scholarly journals Application of Deep Neural Networks as a Prescreening Tool to Assign Individualized Absorption Models in Pharmacokinetic Analysis

Pharmaceutics ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 797
Author(s):  
Mutaz M. Jaber ◽  
Burhaneddin Yaman ◽  
Kyriakie Sarafoglou ◽  
Richard C. Brundage
Keyword(s):  
Deep Neural Networks ◽  
Specific Model ◽  
Classification Performance ◽  
Pharmacokinetic Analysis ◽  
Model Parameters ◽  
Absorption Model ◽  
First Order ◽  
Population Pk ◽  
Absorption Models ◽  
Validation Set

A specific model for drug absorption is necessarily assumed in pharmacokinetic (PK) analyses following extravascular dosing. Unfortunately, an inappropriate absorption model may force other model parameters to be poorly estimated. An added complexity arises in population PK analyses when different individuals appear to have different absorption patterns. The aim of this study is to demonstrate that a deep neural network (DNN) can be used to prescreen data and assign an individualized absorption model consistent with either a first-order, Erlang, or split-peak process. Ten thousand profiles were simulated for each of the three aforementioned shapes and used for training the DNN algorithm with a 30% hold-out validation set. During the training phase, a 99.7% accuracy was attained, with 99.4% accuracy during in the validation process. In testing the algorithm classification performance with external patient data, a 93.7% accuracy was reached. This algorithm was developed to prescreen individual data and assign a particular absorption model prior to a population PK analysis. We envision it being used as an efficient prescreening tool in other situations that involve a model component that appears to be variable across subjects. It has the potential to reduce the time needed to perform a manual visual assignment and eliminate inter-assessor variability and bias in assigning a sub-model.

scholarly journals Determination of exothermic batch reactor specific model parameters

2019 ◽  
Vol 292 ◽  
pp. 01063
Author(s):  
Lubomír Macků
Keyword(s):  
Rate Constant ◽  
Reaction Rate ◽  
Batch Reactor ◽  
Specific Model ◽  
Reaction Rate Constant ◽  
Order Reaction ◽  
First Order Reaction ◽  
Model Parameters ◽  
Reactor Model ◽  
First Order

An alternative method of determining exothermic reactor model parameters which include first order reaction rate constant is described in this paper. The method is based on known in reactor temperature development and is suitable for processes with changing quality of input substances. This method allows us to evaluate the reaction substances composition change and is also capable of the reaction rate constant (parameters of the Arrhenius equation) determination. Method can be used in exothermic batch or semi- batch reactors running processes based on the first order reaction. An example of such process is given here and the problem is shown on its mathematical model with the help of simulations.

scholarly journals Sharing Residual Units Through Collective Tensor Factorization To Improve Deep Neural Networks

2018 ◽  
Author(s):  
Yunpeng Chen ◽  
Xiaojie Jin ◽  
Bingyi Kang ◽  
Jiashi Feng ◽  
Shuicheng Yan
Keyword(s):  
Neural Networks ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
Tensor Decomposition ◽  
Classification Performance ◽  
Model Parameters ◽  
Tensor Factorization ◽  
Unified Framework ◽  
Benchmark Datasets ◽  
Basic Network

The residual unit and its variations are wildly used in building very deep neural networks for alleviating optimization difficulty. In this work, we revisit the standard residual function as well as its several successful variants and propose a unified framework based on tensor Block Term Decomposition (BTD) to explain these apparently different residual functions from the tensor decomposition view. With the BTD framework, we further propose a novel basic network architecture, named the Collective Residual Unit (CRU). CRU further enhances parameter efficiency of deep residual neural networks by sharing core factors derived from collective tensor factorization over the involved residual units. It enables efficient knowledge sharing across multiple residual units, reduces the number of model parameters, lowers the risk of over-fitting, and provides better generalization ability. Extensive experimental results show that our proposed CRU network brings outstanding parameter efficiency -- it achieves comparable classification performance with ResNet-200 while using a model size as small as ResNet-50 on the ImageNet-1k and Places365-Standard benchmark datasets.

scholarly journals Trigonometric Inference Providing Learning in Deep Neural Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6704
Author(s):  
Jingyong Cai ◽  
Masashi Takemoto ◽  
Yuming Qiu ◽  
Hironori Nakajo
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Activation Function ◽  
Trigonometric Approximation ◽  
Model Parameters ◽  
Training Algorithms ◽  
Activation Functions ◽  
Classical Training ◽  
Sum Formula

Despite being heavily used in the training of deep neural networks (DNNs), multipliers are resource-intensive and insufficient in many different scenarios. Previous discoveries have revealed the superiority when activation functions, such as the sigmoid, are calculated by shift-and-add operations, although they fail to remove multiplications in training altogether. In this paper, we propose an innovative approach that can convert all multiplications in the forward and backward inferences of DNNs into shift-and-add operations. Because the model parameters and backpropagated errors of a large DNN model are typically clustered around zero, these values can be approximated by their sine values. Multiplications between the weights and error signals are transferred to multiplications of their sine values, which are replaceable with simpler operations with the help of the product to sum formula. In addition, a rectified sine activation function is utilized for further converting layer inputs into sine values. In this way, the original multiplication-intensive operations can be computed through simple add-and-shift operations. This trigonometric approximation method provides an efficient training and inference alternative for devices with insufficient hardware multipliers. Experimental results demonstrate that this method is able to obtain a performance close to that of classical training algorithms. The approach we propose sheds new light on future hardware customization research for machine learning.

scholarly journals Fate of false vacua in holographic first-order phase transitions

2020 ◽  
Vol 2020 (12) ◽  
Author(s):  
Francesco Bigazzi ◽  
Alessio Caddeo ◽  
Aldo L. Cotrone ◽  
Angel Paredes
Keyword(s):  
Phase Transitions ◽  
Chiral Symmetry ◽  
Metastable Phase ◽  
Chiral Symmetry Breaking ◽  
Model Parameters ◽  
Temperature Phase ◽  
Thin Wall ◽  
Critical Temperatures ◽  
First Order ◽  
First Order Phase

Abstract Using the holographic correspondence as a tool, we study the dynamics of first-order phase transitions in strongly coupled gauge theories at finite temperature. Considering an evolution from the large to the small temperature phase, we compute the nucleation rate of bubbles of true vacuum in the metastable phase. For this purpose, we find the relevant configurations (bounces) interpolating between the vacua and we compute the related effective actions. We start by revisiting the compact Randall-Sundrum model at high temperature. Using holographic renormalization, we compute the derivative term in the effective bounce action, that was missing in the literature. Then, we address the full problem within the top-down Witten-Sakai-Sugimoto model. It displays both a confinement/deconfinement and a chiral symmetry breaking/restoration phase transition which, depending on the model parameters, can happen at different critical temperatures. For the confinement/deconfinement case we perform the numerical analysis of an effective description of the transition and also provide analytic expressions using thick and thin wall approximations. For the chiral symmetry transition, we implement a variational approach that allows us to address the challenging non-linear problem stemming from the Dirac-Born-Infeld action.

scholarly journals New Mathematical Modeling Approach for Predicting Microbial Inactivation by High Hydrostatic Pressure

2007 ◽  
Vol 73 (8) ◽  
pp. 2468-2478 ◽  
Author(s):  
Bernadette Klotz ◽  
D. Leo Pyle ◽  
Bernard M. Mackey
Keyword(s):  
Microbial Inactivation ◽  
Inactivation Kinetics ◽  
Published Data ◽  
Model Parameters ◽  
Order Kinetic ◽  
Square Root ◽  
Additional Time ◽  
Decimal Reduction Time ◽  
First Order ◽  
Primary Model

ABSTRACT A new primary model based on a thermodynamically consistent first-order kinetic approach was constructed to describe non-log-linear inactivation kinetics of pressure-treated bacteria. The model assumes a first-order process in which the specific inactivation rate changes inversely with the square root of time. The model gave reasonable fits to experimental data over six to seven orders of magnitude. It was also tested on 138 published data sets and provided good fits in about 70% of cases in which the shape of the curve followed the typical convex upward form. In the remainder of published examples, curves contained additional shoulder regions or extended tail regions. Curves with shoulders could be accommodated by including an additional time delay parameter and curves with tails shoulders could be accommodated by omitting points in the tail beyond the point at which survival levels remained more or less constant. The model parameters varied regularly with pressure, which may reflect a genuine mechanistic basis for the model. This property also allowed the calculation of (a) parameters analogous to the decimal reduction time D and z, the temperature increase needed to change the D value by a factor of 10, in thermal processing, and hence the processing conditions needed to attain a desired level of inactivation; and (b) the apparent thermodynamic volumes of activation associated with the lethal events. The hypothesis that inactivation rates changed as a function of the square root of time would be consistent with a diffusion-limited process.

scholarly journals Inflationary cosmology in unimodular F(T) gravity

2017 ◽  
Vol 32 (21) ◽  
pp. 1750114 ◽  
Author(s):  
Kazuharu Bamba ◽  
Sergei D. Odintsov ◽  
Emmanuel N. Saridakis
Keyword(s):  
Spectral Index ◽  
Teleparallel Gravity ◽  
Specific Model ◽  
Inflationary Cosmology ◽  
Model Parameters ◽  
De Sitter ◽  
Reconstruction Procedure ◽  
Additional Advantage ◽  
Slow Roll ◽  
Good Agreement

We investigate the inflationary realization in the context of unimodular F(T) gravity, which is based on the F(T) modification of teleparallel gravity, in which one imposes the unimodular condition through the use of Lagrange multipliers. We develop the general reconstruction procedure of the F(T) form that can give rise to a given scale-factor evolution, and then we apply it in the inflationary regime. We extract the Hubble slow-roll parameters that allow us to calculate various inflation-related observables, such as the scalar spectral index and its running, the tensor-to-scalar ratio, and the tensor spectral index. Then, we examine the particular cases of de Sitter and power-law inflation, of Starobinsky inflation, as well as inflation in a specific model of unimodular F(T) gravity. As we show, in all cases the predictions of our scenarios are in a very good agreement with Planck observational data. Finally, inflation in unimodular F(T) gravity has the additional advantage that it always allows for a graceful exit for specific regions of the model parameters.

AR-Tri-Training: Tri-Training with Assistant Strategy

2014 ◽  
Vol 513-517 ◽  
pp. 1840-1844 ◽  
Author(s):  
Long Jie Cui ◽  
Hong Li Wang ◽  
Rong Yi Cui
Keyword(s):  
Learning Strategy ◽  
Voice Recognition ◽  
Classification Performance ◽  
Experimental Results ◽  
Training Algorithm ◽  
Information Strategy ◽  
Testing Rate ◽  
Rich Information ◽  
Validation Set

The classification performance of the classifier is weakened because the noise samples are introduced for the use of unlabeled samples in Tri-training. In this paper a new Tri-training style algorithm named AR-Tri-training (Tri-training with assistant and rich strategy) is proposed. Firstly, the assistant learning strategy is posed. Then the supporting learner is designed by combining the assistant learning strategy with rich information strategy. The number of mislabeled samples produced in the iterations of three classifiers mutually labeling are reduced by use of the supporting learner, moreover the unlabeled samples and the misclassified samples of validation set can be fully used. The proposed algorithm is applied to voice recognition. The experimental results show that AR-Tri-training algorithm can compensate for the shortcomings of Tri-training algorithm, further improve the testing rate.

Unknown Parameter Excitation and Estimation for Complex Systems With Dynamic Performances

2021 ◽  
Vol 143 (9) ◽  
Author(s):  
Yi-Ping Chen ◽  
Kuei-Yuan Chan
Keyword(s):  
Complex Systems ◽  
Simulation Models ◽  
Credible Interval ◽  
Specific Model ◽  
Model Parameters ◽  
Real Model ◽  
Dynamic Case ◽  
Dynamic Performances ◽  
Validation Stage ◽  
Setting Parameters

Abstract Simulation models play crucial roles in efficient product development cycles, therefore many studies aim to improve the confidence of a model during the validation stage. In this research, we proposed a dynamic model validation to provide accurate parameter settings for minimal output errors between simulation models and real model experiments. The optimal operations for setting parameters are developed to maximize the effects by specific model parameters while minimizing interactions. To manage the excessive costs associated with simulations of complex systems, we propose a procedure with three main features: the optimal excitation based on global sensitivity analysis (GSA) is done via metamodel techniques, for estimating parameters with the polynomial chaos-based Kalman filter, and validating the updated model based on hypothesis testing. An illustrative mathematical model was used to demonstrate the detail processes in our proposed method. We also apply our method on a vehicle dynamic case with a composite maneuver for exciting unknown model parameters such as inertial and coefficients of the tire model; the unknown model parameters were successfully estimated within a 95% credible interval. The contributions of this research are also underscored through multiple cases.

scholarly journals Population Pharmacokinetic Analysis of Voriconazole and Anidulafungin in Adult Patients with Invasive Aspergillosis

2014 ◽  
Vol 58 (8) ◽  
pp. 4718-4726 ◽  
Author(s):  
Ping Liu ◽  
Diane R. Mould
Keyword(s):  
Invasive Aspergillosis ◽  
Area Under The Curve ◽  
Compartment Model ◽  
Population Pharmacokinetic Analysis ◽  
Institutional Review Boards ◽  
Pharmacokinetic Analysis ◽  
Population Pharmacokinetic ◽  
Parameter Estimates ◽  
First Order ◽  
Two Compartment Model

ABSTRACTTo assess the pharmacokinetics (PK) of voriconazole and anidulafungin in patients with invasive aspergillosis (IA) in comparison with other populations, sparse PK data were obtained for 305 adults from a prospective phase 3 study comparing voriconazole and anidulafungin in combination versus voriconazole monotherapy (voriconazole, 6 mg/kg intravenously [IV] every 12 h [q12h] for 24 h followed by 4 mg/kg IV q12h, switched to 300 mg orally q12h as appropriate; with placebo or anidulafungin IV, a 200-mg loading dose followed by 100 mg q24h). Voriconazole PK was described by a two-compartment model with first-order absorption and mixed linear and time-dependent nonlinear (Michaelis-Menten) elimination; anidulafungin PK was described by a two-compartment model with first-order elimination. For voriconazole, the normal inverse Wishart prior approach was implemented to stabilize the model. Compared to previous models, no new covariates were identified for voriconazole or anidulafungin. PK parameter estimates of voriconazole and anidulafungin are in agreement with those reported previously except for voriconazole clearance (the nonlinear clearance component became minimal). At a 4-mg/kg IV dose, voriconazole exposure tended to increase slightly as age, weight, or body mass index increased, but the difference was not considered clinically relevant. Estimated voriconazole exposures in IA patients at 4 mg/kg IV were higher than those reported for healthy adults (e.g., the average area under the curve over a 12-hour dosing interval [AUC0–12] at steady state was 46% higher); while it is not definitive, age and concomitant medications may impact this difference. Estimated anidulafungin exposures in IA patients were comparable to those reported for the general patient population. This study was approved by the appropriate institutional review boards or ethics committees and registered on ClinicalTrials.gov (NCT00531479).

Cluster Analysis of Dynamic Parameters of Gene Expression

2003 ◽  
Vol 01 (03) ◽  
pp. 447-458 ◽  
Author(s):  
Xiwei Wu ◽  
T. Gregory Dewey
Keyword(s):  
Gene Expression ◽  
Cell Cycle ◽  
Cluster Analysis ◽  
Hierarchical Cluster ◽  
Specific Model ◽  
Model Parameters ◽  
Dynamic Parameters ◽  
Clustering Methods ◽  
Transition Matrices ◽  
Great Utility

Cluster analysis has proven to be a valuable statistical method for analyzing whole genome expression data. Although clustering methods have great utility, they do represent a lower level statistical analysis that is not directly tied to a specific model. To extend such methods and to allow for more sophisticated lines of inference, we use cluster analysis in conjunction with a specific model of gene expression dynamics. This model provides phenomenological dynamic parameters on both linear and non-linear responses of the system. This analysis determines the parameters of two different transition matrices (linear and nonlinear) that describe the influence of one gene expression level on another. Using yeast cell cycle microarray data as test set, we calculated the transition matrices and used these dynamic parameters as a metric for cluster analysis. Hierarchical cluster analysis of this transition matrix reveals how a set of genes influence the expression of other genes activated during different cell cycle phases. Most strikingly, genes in different stages of cell cycle preferentially activate or inactivate genes in other stages of cell cycle, and this relationship can be readily visualized in a two-way clustering image. The observation is prior to any knowledge of the chronological characteristics of the cell cycle process. This method shows the utility of using model parameters as a metric in cluster analysis.

Sign in / Sign up

Export Citation Format

Share Document