Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMachine Learning for Mechanical Ventilation Control
107
0
0.0
(
0
)
Added by
Daniel Suo
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We consider the problem of controlling an invasive mechanical ventilator for pressure-controlled ventilation: a controller must let air in and out of a sedated patients lungs according to a trajectory of airway pressures specified by a clinician. Hand-tuned PID controllers and similar variants have comprised the industry standard for decades, yet can behave poorly by over- or under-shooting their target or oscillating rapidly. We consider a data-driven machine learning approach: First, we train a simulator based on data we collect from an artificial lung. Then, we train deep neural network controllers on these simulators.We show that our controllers are able to track target pressure waveforms significantly better than PID controllers. We further show that a learned controller generalizes across lungs with varying characteristics much more readily than PID controllers do.
rate research
Read More
Indoor ventilation is essential for a healthy and comfortable living environment. A key issue is to discharge anthropogenic air contamination such as CO2 gas or, more seriously, airborne respiratory droplets. Here, by employing direct numerical simulations, we study the mechanical displacement ventilation with the realistic range of air changes per hour (ACH) from 1 to 10. For this ventilation scheme, a cool lower zone is established beneath the warm upper zone with the interface height h depending on ACH. For weak ventilation, we find the scalings relation of the interface height h ~ ACH^{3/5}, as suggested by Hunt & Linden (Build. Environ., vol. 34, 1999, pp. 707-720). Also, the CO2 concentration decreases with ACH within this regime. However, for too strong ventilation, the interface height h becomes insensitive to ACH, and the CO2 concentration remains unchanged. Our results are in contrast to the general belief that stronger flow is more helpful to remove contaminants. We work out the physical mechanism governing the transition between the low ACH and the high ACH regimes. It is determined by the relative strength of the kinetic energy from the inflow, potential energy from the stably-stratified layers, and energy loss due to drag. Our findings provide a physics-based guideline to optimize displacement ventilation.
Clinical decision support systems (CDSS) will play an in-creasing role in improving the quality of medical care for critically ill patients. However, due to limitations in current informatics infrastructure, CDSS do not always have com-plete information on state of supporting physiologic monitor-ing devices, which can limit the input data available to CDSS. This is especially true in the use case of mechanical ventilation (MV), where current CDSS have no knowledge of critical ventilation settings, such as ventilation mode. To enable MV CDSS to make accurate recommendations related to ventilator mode, we developed a highly performant ma-chine learning model that is able to perform per-breath clas-sification of 5 of the most widely used ventilation modes in the USA with an average F1-score of 97.52%. We also show how our approach makes methodologic improvements over previous work and that it is highly robust to missing data caused by software/sensor error.
Model-based methods are the dominant paradigm for controlling robotic systems, though their efficacy depends heavily on the accuracy of the model used. Deep neural networks have been used to learn models of robot dynamics from data, but they suffer from data-inefficiency and the difficulty to incorporate prior knowledge. We introduce Structured Mechanical Models, a flexible model class for mechanical systems that are data-efficient, easily amenable to prior knowledge, and easily usable with model-based control techniques. The goal of this work is to demonstrate the benefits of using Structured Mechanical Models in lieu of black-box neural networks when modeling robot dynamics. We demonstrate that they generalize better from limited data and yield more reliable model-based controllers on a variety of simulated robotic domains.
Although much progress has been made towards robust deep learning, a significant gap in robustness remains between real-world perturbations and more narrowly defined sets typically studied in adversarial defenses. In this paper, we aim to bridge this gap by learning perturbation sets from data, in order to characterize real-world effects for robust training and evaluation. Specifically, we use a conditional generator that defines the perturbation set over a constrained region of the latent space. We formulate desirable properties that measure the quality of a learned perturbation set, and theoretically prove that a conditional variational autoencoder naturally satisfies these criteria. Using this framework, our approach can generate a variety of perturbations at different complexities and scales, ranging from baseline spatial transformations, through common image corruptions, to lighting variations. We measure the quality of our learned perturbation sets both quantitatively and qualitatively, finding that our models are capable of producing a diverse set of meaningful perturbations beyond the limited data seen during training. Finally, we leverage our learned perturbation sets to train models which are empirically and certifiably robust to adversarial image corruptions and adversarial lighting variations, while improving generalization on non-adversarial data. All code and configuration files for reproducing the experiments as well as pretrained model weights can be found at https://github.com/locuslab/perturbation_learning.
Automated machine learning (AutoML) aims to find optimal machine learning solutions automatically given a machine learning problem. It could release the burden of data scientists from the multifarious manual tuning process and enable the access of domain experts to the off-the-shelf machine learning solutions without extensive experience. In this paper, we review the current developments of AutoML in terms of three categories, automated feature engineering (AutoFE), automated model and hyperparameter learning (AutoMHL), and automated deep learning (AutoDL). State-of-the-art techniques adopted in the three categories are presented, including Bayesian optimization, reinforcement learning, evolutionary algorithm, and gradient-based approaches. We summarize popular AutoML frameworks and conclude with current open challenges of AutoML.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
