检索结果-内蒙古大学图书馆

Ensemble learning-based COVID-19 detection by feature boosting in chest X-ray images

IET IMAGE PROCESSING 2020年第16期14卷 4059-4066页

作者： Upadhyay, Kamini Agrawal, Monika Deepak, Desh IIT Delhi Ctr Appl Res Elect New Delhi India Dr Ram Manohar Lohia Hosp Dept Resp Med New Delhi India

The novel coronavirus has spread quite rapidly across the globe. The current testing rate is failing to match the exponential rate of rising cases. Moreover, the available testing methodologies are expensive and time-consuming. A sensitive automated diagnosis is one of the biggest need of the hour. In the proposed work, the authors analyse the chest X-ray images of normal, pneumonia and coronavirus disease-2019 (COVID-19) patients and process them to boost the COVID-specific features (opacities etc.), which enable to perform sensitive identification of COVID-19 patients. The sets of original and processed images are used with a stack of pre-trained deep models for ensemble learning. They used VGG-16 as base-learners, trained with a diverse set of inputs followed by a logistic regression model, the meta learner, to combine the base-learner predictions. The proposed fusion-based model is trained and tested for three types of classification, TYPE-I: binary (NORMAL/ABNORMAL), TYPE-II: binary (PNEUMONIA/COVID-19) and TYPE-III: multi-class (NORMAL/PNEUMONIA/COVID-19). The diagnosis results are quite promising, with high accuracy and sensitivity values for all the cases. The proposed algorithm can be used to assist the medical experts for quick identification and isolation of COVID-19 patients and thereby mitigating the effect of the virus.

关键词： diseases patient diagnosis learning (artificial intelligence) regression analysis diagnostic radiography medical image processing image fusion COVID-19 patients pre-trained deep models base-learners logistic regression model meta learner base-learner predictions fusion-based model sensitivity values ensemble learning-based COVID-19 detection chest X-ray images novel coronavirus current testing rate exponential rate available testing methodologies sensitive automated diagnosis coronavirus disease COVID-specific features

来源：评论

学校读者我要写书评

暂无评论

The association between manganese exposure with cardiovascular disease in older adults: NHANES 2011-2018

引用

JOURNAL OF ENVIRONMENTAL SCIENCE AND HEALTH PART A-TOXIC/HAZARDOUS SUBSTANCES & ENVIRONMENTAL ENGINEERING 2021年第11期56卷 1221-1227页

作者： Xiao, Shengjue Zhou, Yufei Liu, Tao Hu, Yue Wu, Qi Pan, Qinyuan Wang, Xiaotong Liu, Ailin Liu, Jie Zhu, Hong Yin, Ting Pan, Defeng Xuzhou Med Univ Dept Cardiol Affiliated Hosp 99 Huaihai West Rd Xuzhou 221004 Jiangsu Peoples R China Fudan Univ Zhongshan Hosp Shanghai Inst Cardiovasc Dis Dept Cardiol Shanghai Peoples R China Fudan Univ Inst Biomed Sci Shanghai Peoples R China Xuzhou Med Univ Dept Gen Practice Affiliated Hosp Xuzhou Jiangsu Peoples R China Nanjing Med Univ Dept Cardiol Affiliated Hosp 1 Nanjing Jiangsu Peoples R China

The aim of the current study was to explore possible connections between manganese exposure and the prevalence of cardiovascular disease (CVD) in older US adults. The relationship between serum manganese levels and CVD was explored in 2427 people aged 60 years and over using data from the National Health and Nutrition Examination Survey (NHANES) (2011-2018). Multivariate linear regression analysis was performed to investigate associations between CVD risk factors and serum manganese concentration. The relationship between manganese levels and the prevalence of CVD was probed using generalized linear models and restricted cubic spline curves. Stratified subgroup analysis was subsequently constructed to rule out spurious interactions between variables and manganese. Compared with the lowest quartile, the modified odds ratios (ORs) with 95% confidence intervals (CIs) for CVD prevalence across the manganese quartiles were 0.71 (OR: 0.51;CI: 1.00), 0.70 (0.50, 0.99), and 0.49 (0.34, 0.72). In the full adjusted model, a prominent negative relationship was observed between serum manganese concentration and CVD. A restricted cubic spline curve was used to show a nonlinear negative relationship between manganese concentration and CVD. In summary, manganese levels are negatively correlated with the risk of CVD in a nation-wide study of older US adults.

关键词： Cardiovascular disease exposure manganese order adults logistic regression model

来源：评论

学校读者我要写书评

暂无评论

Predicting Subtype of Growth Hormone Pituitary Adenoma based on Magnetic Resonance Imaging Characteristics

引用

JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY 2022年第1期46卷 124-130页

作者： Liu, Chen-Xi Wang, Sheng-Zhong Heng, Li-Jun Han, Yu Ma, Yu-Hui Yan, Lin-Feng Yu, Ying Wang, Wen Hu, Yu-Chuan Cui, Guang-Bin Fourth Mil Med Univ Air Force Med Univ Dept Radiol & Funct & Mol Imaging Key Lab Shaanxi ProvTangdu Hosp Xian 710038 Shaanxi Peoples R China Shaanxi Univ Tradit Chinese Med Fac Med Technol Xianyang Peoples R China Fourth Mil Med Univ Air Force Med Univ Dept Neurosurg Tangdu Hosp Xian Shaanxi Peoples R China

Purpose This study aimed to investigate the value of magnetic resonance (MR) characteristics in differentiating the subtypes of growth hormone pituitary adenomas. Materials and Methods The clinical and MR imaging data of 70 patients with growth hormone pituitary adenoma confirmed by surgery and pathology were retrospectively analyzed. The tumors were divided into dense granular (DG;36 cases) and sparse granular subtypes (SG;34 cases). The tumors' MR features were analyzed, including the mean and maximum diameters, T2 signal intensity, T2 relative signal intensity (rSI), homogeneity, enhancement degree, and invasiveness (Knosp grade). Mann-Whitney U test and chi(2) test were used to analyze MR characteristics between the 2 groups. The independent predictors and predictive probabilities of tumor subtypes were obtained via a logistic regression model, and the efficacy was compared by receiver operating characteristic curve. Results The mean and maximum diameters of growth hormone adenoma in DG and SG were 1.77 versus 2.45 and 1.95 versus 3.00 cm (median, P < 0.05), respectively. There was a significant difference between the 2 groups in T2 signal intensity and rSI (P values were 0.02 and 0.001, respectively). Most DG adenomas (86.1%) appeared as hypointense on T2 images, and 38.2% of SG adenomas were hyperintense. There was no significant difference in tumor homogeneity (P = 0.622). A significant difference was found in the Knosp grade between the 2 subtypes (P = 0.004). In addition, the enhancement degree of SG adenomas was significantly higher than that of DG adenomas (P = 0.001). logistic regression analysis showed that high T2 rSI value and marked contrast enhancement were independent predictors of the 2 subtypes, and the odds ratios were 4.811 and 4.649, respectively. The multivariate logistic model obtained relatively high predicting efficacy, and the area under the curve, sensitivity, and specificity were 0.765, 0.882, and 0.500, respectively. Conclusions There

关键词： growth hormone pituitary adenoma pathological subtype magnetic resonance imaging logistic regression model

来源：评论

学校读者我要写书评

暂无评论

Credit risk management of scientific and technological enterprises based on text mining

引用

ENTERPRISE INFORMATION SYSTEMS 2021年第6期15卷 851-867页

作者： Li, Chenggang Liu, Qing Huang, Lei Guizhou Univ Finance & Econ Guizhou Key Lab Big Data Stat Anal Guiyang Peoples R China Guizhou Univ Finance & Econ Sch Big Data Applicat & Econ Guiyang 550025 Peoples R China Univ Elect Sci & Technol China Sch Math Sci Chengdu Peoples R China

The purpose of this paper is to verify the impact of financial news on corporate credit risk. Web crawler technology is used to obtain the financial news text from Sina Financial News. The text mining technology is utilized to quantify the financial news text. The quantified financial news text combined with financial indicators is used to build the logistic regression model. The assessment results show that the risk early warning accuracy of the logistic regression model incorporating both the quantified financial news text and financial indicators is higher than the logistic regression model only with pure financial indicators.

关键词： Scientific and technological enterprises credit risk web crawler text mining logistic regression model

来源：评论

学校读者我要写书评

暂无评论

Choice behavior of commuters’rail transit mode during the COVID-19 pandemic based on logistic model

引用

Journal of Traffic and Transportation Engineering(English Edition) 2021年第2期8卷 186-195页

作者： Limin Tan Changxi Ma School of Traffic and Transportation Lanzhou Jiaotong UniversityLanzhou 730070China

To understand whether commuters will take rail transit during the COVID-19 pandemic,a logistic regression model was constructed from three aspects of personal attributes,travel attributes and perception of COVID-19 based on 559 valid *** results show that:occupation,commuting tools before the COVID-19 pandemic,walking time from residence to the nearest subway station,the possibility of being infected in private car and the possibility of being infected in public transport have significant influence on the commuters’choice of rail ***-employed people and freelancers,commuters who used non-public transport before the COVID-19 pandemic,and commuters who take longer to walk from their residences to the nearest subway station are less likely to commute by rail transit during the COVID-19 *** who think that the risk of being infected with the virus in public transport is higher have a lower probability of choosing rail *** confidence in bus/subway/taxi/taxi-hailing of commuters who do not choose to commute by rail transit during the COVID-19 pandemic is not *** study of this paper can provide reference for the formulation of urban rail transit control measures during the COVID-19 pandemic,so as to formulate more perfect measures to ensure the safety of the returning workers.

关键词： Traffic engineering Commuters Rail transit Questionnaire Influencing factors logistic regression model

来源：评论

学校读者我要写书评

暂无评论

Encouraging carpooling for commuting in the Paris area (France): which incentives and for whom?

引用

TRANSPORTATION 2023年第1期50卷 43-62页

作者： Bulteau, Julie Feuillet, Thierry Dantan, Sophie Abbes, Souhir UVSQ Univ Paris Saclay CEARC F-78280 Guyancourt France Univ Paris 08 LADYSS UMR 7533 CNRS St Denis France Univ Cergy Pontoise THEMA UMR 8184 Cergy Pontoise France Univ Sfax Lab Econ & Dev Sfax 3018 Tunisia

The use of individual cars and solo driving is a source of negative externalities. The practice of carpooling for commuting could be a solution to tackle environmental, health and congestion problems. The objective of this study was to explore the incentives to encourage carpooling for commuting in the Paris region. Beyond socio-demographics, individual profiles were characterized by variables related to the residence and work places. We measured the willingness of drivers (n = 1312) to carpool for commuting (1) as a driver and (2) as a passenger. Three logistic regression models were estimated for each case, carpooling as a driver and carpooling as a passenger, integrating different incentives (financial and non-financial). Our results demonstrate that the determinants of carpooling as a driver and as a passenger differ. According to individual profiles, the incentives to encourage carpooling for commuting in the Paris region are not the same. Contextual variables play a major role in the willingness to carpool as a driver, while individual variables only were exhibited regarding carpooling as a passenger. Another major finding is the importance of carpooling with a colleague, exhibiting the key role of trust. Women are more willing to carpool as a driver when there is this psychological incentive. Finally, we highlight that the awareness of carpooling services is significant in the willingness to carpool both as a driver and as a passenger. Public policies could consider these results as potential levers to promote carpooling in the Paris region.

关键词： Carpooling Commuting logistic regression model Contextual effect Psychological incentives Financial incentives

来源：评论

学校读者我要写书评

暂无评论

Study on financial risk prediction of enterprises based on logistic regression

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2021年第5期21卷 1255-1261页

作者： Qi, Qiaoyun Chuzhou Polytech 2188 Fengle Rd Chuzhou 239000 Anhui Peoples R China

Financial risk has a great influence on the development of enterprises, and the prediction of financial risk can help enterprises to treat risks early. In order to realize the prediction of enterprise financial risk, find the risk as early as possible and make a response as soon as possible, according to the principle of predictability and reliability, this study selected 15 financial indicators from aspects of debt repayment level, profit level, operation level, growth level, and cash level, then predicted the risk by the logistic regression model, and analyzed the risk of 36 pairs of enterprises. The results showed that the model designed in this study had an accuracy rate of 91.67%, and the risk of a company was successfully predicted based on the financial situation of the company from 2018 to 2020, which verified the reliability of the method. Thus the model can effectively predict the financial risk of enterprises, and it can be further promoted and applied to ensure the long-term development of enterprises and establish a good market environment.

关键词： logistic regression model financial risk financial crisis financial prediction

来源：评论

学校读者我要写书评

暂无评论

Epigenetic risk score improves prostate cancer risk assessment

引用

PROSTATE 2017年第12期77卷 1259-1264页

作者： Van Neste, Leander Groskopf, Jack Grizzle, William E. Adams, George W. DeGuenther, Mark S. Kolettis, Peter N. Bryant, James E. Kearney, Gary P. Kearney, Michael C. Van Criekinge, Wim Gaston, Sandra M. Maastricht Univ GROW Sch Oncol & Dev Biol Dept Pathol Med Ctr Maastricht Netherlands MDxHealth Irvine CA USA Univ Alabama Birmingham Birmingham AL USA Urol Ctr Alabama Birmingham AL USA Harvard Med Sch Longwood Urol Boston MA USA Univ Ghent Ghent Belgium Tufts Univ Sch Med Tufts Med Ctr Boston MA 02111 USA

BackgroundEarly detection of aggressive prostate cancer (PCa) remains crucial for effective treatment of patients. However, PCa screening remains controversial due to a high rate of overdiagnosis and overtreatment. To better reconcile both objectives, more effective methods for assessing disease severity at the time of diagnosis are needed. MethodsThe relationship between DNA-methylation and high-grade PCa was examined in a cohort of 102 prospectively enrolled men who received standard 12-core prostate biopsies. EpiScore, an algorithm that quantifies the relative DNA methylation intensities of GSTP1, RASSF1, and APC in prostate biopsy tissue, was evaluated as a method to compensate for biopsy under-sampling and improve risk stratification at the time of diagnosis. ResultsDNA-methylation intensities of GSTP1, RASSF1, and APC were higher in biopsy cores from men diagnosed with GS7 cancer compared to men with diagnosed GS 6 disease. This was confirmed by EpiScore, which was significantly higher for subjects with high-grade biopsies and higher NCCN risk categories (both P<0.001). In patients diagnosed with GS7, increased levels of DNA-methylation were present, not only in the high-grade biopsy cores, but also in other cores with no or low-grade disease (P<0.001). By combining EpiScore with traditional clinical risk factors into a logistic regression model, the prediction of high GS reached an AUC of 0.82 (95%CI: 0.73-0.91) with EpiScore, DRE, and atypical histological findings as most important contributors. ConclusionsIn men diagnosed with PCa, DNA-methylation profiling can detect under-sampled high-risk PCa in prostate biopsy specimens through a field effect. Predictive accuracy increased when EpiScore was combined with other clinical risk factors. These results suggest that EpiScore could aid in the detection of occult high-grade disease at the time of diagnosis, thereby improving the selection of candidates for Active Surveillance.

关键词： epigenetic Gleason grade logistic regression model prognosis prostate cancer risk score

来源：评论

学校读者我要写书评

暂无评论

modeling the competitiveness of a bike-sharing system using bicycle GPS and transit smartcard data

引用

TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH 2022年第4期14卷 347-351页

作者： Kapuku, Christian Kho, Seung-Young Kim, Dong-Kyu Cho, Shin-Hyung Seoul Natl Univ Dept Civil & Environm Engn 1 Gwanak Ro Seoul 08826 South Korea Seoul Natl Univ Inst Engn Res Seoul South Korea

Competitiveness is an important factor for the sustainable mobility of an integrated multimodal system. In this study, we explore and answer the question concerning what makes bike-sharing trips more competitive than bus trips. The empirical analysis is conducted using transit smartcard and bike-sharing GPS data collected in Seoul, and logistic regression models were developed to understand the factors contributing to the bike-sharing being more competitive than buses. The findings demonstrate that bike-sharing is not only a complementary mode but could also be competing with buses at certain extents. The results indicate that bike-sharing trips can be more competitive than bus trips with longer detours or when the speed of the bus is reduced, such as peak-time periods and short trips. Travel time of bike-sharing is more reliable than bus's during peak times, while the bike lanes contribute to keeping bike-sharing more competitive even during off-peak times.

关键词： Competitiveness public transport bike-sharing logistic regression model mobility as a service integrated multimodal transportation system

来源：评论

学校读者我要写书评

暂无评论

Analysis and modelling of the contributing factors associated with road traffic crashes in Rwanda

引用

INTERNATIONAL JOURNAL OF CRASHWORTHINESS 2024年

作者： de Dieu, Gatesi Jean Bin, Shuai Labbo, Muwaffaq Safiyanu Southwest Jiaotong Univ Sch Transportat & Logist Chengdu Peoples R China

Rwanda, like other African countries, faced the challenges of road traffic crashes, which increased year-over-year. In this present study, the authors employed logistic regression and discriminant analysis to model the contributing factors associated with crash severity in Rwanda over a study period from January 2010 to December 2022. The logistic regression results revealed that all predicted variables were statistically significant and showed an impact on the occurrence of crashes in Rwanda. The model was correctly classified, with an overall accuracy of 75.4%. For discriminant analysis, the results revealed that all explanatory variables have a high and lesser impact, with a significance probability less than 0.05. The discriminant function was reclassified with an overall accuracy of 64.2%. The predicted models can be used as proactive tools for guiding road safety policy-makers in planning, designing, and executing road infrastructure.

关键词： Crash severity time series forecasting logistic regression model discriminant analysis Rwanda

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：