检索结果-内蒙古大学图书馆

MapReduce-based adaptive random forest algorithm for multi-label classification

NEURAL COMPUTING & APPLICATIONS 2019年第12期31卷 8239-8252页

作者： Wu, Qinghua Wang, Haihui Yan, Xuesong Liu, Xiaobo Wuhan Inst Technol Fac Comp Sci & Engn Wuhan 430205 Hubei Peoples R China China Univ Geosci Sch Comp Sci Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Hubei Peoples R China China Univ Geosci Sch Automat Wuhan 430074 Hubei Peoples R China

Due to the complexity of data characteristics, multi-label learning in data mining has been proposed by scholars to solve the problem of information knowledge in the era of big data. In the era of big data, the complexity of the data structures makes it impossible for traditional single-label learning methods to meet the needs of technological development. Moreover, the importance of multi-label learning is gradually becoming evident. The random forest (RF) algorithm is regarded as one of the best classification algorithms. In this study, the traditional decision tree algorithm was improved, and the traditional RF method was converted into an adaptive RF (ARF) method for multi-label classification. By experiments, the effectiveness of the proposed method was verified. The RF method may not be able to classify massive data in a short time, but Hadoop, which was by Apache, is suitable for data-intensive tasks. On this basis, we modified the MapReduce programming mode to make it suitable for the proposed ARF method. This method was implemented on the cloud platform, and the time effectiveness of the parallel model was verified by experiments.

关键词： Multi-label classification random forest algorithm Hadoop MapReduce

来源：评论

学校读者我要写书评

暂无评论

Selection of breast features for young women in northwestern China based on the random forest algorithm

引用

TEXTILE RESEARCH JOURNAL 2022年第7-8期92卷 957-973页

作者： Zhou, Jie Mao, Qian Zhang, Jun Lau, Newman M. L. Chen, Jianming Xian Polytech Univ Sch Apparel & Art Design 19 Jinhua South Rd Xian 710048 Shaanxi Peoples R China Hong Kong Polytech Univ Sch Design Hong Kong Peoples R China Chinese Univ Hong Kong Dept Biomed Engn Hong Kong Peoples R China

In the research of breast morphology, numerous breast features are measured, whereas only a few parameters are adopted for classification. Therefore, how to extract the key variables from the multi-dimensional features in a rational way is an issue that is focused upon. This study aimed to reduce the complexity of the dimensionality reduction for further improving the objectivity and interpretability of the selected breast features. Since the random forest (RF) algorithm can quantify the feature importance during training, the method was adopted to determine the optimal breast features for classification and recognition in this paper. Firstly, the anthropometric data of 360 females from northwestern China aged from 19 to 27 years were measured by non-contact three-dimensional body scanning technology and the contact manual measurement method. Then, the k-means clustering was applied to categorize breast shapes, and the RF algorithm was utilized to quantify and rank the importance of 25 breast features. Finally, to verify the availability of the RF algorithm on breast feature selection, the t-distributed stochastic neighbor embedding method was adopted to visualize the distribution of breast shape clusters into two dimensions. Meanwhile, four neural networks were determined to recognize the breast morphology. The results demonstrate that fewer breast features can effectively increase the accuracy of breast shape classification and recognition. The best performance of breast shape classification and recognition is obtained when the number of breast features is 13. In this case, the average Hamming loss of four neural networks is the smallest (0.1136). Interestingly, the bust circumference and the horizontal curve of breasts across the bust points are found to be the most important of the 25 breast features in this paper. The importance of the breast curve features is higher than that of the breast cross-sectional features, while the breast positioning features have th

关键词： Breast shape classification random forest algorithm feature selection breast shape recognition

来源：评论

学校读者我要写书评

暂无评论

Predicting lncRNA-protein interactions through deep learning framework employing multiple features and random forest algorithm

引用

BMC BIOINFORMATICS 2024年第1期25卷 1页

作者： Liang, Ying Yin, XingRui Zhang, YangSen Guo, You Wang, YingLong Jiangxi Agr Univ Coll Comp & Informat Engn Zhimin Ave Nanchang Peoples R China Gannan Med Univ Affiliated Hosp 1 Med Coll Rd Ganzhou Peoples R China

RNA-protein interaction (RPI) is crucial to the life processes of diverse organisms. Various researchers have identified RPI through long-term and high-cost biological experiments. Although numerous machine learning and deep learning-based methods for predicting RPI currently exist, their robustness and generalizability have significant room for improvement. This study proposes LPI-MFF, an RPI prediction model based on multi-source information fusion, to address these issues. The LPI-MFF employed protein-protein interactions features, sequence features, secondary structure features, and physical and chemical properties as the information sources with the corresponding coding scheme, followed by the random forest algorithm for feature screening. Finally, all information was combined and a classification method based on convolutional neural networks is used. The experimental results of fivefold cross-validation demonstrated that the accuracy of LPI-MFF on RPI1807 and NPInter was 97.60% and 97.67%, respectively. In addition, the accuracy rate on the independent test set RPI1168 was 84.9%, and the accuracy rate on the Mus musculus dataset was 90.91%. Accordingly, LPI-MFF demonstrated greater robustness and generalization than other prevalent RPI prediction methods.

关键词： LncRNA-protein interactions Multiple features random forest algorithm Features fusion

来源：评论

学校读者我要写书评

暂无评论

Visualizing preferential flow paths using dye tracer and species diversity theory methods to explore their correlation to soil properties with random forest algorithm

引用

JOURNAL OF HYDROLOGY 2024年 638卷

作者： Zhang, Yinghu Tang, Zhiying Zhang, Jinchi Zhang, Zhenming Zhang, Mingxiang Nanjing Forestry Univ Coinnovat Ctr Sustainable Forestry Southern China Nanjing 210037 Peoples R China Nanjing Forestry Univ Jiangsu Prov Key Lab Soil Eros & Ecol Restorat Nanjing 210037 Peoples R China Nanjing Forestry Univ Prior Acad Program Dev Jiangsu High Educ Inst PAPD Nanjing 210037 Peoples R China Beijing Forestry Univ Sch Ecol & Nat Conservat Beijing 100083 Peoples R China

The preferential flow path development is potentially the result of spatial variations in soil properties with soil depth. However, visualizing the evolution of the preferential flow path with soil depth remains a challenge. This paper presents dye tracer and species diversity theory methods for characterizing preferential flow paths. Field dye tracer experiments were performed at three sites (tree, bush, and grass) in the Yellow River Delta wetland and dye distribution diversity indices (Simpson index (Ds), Shannon-Wiener index (H), Margalef index (Dm), and Pielou index (E)) were applied to verify their availability for preferential flow assessment. The results showed that the uniformity of the shallow-infiltrated dye at the tree site, non-uniformity of the shallow-infiltrated dye at the bush site, and deep dye infiltration at the grass site were the three typical infiltration types. The average proportion of dye-stained areas (PDA) gradually decreased with increasing soil depth. The quantitative effects of soil properties on PDA changes were profound, indicating that soil clay content at 0-10 cm depth, soil sand content at 10-20 cm depth, soil drainage capacity at 20-30 cm depth, and soil bulk density at 30-40 cm depth were the most predictive factors controlling PDA changes. Our results also showed that dye-stained patches with extremely high and high dye concentrations were the most distributed;Ds, H, Dm, and E were the highest at the tree site and E was the diversity index with the greatest importance for PDA change. The findings reveal the soil properties controlling the formation of preferential flow paths, which will improve our understanding of water resource management in the vadose zones of coastal wetlands.

关键词： Soil property Preferential flow path Diversity index Coastal wetland random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Analyzing the prominence of road accidents on environmental pollution: utilizing machine learning through the random forest algorithm

引用

INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY 2024年 1-16页

作者： Al-Mulali, U. Raboshuk, A. Ali, A. Abusham, E. E. A. Ozturk, I. Sohar Univ Fac Business Sohar Oman Sohar Univ Fac Comp & IT Sohar Oman Univ Sharjah Coll Business Adm Sharjah U Arab Emirates Nisantasi Univ Fac Econ Adm & Social Sci Istanbul Turkiye Univ Econ & Human Sci Warsaw Dept Econ Warsaw Poland

Road accidents are believed to play an important social, economic, development and public health role claiming more than a million lives yearly worldwide. Therefore, this research is dedicated to analyzing the effects of road accidents on environmental pollution. To achieve the aim of this research, 41 countries were examined for the 2000-2020 period. Moreover, to harness the power of machine learning, the random forest algorithm is the cornerstone of model implementation in our study. Moreover, for achieving robustness in the outcome of this research five panel models where established utilizing system GMM as the prime method of analysis. Three indicators of road accidents were utilized, namely, deaths, injuries, and accidents that involve casualties. Furthermore, 5 indicators of pollution were examined, i.e., Carbon dioxide, Carbon monoxide, Greenhouse gas, Nitrogen oxides, and Sulphur oxides. The results clearly revealed the positive correlation of road accidents with all environmental pollution indicators investigated. Furthermore, the results analogously revealed that road accidents indicators are predicted to have a significant positive effect on environmental pollution indicators in the future.

关键词： Road accidents Environmental pollution Machine learning random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Global sensitivity analysis of water level response to harmonic aquifer disturbances through a Monte-Carlo based surrogate model with random forest algorithm

引用

JOURNAL OF HYDROLOGY 2024年 641卷

作者： Xing, Yixuan Liu, Quan Hu, Rui Gu, Hongbiao Taherdangkoo, Reza Ptak, Thomas Univ Gottingen Geosci Ctr D-37075 Gottingen Germany Hohai Univ Sch Earth Sci & Engn Nanjing 211100 Peoples R China Nanjing Tech Univ Coll Transportat Engn Nanjing 211816 Peoples R China TU Bergakademie Freiberg Inst Geotech D-09599 Freiberg Germany

Oscillatory water levels are often observed in monitoring wells, when aquifers are disturbed by periodical pressure diffusion (PD) sources, such as oscillatory pumping and ocean tide, and by volumetric strain (VS) sources including the far-field seismic wave and earth tide. The measured water level responses are extensively utilized to interpret aquifer properties and seismic hydrological phenomena. However, owing to wellbore effects, water levels are not always truly representative of pore pressure in aquifers, and can be significantly attenuated or even unobservable in wells. To clarify how water level responds to these disturbances, this study analyzes a global parameter sensitivity of the coupled well-aquifer model based on the assumption of a confined homogeneous aquifer. Parameter uncertainties concerning aquifer properties, source characteristics, and wellbore construction are first analyzed separately for the PD and VS sources. Subsequently, Monte-Carlo based surrogate models linking parameters and response indices are developed using the random forest algorithm. For the PD source, sensitivity results indicate that hydraulic conductivity is the most influential parameter for the yes/no responses. When hydraulic conductivity exceeds 10-4-4 m/s, water level observations basically represent pore pressure in aquifers. Significant amplitude changes and phase delay occur when the period of disturbances is less than 50 s, majorly due to water column inertia. For VS sources, water level responses are typically observed in aquifers with hydraulic conductivity larger than 10-7-7 m/s and when disturbed by a source with amplitude greater than 10-3-3 MPa. However, pronounced amplitude changes and phase shifts occur when the source period varies within 100 s. Consideration of the impact of wellbore effects is recommended, when interpreting water level responses induced by all periodic aquifer disturbances, especially in low-conductivity aquifers with conductivities less t

关键词： Global sensitivity analysis Water level response Harmonic aquifer disturbance Coupled well-aquifer model Wellbore effects random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Human activity recognition from smart watch sensor data using a hybrid of principal component analysis and random forest algorithm

引用

MEASUREMENT & CONTROL 2019年第1-2期52卷 37-45页

作者： Balli, Serkan Sagbas, Ensar Arif Peker, Musa Mugla Sitki Kocman Univ Fac Technol Dept Informat Syst Engn TR-48000 Mugla Turkey

Background: Detecting of human movements is an important task in various areas such as healthcare, fitness and eldercare. It is now possible to achieve this aim using mobile applications. These applications provide users, doctors and related persons a better understanding about daily physical activities. It can also lead to various useful habits by following the activities of the users in their daily life. In addition, dangerous actions such as the fall of elderly people or young children are identified and necessary precautions are taken as soon as possible. Classification of human motions with motion sensor data is among the current topics of study. Smart watches have these sensors built-in. Thus, it is possible to follow the activities of a user carrying only a smart watch. Methods: The purpose of this work is to detect human movements using smart watch sensor data and machine learning methods. The data are obtained from the accelerometer, gyroscope, step counter and heart rate sensors of the smart watch. The obtained data have been divided into 2 s windows and a data set containing 500 patterns for each class has been created for each class. Results and Discussion: After the features were determined, the data set to which the principal component analysis has been applied was classified by random forest, support vector machine, C4.5 and k-nearest neighbor methods, and their performances were compared. The most successful result was obtained from the random forest method.

关键词： Smart watch classification of human activity principal component analysis random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Mapping the Distribution of Coffee Plantations from Multi-Resolution, Multi-Temporal, and Multi-Sensor Data Using a random forest algorithm

引用

REMOTE SENSING 2020年第23期12卷 3933-3933页

作者： Tridawati, Anggun Wikantika, Ketut Susantoro, Tri Muji Harto, Agung Budi Darmawan, Soni Yayusman, Lissa Fajri Ghazali, Mochamad Firman Inst Teknol Bandung Fac Earth Sci & Technol Remote Sensing & Geog Informat Sci Res Grp Dept Geodesy & Geomat Bandung 40132 Indonesia Inst Teknol Bandung Ctr Remote Sensing Bandung 40132 Indonesia Univ Lampung Fac Engn Dept Geodesy & Geomat Engn Sumantri Brojonegoro 1 Bandar Lampung 35141 Indonesia Minist Energy & Mineral Resources Res & Dev Ctr Oil & Gas Technol LEMIGAS Jakarta 12230 Indonesia Inst Teknol Nas Bandung PHH Mustofa 23 Bandung 40124 Indonesia

Indonesia is the world's fourth largest coffee producer. Coffee plantations cover 1.2 million ha of the country with a production of 500 kg/ha. However, information regarding the distribution of coffee plantations in Indonesia is limited. This study aimed to assess the accuracy of classification model and determine its important variables for mapping coffee plantations. The model obtained 29 variables which derived from the integration of multi-resolution, multi-temporal, and multi-sensor remote sensing data, namely, pan-sharpened GeoEye-1, multi-temporal Sentinel 2, and DEMNAS. Applying a random forest algorithm (tree = 1000, mtry = all variables, minimum node size: 6), this model achieved overall accuracy, kappa statistics, producer accuracy, and user accuracy of 79.333%, 0.774, 92.000%, and 90.790%, respectively. In addition, 12 most important variables achieved overall accuracy, kappa statistics, producer accuracy, and user accuracy 79.333%, 0.774, 91.333%, and 84.570%, respectively. Our results indicate that random forest algorithm is efficient in mapping coffee plantations in an agroforestry system.

关键词： random forest algorithm tree multi-temporal multi-resolution

来源：评论

学校读者我要写书评

暂无评论

A Credit Card Fraud Detection Method Based on Mahalanobis Distance Hybrid Sampling and random forest algorithm

引用

IEEE ACCESS 2024年 12卷 162788-162798页

作者： Xie, Zhichao Huang, Xuan Jiangxi Univ Finance & Econ Sch Software & Internet Things Engn Nanchang 330031 Peoples R China

Currently, the continuous expansion of the credit card business and the increasingly fierce competition have made all kinds of fraud risks in the overall credit card business the biggest threat. How to detect credit card fraud accurately and effectively through machine learning algorithms has become a research hotspot and challenge in this field. This project addresses the problems of existing credit card fraud detection methods and, based on the domain knowledge of credit card fraud and machine learning theory, proposes a method based on Mahalanobis distance SMOTE-ENN hybrid sampling and random forest for credit card fraud detection. First, fraud detection experiments were conducted by selecting credit card fraud datasets published on the Kaggle platform. Then, to further confirm the effectiveness of the method, the method was used for the credit card customer default dataset in Taiwan for further experimental proof. Finally, the experimental results in this paper were compared with the best experimental results in other articles, reflecting that the method based on Mahalanobis distance SMOTE-ENN hybrid sampling and random forest can be more effective for credit card fraud detection compared with other methods. The proposed method demonstrates a strong application potential and practical effect in credit card fraud detection, which not only improves the accuracy and efficiency of fraud detection but also provides a wide range of insights and methodological references for the solution of similar problems.

关键词： Credit cards Fraud Data models Covariance matrices Sampling methods Euclidean distance Correlation Credit card fraud data balancing processing Mahalanobis distance SMOTE-ENN hybrid sampling random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Gray level co-occurrence and random forest algorithm-based gender determination with maxillary tooth plaster images

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2016年 73卷 102-107页

作者： Akkoc, Betul Arslan, Ahmet Kok, Hatice Selcuk Univ Dept Comp Engn Konya Turkey Konya Food & Agr Univ Dept Comp Engn Konya Turkey Necmettin Erbakan Univ Dept Orthodonti Konya Turkey

Gender is one of the intrinsic properties of identity, with performance enhancement reducing the cluster when a search is performed. Teeth have durable and resistant structure, and as such are important sources of identification in disasters (accident, fire, etc.). In this study, gender determination is accomplished by maxillary tooth plaster models of 40 people (20 males and 20 females). The images of tooth plaster models are taken with a lighting mechanism set-up. A gray level co-occurrence matrix of the image with segmentation is formed and classified via a random forest (RF) algorithm by extracting pertinent features of the matrix. Automatic gender determination has a 90% success rate, with an applicable system to determine gender from maxillary tooth plaster images. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Gender determination Feature extraction Image processing 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：