检索结果-内蒙古大学图书馆

作者： Thakor, Govind Singh University of Guelph

学位级别：硕士

The uRAD A3 air quality monitor uses a linear model to convert the output resistance value of the metal oxide sensor into air quality index in terms of VOC (AQIVOC). To improve this representation of AQIVOC a predictive algorithm was developed to convert the resistance to concentration values and then to AQIVOC. The A3 monitor was first validated through point source emissions and comparison with an analyzer. Then it was calibrated under controlled conditions for three different types of VOCs – acetone, ethanol and hexane. Experiments were performed for each solvent and in combination to observe how each solvent interacted with metal oxide sensor to understand the relationship between the resistance and concentration through analysis. Resistance range of each solvent (acetone - 15.24 to 8.5 Kohms, ethanol - 25.73 to 13.59 Kohms, hexane - 104.25 to 43.49 Kohms) and resistance-concentration relationship served as the basis for algorithm development for predicting total concentration of VOCs and their individual composition

关键词： Air Quality Index predictive algorithm Metal Oxide Sensor VOCs Resistance-Concentration Relationship Air Quality Monitor

来源：评论

学校读者我要写书评

暂无评论

Using Decision Trees to Predict Intent to Use PassiveOccupational Exoskeletons in Manufacturing Tasks

Using Decision Trees to Predict Intent to Use PassiveOccupat...

引用

作者： McNamara, Nathan Patrick Ohio University

学位级别：硕士

A nontraditional decision tree approach was used to predict worker intent to use passive occupational exoskeletons in various manufacturing tasks. A dataset adapted from a previous study containing 33 records of participant, exoskeleton, and task combinations was used to create multiple decision tree models. Worker intent to use the exoskeleton was used as the target variable for all decision tree models. Data were collected during two separate sessions with fifteen participants at five manufacturing facilities in Ohio. Participants wore exoskeletons for under 30 minutes in each session and answered questions pertaining to personal characteristics, task characteristics, and personal preferences. Response data were used to create practitioner and research decision tree models. The practitioner models classified worker intent to use exoskeletons using only task characteristics and personal characteristics. Research models used personal characteristics, task characteristics, and personal preferences features to predict intent to use with all collected data. Both practitioner and research models may be useful for practitioners and exoskeleton developers for better understanding factors related to intent to use exoskeletons. All models created in the study yielded findings consistent with previous exoskeleton literature. This study demonstrated the ability of classification trees to identify nonlinear relationships in datasets relating to intent to use assistive technologies.

关键词： Industrial Engineering Decision tree trees assistive device devices exoskeleton ergonomic intervention ergonomics machine learning human factors predictive algorithm intent to use safety

来源：评论

学校读者我要写书评

暂无评论

An efficient strategy for predicting river dissolved oxygen concentration: application of deep recurrent neural network model

引用

ENVIRONMENTAL MONITORING AND ASSESSMENT 2021年第12期193卷 798-798页

作者： Moghadam, Salar Valizadeh Sharafati, Ahmad Feizi, Hajar Marjaie, Seyed Mohammad Saeid Asadollah, Seyed Babak Haji Seyed Motta, Davide Islamic Azad Univ Dept Civil Engn Sci & Res Branch Tehran Iran Tabriz Univ Fac Agr Dept Water Engn Tabriz Iran Northumbria Univ Dept Mech & Construct Engn Wynne Jones Bldg Newcastle Upon Tyne NE1 8ST Tyne & Wear England

Dissolved oxygen (DO) concentration in water is one of the key parameters for assessing river water quality. Artificial intelligence (AI) methods have previously proved to be accurate tools for DO concentration prediction. This study presents the implementation of a deep learning approach applied to a recurrent neural network (RNN) algorithm. The proposed deep recurrent neural network (DRNN) model is compared with support vector machine (SVM) and artificial neural network (ANN) models, formerly shown to be robust AI algorithms. The Fanno Creek in Oregon (USA) is selected as a case study and daily values of water temperature, specific conductance, streamflow discharge, pH, and DO concentration are used as input variables to predict DO concentration for three different lead times ("t + 1," "t + 3," and "t + 7"). Based on Pearson's correlation coefficient, several input variable combinations are formed and used for prediction. The model prediction performance is evaluated using various indices such as correlation coefficient, Nash-Sutcliffe efficiency, root mean square error, and mean absolute error. The results identify the DRNN model (CCTesting = 0.97, NSETesting = 0.948, RMSETesting = 0.43 and MAE(Testing) = 0.25) as the most accurate among the three models considered, highlighting the potential of deep learning approaches for water quality parameter prediction.

关键词： River water quality Dissolved oxygen concentration predictive algorithm Deep recurrent neural network Artificial neural network Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Climatology of nutrient distributions in the South China Sea based on a large data set derived from a new algorithm

引用

PROGRESS IN OCEANOGRAPHY 2021年 195卷 102586-102586页

作者： Du, Chuanjun He, Ruoying Liu, Zhiyu Huang, Tao Wang, Lifang Yuan, Zhongwei Xu, Yanping Wang, Zhe Dai, Minhan Xiamen Univ Coll Ocean & Earth Sci State Key Lab Marine Environm Sci Xiamen Peoples R China North Carolina State Univ Dept Marine Earth & Atmospher Sci Raleigh NC USA

Nutrients are typically the most important determinant of the productivity of marine ecosystems. Hence, nutrients have been an essential variable of ocean observations in the modern oceanography era. Understanding of marine ecosystems and biogeochemistry, however, is largely limited by the spatiotemporal coverage of nutrient data. Herein, we developed a novel algorithm based on a large observational dataset of nutrients and their relationship with water masses indexed by temperature and salinity in the South China Sea (SCS). The algorithm yielded errors of <= 1.3, <= 0.10 and <= 3.5 mu mol L (-1) for NO3 (-) + NO2 (-) (N + N), phosphate and silicate, respectively. It is then applied to reconstruct nutrient concentrations primarily using temperature and salinity data archived in the World Ocean Database and Argo database during 1940-2018. It increases the nutrient data to similar to 5 million, by ca. three orders of magnitude compared to direct measurements in the SCS. This allows for a full examination of the seasonal climatology of nutrients in the SCS. In summer, in the upper 200 m, nutrient concentrations in the northwest and southernmost SCS are higher than in the rest of the SCS. An overall reversed pattern is revealed in winter, when higher nutrient concentrations are found in the central basin rather than basin margins. The Kuroshio intrusion and the vertical displacement of the nutricline, driven by upwelling/downwelling induced by horizontal convergences/divergences at both meso- and basin scales, determine the spatial and seasonal variation of nutrients. Seasonally, the Kuroshio intrusion and vertical displacements of the nutricline tend to offset the spatial variation of nutrient concentrations in spring, while they show an additive effect in the fall.

关键词： South China Sea Nutrients Climatological distributions predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Methodology for the Improvement of Knowledge Acquisition by a Multimedia Web Tool

引用

INTERNATIONAL JOURNAL OF ENGINEERING EDUCATION 2023年第2期39卷 643-652页

作者： Victor, Gabriel Cerna Pedro Perez-Poch, Antoni Penalba, Francisco Alpiste Torner, Jordi Univ Politecn Cataluna EEBE Ave Eduard Maristany 16 Barcelona 08019 Spain

Adaptive learning is a method that personalizes the teaching-learning strategies in accordance with the needs and preferences of each student. This article describes the design, the implementation and the tests of a web application developed with adaptive learning in order to improve student knowledge acquisition and to simplify the teacher's work. The tool uses EventSource technologies combined with heuristic functions to produce a predictive algorithm, which is capable of being adapted to the students in a customized way by presenting the content adjusted according to their cognitive needs. The design is based on the hypothesis that the acquisition of knowledge can be improved by using a computing application which presents a syllabus to be learned in various forms. In this way, the application determines students' progress within the content of the material, which is classified by branches of knowledge. The tool was applied to one group of students and the data that we obtained was compared with the results of the rest, subject to the usual knowledge transmission system. The results obtained not only improve the academic results, but also enhance the heuristic decision-making about the content to be taught.

关键词： adaptive teaching predictive algorithm evaluation improved learning

来源：评论

学校读者我要写书评

暂无评论

A database for G proteins and their interaction with GPCRs

引用

BMC BIOINFORMATICS 2004年第1期5卷 208-208页

作者： Elefsinioti, AL Bagos, PG Spyropoulos, IC Hamodrakas, SJ Univ Athens Fac Biol Dept Cell Biol & Biophys Athens 15701 Greece

Background: G protein-coupled receptors (GPCRs) transduce signals from extracellular space into the cell, through their interaction with G proteins, which act as switches forming heterotrimers composed of different subunits (alpha,beta,gamma). The alpha subunit of the G protein is responsible for the recognition of a given GPCR. Whereas specialised resources for GPCRs, and other groups of receptors, are already available, currently, there is no publicly available database focusing on G Proteins and containing information about their coupling specificity with their respective receptors. Description: gpDB is a publicly accessible G proteins/GPCRs relational database. Including species homologs, the database contains detailed information for 418 G protein monomers (272 G, 87 Gbeta and 59 Ggamma) and 2782 GPCRs sequences belonging to families with known coupling to G proteins. The GPCRs and the G proteins are classified according to a hierarchy of different classes, families and sub-families, based on extensive literature searchs. The main innovation besides the classification of both G proteins and GPCRs is the relational model of the database, describing the known coupling specificity of the GPCRs to their respective alpha subunit of G proteins, a unique feature not available in any other database. There is full sequence information with cross-references to publicly available databases, references to the literature concerning the coupling specificity and the dimerization of GPCRs and the user may submit advanced queries for text search. Furthermore, we provide a pattern search tool, an interface for running BLAST against the database and interconnectivity with PRED-TMR, PRED-GPCR and TMRPres2D. Conclusions: The database will be very useful, for both experimentalists and bioinformaticians, for the study of G protein/GPCR interactions and for future development of predictive algorithms. It is available for academics, via a web browser at the URL:http://***

关键词： Accessory Protein Relational Scheme predictive algorithm Coupling Specificity GPCR Sequence

来源：评论

学校读者我要写书评

暂无评论

PhiΦBreast & theory of spiral cancer new diagnostic techniques for breast cancer detection

引用

Translational Medicine Communications 2021年第1期6卷 1-10页

作者： Trapanese, Ersilio Tarro, Giulio CMM Diagnostic Center Cava de’ Tirreni Italy Foundation Teresa & Luigi De Beaumont Bonelli for Cancer Research Naples Italy De Beaumont Bonelli Foundation Naples Italy

Today, breast cancer is one of the most aggressive cancers in women and new cases continue to increase worldwide. The incidence of this tumor is kept under control especially with surgery. In order to reduce mortality we need to detect this life threatening disease at an earlier stage. For two years, we have conducted a study for the identification and characterization of suspicious breast lesions using a new diagnostic technique applied to ultrasonography and mammography called “PhiΦBreast.” Identification and characterization of category C4-C5 lesions of the breast with high predictive Positive PPV value, with a new innovative method called “PhiΦBreast” using the Golden Ratio (Phi, or Φ 1.618...) Fibonacci sequence and a predictive algorithm, applied to the ultrasonography and mammography with subsequent deepening with cytological examination using fine needle aspiration (FNAC), according to evaluation criteria of the Breast Imaging Report Data System (BI-RADS) and the American College of Radiology (ACR). Usefulness of this research and the use of this new diagnostic tecnique is to detect the breast cancer in early stage. In addition to develop a classification model of the histological type identified in the section areas and the percentage of probability in relation between the golden spiral and Fibonacci sequence. This amazing intuition and research has given contribution to the new Theory of Spiral Cancer. With the use of Golden Ratio and Fibonacci sequence, applied to ultrasonography and mammography, we have experimented and developed a diagnostic map with characteristics of high probability of identifying suspicious lesions at an early stage. We examined 987 women, 55 lesions detected with PhiΦBreast pattern were classified according to BI-RADS descriptors for US-imaging, including morphologic features that had a high predictive value for the malignancy (p <0.001). This innovative diagnostic technique has shown a sensitivity of 95%, a specificity of 97%,

关键词： PhiΦBreast Theory of Spiral Cancer predictive algorithm Golden Ratio Fibonacci Sequence Gravity Phyllotaxis Breast Cancer

来源：评论

学校读者我要写书评

暂无评论

The Development and Validation of Simplified Machine Learning algorithms to Predict Prognosis of Hospitalized Patients With COVID-19: Multicenter, Retrospective Study

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2022年第1期24卷 e31549页

作者： He, Fang Page, John H. Weinberg, Kerry R. Mishra, Anirban Amgen Inc Ctr Observat Res 1120 Vet Blvd San Francisco CA 94080 USA Amgen Inc Digital Hlth & Innovat Thousand Oaks CA 91320 USA Amgen Inc Ctr Observat Res Thousand Oaks CA 91320 USA

Background: The current COVID-19 pandemic is unprecedented;under resource-constrained settings, predictive algorithms can help to stratify disease severity, alerting physicians of high-risk patients;however, there are only few risk scores derived from a substantially large electronic health record (EHR) data set, using simplified predictors as input. Objective: The objectives of this study were to develop and validate simplified machine learning algorithms that predict COVID-19 adverse outcomes;to evaluate the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and calibration of the algorithms;and to derive clinically meaningful thresholds. Methods: We performed machine learning model development and validation via a cohort study using multicenter, patient-level, longitudinal EHRs from the Optum COVID-19 database that provides anonymized, longitudinal EHR from across the United States. The models were developed based on clinical characteristics to predict 28-day in-hospital mortality, intensive care unit (ICU) admission, respiratory failure, and mechanical ventilator usages at inpatient setting. Data from patients who were admitted from February 1, 2020, to September 7, 2020, were randomly sampled into development, validation, and test data sets;data collected from September 7, 2020, to November 15, 2020, were reserved as the postdevelopment prospective test data set. Results: Of the 3.7 million patients in the analysis, 585,867 patients were diagnosed or tested positive for SARS-CoV-2, and 50,703 adult patients were hospitalized with COVID-19 between February 1 and November 15, 2020. Among the study cohort (n=50,703), there were 6204 deaths, 9564 ICU admissions, 6478 mechanically ventilated or EMCO patients, and 25,169 patients developed acute respiratory distress syndrome or respiratory failure within 28 days since hospital admission. The algorithms demonstrated high accuracy (AUC 0.89, 95% CI 0.89-0.89 on the test data set [n=

关键词： COVID-19 predictive algorithm prognostic model machine learning

来源：评论

学校读者我要写书评

暂无评论

Using real-world data to dynamically predict flares during tapering of biological DMARDs in rheumatoid arthritis: development, validation, and potential impact of prediction-aided decisions

引用

ARTHRITIS RESEARCH & THERAPY 2022年第1期24卷 74-74页

作者： van der Leeuw, Matthijs S. Messelink, Marianne A. Tekstra, Janneke Medina, Ojay van Laar, Jaap M. Haitjema, Saskia Lafeber, Floris Veris-van Dieren, Josien J. van der Goes, Marlies C. den Broeder, Alfons A. Welsing, Paco M. J. Univ Utrecht Univ Med Ctr Utrecht Dept Rheumatol & Clin Immunol Heidelberglaan 100 NL-3584 CX Utrecht Netherlands Univ Utrecht Univ Med Ctr Utrecht Dept Digital Hlth Heidelberglaan 100 NL-3584 CX Utrecht Netherlands Univ Utrecht Univ Med Ctr Utrecht Cent Diagnost Lab Heidelberglaan 100 NL-3584 CX Utrecht Netherlands Reumazorg Zuid West Nederland Van Hertumweg 17-19 NL-4462 EV Goes Netherlands Meander Med Ctr Dept Rheumatol Maatweg 3 NL-3813 TZ Amersfoort Netherlands Sint Maartensklin Dept Rheumatol Hengstdal 3 NL-6574 NA Ubbergen Netherlands

Background Biological disease-modifying antirheumatic drugs (bDMARDs) are effective in the treatment of rheumatoid arthritis. However, as bDMARDs may also lead to adverse events and are expensive, tapering them is of great clinical interest. Tapering according to disease activity-guided dose optimization (DGDO) does not seem to affect long term remission rates, but flares are frequent during this process. Our objective was to develop a model for the prediction of flares during bDMARD tapering using data from routine care and to evaluate its potential clinical impact. Methods We used a joint latent class model to repeatedly predict the probability of a flare occurring within the next 3 months. The model was developed using longitudinal data on disease activity (DAS28) and other routine care data from two clinics. predictive accuracy was assessed in cross-validation and external validation was performed with data from the DRESS (Dose REduction Strategy of Subcutaneous tumor necrosis factor inhibitors) trial. Additionally, we simulated the reduction in number of flares and bDMARD dose when implementing the model as a decision aid during bDMARD tapering in the DRESS trial. Results Data from 279 bDMARD courses were used for model development. The final model included two latent DAS28-trajectories, bDMARD type and dose, disease duration, and seropositivity. The area under the curve of the final model was 0.76 (0.69-0.83) in cross-validation and 0.68 (0.62-0.73) in external validation. In simulation of prediction-aided decisions, the mean number of flares over 18 months decreased from 1.21 (0.99-1.43) to 0.75 (0.54-0.96). The reduction in he bDMARD dose was mostly maintained, increasing from 54 to 64% of full dose. Conclusions We developed a dynamic flare prediction model, exclusively based on data typically available in routine care. Our results show that using this model to aid decisions during bDMARD tapering may significantly reduce the number of flares while maintaini

关键词： Rheumatoid arthritis predictive algorithm Tapering bDMARD therapy Applied data analytics in medicine Biologicals

来源：评论

学校读者我要写书评

暂无评论

Using routine inpatient data to identify patients at risk of hospital readmission

引用

BMC HEALTH SERVICES RESEARCH 2009年第1期9卷 96-96页

作者： Howell, Stuart Coory, Michael Martin, Jennifer Duckett, Stephen Queensland & Hlth Ctr Healthcare Improvement Brisbane Qld Australia Univ Queensland Sch Populat Hlth Brisbane Qld Australia Royal Brisbane & Womens Hosp Dept Internal Med Brisbane Qld Australia Univ Queensland Diamantina Inst Brisbane Qld Australia

Background: A relatively small percentage of patients with chronic medical conditions account for a much larger percentage of inpatient costs. There is some evidence that case-management can improve health and quality-of-life and reduce the number of times these patients are readmitted. To assess whether a statistical algorithm, based on routine inpatient data, can be used to identify patients at risk of readmission and who would therefore benefit from case-management. Methods: Queensland database study of public-hospital patients, who had at least one emergency admission for a chronic medical condition ( e. g., congestive heart failure, chronic obstructive pulmonary disease, diabetes or dementia) during 2005/2006. Multivariate logistic regression was used to develop an algorithm to predict readmission within 12 months. The performance of the algorithm was tested against recorded readmissions using sensitivity, specificity, and Likelihood Ratios ( positive and negative). Results: Several factors were identified that predicted readmission (i.e., age, co-morbidities, economic disadvantage, number of previous admissions). The discriminatory power of the model was modest as determined by area under the receiver operating characteristic (ROC) curve (c = 0.65). At a risk score threshold of 50, the algorithm identified only 44.7% (95% CI: 42.5%, 46.9%) of patients admitted with a reference condition who had an admission in the next 12 months;37.5% ( 95% CI: 35.0%, 40.0%) of patients were flagged incorrectly ( they did not have a subsequent admission). Conclusion: A statistical algorithm based on Queensland hospital inpatient data, performed only moderately in identifying patients at risk of readmission. The main problem is that there are too many false negatives, which means that many patients who might benefit would not be offered case-management.

关键词： Chronic Obstructive Pulmonary Disease Chronic Medical Condition Emergency Admission predictive algorithm Previous Admission

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：