Fast and Intelligent Antenna Design Optimization using Machine Learning

2021 ◽  
Vol 35 (11) ◽  
pp. 1350-1351
Author(s):  
Gopinath Gampala ◽  
C. J. Reddy
Keyword(s):  
Machine Learning ◽  
Mathematical Model ◽  
Design Optimization ◽  
Antenna Design ◽  
Convergence Criteria ◽  
Time Required

Traditional antenna optimization solves the modified version of the original antenna design for each iteration. Thus, the total time required to optimize a given antenna design is highly dependent on the convergence criteria of the selected algorithm and the time taken for each iteration. The use of machine learning enables the antenna designer to generate trained mathematical model that replicates the original antenna design and then apply optimization on the trained model. Use of trained model allows to run thousands of optimization iterations in a span of few seconds.

scholarly journals Statistical and machine learning models for optimizing energy in parallel applications

2019 ◽  
Vol 33 (6) ◽  
pp. 1079-1097 ◽  
Author(s):  
Mark Endrei ◽  
Chao Jin ◽  
Minh Ngoc Dinh ◽  
David Abramson ◽  
Heidi Poxon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Energy Efficiency ◽  
High Performance ◽  
Large Scale ◽  
Energy Use ◽  
Parallel Applications ◽  
Learning Models ◽  
Trade Off ◽  
Time Required ◽  
Machine Learning Models

Rising power costs and constraints are driving a growing focus on the energy efficiency of high performance computing systems. The unique characteristics of a particular system and workload and their effect on performance and energy efficiency are typically difficult for application users to assess and to control. Settings for optimum performance and energy efficiency can also diverge, so we need to identify trade-off options that guide a suitable balance between energy use and performance. We present statistical and machine learning models that only require a small number of runs to make accurate Pareto-optimal trade-off predictions using parameters that users can control. We study model training and validation using several parallel kernels and more complex workloads, including Algebraic Multigrid (AMG), Large-scale Atomic Molecular Massively Parallel Simulator, and Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. We demonstrate that we can train the models using as few as 12 runs, with prediction error of less than 10%. Our AMG results identify trade-off options that provide up to 45% improvement in energy efficiency for around 10% performance loss. We reduce the sample measurement time required for AMG by 90%, from 13 h to 74 min.

scholarly journals Machine Learning for Design Optimization of Electromagnetic Devices: Recent Developments and Future Directions

2021 ◽  
Vol 11 (4) ◽  
pp. 1627
Author(s):  
Yanbin Li ◽  
Gang Lei ◽  
Gerd Bramerdorfer ◽  
Sheng Peng ◽  
Xiaodong Sun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Design Optimization ◽  
Optimization Methods ◽  
Machine Learning Algorithms ◽  
Cloud Services ◽  
Robust Design Optimization ◽  
Support Vector ◽  
Future Directions ◽  
Electromagnetic Devices ◽  
Recent Developments

This paper reviews the recent developments of design optimization methods for electromagnetic devices, with a focus on machine learning methods. First, the recent advances in multi-objective, multidisciplinary, multilevel, topology, fuzzy, and robust design optimization of electromagnetic devices are overviewed. Second, a review is presented to the performance prediction and design optimization of electromagnetic devices based on the machine learning algorithms, including artificial neural network, support vector machine, extreme learning machine, random forest, and deep learning. Last, to meet modern requirements of high manufacturing/production quality and lifetime reliability, several promising topics, including the application of cloud services and digital twin, are discussed as future directions for design optimization of electromagnetic devices.

scholarly journals Feasibility and accuracy of the automated software for dynamic quantification of left ventricular and atrial volumes and function in a large unselected population

2021 ◽  
Vol 22 (Supplement_1) ◽  
Author(s):  
G Italiano ◽  
G Tamborini ◽  
V Mantegazza ◽  
V Volpato ◽  
L Fusini ◽  
...  
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Image Quality ◽  
Normal Subjects ◽  
Left Ventricular ◽  
Systolic Volume ◽  
Unselected Population ◽  
Lv Volumes ◽  
Time Required ◽  
2D Images

Abstract Funding Acknowledgements Type of funding sources: None. Objective. Preliminary studies showed the accuracy of machine learning based automated dynamic quantification of left ventricular (LV) and left atrial (LA) volumes. We aimed to evaluate the feasibility and accuracy of machine learning based automated dynamic quantification of LV and LA volumes in an unselected population. Methods. We enrolled 600 unselected patients (12% in atrial fibrillation) clinically referred for transthoracic echocardiography (2DTTE), who also underwent 3D echocardiography (3DE) imaging. LV ejection fraction (EF), LV and LA volumes were obtained from 2D images; 3D images were analysed using Dynamic Heart Model (DHM) software (Philips) resulting in LV and LA volume-time curves. A subgroup of 140 patients underwent also cardiac magnetic resonance (CMR) imaging. Average time of analysis, feasibility, and image quality were recorded and results were compared between 2DTTE, DHM and CMR. Results. The use of DHM was feasible in 522/600 cases (87%). When feasible, the boundary position was considered accurate in 335/522 patients (64%), while major (n = 38) or minor (n = 149) borders corrections were needed. The overall time required for DHM datasets was approximately 40 seconds, resulting in physiologically appearing LV and LA volume–time curves in all cases. As expected, DHM LV volumes were larger than 2D ones (end-diastolic volume: 173 ± 64 vs 142 ± 58 mL, respectively), while no differences were found for LV EF and LA volumes (EF: 55%±12 vs 56%±14; LA volume 89 ± 36 vs 89 ± 38 mL, respectively). The comparison between DHM and CMR values showed a high correlation for LV volumes (r = 0.70 and r = 0.82, p < 0.001 for end-diastolic and end-systolic volume, respectively) and an excellent correlation for EF (r= 0.82, p < 0.001) and LA volumes. Conclusions. The DHM software is feasible, accurate and quick in a large series of unselected patients, including those with suboptimal 2D images or in atrial fibrillation. Table 1 DHM quality Adjustment Feasibility Good Suboptimal Minor Major Total of patients (n, %) 522/600 (87%) 327/522 (62%) 195/522 (28%) 149/522 (29%) 38/522 (6%) Normal subjects (n, %) 39/40 (97%) 23/39 (57%) 16/39 (40%) 9/39 (21%) 1/39 (3%) Atrial Fibrillation (n, %) 59/73 (81%)* 28/59 (47%) 31/59 (53%) 15/59 (25%) 6/59 (10%) Valvular disease (n, %) 271/312 (87%) 120/271 (%) 151/271 (%) 65/271 (24%) 16/271 (6%) Coronary artery disease (n, %) 47/58 (81%)* 26/47 (46%) 21/47 (37%) 16/47 (34%) 5/47 (11%) Miscellaneous (n, %) 24/25 (96%) 18/24 (75%) 6/24 (25%) 5/24 (21%) 3/24 (12%) Feasibility of DHM, image quality and need to adjustments in global population and in each subgroup. Abstract Figure 1

An Automated Machine Learning-Genetic Algorithm Framework With Active Learning for Design Optimization

2021 ◽  
Vol 143 (8) ◽  
Author(s):  
Opeoluwa Owoyele ◽  
Pinaki Pal ◽  
Alvaro Vidal Torreira
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Design Optimization ◽  
Fuel Injection ◽  
A Priori ◽  
Computational Cost ◽  
Learning Approach ◽  
Data Generation ◽  
Compression Ignition Engine ◽  
Hyperparameter Selection

AbstractThe use of machine learning (ML)-based surrogate models is a promising technique to significantly accelerate simulation-driven design optimization of internal combustion (IC) engines, due to the high computational cost of running computational fluid dynamics (CFD) simulations. However, training the ML models requires hyperparameter selection, which is often done using trial-and-error and domain expertise. Another challenge is that the data required to train these models are often unknown a priori. In this work, we present an automated hyperparameter selection technique coupled with an active learning approach to address these challenges. The technique presented in this study involves the use of a Bayesian approach to optimize the hyperparameters of the base learners that make up a super learner model. In addition to performing hyperparameter optimization (HPO), an active learning approach is employed, where the process of data generation using simulations, ML training, and surrogate optimization is performed repeatedly to refine the solution in the vicinity of the predicted optimum. The proposed approach is applied to the optimization of a compression ignition engine with control parameters relating to fuel injection, in-cylinder flow, and thermodynamic conditions. It is demonstrated that by automatically selecting the best values of the hyperparameters, a 1.6% improvement in merit value is obtained, compared to an improvement of 1.0% with default hyperparameters. Overall, the framework introduced in this study reduces the need for technical expertise in training ML models for optimization while also reducing the number of simulations needed for performing surrogate-based design optimization.

Progress on Machine Learning Informed Design Optimization for Double Shell Capsule Graded Density Inner Layer Targets

2021 ◽  
Author(s):  
Nomita Vazirani ◽  
Michael J. Grosskopf ◽  
David J. Stark ◽  
Paul Bradley ◽  
B. Haines ◽  
...  
Keyword(s):  
Machine Learning ◽  
Design Optimization

Analytical Study of Hydro-Pneumatic Processes for Gorlov's Power System

1994 ◽  
Vol 208 (1) ◽  
pp. 67-70
Author(s):  
A I Ryazanov
Keyword(s):  
Experimental Data ◽  
Mathematical Model ◽  
Power System ◽  
Analytical Study ◽  
Model Tests ◽  
Air Pressure ◽  
Pneumatic Power ◽  
Time Required ◽  
The Mathematical Model

This paper describes the aerohydrodvnamics of processes in chambers of Gorlov's hydro-pneumatic power system. The mathematical model is developed to determine the main parameters of the processes: water and air velocities, air pressure in the chamber, the periods of time required to fill and empty the chambers and the output of energy during the cycle. The results obtained are in agreement with experimental data and model tests.

scholarly journals Machine Learning and Design Optimization for Molecular Biology and Beyond

2020 ◽  
Vol 25 (1) ◽  
Author(s):  
Bryan Hsu ◽  
Natasha Raut ◽  
Kaitlyn Wang ◽  
Elettra Preosti
Keyword(s):  
Machine Learning ◽  
Molecular Biology ◽  
Design Optimization
Sign in / Sign up

Export Citation Format

Share Document