scholarly journals Mining Camera Traces to Estimate Interactions Between Healthcare Workers and Patients

2020 ◽  
Vol 41 (S1) ◽  
pp. s12-s12
Author(s):  
D. M. Hasibul Hasan ◽  
Philip Polgreen ◽  
Alberto Segre ◽  
Jacob Simmering ◽  
Sriram Pemmaraju
Keyword(s):  
Time Of Day ◽  
Microsoft Kinect ◽  
Critical Parameters ◽  
Model Parameters ◽  
Patient Room ◽  
University Of Iowa ◽  
Velocity Change ◽  
Fine Grained ◽  
Visit Frequency ◽  
Contact Patterns

Background: Simulations based on models of healthcare worker (HCW) mobility and contact patterns with patients provide a key tool for understanding spread of healthcare-acquired infections (HAIs). However, simulations suffer from lack of accurate model parameters. This research uses Microsoft Kinect cameras placed in a patient room in the medical intensive care unit (MICU) at the University of Iowa Hospitals and Clinics (UIHC) to obtain reliable distributions of HCW visit length and time spent by HCWs near a patient. These data can inform modeling efforts for understanding HAI spread. Methods: Three Kinect cameras (left, right, and door cameras) were placed in a patient room to track the human body (ie, left/right hands and head) at 30 frames per second. The results reported here are based on 7 randomly selected days from a total of 308 observation days. Each tracked body may have multiple raw segments over the 2 camera regions, which we “stitch” up by matching features (eg, direction, velocity, etc), to obtain complete trajectories. Due to camera noise, in a substantial fraction of the frames bodies display unnatural characteristics including frequent and rapid directional and velocity change. We use unsupervised learning techniques to identify such “ghost” frames and we remove from our analysis bodies that have 20% or more “ghost” frames. Results: The heat map of hand positions (Fig. 1) shows that high-frequency locations are clustered around the bed and more to the patient’s right in accordance with the general medical practice of performing patient exams from their right. HCW visit frequency per hour (mean, 6.952; SD, 2.855) has 2 peaks, 1 during morning shift and 1 during the afternoon shift, with a distinct decrease after midnight. Figure 2 shows visit length (in minutes) distribution (mean, 1.570; SD, 2.679) being dominated by “check in visits” of <30 seconds. HCWs do not spend much time at touching distance from patients during short-length visits, and the fraction of time spent near the patient’s bed seems to increase with visit length up to a point. Conclusions: Using fine-grained data, this research extracts distributions of these critical parameters of HCW–patient interactions: (1) HCW visit length, (2) HCW visit frequency as a function of time of day, and (3) time spent by HCW within touching distance of patient as a function of visit length. To the best of our knowledge, we provide the first reliable estimates of these parameters.Funding: NoneDisclosures: None

scholarly journals Explaining Neural Networks Using Attentive Knowledge Distillation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1280
Author(s):  
Hyeonseok Lee ◽  
Sungchan Kim
Keyword(s):  
Neural Networks ◽  
Model Prediction ◽  
Saliency Map ◽  
Model Parameters ◽  
Learning Capability ◽  
Fine Grained ◽  
Network Layers ◽  
Saliency Maps ◽  
Novel Approach ◽  
Knowledge Distillation

Explaining the prediction of deep neural networks makes the networks more understandable and trusted, leading to their use in various mission critical tasks. Recent progress in the learning capability of networks has primarily been due to the enormous number of model parameters, so that it is usually hard to interpret their operations, as opposed to classical white-box models. For this purpose, generating saliency maps is a popular approach to identify the important input features used for the model prediction. Existing explanation methods typically only use the output of the last convolution layer of the model to generate a saliency map, lacking the information included in intermediate layers. Thus, the corresponding explanations are coarse and result in limited accuracy. Although the accuracy can be improved by iteratively developing a saliency map, this is too time-consuming and is thus impractical. To address these problems, we proposed a novel approach to explain the model prediction by developing an attentive surrogate network using the knowledge distillation. The surrogate network aims to generate a fine-grained saliency map corresponding to the model prediction using meaningful regional information presented over all network layers. Experiments demonstrated that the saliency maps are the result of spatially attentive features learned from the distillation. Thus, they are useful for fine-grained classification tasks. Moreover, the proposed method runs at the rate of 24.3 frames per second, which is much faster than the existing methods by orders of magnitude.

scholarly journals Recrystallization of ice enhances the creep and vulnerability to fracture of ice shelves 

2021 ◽  
Author(s):  
Meghana Ranganathan ◽  
Brent Minchew ◽  
Colin Meyer ◽  
Matej Pec
Keyword(s):  
Grain Size ◽  
Ice Sheet ◽  
Shear Zones ◽  
Dislocation Creep ◽  
Model Parameters ◽  
Localized Deformation ◽  
Ice Shelves ◽  
Fine Grained ◽  
Initiation And Propagation ◽  
Rapid Deformation

&lt;p&gt;The initiation and propagation of fractures in floating regions of Antarctica has the potential to destabilize large regions of the ice sheet, leading to significant sea-level rise. While observations have shown rapid, localized deformation and damage in the margins of fast-flowing glaciers, there remain gaps in our understanding of how rapid deformation affects the creep and toughness of ice. Here we derive a model for dynamic recrystallization in ice and other rocks that includes a novel representation of migration recrystallization, which is absent from existing models but is likely to be dominant in warm areas undergoing rapid deformation within the ice sheet. We show that, in regions of elevated strain rate, grain sizes in ice may be larger than expected (~15 mm) due to migration recrystallization, a significant deviation from solid earth studies which find fine-grained rock in shear zones. This may imply that ice in shear margins deforms primarily by dislocation creep, suggesting a flow-law exponent of n=4 in these regions. Further, we find from existing models that this increase in grain size results in a decrease in tensile strength of ice by ~75% in the margins of glaciers. Thus, we expect that this increase in grain size makes the margins of fast-flowing glaciers less viscous and more vulnerable to fracture than we may suppose from standard model parameters.&lt;/p&gt;

Calculation on the Free Energy of Mixing of some Silane Systems

2011 ◽  
Vol 391-392 ◽  
pp. 1017-1021
Author(s):  
Ru Zhang ◽  
Yan Fen Wu ◽  
Ping Hu
Keyword(s):  
Free Energy ◽  
Thermodynamic Properties ◽  
Activity Coefficients ◽  
Influence Factors ◽  
Critical Parameters ◽  
Model Parameters ◽  
Free Energies ◽  
Wilson Model ◽  
Energy Of Mixing ◽  
Free Energy Of Mixing

Six binary silane systems were chosen to calculate the activity coefficients (γ) and free energies of mixing (ΔGm). These systems included: methyldichlorosilane + methyltrichlorosilane, methyldichlorosilane + methylvinyldichlorosilane, methyldichlorosilane + toluene, methyltrichlorosilane + methylvinyldichlorosilane, methyltrichlorosilane + toluene, methylvinyldichlorosilane + toluene. Based on the Antoine constants, critical parameters of the pure components and Wilson model parameters, γ and ΔGmwere calculated. The influence factors of these thermodynamic properties were also discussed.

Calculation of the Separation Factor for some Silane Systems

2011 ◽  
Vol 391-392 ◽  
pp. 1012-1016
Author(s):  
Zu Min Qiu ◽  
Zhong Wei Liu ◽  
Ping Hu
Keyword(s):  
Mole Fraction ◽  
Separation Factor ◽  
Critical Parameters ◽  
Effect Of Temperature ◽  
Model Parameters ◽  
Wilson Model ◽  
Separation Factors

Six ternary silane systems were selected for the separation factor (s) calculation. These systems were: methyldichlorosilane+methyltrichlorosilane+benzene, methyldichlorosilane+ methyltrichlorosilane+dimethyldichlorosilane, methyldichlorosilane+methyltrichlorosilane+ toluene, methyltrichlorosilane+methylvinyldichlorosilane+toluene,methyldichlorosilane+methyltrichloro- silane+methylvinyldichlorosilane, dimethyldiethoxysilane+methyltriethoxysilane+ethanol. Based on the Antoine constants, critical parameters of the pure components and Wilson model parameters, the separation factors were obtained through a program. The effect of temperature and mole fraction to s was also discussed.

scholarly journals Refining Coarse-Grained Spatial Data Using Auxiliary Spatial Data Sets with Various Granularities

2019 ◽  
Vol 33 ◽  
pp. 5091-5099 ◽  
Author(s):  
Yusuke Tanaka ◽  
Tomoharu Iwata ◽  
Toshiyuki Tanaka ◽  
Takeshi Kurashima ◽  
Maya Okawa ◽  
...  
Keyword(s):  
Gaussian Process ◽  
Spatial Data ◽  
Coarse Grained ◽  
Model Parameters ◽  
Data Sets ◽  
Auxiliary Data ◽  
Fine Grained ◽  
Proposed Model ◽  
Spatial Data Sets ◽  
Target Data

We propose a probabilistic model for refining coarse-grained spatial data by utilizing auxiliary spatial data sets. Existing methods require that the spatial granularities of the auxiliary data sets are the same as the desired granularity of target data. The proposed model can effectively make use of auxiliary data sets with various granularities by hierarchically incorporating Gaussian processes. With the proposed model, a distribution for each auxiliary data set on the continuous space is modeled using a Gaussian process, where the representation of uncertainty considers the levels of granularity. The finegrained target data are modeled by another Gaussian process that considers both the spatial correlation and the auxiliary data sets with their uncertainty. We integrate the Gaussian process with a spatial aggregation process that transforms the fine-grained target data into the coarse-grained target data, by which we can infer the fine-grained target Gaussian process from the coarse-grained data. Our model is designed such that the inference of model parameters based on the exact marginal likelihood is possible, in which the variables of finegrained target and auxiliary data are analytically integrated out. Our experiments on real-world spatial data sets demonstrate the effectiveness of the proposed model.

scholarly journals Actors, actions, and uncertainties: optimizing decision-making based on 3-D structural geological models

Solid Earth ◽  
2019 ◽  
Vol 10 (6) ◽  
pp. 2015-2043 ◽  
Author(s):  
Fabian Antonio Stamm ◽  
Miguel de la Varga ◽  
Florian Wellmann
Keyword(s):  
Decision Making ◽  
Loss Function ◽  
Probabilistic Methods ◽  
Stochastic Simulations ◽  
Critical Parameters ◽  
Model Parameters ◽  
Final Decision ◽  
Expected Loss ◽  
True Value ◽  
Geological Models

Abstract. Uncertainties are common in geological models and have a considerable impact on model interpretations and subsequent decision-making. This is of particular significance for high-risk, high-reward sectors. Recent advances allows us to view geological modeling as a statistical problem that we can address with probabilistic methods. Using stochastic simulations and Bayesian inference, uncertainties can be quantified and reduced by incorporating additional geological information. In this work, we propose custom loss functions as a decision-making tool that builds upon such probabilistic approaches. As an example, we devise a case in which the decision problem is one of estimating the uncertain economic value of a potential fluid reservoir. For subsequent true value estimation, we design a case-specific loss function to reflect not only the decision-making environment, but also the preferences of differently risk-inclined decision makers. Based on this function, optimizing for expected loss returns an actor's best estimate to base decision-making on, given a probability distribution for the uncertain parameter of interest. We apply the customized loss function in the context of a case study featuring a synthetic 3-D structural geological model. A set of probability distributions for the maximum trap volume as the parameter of interest is generated via stochastic simulations. These represent different information scenarios to test the loss function approach for decision-making. Our results show that the optimizing estimators shift according to the characteristics of the underlying distribution. While overall variation leads to separation, risk-averse and risk-friendly decisions converge in the decision space and decrease in expected loss given narrower distributions. We thus consider the degree of decision convergence to be a measure for the state of knowledge and its inherent uncertainty at the moment of decision-making. This decisive uncertainty does not change in alignment with model uncertainty but depends on alterations of critical parameters and respective interdependencies, in particular relating to seal reliability. Additionally, actors are affected differently by adding new information to the model, depending on their risk affinity. It is therefore important to identify the model parameters that are most influential for the final decision in order to optimize the decision-making process.

Model for predicting resilient modulus of unsaturated subgrade soil using soil-water characteristic curve

2015 ◽  
Vol 52 (10) ◽  
pp. 1605-1619 ◽  
Author(s):  
Zhong Han ◽  
Sai K. Vanapalli
Keyword(s):  
Moisture Content ◽  
Soil Water ◽  
Resilient Modulus ◽  
Characteristic Curve ◽  
Optimum Moisture Content ◽  
Model Parameters ◽  
Soil Water Characteristic Curve ◽  
Subgrade Soils ◽  
Fine Grained ◽  
Proposed Model

Soil suction (ψ) is one of the key factors that influence the resilient modulus (MR) of pavement subgrade soils. There are several models available in the literature for predicting the MR–ψ correlations. However, the various model parameters required in the existing models are generally determined by performing regression analysis on extensive experimental data of the MR–ψ relationships, which are cumbersome, expensive, and time-consuming to obtain. In this paper, a model is proposed to predict the variation of the MR with respect to the ψ for compacted fine-grained subgrade soils. The information of (i) the MR values at optimum moisture content condition (MROPT) and saturation condition (MRSAT), which are typically determined for use in pavement design practice; (ii) the ψ values at optimum moisture content condition (ψOPT); and (iii) the soil-water characteristic curve (SWCC) is required for using this model. The proposed model is validated by providing comparisons between the measured and predicted MR–ψ relationships for 11 different compacted fine-grained subgrade soils that were tested following various protocols (a total of 16 sets of data, including 210 testing results). The proposed model was found to be suitable for predicting the variation of the MR with respect to the ψ for all the subgrade soils using a single-valued model parameter ξ, which was found to be equal to 2.0. The proposed model is promising for use in practice, as it only requires conventional soil properties and alleviates the need for experimental determination of the MR–ψ relationships.

Heterogeneities in water contact patterns and the epidemiology of schistosoma haematobium

Parasitology ◽  
1991 ◽  
Vol 103 (3) ◽  
pp. 363-370 ◽  
Author(s):  
S. K. Chandiwana ◽  
M. E. J. Woolhouse
Keyword(s):  
Time Of Day ◽  
Limited Information ◽  
Water Contact ◽  
Contact Rates ◽  
Contact Patterns ◽  
Contact Behaviour ◽  
Control Programmes ◽  
The Mean ◽  
Individual Contact ◽  
Age And Sex

Variations in the amount of water contact made by individuals and in the amount of water contact made at different sites may have significant impacts on patterns of human schistosome infection. Previous studies have reported variations in the rate of water contact and differences in the sites used between age/sex classes, but there is limited information on variations in individual water contact behaviour. In this paper we report and analyse observations of essentially all water contacts made over a two week period by all individuals in a rural community in eastern Zimbabwe. The mean rate of water contact was 0.43 contacts/person/day. These data were over-dispersed, ranging from zero to 3.3 contacts/person/day; 90% of contacts were made by only 37% of the population. Contact rates were related to age (highest in 8 to 10-year-olds) but not sex, with substantial variation unaccounted for by these variables. Age and sex classes differed in types of water-related activities and the time of day of contact. A greater diversity of sites was used by children than by adults and by males than by females. Individual contact rates were correlated with intensities of infection, although the risk of infection per contact was estimated to be highest in 2 to 4-year-old children and higher for males than females. Five contact sites were used during the study period, with more than 50% of contacts occurring at just 2 sites. Different age and sex classes used different sites and there were additional site-related differences in types of activity and the time of day of use. The implications of these water contact patterns for schistosome epidemiology are discussed. In particular the results provide strong quantitative support for control programmes aimed at heavily used sites (e.g. focal mollusciciding) or at the minority of individuals making most water contacts (e.g. targeted chemotherapy).

scholarly journals Experimental and mathematical insights on the interactions between poliovirus and a defective interfering genome

2021 ◽  
Vol 17 (9) ◽  
pp. e1009277
Author(s):  
Yuta Shirogane ◽  
Elsa Rousseau ◽  
Jakub Voznica ◽  
Yinghong Xiao ◽  
Weiheng Su ◽  
...  
Keyword(s):  
Rna Viruses ◽  
Equation Model ◽  
Critical Parameters ◽  
Model Parameters ◽  
Experimental Measurements ◽  
Genome Replication ◽  
Virus Population ◽  
Wild Type ◽  
Ordinary Differential Equation Model ◽  
Differential Equation Model

During replication, RNA viruses accumulate genome alterations, such as mutations and deletions. The interactions between individual variants can determine the fitness of the virus population and, thus, the outcome of infection. To investigate the effects of defective interfering genomes (DI) on wild-type (WT) poliovirus replication, we developed an ordinary differential equation model, which enables exploring the parameter space of the WT and DI competition. We also experimentally examined virus and DI replication kinetics during co-infection, and used these data to infer model parameters. Our model identifies, and our experimental measurements confirm, that the efficiencies of DI genome replication and encapsidation are two most critical parameters determining the outcome of WT replication. However, an equilibrium can be established which enables WT to replicate, albeit to reduced levels.

scholarly journals A Mechanogenetic Model of Exercise-Induced Pulmonary Haemorrhage in the Thoroughbred Horse

Genes ◽  
2019 ◽  
Vol 10 (11) ◽  
pp. 880
Author(s):  
Blott ◽  
Cunningham ◽  
Malkowski ◽  
Brown ◽  
Rauch
Keyword(s):  
Cell Adhesion ◽  
Physical Model ◽  
Cell Biology ◽  
Pulmonary Haemorrhage ◽  
Cell Stiffness ◽  
Critical Parameters ◽  
Primary Study ◽  
Model Parameters ◽  
Exercise Induced ◽  
Cell Cell

Exercise-induced pulmonary haemorrhage (EIPH) occurs in horses performing high-intensity athletic activity. The application of physics principles to derive a ‘physical model’, which is coherent with existing physiology and cell biology data, shows that critical parameters for capillary rupture are cell–cell adhesion and cell stiffness (cytoskeleton organisation). Specifically, length of fracture in the capillary is a ratio between the energy involved in cell–cell adhesion and the stiffness of cells suggesting that if the adhesion diminishes and/or that the stiffness of cells increases EIPH is more likely to occur. To identify genes associated with relevant cellular or physiological phenotypes, the physical model was used in a post-genome-wide association study (GWAS) to define gene sets associated with the model parameters. The primary study was a GWAS of EIPH where the phenotype was based on weekly tracheal wash samples collected over a two-year period from 72 horses in a flat race training yard. The EIPH phenotype was determined from cytological analysis of the tracheal wash samples, by scoring for the presence of red blood cells and haemosiderophages. Genotyping was performed using the Illumina Equine SNP50 BeadChip and analysed using linear regression in PLINK. Genes within significant genome regions were selected for sets based on their GeneOntology biological process, and analysed using fastBAT. The gene set analysis showed that genes associated with cell stiffness (cytoskeleton organisation) and blood flow have the most significant impact on EIPH risk.

Sign in / Sign up

Export Citation Format

Share Document