检索结果-内蒙古大学图书馆

A long short-term memory model for forecasting the surgical case volumes at a hospital

IISE TRANSACTIONS ON HEALTHCARE SYSTEMS ENGINEERING 2023年第3期13卷 226-236页

作者： Bui, Hieu Eksioglu, Sandra D. Villafranca, Adria A. Sanford, Joseph A. Sexton, Kevin W. Univ Arkansas Dept Ind Engn Fayetteville AR 72701 USA Univ Arkansas Med Sci Little Rock AR USA Univ Arkansas Dept Ind Engn Fayetteville AR 72701 USA

Surgical procedures are the primary source of expenditures and revenues for hospitals. Accurate forecasts of the volume of surgical cases enable hospitals to efficiently deliver high-quality care to patients. We propose an algorithm to forecast the expected volume of surgical procedures using multivariate time-series data. This algorithm uses feature engineering techniques to determine factors that affect the volume of surgical cases, such as the number of available providers, federal holidays, weather conditions, etc. These features are incorporated in a long short-term memory (LSTM) network to predict the number of surgical procedures in the upcoming week. The hyperparameters of this model are tuned via grid search and Bayesian optimization techniques. We develop and verify the model using historical data of daily case volume from 2014 to 2020 at an academic hospital in North America. The proposed model is validated using data from 2021. The results show that the proposed model can make accurate predictions six weeks in advance, and the average R 2 = 0.855, RMSE = 2.017, MAE = 1.104. These results demonstrate the benefits of incorporating additional features to improve the model's predictive power for time series forecasting.

关键词： Clustering forecasting surgical case volume feature engineering long short-term memory model machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Predicting Atmospheric Water-Soluble Organic Mass Reversibly Partitioned to Aerosol Liquid Water in the Eastern United States

引用

ENVIRONMENTAL SCIENCE & TECHNOLOGY 2023年第46期57卷 18151-18161页

作者： El-Sayed, Marwa M. H. Parida, Siddharth S. Shekhar, Prashant Sullivan, Amy Hennigan, Christopher J. Embry Riddle Aeronaut Univ Dept Civil Engn Daytona Beach FL 32114 USA Embry Riddle Aeronaut Univ Dept Math Daytona Beach FL 32114 USA Colorado State Univ Dept Atmospher Sci Ft Collins CO 80523 USA Univ Maryland Dept Chem Biochem & Environm Engn Baltimore MD 21250 USA

Water-soluble organic matter (WSOM) formed through aqueous processes contributes substantially to total atmospheric aerosol, however, the impact of water evaporation on particle concentrations is highly uncertain. Herein, we present a novel approach to predict the amount of evaporated organic mass induced by sample drying using multivariate polynomial regression and random forest (RF) machine learning models. The impact of particle drying on fine WSOM was monitored during three consecutive summers in Baltimore, MD (2015, 2016, and 2017). The amount of evaporated organic mass was dependent on relative humidity (RH), WSOM concentrations, isoprene concentrations, and NOx/isoprene ratios. Different models corresponding to each class were fitted (trained and tested) to data from the summers of 2015 and 2016 while model validation was performed using summer 2017 data. Using the coefficient of determination (R-2) and the root-mean-square error (RMSE), it was concluded that an RF model with 100 decision trees had the best performance (R-2 of 0.81) and the lowest normalized mean error (NME < 1%) leading to low model uncertainties. The relative feature importance for the RF model was calculated to be 0.55, 0.2, 0.15, and 0.1 for WSOM concentrations, RH levels, isoprene concentrations, and NOx/isoprene ratios, respectively. The machine learning model was thus used to predict summertime concentrations of evaporated organics in Yorkville, Georgia, and Centerville, Alabama in 2016 and 2013, respectively. Results presented herein have implications for measurements that rely on sample drying using a machine learning approach for the analysis and interpretation of atmospheric data sets to elucidate their complex behavior.

关键词： evaporated organic aerosol aerosol drying aerosol liquid water content machine learning algorithm statistical modeling

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the landslide susceptibility and its spatial difference in the whole Qinghai-Tibetan Plateau region by five learning algorithms

引用

GEOSCIENCE LETTERS 2022年第1期9卷 1-25页

作者： Sajadi, Payam Sang, Yan-Fang Gholamnia, Mehdi Bonafoni, Stefania Mukherjee, Saumitra Chinese Acad Sci Inst Geog Sci & Nat Resources Res Key Lab Water Cycle Related Land Surface Proc Beijing Peoples R China Minist Emergency Management China Key Lab Compound & Chained Nat Hazards Dynam Beijing 100085 Peoples R China Islamic Azad Univ Sanandaj Branch Dept Civil Engn Sanandaj Iran Univ Perugia Dept Engn Perugia Italy Jawaharlal Nehru Univ Sch Environm Sci New Delhi India

Landslides are considered as major natural hazards that cause enormous property damages and fatalities in Qinghai-Tibetan Plateau (QTP). In this article, we evaluated the landslide susceptibility, and its spatial differencing in the whole Qinghai-Tibetan Plateau region using five state-of-the-art learning algorithms;deep neural network (DNN), logistic regression (LR), Naive Bayes (NB), random forest (RF), and support vector machine (SVM), differing from previous studies only in local areas of QTP. The 671 landslide events were considered, and thirteen landslide conditioning factors (LCFs) were derived for database generation, including annual rainfall, distance to drainage (Ds(d)), distance to faults (Ds(f)), drainage density (D-d), elevation (Elev), fault density (F-d), lithology, normalized difference vegetation index (NDVI), plan curvature (Pl(c)), profile curvature (Pr-c), slope (S degrees), stream power index (SPI), and topographic wetness index (TWI). The multi-collinearity analysis and mean decrease Gini (MDG) were used to assess the suitability and predictability of these factors. Consequently, five landslide susceptibility prediction (LSP) maps were generated and validated using accuracy, area under the receiver operatic characteristic curve, sensitivity, and specificity. The MDG results demonstrated that the rainfall, elevation, and lithology were the most significant landslide conditioning factors ruling the occurrence of landslides in Qinghai-Tibetan Plateau. The LSP maps depicted that the north-northwestern and south-southeastern regions (< 32% of total area) were at a higher risk to landslide compared to the center, west, and northwest of the area (> 45% of total area). Moreover, among the five models with a high goodness-of-fit, RF model was highlighted as the superior one, by which higher accuracy of landslide susceptibility assessment and better prone areas management in QTP can be achieved compared to previous results.

关键词： Feature selection technique Landslide susceptibility machine learning algorithm Spatial differencing Qinghai-Tibetan Plateau

来源：评论

学校读者我要写书评

暂无评论

Accurate and Efficient Surrogate Model-Assisted Optimal Design of Flux Reversal Permanent Magnet Arc Motor

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第9期70卷 9312-9325页

作者： Pan, Zhenbao Fang, Shuhua Wang, Hui Zhong, Yuxiang Hefei Univ Technol Sch Elect Engn & Automat Hefei 230009 Peoples R China Southeast Univ Sch Elect Engn Nanjing 210096 Peoples R China Southeast Univ Sch Instrument Sci & Engn Nanjing 210096 Peoples R China

An accurate and efficient surrogate model plays a significant role in the optimal design of electrical motors. This article presents an accurate and efficient surrogate modeling method for a flux reversal permanent magnet arc motor (FR-PMAM) based on machine learning algorithm. Specifically, the motor topology and the optimized design of the FR-PMAM are firstly illustrated. Then, the PM magnetic motive force-permeance model is developed to select structural parameters of FR-PMAM. After that, a finite-element analysis (FEA) model of FR-PMAM is calculated to obtain sample data. A machine learning algorithm random forest is introduced into the field of motor optimal design for the first time to evaluate the contribution of each parameter to the design objectives. Based on the sample data, an efficient machine learning algorithm CatBoost is innovatively employed to establish the accurate and efficient surrogate model of the FR-PMAM that can capture the complex function relationship between output objectives and input parameters. Subsequently, an improved genetic algorithm with the elitist reservation strategy is adopted to obtain the optimal combination of the structural parameters of FR-PMAM. Finally, a prototype of the FR-PMAM is manufactured. The FEA and experimental results validate the effectiveness of the investigated surrogate modeling method.

关键词： Rotors Stator windings Permanent magnet motors Structural engineering machine learning algorithms Windings Support vector machines Finite-element analysis (FEA) genetic algorithm (GA) machine learning algorithm permanent magnet arc motor (PMAM) random forest

来源：评论

学校读者我要写书评

暂无评论

Predicting Driver Errors during Automated Vehicle Takeovers

引用

TRANSPORTATION RESEARCH RECORD 2023年第9期2677卷 410-420页

作者： Alambeigi, Hananeh McDonald, Anthony D. Manser, Michael Shipp, Eva Lenneman, John Pulver, Elizabeth M. Christensen, Scott Texas A&M Univ Wm Michael Barnes 64 Dept Ind & Syst Engn College Stn TX 77843 USA Texas A&M Transportat Inst College Stn TX USA Toyota Motor North Amer Ann Arbor MI USA State Farm Mutual Automobile Insurance Co Bloomington IL USA State Farm Mutual Automobile Insurance Co Salem OR USA

The transition of control between partially automated vehicles and drivers is an important part of the operational design domain and poses unique and important design issues. One approach for enhancing the design of the transition of control mechanisms is to predict driver behavior during a takeover by analyzing his/her state before a takeover. Although there is a wealth of existing literature on modeling the prediction of driver behavior, little is known about the prediction of takeover performance (e.g., driver error) and its underlying data structure (e.g., window sizes or the inclusion of certain features). Thus, the goal of this study is to predict driver error during a takeover event using supervised machine learning algorithms for various window sizes. Three machine learning algorithms (i.e., decision tree, random forest, and support vector machine with a radial basis kernel) were applied to granular driving performance, physiological, and glance data from a driving simulator experiment examining automated vehicle driving. The results showed that a random forest algorithm with an area under the receiver operating characteristic curve of 0.72, trained on a 3 s window before the takeover time, had the best performance with regard to classifying driver error accurately. In addition, we identified the 10 most important predictors that resulted in the best error prediction performance. The results of this study could be useful in developing algorithms for driver state that could be integrated into highly automated systems and, potentially, improve the takeover process.

关键词： driver behavior automated driving transfer of control machine learning algorithm predictive modeling physiological measures

来源：评论

学校读者我要写书评

暂无评论

Phrase Based Information Retrieval Analysis in Various Search Engines Using machine learning algorithms 3rd

Phrase Based Information Retrieval Analysis in Various Searc...

引用

International Conference on Data Management, Analytics and Innovation (ICDMAI)

作者： Amudha, S. Shanthi, I. Elizabeth Avinashilingam Inst Home Sci & Higher Educ Women Dept Comp Sci Coimbatore Tamil Nadu India

ISBN: (纸本)9789811393648;9789811393631

Query-based information retrieval is an essential part of the web search engine. Many researchers have applied different types of web mining technologies to find more relevant information based on the keyword but are not able to know the correct meaning of the term (keyword) single, multiword or phrases. In this paper we address this problem of searching phrases. In this work the phrase searching process is three-fold as whole Phrase, Sequence of term in phrase and Mingle of the term in the phrase. Here the user enters a query as phrases that is passed to various search engines and retrieves the top 'n' list of web pages. Initially preprocessing is performed on the Sequence of Keyword in phrase and Mingle of the keyword in the phrase. Then feature extraction is done based on the web pages in the various search engines using term Frequency-Inverse Document Frequency method. Following the feature extraction, grouping of the top 'n' list of web pages from various search engines based on the parameter as title-based, snippet-based, content-based, address-based, link-based, uniform resource locator-based, and co-occurrence-based calculation is done using LBG clustering algorithm. Then identified the unique link from the above grouping of web pages from the various search engines using SVM classifier and assigned the rank value to the unique linkweb pages are done using proposed ranking algorithm. Finally it is observed from this experiment that precision, recall, f-measure, accuracy, speed, and error rate show significant improvement than the traditional search engines.

关键词： Information retrieval LBG clustering machine learning algorithm Search engine SVM classification

来源：评论

学校读者我要写书评

暂无评论

A comparison between machine learning algorithms for the application of micro-grids Energy management 21

A comparison between Machine learning algorithms for the app...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Khoshlessan, Mahshid Fahimi, Babak Kiani, Morgan Univ Texas Dallas Dept Elect Engn Dallas TX USA Texas Christian Univ Dept Engn Ft Worth TX 76129 USA

ISBN: (纸本)9781728157542

advanced micro-grids are envisioned to be a critical part of future smart grids due to their local intelligence and capability on hosting distributed energy resources. To control a community of micro-grids so that the energy is distributed in a proper manner and reliability in supplying critical loads is increased, a smart decision making should be applied to the system. By using machine learning algorithms, the system can make intelligent, precise, and fast decisions leading to achieving the above mentioned goals. In this paper, five machine learning algorithms are applied to a set of data related to a community of three micro-grids. The data set including test data and training data is obtained based on grid voltage, weather, state of charge (SOC) of the storage system in both micro-grid and it's neighboring unit, and time of the day. The modes of operation are achieved from rational decisions that brings about a wide range of energy distribution from available sources into the most preferable loads. Random Forests, Decision Tree, Logistic Regression, SVM, and Gradient Boosting are the five various algorithms used to manage the distribution of energy and will be compared.

关键词： machine learning algorithm support vector machine decision tree random forests logistic regression gradient boosting

来源：评论

学校读者我要写书评

暂无评论

Destination competitiveness research over the past three decades: a computational literature review using topic modelling

引用

JOURNAL OF TRAVEL & TOURISM MARKETING 2024年第5期41卷 726-742页

作者： Xia, Haiyang Muskat, Birgit Karl, Marion Li, Gang Law, Rob Australian Natl Univ Res Sch Management Canberra ACT 2601 Australia Univ Surrey Sch Hospitality & Tourism Management Guildford England Deakin Univ Ctr Cyber Resilience & Trust CREST Melbourne Australia Univ Macau Asia Pacific Acad Econ & Management Dept Integrated Resort & Tourism Management Fac Business Adm Macau Peoples R China

The aim of this study is to comprehensively review the topics and themes studied in destination competitiveness research and to enrich tourism researchers' literature review toolbox with the computational literature review technique. A novel computational literature review framework that can be applied to review tourism research domains characterised by an abundance of literature is developed. Enabled by the developed computational literature review framework with topic modelling, this study offers a comprehensive review of 1,130 destination competitiveness studies. The results identified several promising research topics, themes and theoretical perspectives that can be perused in future destination competitiveness studies.

关键词： Destination competitiveness computational literature review machine learning algorithm ordinary least squares regression topic modelling tourist destination tourism bertopic comprehensive literature analysis text mining

来源：评论

学校读者我要写书评

暂无评论

How are texts analyzed in blockchain research?A systematic literature review

引用

Financial Innovation 2024年第1期10卷 2304-2338页

作者： Xian Zhuo Felix Irresberger Denefa Bostandzic Manchot Graduate School Heinrich Heine University DüsseldorfUniversitätsstr.140225DüsseldorfGermany Durham University Business School Durham UniversityMill Hill LaneDH13LBDurhamGermany Department of Management and Entrepreneurship Witten/Herdecke UniversityAlfred-Herrhausen-Str.5058448WittenGermany

This paper provides a systematic literature review of text analysis methodologies used in blockchain-related research to comprehend and synthesize existing studies across disciplines and define future research *** summarize the research scope,text data,and methodologies of 124 papers and identify the two most common combinations of these dimensions:(1)papers that focus on specific cryptocurrencies tend to apply sentiment analysis to instant user-generated content or news articles to discover the correlations between public opinion and market behavior,and(2)studies that examine the broad concept of blockchain with text data from documents published by companies tend to apply topic modeling techniques to explore classifications and trends in blockchain *** discover five major research topics in the academic literature:relationship discovery,cryptocurrency performance prediction,classification and trend,crime and regulation,and perception of *** on these findings,we highlight three potential research directions for researchers to select topics and implement suitable methodologies for text analysis.

关键词： Blockchain Text analysis Systematic literature review machine learning algorithm Topic modeling Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Prediction model of colorectal cancer (CRC) lymph node metastasis based on intestinal bacteria

引用

CLINICAL & TRANSLATIONAL ONCOLOGY 2023年第6期25卷 1661-1672页

作者： Wu, Yinhang Zhuang, Jing Zhou, Jie Jin, Yin Wu, Xinyue Song, Yifei Fan, Zhiqing Wu, Wei Han, Shuwen Zhejiang Chinese Med Univ Sch Clin Med 2 548 Binwen Rd Hangzhou Zhejiang Peoples R China Huzhou Univ Huzhou Cent Hosp Affiliated Cent Hosp 1558 Sanhuan North Rd Huzhou 313000 Zhejiang Peoples R China Key Lab Multi Res & Clin Transformat Digest Canc H 1558 Sanhuan North Rd Huzhou 313000 Zhejiang Peoples R China

Background Lymph node metastasis is the main metastatic mode of CRC. Lymph node metastasis affects patient *** To screen differential intestinal bacteria for CRC lymph node metastasis and construct a prediction *** First, fecal samples of 119 CRC patients with lymph node metastasis and 110 CRC patients without lymph node metastasis were included for the detection of intestinal bacterial 16S rRNA. Then, bioinformatics analysis of the sequencing data was performed. Community structure and composition analysis, difference analysis, and intragroup and intergroup correlation analysis were conducted between the two groups. Finally, six machine learning models were used to construct a prediction model for CRC lymph node *** The community richness and the community diversity at the genus level of the two groups were basically consistent. A total of 12 differential bacteria (Agathobacter, Catenibacterium, norank_f__Oscillospiraceae, Lachnospiraceae_FCS020_group, Lachnospiraceae_UCG-004, etc.) were screened at the genus level. Differential bacteria, such as Agathobacter, Catenibacterium, norank_f__Oscillospiraceae, and Lachnospiraceae_FCS020_group, were more associated with no lymph node metastasis in CRC. In the discovery set, the RF model had the highest prediction accuracy (AUC = 1.00, 98.89% correct, specificity = 55.21%, sensitivity = 55.95%). In the test set, SVM model had the highest prediction accuracy (AUC = 0.73, 72.92% correct, specificity = 69.23%, sensitivity = 88.89%). Lachnospiraceae_FCS020_group was the most important variable in the RF model. Lachnospiraceae_UCG - 004 was the most important variable in the SVM *** CRC lymph node metastasis is closely related to intestinal bacteria. The prediction model based on intestinal bacteria can provide a new evaluation method for CRC lymph node metastasis.

关键词： Colorectal cancer (CRC) Lymph node metastasis Intestinal bacteria Prediction model machine learning 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：