scholarly journals ASAMS: An Adaptive Sequential Sampling and Automatic Model Selection for Artificial Intelligence Surrogate Modeling

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5332
Author(s):  
Carlos A. Duchanoy ◽  
Hiram Calvo ◽  
Marco A. Moreno-Armendáriz
Keyword(s):  
Artificial Intelligence ◽  
Model Selection ◽  
Adaptive Sampling ◽  
Search Algorithm ◽  
Sequential Sampling ◽  
Surrogate Modeling ◽  
Kriging Model ◽  
Surrogate Models ◽  
Physical Experiments ◽  
Leave One Out

Surrogate Modeling (SM) is often used to reduce the computational burden of time-consuming system simulations. However, continuous advances in Artificial Intelligence (AI) and the spread of embedded sensors have led to the creation of Digital Twins (DT), Design Mining (DM), and Soft Sensors (SS). These methodologies represent a new challenge for the generation of surrogate models since they require the implementation of elaborated artificial intelligence algorithms and minimize the number of physical experiments measured. To reduce the assessment of a physical system, several existing adaptive sequential sampling methodologies have been developed; however, they are limited in most part to the Kriging models and Kriging-model-based Monte Carlo Simulation. In this paper, we integrate a distinct adaptive sampling methodology to an automated machine learning methodology (AutoML) to help in the process of model selection while minimizing the system evaluation and maximizing the system performance for surrogate models based on artificial intelligence algorithms. In each iteration, this framework uses a grid search algorithm to determine the best candidate models and perform a leave-one-out cross-validation to calculate the performance of each sampled point. A Voronoi diagram is applied to partition the sampling region into some local cells, and the Voronoi vertexes are considered as new candidate points. The performance of the sample points is used to estimate the accuracy of the model for a set of candidate points to select those that will improve more the model’s accuracy. Then, the number of candidate models is reduced. Finally, the performance of the framework is tested using two examples to demonstrate the applicability of the proposed method.

Sequential sampling framework for metamodeling uncertainty reduction in multilevel optimization of hierarchical systems

2021 ◽  
pp. 1-23
Author(s):  
Can Xu ◽  
Ping Zhu ◽  
Zhao Liu
Keyword(s):  
Model Selection ◽  
Sequential Sampling ◽  
Computational Cost ◽  
Selection Criterion ◽  
Kriging Model ◽  
Uncertainty Reduction ◽  
Training Data ◽  
Hierarchical Systems ◽  
Multilevel Optimization ◽  
True Solution

Abstract Metamodels instead of computer simulations are often adopted to reduce the computational cost in the uncertainty based multilevel optimization. However, metamodel techniques may bring prediction discrepancy, which is defined as metamodeling uncertainty, due to the limited training data. An unreliable solution will be obtained when the metamodeling uncertainty is ignored, while an overly conservative solution, which contradicts the original intension of the design, may be got when both parametric and metamodeling uncertainty are treated concurrently. Hence, an adaptive sequential sampling framework is developed for the metamodeling uncertainty reduction of multilevel systems to obtain a solution that approximates the true solution. Based on the Kriging model for the probabilistic analytical target cascading, the proposed framework establishes a revised objective-oriented sampling criterion and sub-model selection criterion, which can realize the location of additional samples and the selection of subsystem requiring sequential sampling. Within the sampling criterion, the metamodeling uncertainty is decomposed by the Karhunen-Loeve expansion into a set of stochastic variables, and then polynomial chaos expansion is employed for uncertainty quantification. The polynomial coefficients are encoded and integrated in the selection criterion to obtain subset sensitivity indices for the sub-model selection. The effectiveness of the developed framework for metamodeling uncertainty reduction is demonstrated on a mathematical example and an application.

Label-Free Mass Spectrometry-Based Plasma Proteomics Identified LY6D, DSC3, CDSN, SERPINB12, and SLURP1,as Novel Protein Biomarkers For Pulmonary Tuberculosis

2019 ◽  
Vol 17 ◽  
Author(s):  
Xiaoli Yu ◽  
Lu Zhang ◽  
Na Li ◽  
Peng Hu ◽  
Zhaoqin Zhu ◽  
...  
Keyword(s):  
Pulmonary Tuberculosis ◽  
Search Algorithm ◽  
Differentially Expressed ◽  
P Value ◽  
Plasma Samples ◽  
Label Free ◽  
Protein Biomarkers ◽  
Protein Database ◽  
Leave One Out ◽  
Potential Biomarkers

Aim: We aimed to identify new plasma biomarkers for the diagnosis of Pulmonary tuberculosis. Background: Tuberculosis is an ancient infectious disease that remains one of the major global health problems. Until now, effective, convenient, and affordable methods for diagnosis of Pulmonary tuberculosis were still lacked. Objective: This study focused on construct a label-free LC-MS/MS based comparative proteomics between six tuberculosis patients and six healthy controls to identify differentially expressed proteins (DEPs) in plasma. Method: To reduce the influences of high-abundant proteins, albumin and globulin were removed from plasma samples using affinity gels. Then DEPs from the plasma samples were identified using a label-free Quadrupole-Orbitrap LC-MS/MS system. The results were analyzed by the protein database search algorithm SEQUEST-HT to identify mass spectra to peptides. The predictive abilities of combinations of host markers were investigated by general discriminant analysis (GDA), with leave-one-out cross-validation. Results: A total of 572 proteins were identified and 549 proteins were quantified. The threshold for differentially expressed protein was set as adjusted p-value < 0.05 and fold change ≥1.5 or ≤0.6667, 32 DEPs were found. ClusterVis, TBtools, and STRING were used to find new potential biomarkers of PTB. Six proteins, LY6D, DSC3, CDSN, FABP5, SERPINB12, and SLURP1, which performed well in the LOOCV method validation, were termed as potential biomarkers. The percentage of cross-validated grouped cases correctly classified and original grouped cases correctly classified is greater than or equal to 91.7%. Conclusion: We successfully identified five candidate biomarkers for immunodiagnosis of PTB in plasma, LY6D, DSC3, CDSN, SERPINB12, and SLURP1. Our work supported this group of proteins as potential biomarkers for pulmonary tuberculosis, and be worthy of further validation.

EXPRESS: Baseline Correction Based on a Search Algorithm from Artificial Intelligence

2020 ◽  
pp. 000370282097751
Author(s):  
Xin Wang ◽  
Xia Chen
Keyword(s):  
Artificial Intelligence ◽  
Objective Function ◽  
Least Squares ◽  
Least Squares Method ◽  
Search Algorithm ◽  
Absolute Error ◽  
Search Problem ◽  
Baseline Correction ◽  
Current Spectrum ◽  
Data Points

Many spectra have a polynomial-like baseline. Iterative polynomial fitting (IPF) is one of the most popular methods for baseline correction of these spectra. However, the baseline estimated by IPF may have substantially error when the spectrum contains significantly strong peaks or have strong peaks located at the endpoints. First, IPF uses temporary baseline estimated from the current spectrum to identify peak data points. If the current spectrum contains strong peaks, then the temporary baseline substantially deviates from the true baseline. Some good baseline data points of the spectrum might be mistakenly identified as peak data points and are artificially re-assigned with a low value. Second, if a strong peak is located at the endpoint of the spectrum, then the endpoint region of the estimated baseline might have significant error due to overfitting. This study proposes a search algorithm-based baseline correction method (SA) that aims to compress sample the raw spectrum to a dataset with small number of data points and then convert the peak removal process into solving a search problem in artificial intelligence (AI) to minimize an objective function by deleting peak data points. First, the raw spectrum is smoothened out by the moving average method to reduce noise and then divided into dozens of unequally spaced sections on the basis of Chebyshev nodes. Finally, the minimal points of each section are collected to form a dataset for peak removal through search algorithm. SA selects the mean absolute error (MAE) as the objective function because of its sensitivity to overfitting and rapid calculation. The baseline correction performance of SA is compared with those of three baseline correction methods: Lieber and Mahadevan–Jansen method, adaptive iteratively reweighted penalized least squares method, and improved asymmetric least squares method. Simulated and real FTIR and Raman spectra with polynomial-like baselines are employed in the experiments. Results show that for these spectra, the baseline estimated by SA has fewer error than those by the three other methods.

Novel Application of Artificial Intelligence with Potential to Transform Well Planning Workflows on the Norwegian Continental Shelf

2021 ◽  
Author(s):  
Jon Gustav Vabø ◽  
Evan Thomas Delaney ◽  
Tom Savel ◽  
Norbert Dolle
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Continental Shelf ◽  
Data Science ◽  
Search Algorithm ◽  
Solution Space ◽  
Good Decision ◽  
Trade Offs ◽  
Well Trajectory ◽  
Norwegian Continental Shelf

Abstract This paper describes the transformational application of Artificial Intelligence (AI) in Equinor's annual well planning and maturation process. Well planning is a complex decision-making process, like many other processes in the industry. There are thousands of choices, conflicting business drivers, lots of uncertainty, and hidden bias. These complexities all add up, which makes good decision making very hard. In this application, AI has been used for automated and unbiased evaluation of the full solution space, with the objective to optimize the selection of drilling campaigns while taking into account complex issues such as anti-collision with existing wells, drilling hazards and trade-offs between cost, value and risk. Designing drillable well trajectories involves a sequence of decisions, which makes the process very suitable for AI algorithms. Different solver architectures, or algorithms, can be used to play this game. This is similar to how companies such as Google-owned DeepMind develop customized solvers for games such as Go and StarCraft. The chosen method is a Tree Search algorithm with an evolutionary layer on top, providing a good balance in terms of performance (i.e., speed) vs. exploration capability (i.e., it looks "wide" in the option space). The algorithm has been deployed in a full stack web-based application that allows users to follow an end-2-end workflow: from defining well trajectory design rules and constraints to running the AI engine and evaluating results to the optimization of multi-well drilling campaigns based on risk, value and cost objectives. The full-size paper describes different Norwegian Continental Shelf (NCS) use cases of this AI assisted well trajectory planning. Results to-date indicate significant CAPEX savings potential and step-change improvements in decision speed (months to days) compared to routine manual workflows. There are very limited real transformative examples of Artificial Intelligence in multi- disciplinary workflows. This paper therefore gives a unique insight how a combination of data science, domain expertise and end user feedback can lead to powerful and transformative AI solutions – implemented at scale within an existing organization.

Stochastic Bayesian optimization for predicting borderline knock

2021 ◽  
pp. 146808742110652
Author(s):  
Jian Tang ◽  
Anuj Pal ◽  
Wen Dai ◽  
Chad Archer ◽  
James Yi ◽  
...  
Keyword(s):  
Fuel Economy ◽  
Learning Algorithm ◽  
Feedforward Control ◽  
Model Development ◽  
Kriging Model ◽  
Optimization Method ◽  
Surrogate Models ◽  
Bayesian Optimization ◽  
Control Parameters ◽  
Operation Conditions

Engine knock is an undesirable combustion that could damage the engine mechanically. On the other hand, it is often desired to operate the engine close to its borderline knock limit to optimize combustion efficiency. Traditionally, borderline knock limit is detected by sweeping tests of related control parameters for the worst knock, which is expensive and time consuming, and also, the detected borderline knock limit is often used as a feedforward control without considering its stochastic characteristics without compensating current engine operational condition and type of fuel used. In this paper, stochastic Bayesian optimization method is used to obtain a tradeoff between stochastic knock intensity and fuel economy. The log-nominal distribution of knock intensity signal is converted to Gaussian one using a proposed map to satisfy the assumption for Kriging model development. Both deterministic and stochastic Kriging surrogate models are developed based on test data using the Bayesian iterative optimization process. This study focuses on optimizing two competing objectives, knock intensity and indicated specific fuel consumption using two control parameters: spark and intake valve timings. Test results at two different operation conditions show that the proposed learning algorithm not only reduces required time and cost for predicting knock borderline but also provides control parameters, based on trained surrogate models and the corresponding Pareto front, with the best fuel economy possible.

On Adaptive Sampling for Single and Multi-Response Bayesian Surrogate Models

2006 ◽  
Author(s):  
David A. Romero ◽  
Cristina H. Amon ◽  
Susan Finger
Keyword(s):  
Experimental Design ◽  
Adaptive Sampling ◽  
Design Space Exploration ◽  
A Priori ◽  
Computer Experiments ◽  
Latin Hypercube Sampling ◽  
Surrogate Models ◽  
Sampling Techniques ◽  
Design And Optimization ◽  
Sampling Points

In order to reduce the time and resources devoted to design-space exploration during simulation-based design and optimization, the use of surrogate models, or metamodels, has been proposed in the literature. Key to the success of metamodeling efforts are the experimental design techniques used to generate the combinations of input variables at which the computer experiments are conducted. Several adaptive sampling techniques have been proposed to tailor the experimental designs to the specific application at hand, using the already-acquired data to guide further exploration of the input space, instead of using a fixed sampling scheme defined a priori. Though mixed results have been reported, it has been argued that adaptive sampling techniques can be more efficient, yielding better surrogate models with less sampling points. In this paper, we address the problem of adaptive sampling for single and multi-response metamodels, with a focus on Multi-stage Multi-response Bayesian Surrogate Models (MMBSM). We compare distance-optimal latin hypercube sampling, an entropy-based criterion and the maximum cross-validation variance criterion, originally proposed for one-dimensional output spaces and implemented in this paper for multi-dimensional output spaces. Our results indicate that, both for single and multi-response surrogate models, the entropy-based adaptive sampling approach leads to models that are more robust to the initial experimental design and at least as accurate (or better) when compared with other sampling techniques using the same number of sampling points.

scholarly journals Penerapan Algoritma Dynamic Programing pada Pergerakan Lawan dalam Permainan Police and Thief

2019 ◽  
Vol 2 (2) ◽  
pp. 114
Author(s):  
Insidini Fawwaz ◽  
Agus Winarta
Keyword(s):  
Artificial Intelligence ◽  
Dynamic Programming ◽  
Search Algorithm ◽  
Dynamic Programming Algorithm ◽  
Minimum Cost ◽  
Programming Algorithm ◽  
Shortest Route ◽  
Basic Meaning ◽  
Dynamic Programing ◽  
Approximate Distance

<p class="8AbstrakBahasaIndonesia"><em>Games have the basic meaning of games, games in this case refer to the notion of intellectual agility. In its application, a Game certainly requires an AI (Artificial Intelligence), and the AI used in the construction of this police and thief game is the dynamic programming algorithm. This algorithm is a search algorithm to find the shortest route with the minimum cost, algorithm dynamic programming searches for the shortest route by adding the actual distance to the approximate distance so that it makes it optimum and complete. Police and thief is a game about a character who will try to run from </em><em>police.</em><em> The genre of this game is arcade, built with microsoft visual studio 2008, the AI used is the </em><em>Dynamic Programming</em> <em>algorithm which is used to search the path to attack players. The results of this test are police in this game managed to find the closest path determined by the </em><em>Dynamic Programming</em> <em>algorithm to attack players</em></p>

POD-Driven Adaptive Sampling for Efficient Surrogate Modeling and its Application to Supersonic Turbine Optimization

2014 ◽  
Author(s):  
Hiromasa Kato ◽  
Ken-ichi Funazaki
Keyword(s):  
Flow Field ◽  
Adaptive Sampling ◽  
Radial Basis Function Network ◽  
Test Case ◽  
Good Prediction ◽  
Impulse Turbine ◽  
New Approach ◽  
A Chain ◽  
Leave One Out ◽  
Proper Orthogonal

A new approach for adaptively sampling a design parameter space using an error estimate through the reconstruction of flow field by a combination of proper orthogonal decomposition (POD) and radial basis function network (RBFN) is presented. It differs from other similar approaches in that it does not use the reconstructed flow field by POD for the evaluation of objective functions, and thus it can be a subset of the flow field. Advantages of this approach include the ease of constructing a chain of simulation codes as well as the flexibility of choosing where and what to reconstruct within the solution domain. An improvement in achieving a good prediction quality, with respect to other adaptive sampling methods, has been demonstrated using supersonic impulse turbine optimization as the test case. A posteriori validation of the surrogate models were also carried out using a set of separately-evaluated samples, which showed a similar trend as the Leave-One-Out (LOO) cross-validation. The progressively enriched surrogate model was then used to achieve the more uniformly populated Pareto front with fewer number of function evaluations.

Sign in / Sign up

Export Citation Format

Share Document