Modern students encounter large, messy datasets long before setting foot in our classrooms. Many of these students need to develop skills in exploratory data analysis and multivariate analysis techniques for their job...
详细信息
Modern students encounter large, messy datasets long before setting foot in our classrooms. Many of these students need to develop skills in exploratory data analysis and multivariate analysis techniques for their jobs after college, but such topics are not covered in traditional introductory statistics courses. This case study describes my experience in designing and teaching an undergraduate course on multivariate data analysis with minimal prerequisites, using real data, active learning, and other interactive activities to help students tackle the material. Multivariate topics covered include clustering and classification (among others) for exploratory data analysis and an introduction to algorithmic modeling. Supplementary materials for this article are available online.
This paper describes a new technique to simulate MATLAB system models in PSpice environment. The algorithmic component of the design is developed using MATLAB, and then exported to a C-model which can be read and simu...
详细信息
ISBN:
(纸本)9781479967612
This paper describes a new technique to simulate MATLAB system models in PSpice environment. The algorithmic component of the design is developed using MATLAB, and then exported to a C-model which can be read and simulated by PSpice using its newly developed PSpice Device modeling Interface (DMI). The paper describes in detail the changes required to make the MATLAB C-Model compatible with PSpice device modeling requirements. Once circuit simulations using PSpice are signed-off, the algorithmic module can be targeted to FPGA, SOC or PCB for implementation.
Two models of anomaly detection are put to use in detecting anomalies in aircraft operation. Self-Organizing Map Neural Network (SOM NN) is used from the culture of algorithmic modeling and One-Class Support Vector Ma...
详细信息
ISBN:
(纸本)9781467384308
Two models of anomaly detection are put to use in detecting anomalies in aircraft operation. Self-Organizing Map Neural Network (SOM NN) is used from the culture of algorithmic modeling and One-Class Support Vector Machine (SVM) is used from the culture of data modeling. The goal of the research is to find anomalies within the data of aircraft operation or otherwise known as Flight Operations Quality Assurance (FOQA) data, and to find out which model performs better. SOM NN found 8800 data points of anomalies over 69 flights and One-Class SVM found 40392 data points of anomalies over 651 flights. The anomalies are divided into three categories: performance anomaly, sensor anomaly, and miscellaneous anomaly, each happened because of different causes. It is concluded that both models could detect anomalies within FOQA data and the One-Class SVM outperforms SOM NN in number of anomalies found, however in runtime length, SOM NN performs better, the best choice of model is then concluded according to computing resource availability since SOM NN could still be improved without an expensive resource compared to One-Class SVM
A leading cause of hospital admission in the elderly is heart failure and it is considered a major financial burden since the hospitalization costs are high. This is intensified with a lack of medical professionals du...
详细信息
ISBN:
(纸本)9781467383615
A leading cause of hospital admission in the elderly is heart failure and it is considered a major financial burden since the hospitalization costs are high. This is intensified with a lack of medical professionals due to a continuing significant increase of patients with heart failure as a result of obesity, diabetes and aging population. Integration of an intelligent decision support system into a home telemonitoring system seems a more-and-more supported solution. Therefore, the use of ambiguity for risk assessment of patients with heart failure is investigated. An algorithmic model is made using ambiguity and notions of fuzzy logic. The algorithmic model stores knowledge about patients as a group of interpretable fuzzy rules and uses them for risk assessment. The study shows that its achieved results are promising in comparison to a Bayesian network classifier, a nearest neighbor classifier, multilayer neural network, 1R classifier, a decision list, and a logistic regression model.
This Technical note presents a parametric algorithmic tool to generate two-dimensional notches allowing the use of the DDT to solve the problem of a crack emanating from an arbitrarily shaped notch subjected to Mode I...
详细信息
This Technical note presents a parametric algorithmic tool to generate two-dimensional notches allowing the use of the DDT to solve the problem of a crack emanating from an arbitrarily shaped notch subjected to Mode I loading. The numerical formulation of the DDT for assessing notches of any shape as well as the basic steps implemented within a graphical algorithm editor to create and discretise the notch geometry are described. Finally, the applicability and accuracy of the procedure is assessed by investigating V-notches, U-notches, semi-elliptical notches and dovetail-like notches. The tool proves to be a simple, general and efficient way of assessing Stress Intensity Factors (SIFs) for cracks emanating from notches with low computational cost and numerical modeling expertise in comparison with other numerical methods, as the Finite Element Method. (C) 2014 Elsevier Ltd. All rights reserved.
This paper examines the decision to refer a sexual assault case for prosecution using a sample of 730 reported sexual assaults in which the victim received a medical/forensic examination. The decision to refer a case ...
详细信息
This paper examines the decision to refer a sexual assault case for prosecution using a sample of 730 reported sexual assaults in which the victim received a medical/forensic examination. The decision to refer a case for prosecution was modeled using an algorithmic modeling technique, Random Forests. The key advantages of this modeling approach include its superiority in predicting case outcomes and its ability to easily uncover nonlinear relationships. Key results indicate that the likelihood of referral increased when sperm was found and documented, when the victim could identify the suspect, and as the severity of nongenital injury increased. Neither the presence nor the severity of genital injury impacted the decision to refer a case for prosecution. On the whole, suspect and report characteristics had the largest impact on referring cases for prosecution, with victim characteristics having little influence.
暂无评论