Using machine learning to discover shape descriptors for predicting emulsion stability in a microfluidic channel

Soft Matter ◽  
2019 ◽  
Vol 15 (6) ◽  
pp. 1361-1372 ◽  
Author(s):  
Jian Wei Khor ◽  
Neal Jean ◽  
Eric S. Luxenberg ◽  
Stefano Ermon ◽  
Sindy K. Y. Tang
Keyword(s):  
Machine Learning ◽  
Prediction Accuracy ◽  
Emulsion Stability ◽  
Microfluidic Channel ◽  
Shape Descriptor ◽  
Shape Descriptors ◽  
High Prediction Accuracy ◽  
High Prediction

A novel shape descriptor identified by machine learning captures diverse droplet shapes and achieves high prediction accuracy of droplet instability.

Profiling the baseline performance and limits of machine learning models for adaptive immune receptor repertoire classification

2021 ◽  
Author(s):  
Chakravarthi Kanduri ◽  
Milena Pavlović ◽  
Lonneke Scheffer ◽  
Keshav Motwani ◽  
Maria Chernigovskaya ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Prediction Accuracy ◽  
Immune Receptor ◽  
Adaptive Immune ◽  
High Prediction Accuracy ◽  
Wide Range ◽  
Benchmark Datasets ◽  
High Prediction ◽  
Penalized Logistic Regression

Background: Machine learning (ML) methodology development for classification of immune states in adaptive immune receptor repertoires (AIRR) has seen a recent surge of interest. However, so far, there does not exist a systematic evaluation of scenarios where classical ML methods (such as penalized logistic regression) already perform adequately for AIRR classification. This hinders investigative reorientation to those scenarios where further method development of more sophisticated ML approaches may be required. Results: To identify those scenarios where a baseline method is able to perform well for AIRR classification, we generated a collection of synthetic benchmark datasets encompassing a wide range of dataset architecture-associated and immune state-associated sequence pattern (signal) complexity. We trained ≈1300 ML models with varying assumptions regarding immune signal on ≈850 datasets with a total of ≈210000 repertoires containing ≈42 billion TCRβ CDR3 amino acid sequences, thereby surpassing the sample sizes of current state-of-the-art AIRR ML setups by two orders of magnitude. We found that L1-penalized logistic regression achieved high prediction accuracy even when the immune signal occurs only in 1 out of 50000 AIR sequences. Conclusions: We provide a reference benchmark to guide new AIRR ML classification methodology by: (i) identifying those scenarios characterised by immune signal and dataset complexity, where baseline methods already achieve high prediction accuracy and (ii) facilitating realistic expectations of the performance of AIRR ML models given training dataset properties and assumptions. Our study serves as a template for defining specialized AIRR benchmark datasets for comprehensive benchmarking of AIRR ML methods.

scholarly journals Modelling postural discomfort perception using CHAID decision tree algorithm

2019 ◽  
Vol 63 (1) ◽  
pp. 1749-1750
Author(s):  
Soomin Hyun ◽  
Woojin Park
Keyword(s):  
Decision Tree ◽  
Prediction Accuracy ◽  
Prediction Models ◽  
Body Part ◽  
Upper Body ◽  
Good Prediction ◽  
Practical Applications ◽  
High Prediction Accuracy ◽  
Good Prediction Accuracy ◽  
High Prediction

Developing quantitative models that predict discomfort levels of working postures has been an important ergonomics research topic. Such modeling not only has practical applications, but also may serve as a useful research method to improve our understanding of the human postural discomfort perception process. While the existing models have focused on achieving high prediction accuracy, less attention has been given to model interpretability, which is vital for understanding a process through modeling. Research is needed to identify the model types or modeling methods that offer high interpretability as well as good prediction accuracy. The goal of this study was to evaluate the utility of the Chi-square Automatic Interaction Detector (CHAID) decision tree modeling method in developing postural discomfort prediction models. Ten individual-specific decision tree models were developed, which predicted overall upper-body discomfort from local body part discomfort ratings. The prediction models were found to achieve high prediction accuracy and interpretability. (150 words)

Stock Price’s Prediction with Decision Tree

2011 ◽  
Vol 48-49 ◽  
pp. 1116-1121
Author(s):  
Tun Li ◽  
Gong Shen Liu
Keyword(s):  
Decision Tree ◽  
Stock Prices ◽  
Prediction Accuracy ◽  
Price Change ◽  
Financial Data ◽  
Average Error ◽  
Careful Selection ◽  
High Prediction Accuracy ◽  
High Prediction ◽  
Error Distance

Establishment of one process and some ameliorations of decision tree’s algorithm in order to predict the second day’s price change. The experiment builds a J48 tree, which is comfortable with continuous attributes, based on 10 years historical stock prices. After careful selection and preprocessing of financial data, high prediction accuracy is obtained. An introduction of dynamic-constructed tree reduces tree’s cost, and increases prediction’s quality on accuracy as well as average error distance.

The DGPS Maximum Speed Prediction Based on AR Model in Full-Scale Speed and Power Trial

2012 ◽  
Vol 424-425 ◽  
pp. 265-269
Author(s):  
Ming Yu Gu ◽  
Yan Ying Wang
Keyword(s):  
Detailed Analysis ◽  
Process Parameters ◽  
Prediction Accuracy ◽  
Prediction Method ◽  
Full Scale ◽  
Ar Model ◽  
Maximum Speed ◽  
High Prediction Accuracy ◽  
Speed Prediction ◽  
High Prediction

It is difficult to decide when the speed of a ship reaches to stability only by the experience of a test personnel in a speed and power trial. In this paper, a speed prediction method based on AR model is proposed to obtain the maximum speed automatically during the speed and power trial. In order to get high prediction accuracy, a detailed analysis is made on prediction process parameters. The results show that the related error between the prediction maximum speed and the actual value is low enough to meet the engineering requirements

scholarly journals Research on Sports Performance Prediction Based on BP Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Sitong Yang ◽  
Lina Luo ◽  
Baohua Tan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Performance Prediction ◽  
Bp Neural Network ◽  
Prediction Accuracy ◽  
Sports Performance ◽  
High Prediction Accuracy ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
High Prediction

Artificial neural network has the advantages of self-training and fault tolerance, while BP neural network has simple learning algorithms and powerful learning capabilities. The BP neural network algorithm has been widely used in practice. This paper conducts research on sports performance prediction based on 5G and artificial neural network algorithms. This paper uses the BP neural network algorithm as a pretest modelling method to predict the results of the 30th Olympic Men’s 100m Track and Field Championships and is supported by the MATLAB neural network toolbox. According to the experimental results, the scheme proposed in this paper has better performance than the other prediction strategies. In order to explore the feasibility and application of the BP neural network in this kind of prediction, there is a lot of work to be done. The model has a high prediction accuracy and provides a new method for the prediction of sports performance. The results show that the BP neural network algorithm can be used to predict sports performance, with high prediction accuracy and strong generalization ability.

BDA Models and Application for Recognizing the Headstreams of Mine Waterburst

2010 ◽  
Vol 34-35 ◽  
pp. 1788-1793
Author(s):  
W. Wan ◽  
L. Jie
Keyword(s):  
Discriminant Analysis ◽  
Prediction Accuracy ◽  
Cross Validation ◽  
Data Sources ◽  
Validation Method ◽  
High Prediction Accuracy ◽  
High Prediction ◽  
Bayes Discriminant Analysis

BAYES discriminant analysis (BDA) method was used in the study of headstreams of prediction of minewater inrush and two BDA models for recognizing two-headstreams and multi-headstreams were constructed. Baesd on the principle of BDA theory and the classical headstream samples of different mines, the discriminant process and cross-validation method were introduced. 10 samples from a mine of HUA BEI Mine and 39 samples of JIAO ZUO Mine were used as data sources. Ca2+, Mg2+, Na+, K+, Cl-, HCO3-, SO42-, NO32-, F- and pH were selected as discriminant genes for two-headstreams BDA model and Na++K+, Ca2+, Mg2+, Cl-, SO42-, HCO3- were regarded as discriminant genes for multi-headstreams BDA model. Compared with the results of SQT method, ANN method and SVM method, the results show that the frame of BDA model was steady and high prediction accuracy can be obtained. BDA method and can be used in practical mine engineering.

Analysis of Pipe Settlement Based on Numerical Simulation

2015 ◽  
Vol 744-746 ◽  
pp. 944-947 ◽  
Author(s):  
Jian Guo ◽  
Peng Xia ◽  
Shuang Shuang Shen
Keyword(s):  
Numerical Simulation ◽  
Simulation Model ◽  
Prediction Accuracy ◽  
Model Performance ◽  
Monitoring Data ◽  
High Prediction Accuracy ◽  
Surrounding Environment ◽  
High Prediction

Settlement of comprehensive pipe is inevitable disturbed by construction and surrounding environment, in order to better understand the settlement rule of comprehensive pipe. Based on a large amount of monitoring data collected from integrated trench, a simulation model is proposed to analyzed comprehensive pipe settlement by using ABAQUS, the case results show that the simulation model performance can analysis the synthesis trench settlement. It has high prediction accuracy and fit for the settlement of integral comprehensive pipe.

A DNA tetrahedron-based molecular computation device for the logic sensing of dual microRNAs in living cells

2020 ◽  
Vol 56 (39) ◽  
pp. 5303-5306
Author(s):  
Qing Lin ◽  
Anmin Wang ◽  
Shiyuan Liu ◽  
Jing Li ◽  
Jiaoli Wang ◽  
...  
Keyword(s):  
Mirna Expression ◽  
Prediction Accuracy ◽  
Expression Patterns ◽  
Living Cells ◽  
Cell Type ◽  
Molecular Computation ◽  
High Prediction Accuracy ◽  
Dna Tetrahedron ◽  
High Prediction

Endogenous miRNA expression patterns are specific to cell type and thus offer high prediction accuracy with regard to different cell identities compared to single miRNA analysis.

Sign in / Sign up

Export Citation Format

Share Document