关键词： Machine learning methodology   Diabetes program   Family medicine clinics   Mexico  

摘要： Background The study aimed to assess the performance of a multidisciplinary-team diabetes care program called DIABETIMSS on glycemic control of type 2 diabetes (T2D) patients, by using available observational patient data and machine-learning-based targeted learning methods. Methods We analyzed electronic health records and laboratory databases from the year 2012 to 2016 of T2D patients from six family medicine clinics (FMCs) delivering the DIABETIMSS program, and five FMCs providing routine care. All FMCs belong to the Mexican Institute of Social Security and are in Mexico City and the State of Mexico. The primary outcome was glycemic control. The study covariates included: patient sex, age, anthropometric data, history of glycemic control, diabetic complications and comorbidity. We measured the effects of DIABETIMSS program through 1) simple unadjusted mean differences;2) adjusted via standard logistic regression and 3) adjusted via targeted machine learning. We treated the data as a serial cross-sectional study, conducted a standard principal components analysis to explore the distribution of covariates among clinics, and performed regression tree on data transformed to use the prediction model to identify patient sub-groups in whom the program was most successful. To explore the robustness of the machine learning approaches, we conducted a set of simulations and the sensitivity analysis with process-of-care indicators as possible confounders. Results The study included 78,894 T2D patients, from which 37,767patients received care through DIABETIMSS. The impact of DIABETIMSS ranged, among clinics, from 2 to 8% improvement in glycemic control, with an overall (pooled) estimate of 5% improvement. T2D patients with fewer complications have more significant benefit from DIABETIMSS than those with more complications. At the FMC's delivering the conventional model the predicted impacts were like what was observed empirically in the DIABETIMSS clinics. The sensitivity an

关键词： Extreme gradient boosting   Meta-analysis   Kriging-calibration   NO2   Extrapolating ability   China  

摘要： It is unclear how to develop a model based on the combined satellite data and ground monitoring data to accurately estimate daily NO2 levels. Furthermore, the conventional cross-validation (CV) results represent average levels but the model performance may vary greatly from grid to grid. It is an essential issue to evaluate model's prediction ability in different grids and determine the factors affecting model extrapolating ability, which have never been well examined to date. The aim of this study was to compare the ability of three different methods to estimate the daily NO2 across mainland China during 2014-2016;and to develop a novel two-stage meta-analysis method for exploring the influence of the number and the distribution of nearby sites on grid-level prediction accuracy. For better estimating the daily NO2 level, we developed and compared three methods, including universal kriging model, satellite-based method (Non-linear exposure-lag-response model & Extreme gradient boosting combined technique) and the kriging-calibrated satellite method. For exploring influencing factors, the two-stage meta-analysis method was purposed. The kriging-calibrated satellite method had an overall CV R-square and root mean square error (RMSE) of 0.85 and 7.87 mu g/m(3), better than the Universal Kriging model and the satellite-based method (CV R-2 = 0.57 and 0.81). The two-stage meta-analysis method revealed that the model performance did decrease with the sparser distribution of nearby sites. And adding 5 sites within 50 km in the random mode can bring 17.51% improvement in model extrapolating ability. The kriging-calibration can help satellite-based machine learning to provide more accurate NO2 prediction. Our novel evaluation method can provide the suggestion of adding new sites effectively within a limit budget. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Surface waters  

摘要： The spatial resolution of Chinese Gaofen-3 (GF-3) Synthetic Aperture Radar (SAR) image, a pixel size of 500 m at azimuth/flight direction for Global Observation (GLO) and 100 m for Wide ScanSAR (WSC) modes, is relatively coarse, and waves shorter than 100 m are undetectable. In this study, SAR images collected under typhoon conditions by the GF-3 mission are exploited for wave retrieval purposes. In detail, six imagery collected during 2017 and 2018 over the China Seas captured four typhoons. The GLO and WSC modes images are collocated with simulated wave fields using a numeric wave model, called WAVEWATCH-III (WW3) and are processed using a machine learning method to retrieve sea surface waves. In this work, the criterion for the training completion in the process of machine learning is set as 0.15 m of Root mean Square Error (RMSE) for the Significant Wave Height (SWH). Then, the retrieved SWH is compared with measurements collected by the Jason-2 altimeter, showing a 0.61 m RMSE. The proposed algorithm is shown to outperform empirical approaches developed to retrieve the SWH using GF-3 SAR imagery acquired in the GLO and WSC imaging modes.

关键词： 长输管线   地质灾害   机器学习   模型预测  

摘要： 地质灾害是影响长输管线安全运行的重要因素,为减少地质灾害对长输管线的影响,有效预防、规避长输管线的安全风险,本文基于西南油气田仁寿作业区的地质灾害数据,以研究区地质灾害为预测变量,高程、坡度、坡向、地表覆盖为响应变量,采用人工神经网络、决策树、支持向量机3种机器学习方法分析研究区域地质灾害的发生规律,并进一步预测研究区内长输管线发生地质灾害的概率。通过模型对比,相较于人工神经网络和支持向量机,决策树的方法具有更高的预测精度,其预测正确率达0.86。本文的分析结果对研究区管线管理部门具有重要参考价值,相关部门可根据模型预测出的管线点发生地质灾害的概率,提前做好地质灾害预防工作。

关键词： Roll model   Shallow water   NLS-SVM   Damping parameters   Parameter identification  

摘要： In order to accurately identify the ship's roll model parameters in shallow water, and solve the problems of difficult estimating nonlinear damping coefficients by traditional methods, a novel Nonlinear Least Squares Support Vector Machine (NLS-SVM) is introduced. To illustrate the validity and applicability of the proposed method, simulation and decay tests data are combined and utilized to estimate unknown parameters and predict the roll motions. Firstly, simulation data is applied in the NLS-SVM model to obtain estimated damping parameters, compared with pre-defined parameters to verify the validity of the proposed method. Subsequently, decay tests data are used in identifying unknown parameters by utilizing traditional models and the new NLS-SVM model, the results illustrate that the intelligent method can improve the accuracy of parametric estimation, and overcome the conventional algorithms' weakness of difficult identification of the nonlinear damping parameter in the roll model. Finally, to show the wide applicability of the proposed model in shallow water, experimental data from various speeds and Under Keel Clearances (UKCs) are applied to identify the damping coefficients. Results reveal the potential of using the NLS-SVM for the problem of the roll motion in shallow water, and the effectiveness and accuracy are verified as well.

关键词： Predictive maintenance   Machine learning   PdM   Systematic literature review   Artificial intelligence  

摘要： The amount of data extracted from production processes has increased exponentially due to the proliferation of sensing technologies. When processed and analyzed, data can bring out valuable information and knowledge from manufacturing process, production system and equipment. In industries, equipment maintenance is an important key, and affects the operation time of equipment and its efficiency. Thus, equipment faults need to be identified and solved, avoiding shutdown in the production processes. Machine Learning (ML) methods have been emerged as a promising tool in Predictive Maintenance (PdM) applications to prevent failures in equipment that make up the production lines in the factory floor. However, the performance of PdM applications depends on the appropriate choice of the ML method. The aim of this paper is to present a systematic literature review of ML methods applied to PdM, showing which are being explored in this field and the performance of the current state-of-the-art ML techniques. This review focuses on two scientific databases and provides a useful foundation on the ML techniques, their main results, challenges and opportunities, as well as it supports new research works in the PdM field.

关键词： arthroplasty   elastic net   FDA   machine learning   random forest   Postmarket surveillance  

摘要： Purpose While joint arthroplasty is generally a safe and effective procedure, there are concerns that some devices are at increased risk of failure. Early identification of total hip arthroplasty devices with increased risk of failure can be challenging because devices consist of multiple components, hundreds of distinct components are currently used in surgery, and any estimated effect needs to address confounding due to device and patient factors. The purpose of this study was to assess the effectiveness of machine learning approaches at identifying recalled components listed by the US Food and Drug Administration using data from a US total joint arthroplasty registry. Methods An open cohort study was conducted using data (January 1, 2001, to December 31, 2015) from 74 520 implantations and 348 unique components in the Kaiser Permanente Total Joint Replacement Registry. Exposures of interest were device components used in elective primary total hip arthroplasty. The outcome was time to first revision surgery, defined as exchange, removal, or addition of any component. Machine learning methods included regularized/unregularized Cox models and random survival forest. Results Among the recalled components detected were ASR acetabular shell/large femoral head, Durom acetabular shell/Metasul large femoral head, and Rejuvenate modular neck stem. The three components not identified were characterized by small numbers of devices recorded in the registry. Conclusions The novel approaches to signal detection may improve postmarket surveillance of frequently used arthroplasty devices, which in turn will improve public health.

关键词： Data processing   Machine learning   Protolith discrimination   Igneous geochemistry   Sedimentary geochemistry  

摘要： The fundamental origins of metamorphic rocks as sedimentary or igneous are integral to the proper interpretation of a terrane's tectonic and geodynamic evolution. In some cases, the protolith class cannot be determined from field relationships, texture, and/or compositional layering. In this study, we utilize machine learning to predict a metamorphic protolith from its major element chemistry so that accurate interpretation of the geology may proceed when the origin is uncertain or to improve confidence in field predictions. We survey the efficacy of several machine learning techniques to predict the protolith class (igneous or sedimentary) for whole rock geochemical analyses using 9 major oxides. The data are drawn from a global geochemical database with >533 000 geochemical analyses. In addition to metamorphic samples, igneous and sedimentary analyses are used to supplement the dataset based on their similar chemical distributions to their metamorphic counterparts. We train the classifiers on most of the data, retaining similar to 10% for post-training validation. We find that the RUSBoost algorithm performs best overall, achieving a true-positive rate of >95% and >85% for igneous- and sedimentary-derived samples, respectively. Even the traditionally-difficult-to-differentiate metasedimentary and metaigneous rocks of granitic-granodioritic composition were consistently identified with a >75% success rate (92% for granite;85% for granodiorite;88% for wacke;76% for arkose). The least correctly identified rock types were iron-rich shale (58%) and quartzolitic rocks (6%). These trained classifiers are able to classify metamorphic protoliths better than common discrimination methods, allowing for the appropriate interpretation of the chemical, physical, and tectonic contextual history of a rock. The preferred classifier is available as a MATLAB function that can be applied to a spreadsheet of geochemical analyses, returning a predicted class and estimated confidence sc

关键词： artificial intelligence   machine learning   sensitivity analysis  

摘要： A method of analysis of a database of patients (n = 10 329) screened for an abdominal aortic aneurysm (AAA) is presented. Self-reported height, weight, age, gender, ethnicity, and parameters "Heart Problems," "Hypertension," "High Cholesterol," "Diabetes Mellitus," "Smoker Past 2 Years," "Ever Smoked?," "Family History AAA," and "Family History Brain Aneurysm" were provided. Incidence of a AAA (defined as 3 cm diameter) was calculated as a function of age and body mass index (BMI) of greater than or less than a BMI 25 for various patient groups. Age was grouped into one of three categories in 15-year intervals (35-50 years, 50-65 years, and 65 to 80 years). Most patients were Caucasian (n = 8575) and the largest group of patients with a AAA was the Caucasian male (198 of 279 total detected AAAs). A machine learning algorithm was written, with learning inputs from the acquired patient database. Of all groups, Caucasian males were found to have the highest incidence of AAA, with males in general higher than females. Smoking within the past two years was highly associated with AAA incidence, and a past history of smoking to a lesser extent. The incidence of AAA increased with age. When dividing groups into two cohorts by a BMI of 25, generally middle-aged patients with a BMI > 25 had a higher incidence of a AAA. However, in general, the older age group with a BMI < 25 had a higher incidence of AAA. The addition of machine learning allows one to note the effect of an input keeping other input parameters constant. This helps identify a parameter that may be an independent predictor of a particular outcome. When using BMI as the single changing input, an increasing BMI was associated with an increased probability of a AAA, most significantly in middle-aged patients, and then narrowing to similar probabilities in older age. This AAA screening program is ongoing. As data continues to be collected with particularly those patient groups presently underrepresented, questions a

关键词： Fungal hexosaminidase   Dikarya   Classification   Classifier  

摘要： Gene clustering based on amino acid sequence similarity has been one of the most important problems and always challenging in molecular biology. The most conventional methods are based on alignment-technique. These methods cannot identify and classify sequences, especially when the lengths of sequence are long and unequal. Therefore, in order to classify fungal hexosaminidase amino acid sequences and put them in the right taxonomical group we evaluate the feasibility of computational free alignment methods based on machine learning classifiers such as SVM, KNN, SOM and ensemble technique. The classifiers have appropriately categorized large Dikarya hexosaminidase amino acid sequences as data sets according to their taxonomical groups in two phyla named, the "Ascomycota" and the "Basidiomycota". Two statistical methods including paired t test and PCA were used for the feature selection and reduce the dimensionality of the features, respectively. Seven classifier performance metrics, randomized complete block design, pairwise Tukey's honestly significant difference tests and the technique for order preference by similarity to ideal solution with modified k-fold cross validation have been used as tools in order to evaluate and ranking of classifiers. In this study, the effect of training data size on the classifier performance was investigated. The results showed that the rank and the performance of classifiers were depended on the training data size. The highest obtained values for the average overall accuracy of the following training data sizes, 80, 60, 40 and 20% using KNN, KNN, ensemble and ensemble classifier were 96.96, 95.81, 94.47 and 92.47%, respectively.