On the zero- and first-order interpolation in synthesized sine waves for testing purposes

Lozano, Albert S.; Rosell, J.; Pallás-Areny, R.

doi:10.1109/19.199415

Cited by 12 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A zero-order interpolation approach [30] is used to address the sparsity of data, the use of this technique is frequent when dealing with clinical time series and also matches the behavior of medical decision-making [31]. The remaining missing data…”

Section: A Data Source and Patient Cohortmentioning

confidence: 99%

A Reinforcement Learning Model for Optimal Treatment Strategies in Intensive Care: Assessment of the Role of Cardiorespiratory Features

Drudi,

Mollura,

Lehman

et al. 2024

IEEE Open J. Eng. Med. Biol.

View full text Add to dashboard Cite

The purpose of this study is to evaluate the importance of cardiorespiratory variables within a Reinforcement Learning (RL) recommendation system aimed at establishing optimal strategies for drug treatment of septic patients in the intensive care unit (ICU).Methods: We developed a RL framework in order to establish drug administration strategies for septic patients by exclusively using a set of cardiorespiratory variables. We then compared this model with other equivalent models trained with a wider set of clinical features, as well as several models with similar dimensionality. We selected patients meeting the Sepsis-3 criteria from the Multi-parameter Intelligent Monitoring in Intensive Care (MIMIC III) database, resulting in a total of 20,496 ICU admissions. Data were normalized and then organized into discrete time-series. A Markov Decision Process (MDP) was built on the discrete time-series using the k-means++ clustering algorithm to define the states and a grid of 25 possible actions composed by a combination of vasopressors and intravenous fluid dosages. A policy iteration algorithm was applied to solve the MDP and obtain the optimal AI policy. The policy performance was then evaluated with the use of the weighted importance sampling estimator (WIS estimator). The process was repeated for each set of variables and compared with a set of baseline benchmark policies.Results: The model trained with cardiorespiratory variables outperformed all other models considered, resulting in a 95% confidence lower bound score of 97.48. This finding highlights the importance of cardiovascular variables in the clinical RL recommendation system.Conclusions: We established an efficient RL framework for sepsis treatment in the ICU and demonstrated that consideration of cardiorespiratory variables provides critical information in devising optimal policies. Given the potentially continuous availability of cardiorespiratory features extracted from bedside physiological waveform monitoring, the proposed framework paves the way for a real time recommendation system for sepsis treatment.

show abstract

Section: A Data Source and Patient Cohortmentioning

confidence: 99%

A Reinforcement Learning Model for Optimal Treatment Strategies in Intensive Care: Assessment of the Role of Cardiorespiratory Features

Drudi,

Mollura,

Lehman

et al. 2024

IEEE Open J. Eng. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Therefore, when t e I 1 , At this point, it whould be methodologically appropriate to succinctly review and delineate the time-discretization methods available for delay-free ( D 0 ) nonlinear control systems that are based on the Taylor series and reported in [9] [10][11]. The ensuing brief description of the Taylor discretization method for delay-free nonlinear systems will serve as a natural point of departure for the development of a similar in spirit discretization scheme that explicitly takes into account the presence of time-delay in the input variable(D ^0).…”

Section: General Order Holdmentioning

confidence: 99%

Comparison study of the Taylor series based discretization method for nonlinear input-delay systems

Zhang

Baek

et al. 2013

2013 Australian Control Conference

View full text Add to dashboard Cite

ABSTRACT² A general order hold time discretization method for input-driven nonlinear continuous time-delay systems is proposed which can be applied for different order sampling hold assumptions. It is based on a combination of Taylor series expansion and the theory of sampling and hold where the mathematical structure for the new discretization scheme is introduced in detail in this paper. The performance of the proposed discretization procedure is compared by different types of systems through various sampling rates, time delays, input signals, order of sampling hold assumptions and truncation orders. Results show that the proposed scheme is applicable for use in control systems and several useful summarized rules for this method are presented in the conclusion.

show abstract

“…where, the map γ Φ can be derived through the direct application of formula (24), and the subsequent calculation of the corresponding Taylor coefficients can be realized through the recursive formulas (25). ( ) x kT and 1 ( ) kT Λ are the instantaneous state vector and input value, respectively, at the instant kT .…”

Section: Time-discretization Of Nonlinear Control Systems With Time-dmentioning

confidence: 99%

“…A high-order method is one that provides increased accuracy with only a modest increase in the computational cost [22][23][24]. The ZOH and FOH assumptions no longer assure good control performance when large sampling intervals are adopted.…”

Section: Introductionmentioning

confidence: 99%

Second order hold and taylor series based discretization of SISO input time-delay systems

Zhang

Chong

2009

J Mech Sci Technol

View full text Add to dashboard Cite

Second order hold is a method that enables the discretization of input-driven nonlinear systems to be carried out with high precision. A new discretization scheme combining second order hold with the Taylor-series is proposed. The sampled-data representation and mathematical structure are explored. Both exact and approximate sampled-data representations are described in detail. The performance of the proposed algorithm is evaluated for three different systems. Various sampling rates, delay times and truncation orders of the Taylor-series are considered to investigate the proposed method. The results demonstrate that the proposed scheme is practical and easy to use for time-delay systems. Comparisons between the second, first and zero orders are given to show the advantages of the proposed method.

show abstract

On the zero- and first-order interpolation in synthesized sine waves for testing purposes

Cited by 12 publications

References 11 publications

A Reinforcement Learning Model for Optimal Treatment Strategies in Intensive Care: Assessment of the Role of Cardiorespiratory Features

A Reinforcement Learning Model for Optimal Treatment Strategies in Intensive Care: Assessment of the Role of Cardiorespiratory Features

Comparison study of the Taylor series based discretization method for nonlinear input-delay systems

Second order hold and taylor series based discretization of SISO input time-delay systems

Contact Info

Product

Resources

About