Model Selection and Evaluation for Machine Learning: Deep Learning in Materials Processing

Kopper, Adam; Karkare, Rasika; Paffenroth, Randy; Apelian, Diran

doi:10.1007/s40192-020-00185-1

Cited by 24 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent sophisticated work, Kooper-Apelian 35 studied HPDC mechanical properties of a die cast tensile testing machine bar and the relationship to process features using large dataset spanning many months of production. They compared the regression models of Random Forest, Support Vector Machine (SVM), Neural Network, and XGBoost.…”

Section: Related Workmentioning

confidence: 99%

Industry 4.0 Foundry Data Management and Supervised Machine Learning in Low-Pressure Die Casting Quality Improvement

et al. 2022

View full text Add to dashboard Cite

Low-pressure die cast (LPDC) is widely used in high performance, precision aluminum alloy automobile wheel castings, where defects such as porosity voids are not permitted. The quality of LPDC parts is highly influenced by the casting process conditions. A need exists to optimize the process variables to improve the part quality against difficult defects such as gas and shrinkage porosity. To do this, process variable measurements need to be studied against occurrence rates of defects. In this paper, industry 4.0 cloud-based systems are used to extract data. With these data, supervised machine learning classification models are proposed to identify conditions that predict defectives in a real foundry Aluminum LPDC process. The root cause analysis is difficult, because the rate of defectives in this process occurred in small percentages and against many potential process measurement variables. A model based on the XGBoost classification algorithm was used to map the complex relationship between process conditions and the creation of defective wheel rims. Data were collected from a particular LPDC machine and die mold over three shifts and six continuous days. Porosity defect occurrence rates could be predicted using 36 features from 13 process variables collected from a considerably small sample (1077 wheels) which was highly skewed (62 defectives) with 87% accuracy for good parts and 74% accuracy for parts with porosity defects. This work was helpful in assisting process parameter tuning on new product pre-series production to lower defectives.

show abstract

Section: Related Workmentioning

confidence: 99%

Industry 4.0 Foundry Data Management and Supervised Machine Learning in Low-Pressure Die Casting Quality Improvement

et al. 2022

View full text Add to dashboard Cite

show abstract

“…e use of mobile APP technology can create a context for teachers' teaching and help teachers' activities with students to smoothly run. However, at this stage, the use of mobile APP technology in teaching still has problems such as not highlighting the subjectivity of students [17].…”

Section: Related Workmentioning

confidence: 99%

Intelligent Interactive English Teaching Discrete Data Modeling and Simulation

Xin

2022

Scientific Programming

View full text Add to dashboard Cite

This study attempts to explore the discrete data modeling and simulation of smart interactive English teaching based on mobile APP, expecting to explore the effective teaching strategies for deep integration of mobile APP technology and smart interactive English teaching, and to conduct discrete data modeling and simulation of English teaching. In this study, we propose a discrete data modeling algorithm for smart interactive English teaching based on discrete data points and normal vectors using B splines. By adding normal vector constraints, this method can maintain good fitting results even when the data points are discrete. The method consists of four parts, namely, discrete point parameterization, B-spline dominant point selection, node vector determination, and least-squares fitting, including both data point error and normal vector error. The mobile APP-based initial intelligent interactive English teaching should adhere to the four principles of autonomy of English course learning, adhere to teacher dominance in the language classroom, grasp the humanistic nature of English course content, and focus on the practical nature of English course implementation. The interactive learning environment based on mobile APP can promote students’ in-depth understanding of knowledge. The higher the student’s interest in learning, the deeper the degree of understanding; the more diverse the learning methods, the more it can promote students’ in-depth understanding of knowledge; the stronger the degree of interaction, the higher the level of understanding. The discrete data modeling of smart interactive English teaching proposed in this study provides a theoretical reference for the design and production of interactive learning resources for English courses, according to which the interactive learning resources for English courses are produced to make up for the lack of English course resources.

show abstract

“…In machine learning, the hold-out method is used to identify discrepancies between feedback and predictions of models (Kopper et al, 2020;Yadav & Shukla, 2016). In our article, the method was used in a different spirit, with the idea that models are trained using feedback whereas they can be tested using participants' responses when no feedback is provided.…”

Section: Limitations and Perspectivesmentioning

confidence: 99%

Hold-out strategy for selecting learning models: Application to categorization subjected to presentation orders

Mezzadri

Laloë

Mathy

et al. 2022

Journal of Mathematical Psychology

View full text Add to dashboard Cite

Model Selection and Evaluation for Machine Learning: Deep Learning in Materials Processing

Cited by 24 publications

References 28 publications

Industry 4.0 Foundry Data Management and Supervised Machine Learning in Low-Pressure Die Casting Quality Improvement

Industry 4.0 Foundry Data Management and Supervised Machine Learning in Low-Pressure Die Casting Quality Improvement

Intelligent Interactive English Teaching Discrete Data Modeling and Simulation

Hold-out strategy for selecting learning models: Application to categorization subjected to presentation orders

Contact Info

Product

Resources

About