检索结果-内蒙古大学图书馆

Subgroup identification of early preterm birth (ePTB): informing a future prospective enrichment clinical trial design

引用

BMC PREGNANCY AND CHILDBIRTH 2017年第1期17卷 18-18页

作者： Zhang, Chuanwu Garrard, Lili Keighley, John Carlson, Susan Gajewski, Byron Univ Kansas Med Ctr Dept Biostat Mail Stop 10263901 Rainbow Blvd Kansas City KS 66160 USA US FDA Div Biometr 3 OB OTS CDER Silver Spring MD 20993 USA Univ Kansas Med Ctr Sch Hlth Profess Dept Dietet & Nutr Mail Stop 10263901 Rainbow Blvd Kansas City KS 66160 USA

Background: Despite the widely recognized association between the severity of early preterm birth (ePTB) and its related severe diseases, little is known about the potential risk factors of ePTB and the sub-population with high risk of ePTB. Moreover, motivated by a future confirmatory clinical trial to identify whether supplementing pregnant women with docosahexaenoic acid (DHA) has a different effect on the risk subgroup population or not in terms of ePTB prevalence, this study aims to identify potential risk subgroups and risk factors for ePTB, defined as babies born less than 34 weeks of gestation. Methods: The analysis data (N = 3,994,872) were obtained from CDC and NCHS' 2014 Natality public data file. The sample was split into independent training and validation cohorts for model generation and model assessment, respectively. Logistic regression and CART models were used to examine potential ePTB risk predictors and their interactions, including mothers' age, nativity, race, Hispanic origin, marital status, education, pre-pregnancy smoking status, pre-pregnancy BMI, pre-pregnancy diabetes status, pre-pregnancy hypertension status, previous preterm birth status, infertility treatment usage status, fertility enhancing drug usage status, and delivery payment source. Results: Both logistic regression models with either 14 or 10 ePTB risk factors produced the same C-index (0.646) based on the training cohort. The C-index of the logistic regression model based on 10 predictors was 0.645 for the validation cohort. Both C-indexes indicated a good discrimination and acceptable model fit. The CART model identified preterm birth history and race as the most important risk factors, and revealed that the subgroup with a preterm birth history and a race designation as Black had the highest risk for ePTB. The c-index and misclassification rate were 0.579 and 0.034 for the training cohort, and 0.578 and 0.034 for the validation cohort, respectively. Conclusions: This study r

关键词： Early preterm birth Risk factor Interaction classification and regression tree Logistic regression Enrichment trial design

来源：评论

学校读者我要写书评

暂无评论

Modeling Vehicle Merging Behavior in Work Zone Merging Areas During the Merging Implementation Period

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2016年第4期17卷 917-925页

作者： Weng, Jinxian Xue, Shan Yan, Xuedong Shanghai Maritime Univ Coll Transport & Commun Shanghai 201306 Peoples R China Beijing Jiaotong Univ MOE Key Lab Urban Transportat Complex Syst Theory Beijing 100044 Peoples R China

Using the classification and regression tree (CART) method, this study aims to model the vehicle merging behavior at work zone merging areas during the merging implementation period. Hereafter, themerging implementation period is defined as the period from the starting time to the completion time of a merging maneuver. From the safety perspective, the times to collision (TTC) between the merging vehicle and its neighboring vehicles are regarded as the factors affecting vehicle merging decisions. The results show that a larger delay, a shorter remaining distance to the work zone, a smaller TTC to the merging lead vehicle, and a higher merging vehicle speed may encourage drivers to complete merging maneuvers early. It is also found that the merging vehicle tends to continue merging when the TTCs between the merging vehicle and its neighboring vehicles in the through lane are too small. In addition, another CART model without the use of TTC is built for comparison. The finding indicates that the use of TTC can not only contribute to a perfect result but also highlight the merging safety situation more clearly. The merging rules of this study are ready to be incorporated into the merging assistance system for guiding a safety merging at work zone merging areas.

关键词： Merging classification and regression tree time-to-collision merging implementation period

来源：评论

学校读者我要写书评

暂无评论

Automatic Microstructural Characterization and classification Using Higher-Order Spectra on Ultrasound Signals

引用

JOURNAL OF NONDESTRUCTIVE EVALUATION 2016年第1期35卷 1-14页

作者： Vejdannik, Masoud Sadr, Ali IUST Sch Elect Engn Tehran 16844 Iran

During the gas tungsten arc welding of nickel based superalloys, the secondary phases such as Laves and carbides are formed in final stage of solidification. But, other phases such as gamma '' and delta phases can precipitate in the microstructure, during aging at high temperatures. Nevertheless, choosing the appropriate conditions of welding can minimize the formation of the Nb-rich Laves phases and thus reduce the susceptibility to solidification cracking. This study aims at the automatic microstructurally characterizing the kinetics of phase transformations on an Nb-base alloy, thermally aged at 650 and 950 degrees C for 10, 100 and 200 h, through backscattered ultrasound signals at frequency of 4 MHz. For this, an automated processing system was designed using the spectrum representation of higher order statistics. The ultrasound signals are inherently non-linear and thus the conventional linear time and frequency domain methods can not reveal the complexity of these signals clearly. Bispectrum (the spectral representation of third order correlation) is a non-linear method which is highly robust to noise. In the proposed system, the bispectrum coefficients are subjected to linear discriminant analysis (LDA) technique to reduce the statistical redundancy and reveal discriminating features. These dimensionality reduced features are fed to the classification and regression tree, random forest and k-nearest neighbor (k-NN) classifiers to automatic microstructural characterization. Bispectrum coupled with LDA and k-NN yielded the highest average accuracy of 95.0 and 78.0 %, respectively for thermal aging at 650 and 950 degrees C. Thus, the proposed processing system provides high reliability to be used for microstructure characterization through ultrasound signals.

关键词： Bispectrum classification and regression tree k-Nearest neighbor Linear discriminant analysis Microstructural characterization Non-destructive inspection Random forest Ultrasound signals

来源：评论

学校读者我要写书评

暂无评论

Low total cholesterol and high total bilirubin are associated with prognosis in patients with prolonged sepsis

引用

JOURNAL OF CRITICAL CARE 2016年第1期31卷 36-40页

作者： Yamano, Shuhei Shimizu, Kentaro Ogura, Hiroshi Hirose, Tomoya Hamasaki, Toshimitsu Shimazu, Takeshi Tasaki, Osamu Nagasaki Univ Hosp Ctr Emergency Med Nagasaki 8528501 Japan Osaka Univ Grad Sch Med Dept Traumatol & Acute Crit Med Suita Osaka 5650871 Japan Natl Cerebral & Cardiovasc Ctr Off Biostat & Data Management Suita Osaka 5658565 Japan

Purpose: Nutritional biochemical indexes are generally used as markers for critically ill patients. However, they are easily influenced by acute phase changes after injury and are difficult to use as common and practical biomarkers. The objective of this study was to determine the most valuable prognostic markers among 15 common laboratory tests in patients with sepsis. Methods: We included all sepsis patients who stayed in the intensive care unit for more than 2 weeks. We evaluated 15 biochemistry indexes including serum albumin, total protein, C-reactive protein, cholinesterase, total cholesterol (T-Cho), triglyceride, sodium, potassium, blood urea nitrogen, creatinine, aspartate aminotransferase, alanine aminotransferase, lactate dehydrogenase, total bilirubin (T-Bil), and prothrombin time. The minimum and maximum values of these indexes during the first 14 days from admission were analyzed by classification and regression tree and multivariate logistic regression analyses. Results: This study comprised 91 patients with sepsis. The primary split was the minimum value of serum T-Cho (T-Cho(Min)), and the cutoff value was 73.5 mg/dL by classification and regression tree analysis. The second split was the maximum value of T-Bil (T-Bil (Max)), and the cutoff value was 1.35 mg/dL. The rate of mortality was 63% (17/27) in the group with T-Cho (Min) less than 73.5 mg/dL and T-Bil (Max) greater than 1.35 mg/dL. Multivariate logistic regression revealed that T-Cho (Min) and T-Bil (Max) were the biomarkers most closely associated with prognosis. Conclusions: Total cholesterol and T-Bil could be associated with prognosis in patients with sepsis. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Sepsis Cholesterol Bilirubin classification and regression tree Nutrition Biomarker

来源：评论

学校读者我要写书评

暂无评论

Subclinical elevation of high-sensitive troponin T levels at the convalescent stage is associated with increased 5-year mortality after ST-elevation myocardial infarction

引用

JOURNAL OF CARDIOLOGY 2016年第3-4期67卷 314-320页

作者： Hara, Masahiko Sakata, Yasuhiko Nakatani, Daisaku Suna, Shinichiro Nishino, Masami Sato, Hiroshi Kitamura, Tetsuhisa Nanto, Shinsuke Hamasaki, Toshimitsu Hori, Masatsugu Komuro, Issei Osaka Univ Hosp Dept Med Innovat Suita Osaka Japan Osaka Univ Grad Sch Med Dept Cardiovasc Med Suita Osaka Japan Tohoku Univ Grad Sch Med Dept Cardiovasc Med Sendai Miyagi 9808574 Japan Osaka Univ Grad Sch Med Dept Adv Cardiovasc Therapeut Suita Osaka Japan Osaka Rosai Hosp Div Cardiol Sakai Osaka Japan Kwansei Gakuin Univ Sch Human Welf Studies Nishinomiya Hyogo Japan Osaka Univ Grad Sch Med Dept Social & Environm Med Div Environm Med & Populat Sci Suita Osaka Japan Natl Cerebral & Cardiovasc Ctr Off Biostat & Data Management Suita Osaka Japan Osaka Med Ctr Canc & Cardiovasc Dis Osaka Prefectural Hosp Org Osaka Japan Univ Tokyo Grad Sch Med Dept Cardiovasc Med Tokyo Japan

Background: It is unclear whether serum high-sensitive troponin T (hs-TnT) levels at the convalescent stage of ST-elevation myocardial infarction (STEMI) are associated with long-term mortality. Methods: This study enrolled a total of 2944 consecutive STEMI patients who were registered in the Osaka Acute Coronary Insufficiency Study between 2000 and 2009, and whose hs-TnT levels were evaluated at the convalescent stage. Patients were divided into four hs-TnT category groups according to the results of survival classification and regression tree (CART) analysis. The impact of hs-TnT levels on 5-year mortality was evaluated using multivariate Cox regression analysis. Results: Only one patient had hs-TnT level below the detection limit of the assay (<0.003 ng/mL). The median hs-TnT level was 0.025 (quartile 0.011-0.083) ng/mL. During the median follow-up period of 1782 days, 188 patients died. Survival CART analysis revealed that the lst, 2nd, and 3rd discriminating hs-TnT levels to discern 5-year mortality were 0.028, 0.008, and 1.340 ng/mL, respectively. The adjusted hazard ratios for the medium-low (0.009-0.028 ng/mL), medium-high (0.029-1.340 ng/mL), and high-risk (>= 1.341 ng/mL) groups were 3.03 (95% confidence interval 1.18-7.77, p = 0.021),4.29 (1.63-11.28, p = 0.003), and 8.68 (2.20-34.27, p = 0.002), respectively. Integrated discrimination improvement (IDI) analysis revealed that incorporation of this hs-TnT classification scheme with other clinical variables statistically improved the discriminatory accuracy for 5-year mortality, with a time-dependent IDI of 0.0076 (p = 0.033). Conclusions: hs-TnT levels at the convalescent stage were associated with long-term mortality in STEMI patients. Even subclinical elevation of hs-TnT levels was associated with increased 5-year mortality. (C) 2015 Japanese College of Cardiology. Published by Elsevier Ltd. All rights reserved.

关键词： High-sensitive troponin T ST-elevation myocardial infarction classification and regression tree Integrated discrimination improvement Mortality

来源：评论

学校读者我要写书评

暂无评论

Process Discovery using classification tree Hidden Semi-Markov Model 17

Process Discovery using Classification Tree Hidden Semi-Mark...

引用

17th IEEE International Conference on Information Reuse and Integration

作者： Kang, Yihuang Zadorozhny, Vladimir Natl Sun Yat Sen Univ Dept Informat Management Kaohsiung Taiwan Univ Pittsburgh Sch Informat Sci Pittsburgh PA 15260 USA

ISBN: (纸本)9781509032075

Various and ubiquitous information systems are being used in monitoring, exchanging, and collecting information. These systems are generating massive amount of event sequence logs that may help us understand underlying phenomenon. By analyzing these logs, we can learn process models that describe system procedures, predict the development of the system, or check whether the changes are expected. In this paper, we consider a novel technique that models these sequences of events in temporal-probabilistic manners. Specifically, we propose a probabilistic process model that combines hidden semi-Markov model and classification trees learning. Our experimental result shows that the proposed approach can answer a kind of question "what are the most frequent sequence of system dynamics relevant to a given sequence of observable events?". For example, "Given a series of medical treatments, what are the most relevant patients' health condition pattern changes at different times?"

关键词： Hidden Semi-Markov Models classification and regression tree Process Discovery Temporal Data Mining

来源：评论

学校读者我要写书评

暂无评论

New Distances Combination For Facial Expression Recognition From Image Sequences 13

New Distances Combination For Facial Expression Recognition ...

引用

13th IEEE/ACS International Conference on Computer Systems and Applications (AICCSA)

作者： Salmam, Fatima Zahra Madani, Abdellah Kissi, Mohamed Univ Chouaib Doukkali Fac Sci Dept Comp Sci Lab LAROSERI El Jadida Morocco Univ Hassan 2 Fac Sci & Technol Dept Comp Sci Lab LIM Casablanca Morocco

ISBN: (纸本)9781509043200

This paper propose a new method of facial expression recognition from image sequences taking into consideration only the first and the last frames, that represent respectively the neutral state and the emotion state. Our proposed method is based on calculating six distances from eleven points of the face. These points are detected and tracked using supervised decent method, and refer to the four internal parts of the face ( eyebrows, eyes, nose, and mouth). After that, two data mining techniques are used to classify facial expression into emotion, taking as input dynamic feature vector deducted from the six distances previously calculated in the first and the last frames. Our method achieved a best recognition rate of 98% in the CK+ database, and 80.6% in the OULU-CASIA VIS database

关键词： Emotion Recognition Facial expression Supervised Descent Method classification and regression tree Neural Network

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition using Decision trees 13

Facial Expression Recognition using Decision Trees

引用

13th International Conference on Computer Graphics, Imaging and Visualization (CGiV)

作者： Salmam, Fatima Zahra Madani, Abdellah Kissi, Mohamed Univ Chouaib Doukkali Fac Sci Dept Comp Sci Lab LAROSERI El Jadida Morocco Univ Chouaib Doukkali Fac Sci Dept Comp Sci Lab LIMA El Jadida Morocco

ISBN: (纸本)9781509008117

Emotion recognition from facial expressions is generally performed in three steps: face detection, features extraction and classification of expressions. The present work focuses on two points: Firstly, a new extraction method is presented based on the geometric approach. This method consists of calculating six distances in order to measure parts of the face that better describe a facial expression. Secondly, an automatic supervised learning method called decision tree is applied on two databases (JAFEE and COHEN), in order to have a facial expressions classifying system with seven possible classes (six basic emotions plus neutral);this system uses as input the six distances previously calculated (using Euclidian,Manhattan or Minkowski distance) for each face. Our results achieved a recognition rate of 89.20% and 90.61% respectively in JAFFE and COHEN database.

关键词： classification and regression tree Emotions recognition Facial expressions Facial landmarks Supervised Descent Method

来源：评论

学校读者我要写书评

暂无评论

MIXED-VARIABLE METAMODELING METHODS FOR DESIGNING MULTI-MATERIAL STRUCTURES

MIXED-VARIABLE METAMODELING METHODS FOR DESIGNING MULTI-MATE...

引用

ASME International Design Engineering Technical Conference / Computer and Information in Engineering Conference (IDETC/CIE)

作者： Xu, Hongyi Chuang, Ching-Hung Yang, Ren-Jye Ford Motor Co Res & Adv Engn Dearborn MI 48121 USA

ISBN: (纸本)9780791850114

To establish metamodels for the multi-material structure design problems, the material selection of each component is considered as a categorical design variable. One challenging task is to establish an accurate mixed-variable metamodel. It is critical to reduce the prediction error of the mixed-variable metamodel in order to achieve a feasible design with superior performance in the metamodel-based optimization. This paper investigates two different strategies of mixed-variable metamodeling: "feature separating" strategy and "all-in-one" strategy. A supervised learning-aided method is proposed to improve the "feature separating" metamodels. The proposed method is compared with several existing mixed-variable metamodeling methods on three engineering benchmark problems to understand their relative merits. These methods include Neural Network (NN) regression, classification and regression tree (CART) and Gaussian Process (GP). A new Polynomial Coefficient Metric is developed to quantify the adequacy of training data. This study provides insight and guidance for establishing proper metamodels on multi-material structural design problems.

关键词： Multi-material Mixed-variable CoKriging Neural network classification and regression tree Gaussian Supervised learning Data adequacy

来源：评论

学校读者我要写书评

暂无评论

The bank of things An empirical investigation on the profitability of the financial services of the future

引用

BUSINESS PROCESS MANAGEMENT JOURNAL 2016年第2期22卷 324-340页

作者： Del Giudice, Manlio Campanella, Francesco Dezi, Luca Paris Sch Business Paris France Univ Naples 2 Dept Econ Capua Italy Univ Naples Parthenope Dept Business & Quantitat Studies Naples Italy

Purpose - The purpose of this paper is to study the existing relationship between the products offered by the banks of things and the relative return on equity (ROE). This can be used to highlight the benefit of carrying out investments to transform traditional banks into banks of things. Design/methodology/approach - The sample used in this empirical research contained 3,692 banks that, in 2013, were located in 28 European countries. To determine whether the Internet of Things (IoT) has an effect on the banks' profitability, the authors employed the classification analysis method (classification and regression tree). Findings - The empirical analysis shows that a high ROE for banks is expressed by the following features: first, banks offer IoT retail services to customers;second, banks offer IoT corporate services to customers;third, banks offer customers a large number of home banking services;and finally, banks offer customers a large number of traditional investment services. Research limitations/implications - The survey covers a sample of European banks. It would be necessary to extend the sample to other geographical areas. It would be possible to generalize the results. Originality/value - Scientific research on the implications of the "Bank of things" are still few and fragmented.

关键词： Profitability Internet of things Financial services Bank of things classification and regression tree Return on equity

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：