检索结果-内蒙古大学图书馆

Influence of Data Balancing on Transformer DGA Fault Classification With machine learning algorithms

IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION 2023年第1期30卷 385-392页

作者： Rajesh, Kandala N. V. P. S. Rao, U. Mohan Fofana, I. Rozga, P. Paramane, Ashish VIT AP Univ Sch Elect Engn Amaravati 522237 India Univ Quebec Chicoutimi Res Chair Aging Power Network Infrastructure ViAHT Dept Appl Sci Saguenay PQ G7H 2B1 Canada Lodz Univ Technol Inst Elect Power Engn PL-90537 Lodz Poland Lodz Univ Technol Inst Elect Power Engn PL-90537 Lodz Poland NIT Silchar Dept Elect Engn Silchar 788010 Assam India

The application of artificial intelligence algorithms for transformer incipient fault classification using dissolved gas analysis (DGA) is an interesting engineering approach. However, there are various factors that affect the performance of artificial intelligence algorithms. This article presents the influence of the data balancing approach on transformer DGA fault classification with the machine learning (ML) approach. In this work, a total of 4580 DGA samples from in-service transformers are considered for training various ML models. The main challenge for the DGA problem lies in the availability of the normal degradation transformer data and its uniformity corresponding to different faults is almost impossible. This is because DGA is not an exact science, but an empirical approach subjects to variability. Thus, it is a usual practice to apply data sampling techniques that largely influence the efficiency of the algorithms. The present work reports the impact of the data balancing schemes on the performance of the fault classification and demonstrates that a careful choice of the data sampling method and ML algorithm is essential for DGA problems. To demonstrate the global scale ability of the propose model, the model is tested on the IEC TC ten data (field inspection data), while these data are not exposed to the machine during the learning stage. The ability of the ADASYN method in significant enhancement of the global scale capability of AI-based transformer DGA fault classification is reported. This approach will be helpful for condition monitoring engineers in transformer insulation diagnosis in implementing the monitoring modules for large transformer fleets and understanding the insulation oil behavior over years.

关键词： Power transformer insulation Oil insulation Classification algorithms Training Data models Testing machine learning algorithms Dissolved gas analysis (DGA) fault diagnosis insulation liquids transformers

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis of machine learning algorithms for Crime Prediction Using Stacked Generalization: An Ensemble Approach

引用

IEEE ACCESS 2021年 9卷 67488-67500页

作者： Kshatri, Sapna Singh Singh, Deepak Narain, Bhavana Bhatia, Surbhi Quasim, Mohammad Tabrez Sinha, G. R. MATS Univ Dept Comp Sci & Applicat Raipur 492001 Madhya Pradesh India Bennett Univ Dept Comp Sci & Engn Noida 201310 India King Faisal Univ Dept Informat Syst Coll Comp Sci & Informat Technol Al Hasa 36362 Saudi Arabia Univ Bisha Coll Comp & Informat Technol Bisha 67714 Saudi Arabia Myanmar Inst Informat Technol MIIT Dept Elect & Commun Engn Mandalay 05053 Myanmar

Ensemble learning method is a collaborative decision-making mechanism that implements to aggregate the predictions of learned classifiers in order to produce new instances. Early analysis has shown that the ensemble classifiers are more reliable than any single part classifier, both empirically and logically. While several ensemble methods are presented, it is still not an easy task to find an appropriate configuration for a particular dataset. Several prediction-based theories have been proposed to handle machine learning crime prediction problem in India. It becomes a challenging problem to identify the dynamic nature of crimes. Crime prediction is an attempt to reduce crime rate and deter criminal activities. This work proposes an efficient authentic method called assemble-stacking based crime prediction method (SBCPM) based on SVM algorithms for identifying the appropriate predictions of crime by implementing learning-based methods, using MATLAB. The SVM algorithm is applied to achieve domain-specific configurations compared with another machine learning model J48, SMO Naive byes bagging and, the Random Forest. The result implies that a model of a performer does not generally work well. In certain cases, the ensemble model outperforms the others with the highest coefficient of correlation, which has the lowest average and absolute errors. The proposed method achieved 99.5% classification accuracy on the testing data. The model is found to produce more predictive effect than the previous researches taken as baselines, focusing solely on crime dataset based on violence. The results also proved that any empirical data on crime, is compatible with criminological theories. The proposed approach also found to be useful for predicting possible crime predictions. And suggest that the prediction accuracy of the stacking ensemble model is higher than that of the individual classifier.

关键词： Predictive models Data models machine learning Prediction algorithms machine learning algorithms Artificial neural networks Support vector machines Boosting classifier ensemble classifiers Indian crime prediction machine learning statistical classifiers stacking

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of Network-Based Attacks by Hybrid machine learning algorithms Utilizing Bayesian Optimization, Logistic Regression, and Random Forest Algorithm

引用

IEEE ACCESS 2024年 12卷 142721-142732页

作者： Sannigrahi, Manisankar Thandeeswaran, R. Vellore Inst Technol Sch Comp Sci Engn & Informat Syst Vellore 632014 Tamil Nadu India

These days, intrusion detection systems are one of the newest trends in society. These technologies serve as a defense against a variety of security breaches, the number of which has been rising recently. The need for adaptive security solutions is pressing since the sorts of attacks that arise are ever-changing. This study aims to enhance the performance of intrusion detection models on the KDD99 and NSL-KDD datasets through advanced optimization techniques. By addressing challenges related to evolving attack strategies and intricate tasks, the research introduces innovative machine learning approaches tailored for intrusion detection, focusing on both binary and multiclass classification scenarios. The study employs a Bayesian Optimization-enhanced Random Forest (BO_RF) algorithm for binary classification and a hybrid Logistic Regression and Random Forest (LR_RF) algorithm for multiclass classification. Our models were implemented and evaluated in a Jupyter Notebook environment using key metrics: Accuracy, Precision, Recall, and F1-Score. For binary classification, eight metrics were assessed, while twenty-six were analyzed for multiclass classification across both datasets. The results demonstrate the effectiveness of the proposed approaches in both classification types, highlighting their potential for robust and adaptable intrusion detection. Theoretical contributions include advancing the understanding of intrusion detection methodologies and the effectiveness of machine learning algorithms in cybersecurity. From a practical perspective, the proposed model can offers a robust and adaptable solution for real-world intrusion detection scenarios, potentially minimizing security breaches and enhancing overall cyber security posture.

关键词： Classification algorithms machine learning algorithms Intrusion detection Bayes methods Support vector machines Random forests NSL-KDD machine learning (ML) network attacks classification intrusion detection system (IDS)

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of Undegraded and Aged Polyethylene Terephthalate Microplastics from ATR-FTIR Spectroscopy using machine learning algorithms

引用

JOURNAL OF POLYMERS AND THE ENVIRONMENT 2024年第9期32卷 4143-4158页

作者： Enyoh, Christian Ebere Wang, Qingyue Saitama Univ Grad Sch Sci & Engn 255 Shimo OkuboSakura Ku Saitama City Saitama 3388570 Japan

Automated analysis of microplastics is essential due to the labor-intensive, time-consuming, and error-prone nature of manual methods. Attenuated Total Reflectance Fourier Transform Infrared (ATR-FTIR) spectroscopy offers valuable molecular information about microplastic composition. However, efficient data analysis tools are required to effectively differentiate between various types of microplastics due to the large volume of spectral data generated by ATR-FTIR. In this study, we propose a machine learning (ML) approach utilizing ATR-FTIR spectroscopy data for accurate and efficient classification of undegraded and aged polyethylene terephthalate (PET) microplastics (MPs). We evaluate seven ML algorithms, including Random Forest (RF), Gradient Boosting (GB), Decision Tree (DT), k-Nearest Neighbors (k-NN), Logistic Regression (LR), Support Vector machine (SVM), and Multi-Layer Perceptron (MLP), to assess their performance. The models were optimized using fivefold cross-validation and evaluated using multiple metrics such as confusion matrix, accuracy, precision, recall (sensitivity), and F1-score. The experimental results demonstrate exceptional performance by RF, GB, DT, and k-NN models, achieving an accuracy of 99% in correctly classifying undegraded and aged PET MPs. The proposed approach capitalizes on the potential of ATR-FTIR spectra to discern distinct chemical signatures of undegraded and aged PET particles, enabling precise and reliable classification. Furthermore, the method offers the benefit of automating the classification process, streamlining the analysis of environmental samples. It also presents the advantage of providing an effective means for method standardization, facilitating more automated and optimized extraction of information from spectral data. The method's versatility and potential for large-scale application make it a valuable contribution to the field of MP environmental research.

关键词： Automated classification PET microplastics ATR-FTIR spectroscopy machine learning algorithms Environmental analysis Method standardization

来源：评论

学校读者我要写书评

暂无评论

A survey of big data architectures and machine learning algorithms in healthcare

引用

INTERNATIONAL JOURNAL OF BIOMEDICAL ENGINEERING AND TECHNOLOGY 2017年第2-4期25卷 182-211页

作者： Manogaran, Gunasekaran Lopez, Daphne Vellore Inst Technol Univ Sch Informat Technol & Engn Vellore Tamil Nadu India

Big Data has gained much attention from researchers in healthcare, bioinformatics, and information sciences. As a result, data production at this stage will be 44 times greater than that in 2009. Hence, the volume, velocity, and variety of data rapidly increase. Hence, it is difficult to store, process and visualise this huge data using traditional technologies. Many organisations such as Twitter, LinkedIn, and Facebook are used big data for different use cases in the social networking domain. Also, implementations of such architectures of the use cases have been published worldwide. However, a conceptual architecture for specific big data application has been limited. The intention of this paper is application-oriented architecture for big data systems, which is based on a study of published big data architectures for specific use cases. This paper also provides an overview of the state-of-the-art machine learning algorithms for processing big data in healthcare and other applications.

关键词： big data big data architectures machine learning algorithms healthcare big data applications big data opportunities and challenges

来源：评论

学校读者我要写书评

暂无评论

Automated lithological mapping by integrating spectral enhancement techniques and machine learning algorithms using AVIRIS-NG hyperspectral data in Gold-bearing granite-greenstone rocks in Hutti, India

引用

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 2020年 86卷

作者： Kumar, Chandan Chatterjee, Snehamoy Oommen, Thomas Guha, Arindam Michigan Technol Univ Geol & Min Engn & Sci 1400 Townsend Dr Houghton MI 49931 USA Indian Space Res Org Natl Remote Sensing Ctr Hyderabad India

In this study, we proposed an automated lithological mapping approach by using spectral enhancement techniques and machine learning algorithms (MLAs) using Airborne Visible Infrared Imaging Spectroradiometer-Next Generation (AVIRIS-NG) hyperspectral data in the greenstone belt of the Hutti area, India. We integrated spectral enhancement techniques such as Principal Component Analysis (PCA) and Independent Component Analysis (ICA) transformation and different MLAs for an accurate mapping of rock types. A conjugate utilization of conventional geological map and spectral enhancement products derived from ASTER data were used for the preparation of a high-resolution reference lithology map. Feature selection and extraction methods were applied on the AVIRIS-NG data to derive different input dataset such as (a) all spectral bands, (b) shortwave infrared bands, (c) Joint Mutual Information Maximization (JMIM) based optimum bands, and (d) optimum bands using PCA, to choose optimum input dataset for automated lithological mapping. The comparative analysis of different MLAs shows that the Support Vector machine (SVM) outperforms other machine learning (ML) models. The SVM achieved an Overall Accuracy (OA) and Kappa Coefficient (k) of 85.48% and 0.83, respectively, using JMIM based optimum bands. The JMIM based optimum bands were more suitable than other input datasets to classify most of the lithological units (i.e. metabasalt, amphibolite, granite, acidic intrusive and migmatite) within the study area. The sensitivity analysis performed in this study illustrates that the SVM is less sensitive to the number of samples and mislabeling in the model training than other MLAs. The obtained high-resolution classified map with accurate litho-contacts of amphibolite, metabasalt, and granite can be coupled with an alteration map of the area for targeting the potential zone of gold mineralization.

关键词： AVIRIS-NG Hyperspectral Lithological mapping machine learning algorithms SVM

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of 500kW solar PV plant based on machine learning algorithms

引用

SMART SCIENCE 2024年

作者： Balachandran, Karthikeyan Ramasamy, Karthigaivel Vairamani, Rajasekaran Sethu Inst Technol Dept Elect & Elect Engn Virudunagar India PSNA Coll Engn & Technol Dept Elect & Elect Engn Dindigul 624622 India

This research presents a comprehensive performance analysis of a 500 kW solar photovoltaic (PV) plant, utilizing machine learning (ML) algorithms, installed at PSNA College of Engineering and Technology, Dindigul, India. Real-time experimental data, collected from November 2021 to October 2022, was used to enhance the operational efficiency of the solar PV system. The study focuses on forecasting the output of the 500 kW plant by employing six machine learning algorithms, with a comparative analysis conducted to evaluate the predictive capabilities of each model. Kernel Ridge Regression (KRR) demonstrated superior performance among the algorithms tested, producing results closely aligned with the actual data. Key performance metrics were assessed, including forecasted output power, final yield, system efficiency, performance ratio, and capacity factor. Notably, the system's efficiency increased from 12% to 13.6%.These findings provide critical insights for optimizing the operational performance of solar PV plants, offering valuable contributions to improving energy management and sustainability.

关键词： machine learning algorithms forecasting solar PV plant kernel ridge regression

来源：评论

学校读者我要写书评

暂无评论

Combined metabolomics and machine learning algorithms to explore metabolic biomarkers for diagnosis of acute myocardial ischemia

引用

INTERNATIONAL JOURNAL OF LEGAL MEDICINE 2023年第1期137卷 169-180页

作者： Cao, Jie Li, Jian Gu, Zhen Niu, Jia-jia An, Guo-shuai Jin, Qian-qian Wang, Ying-yuan Huang, Ping Sun, Jun-hong Acad Forens Sci Shanghai Key Lab Forens Med Shanghai 200063 Peoples R China Shanxi Med Univ Sch Forens Med 98 Univ St Jinzhong 030604 Shanxi Peoples R China

Acute myocardial ischemia (AMI) remains the leading cause of death worldwide, and the post-mortem diagnosis of AMI represents a current challenge for both clinical and forensic pathologists. In the present study, the untargeted metabolomics based on ultra-performance liquid chromatography combined with high-resolution mass spectrometry was applied to analyze serum metabolic signatures from AMI in a rat model (n = 10 per group). A total of 28 endogenous metabolites in serum were significantly altered in AMI group relative to control and sham groups. A set of machine learning algorithms, namely gradient tree boosting (GTB), support vector machine (SVM), random forest (RF), logistic regression (LR), and multilayer perceptron (MLP) models, was used to screen the more valuable metabolites from 28 metabolites to optimize the biomarker panel. The results showed that classification accuracy and performance of MLP model were better than other algorithms when the metabolites consisting of L-threonic acid, N-acetyl-L-cysteine, CMPF, glycocholic acid, L-tyrosine, cholic acid, and glycoursodeoxycholic acid. Finally, 17 blood samples from autopsy cases were applied to validate the classification model's value in human samples. The MLP model constructed based on rat dataset achieved accuracy of 88.23%, and ROC of 0.89 for predicting AMI type II in autopsy cases of sudden cardiac death. The results demonstrated that MLP model based on 7 molecular biomarkers had a good diagnostic performance for both AMI rats and autopsy-based blood samples. Thus, the combination of metabolomics and machine learning algorithms provides a novel strategy for AMI diagnosis.

关键词： Acute myocardial ischemia Sudden cardiac death Metabolomics machine learning algorithms Potential biomarkers

来源：评论

学校读者我要写书评

暂无评论

Exploration and verification a 13-gene diagnostic framework for ulcerative colitis across multiple platforms via machine learning algorithms

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-14页

作者： Wang, Jing Li, Lin Chen, Pingbo He, Chiyi Niu, Xiaoping Wan Nan Med Coll Affiliated Hosp 1 Dept Gastroenterol Wuhu 241001 Peoples R China Wan Nan Med Coll Affiliated Hosp 1 Dept Joint Orthoped Wuhu 241001 Peoples R China

Ulcerative colitis (UC) is a chronic inflammatory bowel disease with intricate pathogenesis and varied presentation. Accurate diagnostic tools are imperative to detect and manage UC. This study sought to construct a robust diagnostic model using gene expression profiles and to identify key genes that differentiate UC patients from healthy controls. Gene expression profiles from eight cohorts, encompassing a total of 335 UC patients and 129 healthy controls, were analyzed. A total of 7530 gene sets were computed using the GSEA method. Subsequent batch correction, PCA plots, and intersection analysis identified crucial pathways and genes. machine learning, incorporating 101 algorithm combinations, was employed to develop diagnostic models. Verification was done using four external cohorts, adding depth to the sample repertoire. Evaluation of immune cell infiltration was undertaken through single-sample GSEA. All statistical analyses were conducted using R (Version: 4.2.2), with significance set at a P value below 0.05. Employing the GSEA method, 7530 gene sets were computed. From this, 19 intersecting pathways were discerned to be consistently upregulated across all cohorts, which pertained to cell adhesion, development, metabolism, immune response, and protein regulation. This corresponded to 83 unique genes. machine learning insights culminated in the LASSO regression model, which outperformed others with an average AUC of 0.942. This model's efficacy was further ratified across four external cohorts, with AUC values ranging from 0.694 to 0.873 and significant Kappa statistics indicating its predictive accuracy. The LASSO logistic regression model highlighted 13 genes, with LCN2, ASS1, and IRAK3 emerging as pivotal. Notably, LCN2 showcased significantly heightened expression in active UC patients compared to both non-active patients and healthy controls (P < 0.05). Investigations into the correlation between these genes and immune cell infiltration in UC highlighted

关键词： Ulcerative colitis Diagnostic model machine learning algorithms Gene set enrichment analysis Immunocytes infiltration

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation and Comparative Analysis of Different machine learning algorithms in Predicting Cardiovascular Disease

引用

ENGINEERING LETTERS 2021年第2期29卷 731-741页

作者： Asif, Md Asfi-Ar-Raihan Nishat, Mirza Muntasir Faisal, Fahim Dip, Rezuanur Rahman Udoy, Mahmudul Hasan Shikder, Md Fahim Ahsan, Ragib Islamic Univ Technol Dept EEE Dhaka Bangladesh

This study focuses on investigating the performance of different machine learning algorithms and corresponding comparative analysis in predicting cardiovascular disease. Globally this fatal disease causes a plethora of mortality among mankind and so, machine learning algorithms can play a significant role in early detection which will ensure proper treatment for the patients and reduce severity in many cases. The University of California, Irvine (UCI) data repository is utilized for the training and testing of the model. Twelve machine learning algorithms were studied and the performances were observed for default hyperparameter (DHP), grid search cross validation (GSCV) and random search cross validation (RSCV) method. Moreover, computational time were also calculated for both GSCV and RSCV. An accuracy of 92% has been found in both hard and soft voting ensemble classifiers (EVCH and EVCS). However, it observed that Adaboost algorithm outperforms EVCH and EVCS in terms of precision and specificity . Hence, the overall comparative analyses among all the algorithms are carried out extensively where accuracy, precision, sensitivity, specificity, F1 score, and ROC-AUC are brought into action. Jupyter notebook 6.0.3 is utilized for simulation.

关键词： Cardiovascular disease UCI dataset Accuracy machine learning algorithms

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：