scholarly journals A Multi-Factor Analysis of Forecasting Methods: A Study on the M4 Competition

Data ◽  
2020 ◽  
Vol 5 (2) ◽  
pp. 41
Author(s):  
Pantelis Agathangelou ◽  
Demetris Trihinas ◽  
Ioannis Katakis
Keyword(s):  
Risk Assessment ◽  
Factor Analysis ◽  
Everyday Life ◽  
Predictive Performance ◽  
Computational Performance ◽  
Forecasting Methods

As forecasting becomes more and more appreciated in situations and activities of everyday life that involve prediction and risk assessment, more methods and solutions make their appearance in this exciting arena of uncertainty. However, less is known about what makes a promising or a poor forecast. In this article, we provide a multi-factor analysis on the forecasting methods that participated and stood out in the M4 competition, by focusing on Error (predictive performance), Correlation (among different methods), and Complexity (computational performance). The main goal of this study is to recognize the key elements of the contemporary forecasting methods, reveal what made them excel in the M4 competition, and eventually provide insights towards better understanding the forecasting task.

scholarly journals Generalized Read-Across prediction using genra-py

2021 ◽  
Author(s):  
Imran Shah ◽  
Tia Tate ◽  
Grace Patlewicz
Keyword(s):  
Risk Assessment ◽  
Human Health Risk ◽  
Chemical Properties ◽  
Predictive Performance ◽  
Hazard Identification ◽  
Data Driven ◽  
Chemical Safety ◽  
Physico Chemical ◽  
Data Driven Approach ◽  
Assessment Problems

Abstract Motivation Generalized Read-Across (GenRA) is a data-driven approach to estimate physico-chemical, biological or eco-toxicological properties of chemicals by inference from analogues. GenRA attempts to mimic a human expert’s manual read-across reasoning for filling data gaps about new chemicals from known chemicals with an interpretable and automated approach based on nearest-neighbors. A key objective of GenRA is to systematically explore different choices of input data selection and neighborhood definition to objectively evaluate predictive performance of automated read-across estimates of chemical properties. Results We have implemented genra-py as a python package that can be freely used for chemical safety analysis and risk assessment applications. Automated read-across prediction in genra-py conforms to the scikit-learn machine learning library's estimator design pattern, making it easy to use and integrate in computational pipelines. We demonstrate the data-driven application of genra-py to address two key human health risk assessment problems namely: hazard identification and point of departure estimation. Availability and implementation The package is available from github.com/i-shah/genra-py.

The Public Perception of Science and Technology in a Periphery Society: A Critical Analysis from a Quantitative Perspective

2007 ◽  
Vol 12 (1) ◽  
pp. 141-163 ◽  
Author(s):  
Leonardo Silvio Vaccarezza
Keyword(s):  
Factor Analysis ◽  
Everyday Life ◽  
Scientific Knowledge ◽  
Critical Analysis ◽  
Public Perception ◽  
Science And Technology ◽  
Public Understanding ◽  
The Public ◽  
Different Dimensions ◽  
Level Of Understanding

In this article a series of variables referred to the general public's valuations of science and technology are analysed. These valuations refer to different dimensions of science and technology—as a utility of scientific knowledge, their legitimacy, their bond with the cultural matrix of everyday life. The analysis is based on information from a survey carried out in a great urban conglomerate of a little scientific developing country, Argentina. We see that valuation variables discriminate the public according to their positive or negative responses about science, but that there is no evident association between them. We consider one variable in particular dividing the public into those who are ‘trustful’ and those who are ‘cautious’ regarding the advances of science, and we see how it is related to other significations of valuation. The pre-eminence of positions of ambivalence or contradiction in the population's perception regarding this topic is discussed. A factor analysis is presented that comprises these variables and that presents a set of ‘valuation orientations’ towards science as a result. Finally, it is interesting to see how education and the level of understanding of scientific knowledge affect the public's valuation, which questions the basic supposition of the tradition of public understanding studies.

REALIZATION OF LOGISTICAL VENTURE IN CONDITIONS OF RISKS

2011 ◽  
Vol 159 (1) ◽  
pp. 239-252
Author(s):  
Dariusz SKORUPKA ◽  
Artur DUCHACZEK
Keyword(s):  
Risk Factors ◽  
Risk Assessment ◽  
Factor Analysis ◽  
Risk Factor ◽  
Potential Risk ◽  
Original Method ◽  
Ahp Method ◽  
Low Level ◽  
Military Bridge ◽  
Potential Applications

The material presents an analysis of a potential risk assessment of operating military bridge facilities. Three types of steel military bridges were analysed: assembled bridges, vehicle-launched bridges and low-level bridges. The material presents an original method of a fatigue risk factor analysis. Furthermore, the author presents potential applications of the AHP method to determine weights for risk factors under analysis. It is assumed that at the further stage of research a thorough identification and quantification of other risk factors will be conducted.

scholarly journals Risk Assessment Using Early Quantitative Chest CT Parameters for the Severity of COVID-19

2021 ◽  
Vol 18 (3) ◽  
Author(s):  
Xun Ding ◽  
Jia Xu ◽  
Haibo Xu ◽  
Jun Zhou ◽  
Qingyun Long
Keyword(s):  
Risk Assessment ◽  
Lung Volume ◽  
Roc Curve ◽  
Predictive Performance ◽  
Chest Ct ◽  
Critical Group ◽  
Quantitative Ct ◽  
Critical Stage ◽  
Volume Percentage ◽  
Risk Of Progression

Background: Today, the outbreak of coronavirus disease 2019 (COVID-19) is known as a public health emergency by the World Health Organization (WHO). Therefore, risk assessment is necessary for making a correct decision in disease management. Objectives: This study aimed to assess the risk of progression to the critical stage in COVID-19 patients, based on the early quantitative chest computed tomography (CT) parameters. Patients and Methods: In this case-control study, 39 laboratory-confirmed critical or expired COVID-19 cases (critical group), as well as 117 laboratory-confirmed COVID-19 patients including mild, moderate, and severe cases (non-critical group), were enrolled. Seven quantitative CT parameters, representing the lung volume percentages at different density intervals, were automatically calculated, using the artificial intelligence (AI) algorithms. Multivariable-adjusted logistic regression models, based on the quantitative CT parameters, were established to predict the adverse outcomes (critical vs. non-critical). The predictive performance was estimated using the receiver operating characteristic (ROC) curve analysis and by measuring the area under the ROC curve (AUC). The quantitative CT parameters in different stages were compared between the two groups. Results: No significant differences were found between the two groups regarding the lung volume percentages at different density intervals within 0 - 4 days (P = 0.596-0.938); however, this difference began to become significant within 5 - 9 days and persisted even after one month. Overall, the quantitative CT parameters could well predict the severity of COVID-19. The lung volume percentage of -7 Hounsfield units (-7 HUs) had the largest crude odds ratio (OR: 1.999; 95% CI, 1.453 ~ 2.750; P < 0.001) and adjusted OR (adjusted OR: 1.768; 95% CI, 1.114 ~ 2.808; P = 0.016). The lung volume percentage of -6 HU showed the best predictive performance with the largest AUC of 0.808; the cutoff value of 5.93% showed 71.79% sensitivity and 84.62% specificity. Conclusion: Early quantitative chest CT parameters can be measured to assess the risk of progression to the critical stage of COVID-19; this is of critical importance in the clinical management of this disease.

Sign in / Sign up

Export Citation Format

Share Document