scholarly journals Understanding melanopsin using bayesian generative models − an Introduction

2016 ◽  
Author(s):  
Benedikt V Ehinger ◽  
Dennis Eickelbeck ◽  
Katharina Spoida ◽  
Stefan Herlitze ◽  
Peter König
Keyword(s):  
Hierarchical Modeling ◽  
Ganglion Cells ◽  
Rapid Development ◽  
Quantitative Description ◽  
Specific Protein ◽  
Generative Models ◽  
Bayesian Hierarchical ◽  
Basic Model ◽  
Hidden Markov Process ◽  
Different Color

Understanding biological processes implies a quantitative description. In recent years a new tool set, Bayesian hierarchical modeling, has seen rapid development. We use these methods to model kinetics of a specific protein in a neuroscience context: melanopsin. Melanopsin is a photoactive protein in retinal ganglion cells. Due to its photoactivity, melanopsin is widely used in optogenetic experiments and an important component in the elucidation of neuronal interactions. Thus it is important to understand the relevant processes and develop mechanistic models. Here, with a focus on methodological aspects, we develop, implement, fit and discuss Bayesian generative models of melanopsin dynamics. We start with a sketch of a basic model and then translate it into formal probabilistic language. As melanopsin occurs in at least two states, a resting and a firing state, a basic model is defined by a non-stationary two state hidden Markov process. Subsequently we add complexities in the form of (1) an hierarchical extension to fit multiple cells; (2) a wavelength dependency, to investigate the response at different color of light stimulation; (3) an additional third state to investigate whether melanopsin is bi- or tri-stable; (4) differences between different sub-types of melanopsin as found in different species. This application of modeling melanopsin dynamics demonstrates several benefits of Bayesian methods. They directly model uncertainty of parameters, are flexible in the distributions and relations of parameters in the modeling, and allow including prior knowledge, for example parameter values based on biochemical data.  

scholarly journals Variance prior specification for a basket trial design using Bayesian hierarchical modeling

2018 ◽  
Vol 16 (2) ◽  
pp. 142-153 ◽  
Author(s):  
Kristen M Cunanan ◽  
Alexia Iasonos ◽  
Ronglai Shen ◽  
Mithat Gönen
Keyword(s):  
Standard Deviation ◽  
Prior Distribution ◽  
Hierarchical Modeling ◽  
Bayesian Hierarchical Modeling ◽  
Bayesian Hierarchical ◽  
Inverse Gamma ◽  
Wide Range ◽  
Basket Trial ◽  
Basket Trials ◽  
Variance Parameter

Background: In the era of targeted therapies, clinical trials in oncology are rapidly evolving, wherein patients from multiple diseases are now enrolled and treated according to their genomic mutation(s). In such trials, known as basket trials, the different disease cohorts form the different baskets for inference. Several approaches have been proposed in the literature to efficiently use information from all baskets while simultaneously screening to find individual baskets where the drug works. Most proposed methods are developed in a Bayesian paradigm that requires specifying a prior distribution for a variance parameter, which controls the degree to which information is shared across baskets. Methods: A common approach used to capture the correlated binary endpoints across baskets is Bayesian hierarchical modeling. We evaluate a Bayesian adaptive design in the context of a non-randomized basket trial and investigate three popular prior specifications: an inverse-gamma prior on the basket-level variance, a uniform prior and half-t prior on the basket-level standard deviation. Results: From our simulation study, we can see that the inverse-gamma prior is highly sensitive to the input hyperparameters. When the prior mean value of the variance parameter is set to be near zero [Formula: see text], this can lead to unacceptably high false-positive rates [Formula: see text] in some scenarios. Thus, use of this prior requires a fully comprehensive sensitivity analysis before implementation. Alternatively, we see that a prior that places sufficient mass in the tail, such as the uniform or half-t prior, displays desirable and robust operating characteristics over a wide range of prior specifications, with the caveat that the upper bound of the uniform prior and the scale parameter of the half-t prior must be larger than 1. Conclusion: Based on the simulation results, we recommend that those involved in designing basket trials that implement hierarchical modeling avoid using a prior distribution that places a majority of the density mass near zero for the variance parameter. Priors with this property force the model to share information regardless of the true efficacy configuration of the baskets. Many commonly used inverse-gamma prior specifications have this undesirable property. We recommend to instead consider the more robust uniform prior or half-t prior on the standard deviation.

scholarly journals Employee engagement and Emotional Exhaustion of Fly-In-Fly-Out Workers: A Diary Study

2018 ◽  
Author(s):  
Simon Albrecht ◽  
Jeromy Anglim
Keyword(s):  
Employee Engagement ◽  
Emotional Exhaustion ◽  
Hierarchical Modeling ◽  
Job Demands ◽  
Job Resources ◽  
Future Research ◽  
Bayesian Hierarchical ◽  
Emotional Demand ◽  
Work Cycle ◽  
Emotional Demands

Objective: Although Fly-in-Fly-Out (FIFO) work practices are widely used, little is known about their impact on the motivation and wellbeing of FIFO workers across the course of their work cycles. Drawing from the Job Demands-Resources model, we aimed to test for the within-person effects of time of work cycle, job demands, and job resources on emotional exhaustion and employee engagement at three day-intervals. Method: Fifty-two FIFO workers filled out three or more on-line diary surveys after every three days of their on-site work roster. The survey consisted of items drawn from previously validated scales. Bayesian hierarchical modeling of the day-level data was conducted. Results: Workers, on average, showed a decline in engagement and supervisor support, and an increase in emotional demand over the course of the work cycle. The results of the hierarchical modeling showed that day-level autonomy predicted day-level engagement and that day-level workload and emotional demands predicted emotional exhaustion. Conclusions: The findings highlight the importance of managing FIFO employees' day-to-day experiences of job demands and job resources because of their influence on employee engagement and emotional exhaustion. To best protect FIFO worker day-level wellbeing, employing organisations should ensure optimal levels of job autonomy, workload, and emotional demands. Practical implications, study limitations and areas for future research are outlined.

scholarly journals Curriculum Learning for Natural Answer Generation

2018 ◽  
Author(s):  
Cao Liu ◽  
Shizhu He ◽  
Kang Liu ◽  
Jun Zhao
Keyword(s):  
Full Advantage ◽  
Real World ◽  
Large Scale ◽  
Question Answering ◽  
Generative Models ◽  
The Internet ◽  
Basic Model ◽  
The Arts ◽  
Learning Data

By reason of being able to obtain natural language responses, natural answers are more favored in real-world Question Answering (QA) systems. Generative models learn to automatically generate natural answers from large-scale question answer pairs (QA-pairs). However, they are suffering from the uncontrollable and uneven quality of QA-pairs crawled from the Internet. To address this problem, we propose a curriculum learning based framework for natural answer generation (CL-NAG), which is able to take full advantage of the valuable learning data from a noisy and uneven-quality corpus. Specifically, we employ two practical measures to automatically measure the quality (complexity) of QA-pairs. Based on the measurements, CL-NAG firstly utilizes simple and low-quality QA-pairs to learn a basic model, and then gradually learns to produce better answers with richer contents and more complete syntaxes based on more complex and higher-quality QA-pairs. In this way, all valuable information in the noisy and uneven-quality corpus could be fully exploited. Experiments demonstrate that CL-NAG outperforms the state-of-the-arts, which increases 6.8% and 8.7% in the accuracy for simple and complex questions, respectively.

Comparative Experiment of Color Reproduction Methods

2014 ◽  
Vol 1051 ◽  
pp. 967-970
Author(s):  
Qi Jia ◽  
Xu Liang Lv ◽  
Wei Dong Xu ◽  
Jiang Hua Hu ◽  
Xian Hui Rong
Keyword(s):  
Polynomial Regression ◽  
Rapid Development ◽  
Color Space ◽  
Digital Camera ◽  
Color Difference ◽  
High Tech ◽  
Comparative Experiment ◽  
Color Reproduction ◽  
Different Color ◽  
Time Image

Digital camera which has the advantage of real-time image transferring and easily processing is more and more widely used in the packaging and printing industry with the rapid development of high-tech electronics industry. However, the color in digital camera is not accurate which affect the application. To minimize the color difference between the color in the digital camera and the real color, the color reproduction methods is developing. The field comparative experiment is carried out to compare the performance of color reproduction methods, such as polynomial regression algorithm in different color space, and color checker passport. The results show that fourth order polynomial regression color reproduction in XYZ color space has the best performance.

A bank-account-information-based credit scoring method with Bayesian hierarchical modeling

2021 ◽  
pp. 2150036
Author(s):  
Suguru Yamanaka ◽  
Rei Yamamoto
Keyword(s):  
Hierarchical Modeling ◽  
Credit Scoring ◽  
Information Criterion ◽  
Bayesian Hierarchical Modeling ◽  
Scoring Method ◽  
Bank Account ◽  
Bayesian Hierarchical ◽  
Account Information ◽  
Activity Information ◽  
Financial Technology

Recent interest in financial technology (fintech) lending business has caused increasing challenges of credit scoring models using bank account activity information. Our work aims to develop a new credit scoring method based on bank account activity information. This method incorporates borrower firms’ segment-level heterogeneity, such as a segment of sales size and firm age. We employ Bayesian hierarchical modeling, which mitigates data sparsity issue due to data segmentation. We describe our modeling procedures, including data handling and variable selection. Empirical results show that our model outperforms the traditional logistic model for credit scoring in information criterion. Our model realizes advanced credit scoring based on bank account activity information in fintech lending businesses, taking segment-specific features into credit risk assessment.

Reanalysis of Historical Mourning Dove Nest Data by Using a Bayesian Approach

2016 ◽  
Vol 7 (2) ◽  
pp. 292-303 ◽  
Author(s):  
John Snyder ◽  
Xiaoming Gao ◽  
John H. Schulz ◽  
Joshua J. Millspaugh
Keyword(s):  
Hierarchical Modeling ◽  
Nest Survival ◽  
Original Study ◽  
Egg Laying ◽  
Mourning Dove ◽  
Zenaida Macroura ◽  
Bayesian Hierarchical ◽  
Trade Offs ◽  
Original Dataset ◽  
Nest Height

Abstract We reconstructed a historical mourning dove Zenaida macroura nesting dataset to estimate nest survival and investigate the effect of covariates by using a Bayesian hierarchical model. During 1979–1980, 106 study areas, across 27 states, were established to conduct weekly nest searches during February–October. We used roughly 11,000 data sheets to reconstruct the dataset containing 7,139 nests compared to 6,950 nests in the original study. Original and reconstructed nest survival estimates showed little difference by using the original analysis methodology, that is, the Mayfield method. Thus, we assumed we closely replicated the original dataset; distributions of nests found, birds hatched, and birds fledged also showed similar trends. After confirming the validity of the reconstructed dataset, we evaluated 10 different models by using a Bayesian hierarchical modeling approach; the final model contained variables for nest age or stage, nest height, region, but not habitat. The year 1980 had a higher probability of nest survival compared to 1979, and nest survival increased with nest height. The nest encounter probability increased at days 4 and 11 of the nesting cycle, providing some insight into the convenience sampling used in the original study. Our reanalysis with the use of covariates confirms previous hypotheses that mourning doves are habitat generalists, but it adds new information showing lower nest survival during nest initiation and egg laying and a decline when fledglings would be 4 or 5 d old. Regional differences in mourning dove nest survival confirm existing hypotheses about northern states demonstrating greater nest success compared to southern states where differences may reflect trade-offs associated with northern latitudes, weather differences, or food availability.

Sign in / Sign up

Export Citation Format

Share Document