies can be taken.

关键词： Course grade prediction Educational data mining Influencing factors random forest algorithm Student performance

来源：评论

学校读者我要写书评

暂无评论

Climate-driven water stress and hydrological drought vulnerability in the dry zone basins in Sri Lanka: insights from climate modelling and random forest algorithm

引用

MODELING EARTH SYSTEMS AND ENVIRONMENT 2024年第6期10卷 6931-6948页

作者： Wijekoon, Tharindi Rajapakse, Lalith Matheswaran, Karthikeyan Univ Moratuwa UNESCO Madanjeet Singh Ctr South Asia Water Management Moratuwa Sri Lanka Int Water Management Inst IWMI Colombo Sri Lanka

Drought, a consequence of prolonged precipitation deficiencies, is a significant hazard exacerbated by climate change. Highly susceptible to extreme climatic events, Sri Lanka faces drought as its most prominent hazard, necessitating comprehensive assessments. This study focuses on the escalating impact of hydrological drought intensified by climate change on the Maduru Oya and Kirindi Oya dry zone basins in Sri Lanka, crucial due to their vulnerability to altered hydroclimatic dynamics. Monitoring hydrological droughts in these regions is paramount for ensuring a reliable water supply for irrigation and other purposes. The research utilizes the Streamflow Drought Index for the monitoring of hydrological droughts. It considers six CMIP6 (Sixth Phase of the Coupled Model Intercomparison Project) Global Climate Models, with the CNRM-HR-1 model chosen as the preferred model. Two future Shared Socio-economic Pathway scenarios, SSP1-2.6 and SSP5-8.5, were selected to project future climatic conditions. The random forest algorithm was utilized to predict future streamflow in the two selected sub-basins. The hydrological drought assessment reveals the heightened vulnerability of the Padiyathalawa sub-basin in the Maduru Oya basin, with a notable rise in moderate hydrological drought occurrences under both future scenarios. Conversely, the Wellawaya sub-basin in the Kirindi Oya basin exhibits susceptibility to frequent moderate hydrological droughts, along with an 80% increase in severe drought occurrences under the SSP5-8.5. Consequently, both basins are projected to face water scarcity in the future. This underscores the importance of implementing measures to ensure a reliable water supply, given the substantial impact of climate change on watershed hydrology.

关键词： Climate change CMIP6 GCM projections random forest algorithm Streamflow prediction Watershed hydrology

来源：评论

学校读者我要写书评

暂无评论

Analysis of Neural Network algorithm in Comparison to Multiple Linear Regression and random forest algorithm

Analysis of Neural Network Algorithm in Comparison to Multip...

引用

2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024

作者： Meghana, Pagolu Annepu, Visalakshi Jweeg, Muhsin Jaber Bagadi, Kalapraveen Aljibori, H.S.S. Mohammed, M.N. Abdullah, Oday I. Aldulaimi, Saeed Alfiras, M. School of Comp. Sci. and Engineering VIT-AP University Amravati India College of Technical Engineering AI-F Farahidi University Baghdad Iraq School of Electronics Engineering VIT-AP University Amravati India Al-Warith Center for Crowd Engineering and Management Research University of Warith AI-Anbiyaa Karbala Iraq Gulf University Mechanical Engineering Department Sanad Bahrain University of Baghdad Dept of Energy Engineering Iraq College of Engineering Gulf University Mechanical Engineering Dept Sanad26489 Bahrain Manama Bahrain College of Engineering Gulf University Electrical and Electronic Engineering Department Sanad26489 Bahrain

ISBN: (纸本)9798350372229

Regression analysis, a stalwart in statistical methodology, offers a robust framework for predicting outcomes based on historical data. It hinges on the premise that by scrutinizing past input data, one can discern the relationships between independent and dependent variables, enabling the forecasting of final results. In the dynamic landscape of Machine Learning, a multitude of regression techniques exists. Nevertheless, many real-world companies grapple with optimizing their return on investment due to the perplexing task of selecting the most apt model for their specific datasets. This research endeavor seeks to bridge this knowledge gap by conducting a comprehensive comparative analysis of three widely used and highly proficient regression algorithms: Multiple Linear Regression (MLR), random forest (RF), and Neural Networks (NNs). MLR offers a simple and interpretable linear model, while RF harnesses ensemble learning to handle complex relationships, and NN s employ intricate, nonlinear modeling capabilities. The study subjects two distinct datasets, Crop Yield, and Cardiovascular Disease, to scrutiny. The former addresses agricultural productivity forecasting, while the latter explores healthcare applications. By evaluating these datasets using the three regression models, the research aims to determine the most suitable model for each dataset's unique characteristics, enabling data-driven decision-making and enhancing the efficacy of regression analysis in practical, real-world scenarios. © 2024 IEEE.

关键词： Data set for prediction Multiple Linear Regression Neural Networks random forest algorithm Regression

来源：评论

学校读者我要写书评

暂无评论

Predicting Incidence Time Series Based on LSTM Recurrent Neural Network and Key Feature Analysis Based on random forest algorithm

Predicting Incidence Time Series Based on LSTM Recurrent Neu...

引用

2024 International Conference on Electronics and Devices, Computational Science, ICEDCS 2024

作者： Du, Jinqi Yang, Yujie Geng, Shuai Liu, Xin Wang, Yafei Shenyang University of Chemical Technology School of Mechanical and Power Engineering Shenyang China

ISBN: (纸本)9798331527624

This paper presents a study on the prediction of the incidence rate time series and the analysis of key features using the LSTM recurrent neural network and the random forest algorithm. Specifically, the study focuses on forecasting the incidence rate for the years 2021-2024 using the ARIMA algorithm and the LSTM recurrent neural network. The ARIMA prediction revealed that the number of diagnosed cases of pulmonary tuberculosis in Liaoning Province reached its lowest point in 2020 over the past decade, showing a 2.4/100,000 decrease in the incidence rate compared to 2019. Furthermore, the LSTM recurrent neural network predicted a continuous decrease in the overall number of cases, indicating a declining trend in the incidence rate. Finally, the random forest algorithm was employed to extract the key features influencing the incidence rate. © 2024 IEEE.

关键词： ARIMA algorithm LSTM recurrent neural network random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Smart Stick Detecting Obstacles Early Using random forest algorithm 4

Smart Stick Detecting Obstacles Early Using Random Forest Al...

引用

4th International Conference of Science and Information Technology in Smart Administration, ICSINTESA 2024

作者： Viet, Thanh Pham Minh, Bac Nguyen Van, Tinh Tran Manh, Hoang Tran Tan, Nghia Duong Huu, Phat Nguyen VNU-HCM High School for the Gifted HoChiMinh Viet Nam School of Electronic and Electrical Engineering Hanoi Viet Nam

ISBN: (纸本)9798350376111

In everyday life, blind people always have to face more difficulty. In modern technology, we can design convenient devices to help them live more easily. This paper focuses on designing a product for them. Specifically, a smart cane will be designed to help blind people avoid objects. To identify and classify objects, we use the random forest algorithm. Our main contribution is to build a detection system and classify obstacles early using cheap sensors and cameras. The results show that the model achieves an accuracy of up to 9 7. 8 7% at a distance of up to 94 cm. The results show that the device is promised feasibility when applied in practice. © 2024 IEEE.

关键词： AI image recognition machine learning random forest algorithm smart stick

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：