In this work, two algorithms (overlapping method and the probability-based method) for design space calculation were compared by using the data collected from extraction process of Codonopsis Radix as an example. In the probability-based method, experimental error was simulated to calculate the probability of reaching the standard. The effects of several parameters on the calculated design space were studied, including simulation number, step length, and the acceptable probability threshold. For the extraction process of Codonopsis Radix, 10 000 times of simulation and 0.02 for the calculation step length can lead to a satisfactory design space. In general, the overlapping method is easy to understand, and can be realized by several kinds of commercial software without coding programs, but the reliability of the process evaluation indexes when operating in the design space is not indicated. Probability-based method is complex in calculation, but can provide the reliability to ensure that the process indexes can reach the standard within the acceptable probability threshold. In addition, there is no probability mutation in the edge of design space by probability-based method. Therefore, probability-based method is recommended for design space calculation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.19540/j.cnki.cjcmm.20180312.004 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
MutualDTA: An Interpretable Drug-Target Affinity Prediction Model Leveraging Pretrained Models and Mutual Attention.
J Chem Inf Model
January 2025
School of Information Science & Engineering, Lanzhou University, Lanzhou 730000, China.
Efficient and accurate drug-target affinity (DTA) prediction can significantly accelerate the drug development process. Recently, deep learning models have been widely applied to DTA prediction and have achieved notable success. However, existing methods often encounter several common issues: first, the data representations lack sufficient information; second, the extracted features are not comprehensive; and third, most methods lack interpretability when modeling drug-target binding.
View Article and Find Full Text PDFOptimizing mechanical performance: Epoxy-graphene oxide nanocomposites for enhanced strength in lattice structure.
Heliyon
January 2025
Faculty of Material and Manufacturing Technologies, Malek Ashtar University of Technology, P.O. Box 1774-15875, Tehran, Iran.
The potential of epoxy-graphene oxide (GO) nanocomposites to improve the mechanical characteristics of conventional epoxy resins is causing them to gain prominence. This makes them appropriate for advanced engineering applications, including structural materials, automotive, and aerospace. This study aimed to develop an epoxy/GO composite with improved mechanical properties through synthesizing epoxy/GO samples with varying GO content (from 0.
View Article and Find Full Text PDFPerspective on the role of norms for institutional behavior and policy design in European cross-border regions.
Front Sociol
January 2025
School of Education, Humanities and Social Sciences, Halmstad University, Halmstad, Sweden.
The article analyses how a norm scientific perspective can advance our understanding of cross-border regions and guide future directions of research. Cross-border regions are territorial spaces comprising territory from two or more national states, located directly at the borders of those spaces. Since the 1950s it has become increasingly common that cross-border organizations, constituted by local municipalities and regional authorities and sometimes private entities, are established to coordinate governance processes around shared policy problems.
View Article and Find Full Text PDFThe design space of E(3)-equivariant atom-centred interatomic potentials.
Nat Mach Intell
January 2025
Engineering Laboratory, University of Cambridge, Cambridge, UK.
Molecular dynamics simulation is an important tool in computational materials science and chemistry, and in the past decade it has been revolutionized by machine learning. This rapid progress in machine learning interatomic potentials has produced a number of new architectures in just the past few years. Particularly notable among these are the atomic cluster expansion, which unified many of the earlier ideas around atom-density-based descriptors, and Neural Equivariant Interatomic Potentials (NequIP), a message-passing neural network with equivariant features that exhibited state-of-the-art accuracy at the time.
View Article and Find Full Text PDFAccurate forecasting of contagious illnesses has become increasingly important to public health policymaking, and better prediction could prevent the loss of millions of lives. To better prepare for future pandemics, it is essential to improve forecasting methods and capabilities. In this work, we propose a new infectious disease forecasting model based on physics-informed neural networks (PINNs), an emerging area of scientific machine learning.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!