scholarly journals Machine Learning Control Based on Approximation of Optimal Trajectories

Mathematics ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 265
Author(s):  
Askhat Diveev ◽  
Sergey Konstantinov ◽  
Elizaveta Shmalko ◽  
Ge Dong
Keyword(s):  
Machine Learning ◽  
Control Function ◽  
Mathematical Formulation ◽  
Quality Criterion ◽  
Learning Control ◽  
Supervised Machine Learning ◽  
Training Set ◽  
Initial State ◽  
Regression Methods ◽  
General Synthesis

The paper is devoted to an emerging trend in control—a machine learning control. Despite the popularity of the idea of machine learning, there are various interpretations of this concept, and there is an urgent need for its strict mathematical formalization. An attempt to formalize the concept of machine learning is presented in this paper. The concepts of an unknown function, work area, training set are introduced, and a mathematical formulation of the machine learning problem is presented. Based on the presented formulation, the concept of machine learning control is considered. One of the problems of machine learning control is the general synthesis of control. It implies finding a control function that depends on the state of the object, which ensures the achievement of the control goal with the optimal value of the quality criterion from any initial state of some admissible region. Supervised and unsupervised approaches to solving a problem based on symbolic regression methods are considered. As a computational example, a problem of general synthesis of optimal control for a spacecraft landing on the surface of the Moon is considered as supervised machine learning control with a training set.

scholarly journals Control Synthesis as Machine Learning Control by Symbolic Regression Methods

2021 ◽  
Vol 11 (12) ◽  
pp. 5468
Author(s):  
Elizaveta Shmalko ◽  
Askhat Diveev
Keyword(s):  
Machine Learning ◽  
Genetic Programming ◽  
Mathematical Formulation ◽  
Small Variation ◽  
Learning Control ◽  
Symbolic Regression ◽  
Control Technique ◽  
Control Synthesis ◽  
Basic Solution ◽  
Regression Methods

The problem of control synthesis is considered as machine learning control. The paper proposes a mathematical formulation of machine learning control, discusses approaches of supervised and unsupervised learning by symbolic regression methods. The principle of small variation of the basic solution is presented to set up the neighbourhood of the search and to increase search efficiency of symbolic regression methods. Different symbolic regression methods such as genetic programming, network operator, Cartesian and binary genetic programming are presented in details. It is shown on the computational example the possibilities of symbolic regression methods as unsupervised machine learning control technique to the solution of MLC problem of control synthesis for obtaining the stabilization system for a mobile robot.

scholarly journals Effects of Training Set Size on Supervised Machine-Learning Land-Cover Classification of Large-Area High-Resolution Remotely Sensed Data

2021 ◽  
Vol 13 (3) ◽  
pp. 368
Author(s):  
Christopher A. Ramezan ◽  
Timothy A. Warner ◽  
Aaron E. Maxwell ◽  
Bradley S. Price
Keyword(s):  
Machine Learning ◽  
Sample Size ◽  
Remotely Sensed ◽  
Training Data ◽  
Supervised Machine Learning ◽  
Sample Sizes ◽  
Remotely Sensed Data ◽  
Large Area ◽  
Training Set ◽  
Set Size

The size of the training data set is a major determinant of classification accuracy. Nevertheless, the collection of a large training data set for supervised classifiers can be a challenge, especially for studies covering a large area, which may be typical of many real-world applied projects. This work investigates how variations in training set size, ranging from a large sample size (n = 10,000) to a very small sample size (n = 40), affect the performance of six supervised machine-learning algorithms applied to classify large-area high-spatial-resolution (HR) (1–5 m) remotely sensed data within the context of a geographic object-based image analysis (GEOBIA) approach. GEOBIA, in which adjacent similar pixels are grouped into image-objects that form the unit of the classification, offers the potential benefit of allowing multiple additional variables, such as measures of object geometry and texture, thus increasing the dimensionality of the classification input data. The six supervised machine-learning algorithms are support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), single-layer perceptron neural networks (NEU), learning vector quantization (LVQ), and gradient-boosted trees (GBM). RF, the algorithm with the highest overall accuracy, was notable for its negligible decrease in overall accuracy, 1.0%, when training sample size decreased from 10,000 to 315 samples. GBM provided similar overall accuracy to RF; however, the algorithm was very expensive in terms of training time and computational resources, especially with large training sets. In contrast to RF and GBM, NEU, and SVM were particularly sensitive to decreasing sample size, with NEU classifications generally producing overall accuracies that were on average slightly higher than SVM classifications for larger sample sizes, but lower than SVM for the smallest sample sizes. NEU however required a longer processing time. The k-NN classifier saw less of a drop in overall accuracy than NEU and SVM as training set size decreased; however, the overall accuracies of k-NN were typically less than RF, NEU, and SVM classifiers. LVQ generally had the lowest overall accuracy of all six methods, but was relatively insensitive to sample size, down to the smallest sample sizes. Overall, due to its relatively high accuracy with small training sample sets, and minimal variations in overall accuracy between very large and small sample sets, as well as relatively short processing time, RF was a good classifier for large-area land-cover classifications of HR remotely sensed data, especially when training data are scarce. However, as performance of different supervised classifiers varies in response to training set size, investigating multiple classification algorithms is recommended to achieve optimal accuracy for a project.

Support Vector Machine

2009 ◽  
pp. 501-522 ◽  
Author(s):  
A. B.M. Shawkat Ali
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
System Analysis ◽  
Learning Algorithm ◽  
Mathematical Formulation ◽  
Supervised Machine Learning ◽  
Future Research ◽  
Support Vector ◽  
Analysis And Design ◽  
Simple Demonstration

From the beginning, machine learning methodology, which is the origin of artificial intelligence, has been rapidly spreading in the different research communities with successful outcomes. This chapter aims to introduce for system analysers and designers a comparatively new statistical supervised machine learning algorithm called support vector machine (SVM). We explain two useful areas of SVM, that is, classification and regression, with basic mathematical formulation and simple demonstration to make easy the understanding of SVM. Prospects and challenges of future research in this emerging area are also described. Future research of SVM will provide improved and quality access to the users. Therefore, developing an automated SVM system with state-of-the-art technologies is of paramount importance, and hence, this chapter will link up an important step in the system analysis and design perspective to this evolving research arena.

scholarly journals Machine learning for transient recognition in difference imaging with minimum sampling effort

2020 ◽  
Vol 499 (4) ◽  
pp. 6009-6017
Author(s):  
Y-L Mong ◽  
K Ackley ◽  
D K Galloway ◽  
T Killestein ◽  
J Lyman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Representation ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Sampling Effort ◽  
Training Set ◽  
The Real ◽  
Learning Techniques ◽  
The Difference ◽  
Difference Imaging

ABSTRACT The amount of observational data produced by time-domain astronomy is exponentially increasing. Human inspection alone is not an effective way to identify genuine transients from the data. An automatic real-bogus classifier is needed and machine learning techniques are commonly used to achieve this goal. Building a training set with a sufficiently large number of verified transients is challenging, due to the requirement of human verification. We present an approach for creating a training set by using all detections in the science images to be the sample of real detections and all detections in the difference images, which are generated by the process of difference imaging to detect transients, to be the samples of bogus detections. This strategy effectively minimizes the labour involved in the data labelling for supervised machine learning methods. We demonstrate the utility of the training set by using it to train several classifiers utilizing as the feature representation the normalized pixel values in 21 × 21 pixel stamps centred at the detection position, observed with the Gravitational-wave Optical Transient Observer (GOTO) prototype. The real-bogus classifier trained with this strategy can provide up to $95{{\ \rm per\ cent}}$ prediction accuracy on the real detections at a false alarm rate of $1{{\ \rm per\ cent}}$.

Aerosol classification using sun photometer and lidar data within a machine learning algorithm-a possible nowcasting application

2021 ◽  
Author(s):  
Joelle Buxmann ◽  
Martin Osborne ◽  
Mike Protts ◽  
Debbie O'Sullivan
Keyword(s):  
Machine Learning ◽  
Biomass Burning ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Training Set ◽  
Angstrom Exponent ◽  
Ångström Exponent ◽  
Aerosol Classification ◽  
Aerosol Types ◽  
Ångstrom Exponent

<p>The Met Office operates a ground based operational network of nine polarisation Raman lidars (aerosol profiling instruments) and sun photometers (column integrated information). An aerosol classification scheme using supervised machine learning has been developed. The concept of Mahalanobis (~normalized) distance to identify the aerosol type  from individual Aerosol Robotic Network (AERONET) measurements including Extinction Angstrom Exponent, Absorption Angstrom Exponent, Single Scattering Albedo and Index of refraction is used for a subset of AERONET stations around the globe of known main aerosol types (training set). The aerosol types  include maritime, urban industrial, biomass burning and dust. We build a predictive model from this training set using K nearest neighbour machine learning algorithms. The relation of particle polarisation ratio and lidar ratio from the Raman lidar is used as a sanity check.  We apply the model to 3- 4 years of AERONET and profiling data across the UK, with instruments evenly distributed across the country, from Camborne in Cornwall to Lerwick in the Shetland Islands. We are showing more detailed data of a dust event in May 2016, dust/biomass burning aerosol mix from October 2017 (hurricane Ophelia) and more recent aerosol transported from the Canadian wild fires in September 2020. AERONET Level 2.0  data is compared to level 1.5 in order to determine the implications for the aerosol classification. Level 1.5 data are cloud-screened, but not quality assured and may not have the final calibration applied. Level 2.0  data have pre- and post-field calibration applied, are cloud-screened, and quality-assured data. As level 2.0 data is usually only available after 1-2 years (after a new calibration has been performed), it is important to understand the  usefulness of more readily available level 1.5 (cloud screened) data.</p><p>The aim is to build a real time aerosol classification application that can be used in Nowcasting.</p>

scholarly journals A Combined DFT/Machine Learning Framework for Materials Discovery: Application to Spinels and Assessment of Search Completeness and Efficiency

2020 ◽  
Author(s):  
Elif Ertekin ◽  
Joshua A. Schiller
Keyword(s):  
Machine Learning ◽  
Physical Modeling ◽  
Density Functional ◽  
Search Space ◽  
Supervised Machine Learning ◽  
Search Efficiency ◽  
Learning Approaches ◽  
Training Set ◽  
Learning Framework ◽  
Single Feature

It is challenging to evaluate machine learning approaches developed for accelerating materials search and discovery in a realistic way. Machine learning approaches to materials stability prediction are typically assessed by their ability to reproduce results from direct physical modeling, whereas ideally both machine learning and direct physical modeling should be assessed by their ability to reproduce reality. Additionally, traditional evaluation metrics do not directly reflect the experience of an experimental search for unknown compounds in a large candidate phase space, and often result in overly optimistic assessments. Here, we (i) present a framework that combines density functional theory and traditional supervised machine learning methods (ML/DFT), and (ii) introduce the concepts of search completeness – the fraction of discoverable compounds found relative to the fraction of search space explored – and search efficiency – the rate of discovery relative to the fraction of search space explored – to evaluate it. The ML/DFT framework is an iterative approach to predict stable chemistries of a fixed crystal structure (here, spinels) that uses DFT to generate a training set of unstable compounds. The training set of stable compounds is given by experimentally known spinels. The method is carried out using random forest, LASSO, and ridge regression to predict as-of-yet undiscovered spinel chemistries. TreeSHAP analysis is used to determine features that most contribute to stability/instability classification. While no single feature dominates, several emerge that align with chemical intuition. To estimate the efficacy of ML/DFT compared to pure DFT, we introduce a Bayesian description of DFT distribution of energies for stable and unstable spinels. The Bayesian model enables quantifying the search completeness and search efficiency of DFT, which is then compared to that of ML/DFT. ML/DFT achieves search completeness and efficiency on par with pure DFT, despite requiring fewer DFT simulations (∼300 vs. 14,200). More importantly, by quantitatively assessing ML approaches in ways that better reflect how they would be used in materials discovery experiments, we obtain key insights into the challenges that need to be overcome by such methods: that the small number of stable compounds to be found in a search space orders of magnitude larger places stringent demands on model accuracy to achieve good search efficiency. Finally, we report the top candidates of our spinel search, which may be of interest for synthesis experiments<br>

scholarly journals Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods

Energies ◽  
2020 ◽  
Vol 13 (16) ◽  
pp. 4231 ◽  
Author(s):  
Ahmad Almaghrebi ◽  
Fares Aljuheshi ◽  
Mostafa Rafaie ◽  
Kevin James ◽  
Mahmoud Alahmad
Keyword(s):  
Machine Learning ◽  
Supervised Machine Learning ◽  
Grid Integration ◽  
Regression Methods ◽  
Demand Prediction ◽  
Utility Companies ◽  
Input Variables ◽  
Charging Stations ◽  
Micro Grids ◽  
Charging Demand

Plug-in Electric Vehicle (PEV) user charging behavior has a significant influence on a distribution network and its reliability. Generally, monitoring energy consumption has become one of the most important factors in green and micro grids; therefore, predicting the charging demand of PEVs (the energy consumed during the charging session) could help to efficiently manage the electric grid. Consequently, three machine learning methods are applied in this research to predict the charging demand for the PEV user after a charging session starts. This approach is validated using a dataset consisting of seven years of charging events collected from public charging stations in the state of Nebraska, USA. The results show that the regression method, XGBoost, slightly outperforms the other methods in predicting the charging demand, with an RMSE equal to 6.68 kWh and R2 equal to 51.9%. The relative importance of input variables is also discussed, showing that the user’s historical average demand has the most predictive value. Accurate prediction of session charging demand, as opposed to the daily or hourly demand of multiple users, has many possible applications for utility companies and charging networks, including scheduling, grid stability, and smart grid integration.

scholarly journals Supervised learning of few dirty bosons with variable particle number

2021 ◽  
Vol 10 (3) ◽  
Author(s):  
Pere Mujal ◽  
Àlex Martínez Miguel ◽  
Artur Polls ◽  
Bruno Juliá-Díaz ◽  
Sebastiano Pilati
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Network Architecture ◽  
Particle Number ◽  
Learning Strategy ◽  
Supervised Machine Learning ◽  
Training Set ◽  
Universal Power Law ◽  
Heterogeneous Datasets

We investigate the supervised machine learning of few interacting bosons in optical speckle disorder via artificial neural networks. The learning curve shows an approximately universal power-law scaling for different particle numbers and for different interaction strengths. We introduce a network architecture that can be trained and tested on heterogeneous datasets including different particle numbers. This network provides accurate predictions for all system sizes included in the training set and, by design, is suitable to attempt extrapolations to (computationally challenging) larger sizes. Notably, a novel transfer-learning strategy is implemented, whereby the learning of the larger systems is substantially accelerated and made consistently accurate by including in the training set many small-size instances.

Abstract 16725: Predicting the Need for a Permanent Pacemaker Device Following Transcatheter Aortic Valve Replacement Using Supervised Machine Learning

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Wasiq Sheikh ◽  
Anshul Parulkar ◽  
Malik B Ahmed ◽  
Suleman Ilyas ◽  
Esseim Sharma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forests ◽  
Cost Savings ◽  
Permanent Pacemaker ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Training Set ◽  
Data Set ◽  
Test Set ◽  
Discriminatory Ability

Introduction: TAVR is approved for use for a range of patients with aortic stenosis. The need for a permanent pacemaker device (PPD) after TAVR varies, but can range from 2 to 51%. Risk factors for requiring PPD after TAVR appear to include being male and having baseline conduction disturbances. Being able to predict who may require PPD could identify at risk patients early and may confer cost savings. Given the advent of machine learning classifier techniques, random forests may aid in better predicting need for PPD after TAVR by using pre-operative variables. Hypothesis: Random Forests offer discriminatory ability in predicting the need for PPD after TAVR using primarily pre-operative variables. Methods: Pre-operative data from a single institution were collected patients undergoing TAVR without a history of PPD between January 2016 and December 2019. EKG data was obtained including underlying rhythm, QRS duration and any underlying conduction abnormality. Other variables included anti-arrhythmic data, comorbidities, and eGFR. Data was imported into Python and a stratified 5 fold cross validation with SMOTE oversampling running at every fold to avoid overfitting was run on the training set. The model that optimized the receiver under the operator curve was exported and applied to a test data set. Precision and recall were calculated to assess classification. Results: A total of 513 patients were identified with nearly 9% eventually requiring PPD. A total of 40 predictor variables were utilized in the modeling. A stratified split of the data resulted in a training set of 384 patients and a test set of 129 patients. A total of 500 trees were used on the training set. The final optimized model had an ROC of 0.71 with the following parameters: gini criterion, max depth of 4, and logarithm max features . When applied to the test set, the model had an ROC of 0.63. Overall accuracy was 0.78, with a precision and recall for no PPD after TAVR being 0.94 and 0.81 and a precision and recall for PPD after TAVR of 0.18 and 0.45. Conclusions: Our results show that machine learning techniques, specifically random forests have discriminatory ability in predicting PPD after TAVR. More tuning of the models are required to achieve better discrimination.

Sign in / Sign up

Export Citation Format

Share Document