Preliminary Local Calibration of Performance Prediction Models in AASHTOWare Pavement ME Design for Flexible Pavement Rehabilitation in Oregon

2019 ◽  
Vol 145 (2) ◽  
pp. 05019002 ◽  
Author(s):  
Md S. Rahman ◽  
Joseph H. Podolsky ◽  
Todd Scholz
Keyword(s):  
Performance Prediction ◽  
Prediction Models ◽  
Flexible Pavement ◽  
Local Calibration ◽  
Pavement Rehabilitation ◽  
Pavement Me Design

Iowa Experience on Local Calibration of AASHTOWare Pavement ME Design (PMED) for Jointed Plain Concrete Pavements

2021 ◽  
Author(s):  
Orhan Kaya ◽  
Leela Sai Praveen Gopisetti ◽  
Halil Ceylan ◽  
Sunghwan Kim ◽  
Bora Cetin
Keyword(s):  
Performance Prediction ◽  
Prediction Models ◽  
Plain Concrete ◽  
Pavement Performance ◽  
Local Calibration ◽  
Performance Models ◽  
Local Conditions ◽  
Calibration And Validation ◽  
State Highway ◽  
Pavement Me Design

The AASHTO Mechanistic-Empirical Pavement Design Guide (MEPDG) pavement performance models and the associated AASHTOWare pavement ME design (PMED) software are nationally calibrated using design inputs and distress data largely obtained from National Long-Term Pavement Performance (LTPP) to predict Jointed Plain Concrete Pavement (JPCP) performance measures. To improve the accuracy of nationally-calibrated JPCP performance models for various local conditions, further calibration and validation studies in accordance with the local conditions are highly recommended, and multiple updates have been made to the PMED since its initial release in 2011, with the latest version (i.e., Ver. 2.5.X) becoming available in 2019. Validation of JPCP performance models after such software updates is necessary as part of PMED implementation, and such local calibration and validation activities have been identified as the most difficult or challenging parts of PMED implementation. As one of the states at the forefront of implementing the MEPDG and PMED, Iowa has conducted local calibration of JPCP performance models extending from MEPDG to updated versions of PMED. The required MEPDG and PMED inputs and the historical performance data for the selected JPCP sections were extracted from a variety of sources and the accuracy of the nationally-calibrated MEPDG and PMED performance prediction models for Iowa conditions was evaluated. To improve the accuracy of model predictions, local calibration factors of MEPDG and PMED performance prediction models were identified and gained local calibration experiences of MEPDG and PMED in Iowa are presented and discussed here to provide insight of local calibration for other State Highway Agencies (SHAs).

scholarly journals Machine Learning–enabled Scalable Performance Prediction of Scientific Codes

2021 ◽  
Vol 31 (2) ◽  
pp. 1-28
Author(s):  
Gopinath Chennupati ◽  
Nandakishore Santhi ◽  
Phill Romero ◽  
Stephan Eidenbenz
Keyword(s):  
Machine Learning ◽  
Performance Prediction ◽  
Prediction Models ◽  
Radiation Transport ◽  
Discrete Event ◽  
Basic Block ◽  
Distribution Models ◽  
Scientific Application ◽  
High Level ◽  
Access Patterns

Hardware architectures become increasingly complex as the compute capabilities grow to exascale. We present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters as input and predicts runtime of that code on the target hardware platform, which is defined in the input parameters. PPT-AMMP transforms the code to an (architecture-independent) intermediate representation, then (i) analyzes the basic block structure of the code, (ii) processes architecture-independent virtual memory access patterns that it uses to build memory reuse distance distribution models for each basic block, and (iii) runs detailed basic-block level simulations to determine hardware pipeline usage. PPT-AMMP uses machine learning and regression techniques to build the prediction models based on small instances of the input code, then integrates into a higher-order discrete-event simulation model of PPT running on Simian PDES engine. We validate PPT-AMMP on four standard computational physics benchmarks and present a use case of hardware parameter sensitivity analysis to identify bottleneck hardware resources on different code inputs. We further extend PPT-AMMP to predict the performance of a scientific application code, namely, the radiation transport mini-app SNAP. To this end, we analyze multi-variate regression models that accurately predict the reuse profiles and the basic block counts. We validate predicted SNAP runtimes against actual measured times.

scholarly journals Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance

Algorithms ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 318
Author(s):  
Thao-Trang Huynh-Cam ◽  
Long-Sheng Chen ◽  
Huynh Le
Keyword(s):  
Random Forest ◽  
Performance Prediction ◽  
Prediction Models ◽  
Family Background ◽  
Educational Practice ◽  
Poor Performance ◽  
Learning Performance ◽  
First Year ◽  
First Year Students ◽  
Early Performance

First-year students’ learning performance has received much attention in educational practice and theory. Previous works used some variables, which should be obtained during the course or in the progress of the semester through questionnaire surveys and interviews, to build prediction models. These models cannot provide enough timely support for the poor performance students, caused by economic factors. Therefore, other variables are needed that allow us to reach prediction results earlier. This study attempts to use family background variables that can be obtained prior to the start of the semester to build learning performance prediction models of freshmen using random forest (RF), C5.0, CART, and multilayer perceptron (MLP) algorithms. The real sample of 2407 freshmen who enrolled in 12 departments of a Taiwan vocational university will be employed. The experimental results showed that CART outperforms C5.0, RF, and MLP algorithms. The most important features were mother’s occupations, department, father’s occupations, main source of living expenses, and admission status. The extracted knowledge rules are expected to be indicators for students’ early performance prediction so that strategic intervention can be planned before students begin the semester.

Sign in / Sign up

Export Citation Format

Share Document