检索结果-内蒙古大学图书馆

A Flat-Hierarchical Approach Based on machine learning Model for e-Commerce Product Classification

IEEE ACCESS 2024年 12卷 72730-72745页

作者： Cotacallapa, Harold Saboya, Nemias Canas Rodrigues, Paulo Salas, Rodrigo Linkolk Lopez-Gonzales, Javier Univ Peruana Union Fac Ingn & Arquitectura Lima 15464 Peru Univ Fed Bahia Dept Stat BR-40110909 Salvador Brazil Univ Valparaiso Escuela Ingn C Biomed Valparaiso 2362905 Chile Millennium Inst Intelligent Healthcare Engn iHealt Santiago 7820436 Chile Univ Peruana Union Escuela Posgrad Lima 15464 Peru

Within the e-commerce sphere, optimizing the product classification process assumes pivotal importance, owing to its direct influence on operational efficiency and profitability. In this context, employing machine learning algorithms stands out as a premier solution for effectively automating this process. The design of these models commonly adopts either a flat or local (hierarchical) approach. However, each of them exhibits significant limitations. The regional approach introduces taxonomic inconsistencies in predictions, whereas the flat approach becomes inefficient when dealing with extensive datasets featuring high granularity. Therefore, our research introduces a solution for hierarchical product classification based on a machine learning model that integrates flat and local (hierarchical) classification approaches using a 4-level electronic product dataset obtained from a renowned e-commerce platform in Latin America. In pursuit of this goal, a comparative analysis of seven machine learning algorithms, including Multinomial Naive Bayes, Linear Support Vector Classifier, Multinomial Logistic Regression, Random Forest, XGBoost, FastText, and Voting Ensemble, was conducted. This hybrid approach model performs better than models using a single approach. It surpassed the top-performing flat approach model by 0.15% and outperformed the leading local approach (Local Classifier per Level) model by 4.88%, as measured by the weighted F1-score. Additionally, this paper contributes to the academic community by presenting a significant Spanish-language dataset comprising over one million products and discussing the preprocessing techniques tailored for the dataset. It also addresses the study's inherent limitations and potential avenues for future exploration in this field.

关键词： Electronic commerce Classification algorithms machine learning algorithms Bayes methods Support vector machines Random forests Performance evaluation Data models South America Logistic regression Inventory management Product delivery machine learning e-commerce hierarchical product classification local classifier per level ensemble

来源：评论

学校读者我要写书评

暂无评论

Seismic fragility analysis of RC frame structures based on IDA analysis and machine learning

引用

STRUCTURES 2024年 65卷

作者： Xu, Weixiao Zhao, Yanshun Yang, Weisong Yu, Dehu Zhao, Yudong Qingdao Univ Technol Coll Civil Engn Qingdao 266520 Peoples R China Minist Educ Engn Res Ctr Concrete Technol Marine Environm Qingdao 266520 Peoples R China Shandong Jianzhu Univ Coll Civil Engn Jinan 250101 Peoples R China

This study introduces a machine learning-based methodology designed to rapidly predict the seismic responses of reinforced concrete (RC) frame structures. The research focuses on three types of RC frame structures: low-rise, multi-story, and small high-rise buildings. Ground shaking records are selected according to the conditional mean spectrum (CMS). A sample database, constructed via Incremental Dynamic Analysis (IDA), facilitates the prediction of structural responses using ground shaking intensity and structural details as inputs. Concurrently, the study performs a feature importance analysis of the model. machine learning algorithms, including integrated learning and neural networks, are utilized to predict the seismic responses of the RC frame structures. This methodology also assists in evaluating the seismic fragility of these structures. The results show that the discrepancy between the neural network-based seismic fragility assessments and the IDA results is minimal, indicating a high degree of accuracy in the proposed methodology. Among the characteristic parameters, Average Spectral Acceleration (AvgSa) is identified as the most significant. This methodology serves as a valuable tool for the rapid prediction of seismic responses in RC frame structures, demonstrating substantial practical value.

关键词： RC frame structures Seismic fragility IDA analysis machine learning algorithms Seismic response

来源：评论

学校读者我要写书评

暂无评论

DAS: A DRL-Based Scheme for Workload Allocation and Worker Selection in Distributed Coded machine learning

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第15期11卷 26076-26090页

作者： Zhou, Yitong Ye, Qiang Huang, Hui Dalhousie Univ Fac Comp Sci Halifax NS B3H 4R2 Canada

machine learning (ML) has been widely applied to successfully address a variety of different problems across diverse domains, such as robotics, healthcare, and finance. However, high-complexity ML algorithms often require overlong computation time, which significantly impacts their feasibility. Distributed ML (DML) has been used to tackle the slow computation problem with high-complexity ML algorithms. Nevertheless, with DML, the computation results from all participating computing devices need to be collected in order to complete an ML task. When part of the participating devices, known as the stragglers, cannot return their results in time, the overall computation time will be extended. Distributed coded ML (DCML) is a promising solution to mitigate the negative impact of the stragglers. With DCML, redundancy is injected into an ML task so that only a subset of the results from participating devices are required to finish the ML task. In DCML, how to select proper participating devices, referred to as workers, and how to allocate appropriate workloads to the selected workers are two challenging problems. In this article, we consider a DCML scenario where numerous computing devices are available for an ML task. These devices are willing to offer their computation capacity in exchange for compensation. To encourage the computing devices to participate in the distributed computation, a reverse auction-based incentive mechanism is employed. With the objective of minimizing both the completion time of the ML task and the compensation for participating devices, we propose a deep-reinforcement-learning-based workload allocation and worker selection scheme for DCML, DAS. To our knowledge, this is the first attempt to simultaneously tackle both the workload allocation and worker selection issues in DCML. Our experimental results indicate that DAS outperforms the state-of-the-art schemes in terms of completion time and compensation.

关键词： Task analysis Encoding Resource management Termination of employment machine learning algorithms Vectors Optimization Deep reinforcement learning (DRL) distributed coded machine learning (DCML) worker selection workload allocation

来源：评论

学校读者我要写书评

暂无评论

Disseminating the Risk Factors With Enhancement in Precision Medicine Using Comparative machine learning Models for Healthcare Data

引用

IEEE ACCESS 2024年 12卷 72794-72812页

作者： Sheik Abdullah, A. Naga Pranava Shashank, V. Altrin Lloyd Hudson, D. Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 Tamil Nadu India

The field of healthcare analytics, as an expanding discipline that integrates data analysis, machine learning, and clinical expertise, is seen to hold great promise for improving patient outcomes and the overall delivery of healthcare services. With the increasing availability of Electronic Health Records (EHRs), a wealth of healthcare data has emerged, presenting opportunities to enhance disease prediction and personalize treatments. The objective of the research is to develop and evaluate machine-learning models for predicting cancer, diabetic, diabetic retina, and heart-related outcomes using demographic and clinical data from Electronic Health Records (EHRs). Through thorough testing on diverse datasets, the study aims to assess the performance of these models in terms of accuracy, precision, and recall metrics, with the ultimate goal of advancing disease prediction and enhancing patient outcomes within the field of healthcare analytics. The proposed model demonstrates high accuracy, particularly in predicting cancer (97.080%) and diabetic (97.33%) outcomes using Support Vector machines (SVM) and Decision Trees. Additionally, logistic regression achieves a notable accuracy of 76.521% for diabetic retina dataset, while Decision Trees exhibit 86.419% accuracy for heart-related predictions. SVM accuracy for Pima diabetic dataset stands at 79.746%. To assess the model's performance, thorough testing was conducted on a diverse and extensive dataset, employing a combination of accuracy, precision, and recall metrics. This research represents a substantial contribution to the field of healthcare analytics, emphasizing the potential of machine learning to advance disease prediction and, ultimately, enhance patient outcomes.

关键词： Medical services machine learning Predictive models Prediction algorithms machine learning algorithms Breast cancer Precision medicine Decision trees Random forests Support vector machines Diabetes Hyperparameter optimization decision trees logistic regression random forest classifier support vector machine breast cancer heart disease PIMA Indian diabetes diabetic retinopathy diabetes comparative analysis hyperparameter tuning

来源：评论

学校读者我要写书评

暂无评论

Using machine learning models to estimate Escherichia coli concentration in an irrigation pond from water quality and drone-based RGB imagery data

引用

WATER RESEARCH 2024年 260卷 121861页

作者： Hong, Seok Min Morgan, Billie J. Stocker, Matthew D. Smith, Jaclyn E. Kim, Moon S. Cho, Kyung Hwa Pachepsky, Yakov A. USDA ARS Environm Microbial & Food Safety Lab 10300 Baltimore AveBldg 173 Beltsville MD 20705 USA Ulsan Natl Inst Sci & Technol Dept Civil Urban Earth & Environm Engn UNIST-gil 50 Ulsan 44919 South Korea Korea Univ Sch Civil Environm & Architectural Engn Seoul 02841 South Korea

The rapid and efficient quantification of Escherichia coli concentrations is crucial for monitoring water quality. Remote sensing techniques and machine learning algorithms have been used to detect E. coli in water and estimate its concentrations. The application of these approaches, however, is challenged by limited sample availability and unbalanced water quality datasets. In this study, we estimated the E. coli concentration in an irrigation pond in Maryland, USA, during the summer season using demosaiced natural color (red, green, and blue: RGB) imagery in the visible and infrared spectral ranges, and a set of 14 water quality parameters. We did this by deploying four machine learning models - Random Forest (RF), Gradient Boosting machine (GBM), Extreme Gradient Boosting (XGB), and K-nearest Neighbor (KNN) - under three data utilization scenarios: water quality parameters only, combined water quality and small unmanned aircraft system (sUAS)-based RGB data, and RGB data only. To select the training and test datasets, we applied two data-splitting methods: ordinary and quantile data splitting. These methods provided a constant splitting ratio in each decile of the E. coli concentration distribution. Quantile data splitting resulted in better model performance metrics and smaller differences between the metrics for both the training and testing datasets. When trained with quantile data splitting after hyperparameter optimization, models RF, GBM, and XGB had R-2 values above 0.847 for the training dataset and above 0.689 for the test dataset. The combination of water quality and RGB imagery data resulted in a higher R-2 value (>0.896) for the test dataset. Shapley additive explanations (SHAP) of the relative importance of variables revealed that the visible blue spectrum intensity and water temperature were the most influential parameters in the RF model. Demosaiced RGB imagery served as a useful predictor of E. coli concentration in the studied irrigation pond

关键词： Microbial water quality Water qualoity parameters RGB images unmanned aerial Vehicle machine learning algorithms Escherichia coli

来源：评论

学校读者我要写书评

暂无评论

Flight Delay Prediction Using Different Regression algorithms in machine learning

Flight Delay Prediction Using Different Regression Algorithm...

引用

International Conference on Signal Processing and Communication (ICSPC)

作者： A. Evangeline R. Catherine Joy A. Albert Rajan Department of Electronics and Communication Engineering Karunya Institute of Technology and Sciences Coimbatore India

The two forms of regression algorithms are investigated and compared in this Article Such as LASSO and RIDGE regression. For scheduled airlines to improve customer satisfaction and success, accurate forecasting of delay is essential. There is no way to stop a flight from being delayed, yet they significantly affect the profits and losses of carriers. This research investigates a larger spectrum of potential flight delay difficulties and compares two machine learning algorithms in defined extended flight delay time series forecasting. A dataset for the suggested technique is created by gathering, decoding, and linking automatic dependent surveillance-broadcast (ADS-B) signals with additional data including weather, flight schedules, and airport information. A regression approach is used in conjunction with a number of forecasting tasks as part of the defined prediction challenges. The accuracy of the suggested prediction model was examined and compared to current prediction approaches. The results of LASSO and RIDGE regression with the mean absolute errorMAE (0.2 and 0.1), mean squared error-MSE (0.1 and 0.04), root mean square error-RMSE (0.3 and 0.2) and Accuracy (99.7% and 99.8%) respectively.

关键词： machine learning algorithms Atmospheric modeling Time series analysis Signal processing algorithms machine learning Predictive models Airports

来源：评论

学校读者我要写书评

暂无评论

machine learning Methods for the Prediction of Wastewater Treatment Efficiency and Anomaly Classification with Lack of Historical Data

引用

APPLIED SCIENCES-BASEL 2024年第22期14卷

作者： Gulshin, Igor Kuzina, Olga Moscow State Univ Civil Engn Res & Educ Ctr Water Supply & Wastewater Treatment 26 Yaroslaskoye Highway Moscow 129337 Russia Moscow State Univ Civil Engn Dept Informat Syst Technol & Automat Construct 26 Yaroslaskoye Highway Moscow 129337 Russia

This study examines an algorithm for collecting and analyzing data from wastewater treatment facilities, aimed at addressing regression tasks for predicting the quality of treated wastewater and classification tasks for preventing emergency situations, specifically filamentous bulking of activated sludge. The feasibility of using data obtained under laboratory conditions and simulating the technological process as a training dataset is explored. A small dataset collected from actual wastewater treatment plants is considered as the test dataset. For both regression and classification tasks, the best results were achieved using gradient-boosting models from the CatBoost family, yielding metrics of SMAPE = 9.1 and ROC-AUC = 1.0. A set of the most important predictors for modeling was selected for each of the target features.

关键词： machine learning algorithms wastewater treatment effluent quality soft sensors

来源：评论

学校读者我要写书评

暂无评论

Traffic Intrusion Detection of Medical Consumption Electronics in the Field of Medical Management Based on Integrated learning

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 1334-1341页

作者： Sun, Tianyi Zhang, Xinyue Wang, Xinyi Zhuang, Yuan He, Zheng China Med Univ Hosp 1 Dept Communist Youth League Shenyang 110001 Liaoning Peoples R China China Med Univ Hosp 1 Dept Anesthesiol Shenyang 110001 Liaoning Peoples R China China Med Univ Hosp 1 Dept Acad Affairs Shenyang 110001 Liaoning Peoples R China China Med Univ Hosp 1 Dept Radiat Oncol Shenyang 110001 Liaoning Peoples R China

The medical and health industry is evolving from traditional single management to modern scientific and systematic management. From the perspective of medical management, medical consumer electronics have developed rapidly. Various medical consumer electronics have been widely used, and the security of medical electronic networks has gradually become the focus of researchers. Traffic intrusion detection is a network security system running at all times, and its importance is self-evident. Traditional intrusion detection mainly relies on expert experience, which leads to the limitations of intrusion detection technology. To address this issue, this work designs a medical consumer electronic traffic intrusion detection network via deep learning and integrated learning. First, this work proposes a classification model (NDR-BiLSTM) based on the combination of the nonlinear dimensionality reduction method and BiLSTM. Secondly, this work proposes a processing model for unbalanced data problems (SMOTE-IAdaboost). This model can promote classification effect of minority data in intrusion detection. SMOTE-IAdaboost uses NDR-BiLSTM intrusion detection model as a weak classifier in ensemble learning. This eventually forms an intrusion detection model that improves the ability of unbalanced data processing. Finally, this work conducts systemic experiments, the data verify the superiority of SMOTE-IAdaboost for medical consumer electronic traffic intrusion detection.

关键词： Intrusion detection Feature extraction Deep learning machine learning algorithms Data models Dimensionality reduction Consumer electronics Traffic intrusion detection medical consumption electronics medical management integrated learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Cross-Selling Health Insurance Products Using machine-learning Techniques

引用

JOURNAL OF COMPUTER INFORMATION SYSTEMS 2024年

作者： Mavundla, Khulekani Thakur, Surendra Adetiba, Emmanuel Abayomi, Abdultaofeek Durban Univ Technol Durban South Africa Covenant Univ Ota Nigeria Walter Sisulu Univ HRA East London South Africa

This study delves into the utilization of machine learning (ML) techniques for predicting health insurance cross-selling behavior in South African consumers. The main goal is to create a robust ML model that assists health insurance companies in pinpointing potential customers with higher probabilities of purchasing additional health insurance products. Employing quantitative methodology, the study extracted consumer data and applied various ML algorithms such as random forest, K-nearest neighbors, XGBoost classifier, and logistic regression using Python. Tailored feature engineering techniques were employed to enhance predictive accuracy. Analyzing 1,000,000 customer records with 16 features, Random Forest emerged as the top-performing model, achieving an accuracy score of 0.99 and F1 score of 1.00. The study reveals that customers aged 25-70, with prior insurance and longer service history, are more inclined to purchase additional health insurance products. These findings provide actionable insights for refining marketing strategies, boosting customer acquisition, and increasing revenue.

关键词： Health insurance cross-selling customer churn machine learning algorithms prediction model training

来源：评论

学校读者我要写书评

暂无评论

Predicting Patent Quality Based on machine learning Approach

引用

IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT 2024年 71卷 3144-3157页

作者： Erdogan, Zulfiye Altuntas, Serkan Dereli, Turkay Iskenderun Tech Univ Dept Ind Engn TR-31200 Antakya Turkiye Yildiz Tech Univ Dept Ind Engn TR-34349 Istanbul Turkiye Hasan Kalyoncu Univ Off President TR-27000 Gaziantep Turkiye

The investment budget allocated by companies in R&D activities has increased due to increased competition in the market. Applications for industrial property rights by countries, investors, companies, and universities to protect inventions obtained as an outcome of investments have also increased. The selection of the patent to be invested becomes more difficult with the increasing number of applications. Therefore, predicting patent quality is quite significant for companies to be successful in the future. The level to which a patent meets the expectations of decision makers is referred to as patent quality. Patent indices represent decision makers' expectations. In this study, an approach is proposed to predict patent quality in practice. The proposed approach uses supervised learning algorithms and analytic hierarchy process (AHP) method. The proposed approach is applied to patents related to personal digital assistant technologies. The performances of individual and ensemble machine learning methods have been also analyzed to establish the prediction model. In addition, 75% split ratio and the five-fold cross-validation methods have been used to verify the prediction model. The multilayer perceptron algorithm has 76% accuracy value. The proposed prediction model is essential in directing R&D studies to the right technology areas and transferring the incentives to patent applications with a high quality rate.

关键词： Patents Codes Clustering algorithms Prediction algorithms machine learning algorithms Predictive models Technological innovation Analytic hierarchy process (AHP) machine learning multilayer perceptron patent indices supervised 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：