检索结果-内蒙古大学图书馆

Friction stir welding tool condition monitoring using vibration signals and Random forest algorithm – A Machine learning approach

引用

Materials Today: Proceedings 2021年 46卷 1174-1180页

作者： K. Balachandar R. Jegadeeshwaran School of Mechanical Engineering Vellore Institute of Technology Chennai Tamil Nadu 600127 India Department of Mechanical Engineering Prathyusha Engineering College Thiruvallur Tamil Nadu 602025 India

Friction stir welding (FSW) is a new kind of solid-state welding technique. Rigid and reliable joints in intricate shapes are possible with FSW. This type of welding process is frequently used in many commercial applications like automobile, shipbuilding, aerospace, and many more. The monitoring of the welding tool condition is essential for the inline process to identify and avoid the early defect of the workpiece and the breakdown due to the increase of the ideal condition of the machinery. Condition monitoring of the FSW tool is an advanced and novel predictive maintenance technique, in which the real-time vibration data are collected from the FSW machine under different operating conditions using an accelerometer sensor. The acquired vibration signals were analyzed using the machine learning approaches through feature extraction and feature classification. This paper aims the vibration analysis based on FSW tool condition monitoring using machine learning algorithms such as decision tree, logistic model tree (LMT), Hoeffeding, and Random forest. Among all classifiers, Random Forest gives better results.

关键词： Friction stir welding logistic model tree Statistical features Random forest Confusion matrix

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Ball Bearing Using Walsh–Hadamard Transform and Random tree Classifier 1st

Fault Diagnosis of Ball Bearing Using Walsh–Hadamard Transf...

引用

1st International and 4th National Conference on Reliability and Safety Engineering, INCRS 2018

作者： Dave, Vipul Vakharia, V. Pandit Deendayal Petroleum University Gandhinagar320007 India

ISBN: (纸本)9789811537455

Bearing failure may result in the breakdown of machinery or possibly damage the human being operating the machinery. It is therefore necessary to diagnose bearing faults at an early stage. This paper presents the application of Walsh–Hadamard transform and tree-based classifier for detecting bearing faults. An experimental was conducted from the Case Western Reserve University bearing data center. At the initial stage, coefficients from inner race fault, outer race fault, ball fault, and healthy bearing were calculated from the measured signal. Twenty-five statistical features are calculated from the acquire signals with different speeds and fault sizes. Feature vector form is used for classification purpose using various classifiers, i.e., random tree and logistic model tree. Training and testing of classifier are done, and the result revealed that 100% fault identification accuracy is obtained with random tree for both training and testing. Similarly, 98.43% training and 100% fault identification accuracy are obtained with logistic model tree. The result shows that the methodology adopted is effective to diagnose various bearing faults. © Springer Nature Singapore Pte Ltd. 2020.

关键词： logistic model tree Random tree Walsh–Hadamard transform

来源：评论

学校读者我要写书评

暂无评论

Polychronicity tendency-based online behavioral signature

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2019年第8期10卷 2103-2118页

作者： Ikuesan, Adeyemi Richard Abd Razak, Shukor Venter, Hein S. Salleh, Mazleena Univ Pretoria Pretoria Gauteng South Africa Univ Teknol Malaysia Dept Comp Sci Johor Baharu Malaysia

The proliferation of ubiquitous and pervasive computing devices has led to the emergence of research areas like Internet of things, and the Big-Data, which has seen a rise in obfuscation of online identity thus fueling an increase in online anonymity. Online anonymity constitutes a major platform for the exploitation of the potentials of cyber-crime;at the same time, it also inhibits the potential economic power that can be harnessed from the surging Internet population. Methods of online identification, such as usage profiling, demographic profiling, cookie-based identification process, media fingerprinting as well as token-based identification processes, are limited to either system identification or one-to-one identification. Current one-to-one identification mechanisms require huge volume of templates of known users, and cannot be applied to novel users. This study proposed a psychosocial approach that integrates the composition of human Polyphasia tendency into online identification processes for a one-to-many identification process. To achieve this, the study administered a Polychronic-Monochronic tendency scale measurement instrument to staff members of a research unit in a university, and the server-side network traffic of each respondent was monitored and collected in eight-months duration. A logistic model tree-after an initial classifier exploration process-was adapted for the one-to-many classification model based on human intrinsic features extracted from the network traffic and Polyphasia dichotomy. High degree of reliable accuracy of > 80% was achieved which suggests a reliable model that supports the underlying hypothesis of the proposed model. Based on this accuracy, the approach finds practical relevance in online profiling process for online identification as well as online demographic profiling for e-commerce and e-learning. Furthermore, this approach can be applied to improve recommender systems in areas such as prediction and profile delivery t

关键词： Polyphasia tendency logistic model tree Digital time preference signature One-to-many identification Intrinsic network feature Online psychosocial fingerprint

来源：评论

学校读者我要写书评

暂无评论

Combining Sequence Entropy and Subgraph Topology for Complex Prediction in Protein Protein Interaction (PPI) Network

引用

CURRENT BIOINFORMATICS 2019年第6期14卷 516-523页

作者： Sikandar, Aisha Anwar, Waqas Sikandar, Misba COMSATS Inst Informat Technol Dept Comp Sci Abbottabad Pakistan COMSATS Inst Informat Technol Dept Comp Sci Lahore Pakistan

Background: Complex prediction from interaction network of proteins has become a challenging task. Most of the computational approaches focus on topological structures of protein complexes and fewer of them consider important biological information contained within amino acid sequences. Objective: To capture the essence of information contained within protein sequences we have computed sequence entropy and length. Proteins interact with each other and form different sub graph topologies. Methods: We integrate biological features with sub graph topological features and model complexes by using a logistic model tree. Results: The experimental results demonstrated that our method out performs other four state-of-art computational methods in terms of the number of detecting known protein complexes correctly. Conclusion: In addition, our framework provides insights into future biological study and might be helpful in predicting other types of sub graph topologies.

关键词： Protein Protein Interaction (PPI) sequence entropy sub graph topology biological features logistic model tree cluster

来源：评论

学校读者我要写书评

暂无评论

Optimization of Computational Intelligence models for Landslide Susceptibility Evaluation

引用

REMOTE SENSING 2020年第14期12卷 2180-2180页

作者： Zhao, Xia Chen, Wei Xian Univ Sci & Technol Coll Geol & Environm Xian 710054 Peoples R China Minist Nat Resources Key Lab Coal Resources Explorat & Comprehens Util Xian 710021 Peoples R China

This paper focuses on landslide susceptibility prediction in Nanchuan, a high-risk landslide disaster area. The evidential belief function (EBF)-based function tree (FT), logistic regression (LR), and logistic model tree (LMT) were applied to Nanchuan District, China. Firstly, an inventory with 298 landslides was compiled and separated into two parts (70%: 209;30%: 89) as training and validation datasets. Then, based on the EBF method, theBelvalues of 16 conditioning factors related to landslide occurrence were calculated, and theseBelvalues were used as input data for building other models. The receiver operating characteristic (ROC) curve and the values of the area under the ROC curve (AUC) were used to evaluate and compare the prediction ability of the four models. All the models achieved good results and performed well. In particular, the LMT model had the best performance (0.847 and 0.765, obtained from the training and validation datasets, respectively). This paper also demonstrates the superiority of integration and optimization of models in landslide susceptibility evaluation. Finally, the best classification method was selected to draw landslide susceptibility maps, which may be helpful for government administrators and engineers to carry out land design and planning.

关键词： evidential belief function function tree logistic regression logistic model tree Nanchuan District

来源：评论

学校读者我要写书评

暂无评论

Predicting circRNA-disease associations using deep generative adversarial network based on multi-source fusion information

Predicting circRNA-disease associations using deep generativ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Wang, Lei You, Zhu-Hong Li, Li-Ping Zheng, Kai Wang, Yan-Bin Chinese Acad Sci Xinjiang Tech Inst Phys & Chem Urumqi 830011 Peoples R China China Univ Min & Technol Sch Comp Sci & Technol Xuzhou Jiangsu Peoples R China

ISBN: (纸本)9781728118673

Circular RNA (circRNA) is a kind of novel discovered non-coding RNA molecule with a closed loop structure, which plays a critical regulatory role in human diseases. Identifying the association between circRNAs and diseases has important potential value for the diagnosis and treatment of complex human diseases. Although biological experiments can more accurately identify the association between circRNAs and diseases, they are usually blind and limited by small scale and high cost. Therefore, there is an urgent need for efficient and feasible computational methods to predict the potential circRNA-disease associations on a large scale, so as to provide the most promising candidate for biological experiments. In this paper, we propose a novel computational method based on the deep Generative Adversarial Network (GAN) algorithm combined with the multi-source similarity information to predict the circRNA-disease associations. Firstly, we fuse the multi-source information of disease semantic similarity, disease and circRNA Gaussian interaction profile kernel similarity, and then use GAN to extract the hidden features of fusion information objectively and effectively in the way of confrontation learning, and finally send them to logistic model tree (LMT) classifier for accurate prediction. The 5-fold cross-validation experiment of the proposed model achieved 89.2% accuracy with 89.4% precision at the AUC of 90.6% on the CIRCR2Disease dataset. Compared with the state-of-the-art SVM classifier and other feature extraction methods, the proposed model shows strong competitiveness. In addition, the predicted results of this model are supported by the biological experiments, and 9 of the top 15 circRNA-disease associations with the highest scores were confirmed by recently published literature. These promising results indicate that the proposed model is an effective tool for predicting circRNA- disease associations and can provide reliable candidates for biological experiments.

关键词： Circular RNA Complex diseases CircRNA-disease association prediction Machine learning Generative adversarial network logistic model tree Biological networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Android Malware 5th

A Comparative Analysis of Android Malware

引用

5th International Conference on Information Systems Security and Privacy (ICISSP)

作者： Chavan, Neeraj Di Troia, Fabio Stamp, Mark San Jose State Univ Dept Comp Sci San Jose CA 95192 USA

ISBN: (纸本)9789897583599

In this paper, we present a comparative analysis of benign and malicious Android applications, based on static features. In particular, we focus our attention on the permissions requested by an application. We consider both binary classification of malware versus benign, as well as the multiclass problem, where we classify malware samples into their respective families. Our experiments are based on substantial malware datasets and we employ a wide variety of machine learning techniques, including decision trees and random forests, support vector machines, logistic model trees, AdaBoost, and artificial neural networks. We find that permissions are a strong feature and that by careful feature engineering, we can significantly reduce the number of features needed for highly accurate detection and classification.

关键词： Malware Android Machine Learning Random Forest logistic model tree Artificial Neural Network

来源：评论

学校读者我要写书评

暂无评论

Groundwater spring potential modelling: Comprising the capability and robustness of three different modeling approaches

引用

JOURNAL OF HYDROLOGY 2018年 565卷 248-261页

作者： Rahmati, Omid Naghibi, Seyed Amir Shahabi, Himan Dieu Tien Bui Pradhan, Biswajeet Azareh, Ali Rafiei-Sardooi, Elham Samani, Aliakbar Nazari Melesse, Assefa M. Islamic Azad Univ Khorramabad Branch Young Researchers & Elites Club Khorramabad Iran Tarbiat Modares Univ Dept Watershed Management Engn Mazandaran Iran Univ Kurdistan Fac Nat Resources Dept Geomorphol Sanandaj Iran Univ Coll Southeastern Norway Dept Business & IT Geog Informat Syst Grp Gullbringvegen 36 N-3800 Bo I Telemark Norway Univ Technol Sydney Fac Engn & IT Ctr Adv Modeling & Geospatial Syst CAMGIS Sydney NSW 2007 Australia Sejong Univ Dept Energy & Mineral Resources Engn 209 Neungdong Ro Seoul 05006 South Korea Univ Jiroft Dept Geog Kerman Iran Univ Jiroft Fac Nat Resources Kerman Iran Univ Tehran Fac Nat Resources Dept Reclamat Arid & Mountainous Reg Karaj Iran Florida Int Univ Dept Earth & Environm AHC 5-390 Miami FL 33199 USA

Sustainable water resources management in arid and semi-arid areas needs robust models, which allow accurate and reliable predictive modeling. This issue has motivated the researchers to develop hybrid models that offer solutions on modelling problems and accurate predictions of groundwater potential zonation. For this purpose, this research aims to investigate the capability and robustness of a novel hybrid model, namely the logistic model tree (LMT) and compares it with state-of-the-art models such as the support vector machine and C4.5 models that locate potential zones for groundwater springs. A spring location dataset consisting of 359 springs was provided by field surveys and national reports and from which three different sample data sets (S1-S3) were randomly prepared (70% for training and 30% for validation). Additionally, 16 spring-related factors were analyzed using regression logistic analysis to find which factors play a significant role in spring occurrence. Twelve significant geo-environmental and morphometric factors were identified and applied in all models. The accuracy of models was evaluated by three different threshold-dependent and -Independent methods including efficiency (E), true skill statistic (TSS), and area under the receiver operating characteristics curve (AUC-ROC) methods. Results showed that the LMT model had the highest accuracy performance for all three validation datasets (E-mean = 0.860, TSSmean = 0.718, AUC-ROCmean = 0.904);although a slight sensitivity to change in input data was sometimes observed for this model. Furthermore, the findings showed that relative slope position (RSP) was the most important factor followed by distance from faults and lithology.

关键词： Hybrid model Groundwater spring Robustness GIS logistic model tree

来源：评论

学校读者我要写书评

暂无评论

A comparison study of DRASTIC methods with various objective methods for groundwater vulnerability assessment

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2018年 642卷 1032-1049页

作者： Khosravi, Khabat Sartaj, Majid Tsai, Frank T-C Singh, Vijay P. Kazakis, Nerantzis Melesse, Assefa M. Prakash, Indra Bui, Dieu Tien Binh Thai Pham Sari Agr Sci & Nat Resources Univ Fac Nat Resources Sari Iran Univ Ottawa Civil Engn Dept Ottawa ON K1N 6N5 Canada Louisiana State Univ Dept Civil & Environm Engn Baton Rouge LA 70803 USA Texas A&M Univ Dept Biol & Agr Engn College Stn TX 77843 USA Texas A&M Univ Zachry Dept Civil Engn College Stn TX 77843 USA Aristotle Univ Thessaloniki Sch Geol Thessaloniki Greece Florida Int Univ Dept Earth & Environm AHC 5-390 Miami FL USA Bhaskarchalya Inst Space Applicat & Geoinformat B Dept Sci & Technol Gandhinagar India Univ South Eastern Norway Dept Business & IT Geog Informat Syst Grp Gullbringvegen 36 N-3800 Bo I Telemark Norway Ton Duc Thang Univ Geog Informat Sci Res Grp Ho Chi Minh City Vietnam Ton Duc Thang Univ Fac Environm & Labour Safety Ho Chi Minh City Vietnam

Groundwater vulnerability assessment is a measure of potential groundwater contamination for areas of interest. The main objective of this study is to modify original DRASTIC model using four objective methods, Weights-of-Evidence (WOE), Shannon Entropy (SE), logistic model tree (LMT), and Bootstrap Aggregating (BA) to create a map of groundwater vulnerability for the Sari-Behshahr plain, Iran. The study also investigated impact of addition of eight additional factors (distance to fault, fault density, distance to river, river density, land-use, soil order, geological time scale, and altitude) to improve groundwater vulnerability assessment. A total of 109 nitrate concentration data points were used for modeling and validation purposes. The efficacy of the four methods was evaluated quantitatively using the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC). AUC value for original DRASTIC model without any modification of weights and rates was 0.50. Modification of weights and rates resulted in better performance with AUC values of 0.64, 0.65, 0.75, and 0.81 for BA, SE, LMT, and WOE methods, respectively. This indicates that performance of WOE is the best in assessing groundwater vulnerability for DRASTIC model with 7 factors. The results also show more improvement in predictability of the WOE model by introducing 8 additional factors to the DRASTIC as ADC value increased to 0.91. The most effective contributing factor for ground water vulnerability in the study area is the net recharge. The least effective factors are the impact of vadose zone and hydraulic conductivity. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Groundwater vulnerability DRASTIC Weights-of-Evidence Shannon Entropy logistic model tree Bootstrap Aggregating

来源：评论

学校读者我要写书评

暂无评论

Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2018年 626卷 1121-1135页

作者： Chen, Wei Peng, Jianbing Hong, Haoyuan Shahabi, Himan Pradhan, Biswajeet Liu, Junzhi Zhu, A-Xing Pei, Xiangjun Duan, Zhao Xian Univ Sci & Technol Coll Geol & Environm Xian 710054 Shaanxi Peoples R China Changan Univ Dept Geol Engn Xian 710054 Shaanxi Peoples R China Nanjing Normal Univ Key Lab Virtual Geog Environm Nanjing 210023 Jiangsu Peoples R China State Key Lab Cultivat Base Geog Environm Evolut Nanjing 210023 Jiangsu Peoples R China Jiangsu Ctr Collaborat Innovat Geog Informat Reso Nanjing 210023 Jiangsu Peoples R China Univ Kurdistan Fac Nat Resources Dept Geomorphol Sanandaj Iran Univ Technol Sydney Sch Syst Management & Leadership Fac Engn & IT CB11-06-217Bldg 1181 BroadwayPOB 123 Ultimo NSW 2007 Australia Sejong Univ Dept Energy & Mineral Resources Engn 209 Neungdong Ro Seoul 05006 South Korea Chengdu Univ Technol State Key Lab Geohazard Prevent & Geoenvironm Pro Chengdu 610059 Sichuan Peoples R China

The preparation of a landslide susceptibility map is considered to be the first step for landslide hazard mitigation and risk assessment. However, these maps are accepted as end products that can be used for land use planning. The main goal of this study is to assess and compare four advanced machine learning techniques, namely the Bayes' net (BN), radical basis function (RBF) classifier, logisticmodel tree (LMT), and randomforest (RF) models, for landslide susceptibility modelling in Chongren County, China. A total of 222 landslide locations were identified in the study area using historical reports, interpretation of aerial photographs, and extensive field surveys. The landslide inventory data was randomly split into two groups with a ratio of 70/30 for training and validation purposes. Fifteen landslide conditioning factors were prepared for landslide susceptibility modelling. The spatial correlation between landslides and conditioning factors was analyzed using the information gain (IG) method. The BN, RBF classifier, LMT, and RF models were constructed using the training dataset. Finally, the receiver operating characteristic (ROC) and statistical measures, including sensitivity, specificity, and accuracy, were employed to validate and compare the predictive capabilities of the models. Out of the tested models, the RF model had the highest sensitivity, specificity, and accuracy values of 0.787, 0.716, and 0.752, respectively, for the training dataset. Overall, the RF model produced an optimized balance for the training and validation datasets in terms of AUC values and statistical measures. The results of this study also demonstrate the benefit of selecting optimal machine learning techniques with proper conditioning selection methods for landslide susceptibility modelling. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Landslide susceptibility Bayes' net Radical basis function classifier logistic model tree Random forest China

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：