scholarly journals Conclusions: Towards a Bayesian Modelling Process

2021 ◽  
pp. 185-192
Author(s):  
Jakub Bijak ◽  
Peter W. F. Smith
Keyword(s):  
Bayesian Model ◽  
Research Programme ◽  
Lessons Learned ◽  
Bayesian Modelling ◽  
Self Reflection ◽  
Model Based ◽  
Embedded Model ◽  
Recent Developments ◽  
Future Viability ◽  
Modelling Process

AbstractIn the concluding chapter we summarise the theoretical, methodological and practical outcomes of the model-based process of scientific enquiry presented in the book, against the wider background of recent developments in demography and population studies. We offer a critical self-reflection on further potential and on limitations of Bayesian model-based approaches, alongside the lessons learned from the modelling exercise discussed throughout this book. As concluding thoughts, we suggest potential ways forward for statistically-embedded model-based computational social studies, including an assessment of the future viability of the wider model-based research programme, and its possible contributions to policy and decision making.

An interpretable mechanism for personalized recommendation based on cross feature

2021 ◽  
pp. 1-12
Author(s):  
Lv YE ◽  
Yue Yang ◽  
Jian-Xu Zeng
Keyword(s):  
Recommender System ◽  
Online Shopping ◽  
Side Information ◽  
Attention Mechanism ◽  
Personalized Recommendation ◽  
Model Based ◽  
Embedded Model ◽  
Feature Attention ◽  
Match Score

The existing recommender system provides personalized recommendation service for users in online shopping, entertainment, and other activities. In order to improve the probability of users accepting the system’s recommendation service, compared with the traditional recommender system, the interpretable recommender system will give the recommendation reasons and results at the same time. In this paper, an interpretable recommendation model based on XGBoost tree is proposed to obtain comprehensible and effective cross features from side information. The results are input into the embedded model based on attention mechanism to capture the invisible interaction among user IDs, item IDs and cross features. The captured interactions are used to predict the match score between the user and the recommended item. Cross-feature attention score is used to generate different recommendation reasons for different user-items.Experimental results show that the proposed algorithm can guarantee the quality of recommendation. The transparency and readability of the recommendation process has been improved by providing reference reasons. This method can help users better understand the recommendation behavior of the system and has certain enlightenment to help the recommender system become more personalized and intelligent.

scholarly journals A Reference Framework to Combine Model-Based Design and AR to Improve Social Sustainability

2021 ◽  
Vol 13 (4) ◽  
pp. 2031
Author(s):  
Fabio Grandi ◽  
Riccardo Karim Khamaisi ◽  
Margherita Peruzzini ◽  
Roberto Raffaeli ◽  
Marcello Pellicciari
Keyword(s):  
Positive Impact ◽  
Cost Effective ◽  
Digital Models ◽  
Model Based ◽  
Digital Contents ◽  
Recent Developments ◽  
Virtual Simulations ◽  
Product And Process ◽  
The Impact ◽  
Time Information

Product and process digitalization is pervading numerous areas in the industry to improve quality and reduce costs. In particular, digital models enable virtual simulations to predict product and process performances, as well as to generate digital contents to improve the general workflow. Digital models can also contain additional contents (e.g., model-based design (MBD)) to provide online and on-time information about process operations and management, as well as to support operator activities. The recent developments in augmented reality (AR) offer new specific interfaces to promote the great diffusion of digital contents into industrial processes, thanks to flexible and robust applications, as well as cost-effective devices. However, the impact of AR applications on sustainability is still poorly explored in research. In this direction, this paper proposed an innovative approach to exploit MBD and introduce AR interfaces in the industry to support human intensive processes. Indeed, in those processes, the human contribution is still crucial to guaranteeing the expected product quality (e.g., quality inspection). The paper also analyzed how this new concept can benefit sustainability and define a set of metrics to assess the positive impact on sustainability, focusing on social aspects.

Justice versus Social Justice in South Africa: Quo vadis?

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Marelize Isabel Schoeman
Keyword(s):  
South Africa ◽  
Social Justice ◽  
Criminal Justice ◽  
Criminal Justice System ◽  
Justice System ◽  
Lessons Learned ◽  
Historical Discourse ◽  
Self Reflection ◽  
Underlying Basis ◽  
Quo Vadis

This article explores the concept of criminal justice as a formal process in which parties are judged and often adjudged from the paradigmatic perspective of legal guilt versus legal innocence. While this function of a criminal-justice system is important – and indeed necessary – in any ordered society, a society in transition such as South Africa must question the underlying basis of justice. This self-reflection must include an overview questioning whether the criminal-justice system and its rules are serving the community as originally intended or have become a self-serving function of state in which the final pursuit is outcome-driven as opposed to process-driven. The process of reflection must invariably find its genesis in the question: ‘What is justice?’ While this rhetorical phraseology has become trite through overuse, the author submits that the question remains of prime importance when considered contemporarily but viewed through the lens of historical discourse in African philosophy. In essence, the question remains unanswered. Momentum is added to this debate by the recent movement towards a more human rights and restorative approach to justice as well as the increased recognition of traditional legal approaches to criminal justice. This discussion is wide and in order to delimit its scope the author relies on a Socratically influenced method of knowledge-mining to determine the philosophical principles underpinning the justice versus social justice discourse. It is proposed that lessons learned from African philosophies about justice and social justice can be integrated into modern-day justice systems and contribute to an ordered yet socially oriented approach to justice itself.

Model-Based Systems Engineering: Lessons Learned from the Joint Tactical Radio System

2017 ◽  
Vol 89 (1) ◽  
pp. 97-106 ◽  
Author(s):  
Vincent J. Kovarik ◽  
Raghavan Muralidharan
Keyword(s):  
Systems Engineering ◽  
Lessons Learned ◽  
Radio System ◽  
Model Based ◽  
Joint Tactical Radio System ◽  
Model Based Systems Engineering

USING CLASSIFICATION TREES FOR SOFTWARE QUALITY MODELS: LESSONS LEARNED

1999 ◽  
Vol 09 (02) ◽  
pp. 217-231 ◽  
Author(s):  
TAGHI M. KHOSHGOFTAAR ◽  
EDWARD B. ALLEN ◽  
ARCHANA NAIK ◽  
WENDELL D. JONES ◽  
JOHN P. HUDEPOHL
Keyword(s):  
Software Quality ◽  
Classification Trees ◽  
Lessons Learned ◽  
Quality Models ◽  
Model Based ◽  
Software Product ◽  
High Assurance ◽  
Process Metrics ◽  
Product And Process ◽  
Software Quality Models

High software reliability is an important attribute of high-assurance systems. Software quality models yield timely predictions of quality indicators on a module-by-module basis, enabling one to focus on finding faults early in development. This paper introduces the Classification And Regression Trees (CART) a algorithm to practitioners in high-assurance systems engineering. This paper presents practical lessons learned on building classification trees for software quality modeling, including an innovative way to control the balance between misclassification rates. A case study of a very large telecommunications system used CART to build software quality models. The models predicted whether or not modules would have faults discovered by customers, based on various sets of software product and process metrics as independent variables. We found that a model based on two software product metrics had comparable accuracy to a model based on forty product and process metrics.

scholarly journals Hybrid elicitation and indirect Bayesian inference with quantile-parametrized likelihood

2021 ◽  
Author(s):  
Dmytro Perepolkin ◽  
Benjamin Goodrich ◽  
Ullrika Sahlin
Keyword(s):  
Bayesian Inference ◽  
Bayesian Model ◽  
Probability Distributions ◽  
Expert Elicitation ◽  
Model Based ◽  
Dirichlet Prior

This paper extends the application of indirect Bayesian inference to probability distributions defined in terms of quantiles of the observable quantities. Quantile-parameterized distributions are characterized by high shape flexibility and interpretability of its parameters, and are therefore useful for elicitation on observables. To encode uncertainty in the quantiles elicited from experts, we propose a Bayesian model based on the metalog distribution and a version of the Dirichlet prior. The resulting “hybrid” expert elicitation protocol for characterizing uncertainty in parameters using questions about the observable quantities is discussed and contrasted to parametric and predictive elicitation.

A Hierarchical Bayesian Model-Based Uncertainty Analysis for Tsunami Heights along Shorelines in Korea

2016 ◽  
Vol 75 (sp1) ◽  
pp. 1157-1161 ◽  
Author(s):  
Hyun-Han Kwon ◽  
Jin-Young Kim ◽  
Byoung Han Choi ◽  
Yong-Sik Cho
Keyword(s):  
Uncertainty Analysis ◽  
Bayesian Model ◽  
Hierarchical Bayesian ◽  
Hierarchical Bayesian Model ◽  
Model Based

Continual Learning with Bayesian Model Based on a Fixed Pre-trained Feature Extractor

2021 ◽  
pp. 397-406
Author(s):  
Yang Yang ◽  
Zhiying Cui ◽  
Junjie Xu ◽  
Changhong Zhong ◽  
Ruixuan Wang ◽  
...  
Keyword(s):  
Bayesian Model ◽  
Model Based ◽  
Feature Extractor ◽  
Continual Learning

scholarly journals A Bayesian model integration for mutation calling through data partitioning

2019 ◽  
Vol 35 (21) ◽  
pp. 4247-4254 ◽  
Author(s):  
Takuya Moriyama ◽  
Seiya Imoto ◽  
Shuto Hayashi ◽  
Yuichi Shiraishi ◽  
Satoru Miyano ◽  
...  
Keyword(s):  
Hierarchical Model ◽  
Bayesian Model ◽  
Information Sources ◽  
Tumor Model ◽  
Bayesian Hierarchical Model ◽  
Generative Models ◽  
Error Model ◽  
Model Integration ◽  
Bayesian Hierarchical ◽  
Model Based

Abstract Motivation Detection of somatic mutations from tumor and matched normal sequencing data has become among the most important analysis methods in cancer research. Some existing mutation callers have focused on additional information, e.g. heterozygous single-nucleotide polymorphisms (SNPs) nearby mutation candidates or overlapping paired-end read information. However, existing methods cannot take multiple information sources into account simultaneously. Existing Bayesian hierarchical model-based methods construct two generative models, the tumor model and error model, and limited information sources have been modeled. Results We proposed a Bayesian model integration framework named as partitioning-based model integration. In this framework, through introducing partitions for paired-end reads based on given information sources, we integrate existing generative models and utilize multiple information sources. Based on that, we constructed a novel Bayesian hierarchical model-based method named as OHVarfinDer. In both the tumor model and error model, we introduced partitions for a set of paired-end reads that cover a mutation candidate position, and applied a different generative model for each category of paired-end reads. We demonstrated that our method can utilize both heterozygous SNP information and overlapping paired-end read information effectively in simulation datasets and real datasets. Availability and implementation https://github.com/takumorizo/OHVarfinDer. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Development of a Hydrogeological Model of the Borrowdale Volcanics at Sellafield

1997 ◽  
Vol 1 (1) ◽  
pp. 35-46 ◽  
Author(s):  
R. J. Lunn ◽  
A. D. Lunn ◽  
R. Mackay
Keyword(s):  
Radioactive Waste ◽  
Transport Model ◽  
Research Programme ◽  
Maximum Principal Stress ◽  
Hydrogeological Model ◽  
Borehole Data ◽  
The Matrix ◽  
Recent Developments ◽  
Conceptual Hydrogeological Model ◽  
Current Maximum

Abstract. This work has arisen out of recent developments within the radioactive waste research programme managed by Her Majesty's Inspectorate of Pollution, UK (HMIP)*, to develop an integrated flow and transport model for the potential deep radioactive waste repository at Sellafield. One of the largest sources of uncertainty in model predictions, is the characterisation of the hydrogeological properties of the underlying strata, in particular, of the Borrowdale Volcanic Group (BVG) within which the repository is to be located. Analysis of the available borehole data (that released by the proponent company, Nirex, by December 1995) for the BVG formation has indicated a dual regime consisting of flow within faults and flow within the matrix (or an equivalent porous medium containing micro-fractures). Significant relationships between permeability, depth and the presence and orientation of faults have been identified; they account for a variation of up to 6 orders of magnitude in mean permeability measurements. This can be explained in part by the effect of the orientation of the current maximum principal stress directions within the BVG: however, it is likely that permeability is also dependent on the existence of fracture families, which cannot be effectively identified from the data currently available. These analyses have enabled considerable insight to be gained into the dominant features of flow within the BVG. The conceptual hydrogeological model derived here will have a significant effect on the outcome and reliability of future radionuclide transport predictions in the Sellafield area.

Sign in / Sign up

Export Citation Format

Share Document