ENBIS-11 in Coimbra

4 – 8 September 2011 Abstract submission: 1 January – 25 June 2011

My abstracts


The following abstracts have been accepted for this event:

  • Supporting tool on the decision-making for the comfort conditions optimization

    Authors: Matilde A. Rodrigues, Celina P. Leão, Mónica Barroso, Pedro M. Arezes
    Affiliation: Engineering School of University of Minho, Guimarães, Portugal
    Primary area of focus / application: Business
    Keywords: Comfort , Decision-making , Environmental factors , Objective analysis , Subjective analysis
    Submitted at 21-Jun-2011 21:08 by Celina Leao
    Accepted (view paper)
    5-Sep-2011 16:49 Supporting tool on the decision-making for the comfort conditions optimization
    Briefly, comfort can be defined as a subjective reaction of an individual to his/her surrounding environment, stating a wellbeing feeling. One of the ergonomists’ objects of study and intervention, in indoor environments, is the comfort condition analysis. However, there are several environmental factors constraints to be taken into account, which are interpreted differently by each individual. Therefore, create comfortable environmental conditions for all individuals it is a complex process. The main goal of this work is to describe the developed tool to support the decision-making process in the environmental factors optimization.
    Environmental factors associated with comfort, noise, lighting, thermal environment and furniture, were analysed in two academic libraries, through an objective and subjective approach. The objective approach was based on a check-list application and on the thermal environment parameters, illuminance and noise levels and furniture dimensions measurements. For the subjective approach, was developed and applied a questionnaire, the tool used for the characterization of working conditions and comfort in both academic libraries. The internal consistency reliability of the questionnaire was analysed. The questionnaire allowed the characterization of the respondents (users) and the qualification of the environmental factors in relation to their perception, preference, acceptance and affection.
    The questionnaire provided information of how individuals express their comfort, which environmental factors are capable of induces discomfort sensations and the way of how individuals liked to modify these ones. The relation between the objective and subjective data allowed understanding which values of the environmental factors are capable to induce discomfort and the right way to its optimization.
    The obtained results show that the developed tool allows to classify and to characterize the environmental factors, as additional information to the analytical methods. The use of a subjective analysis tool as a complement to an objective approach is essential since the analytical methods do not express the individuals’ needs and expectations in the comfort definition.
  • Fractal Geometry Statistical Process Control for Pattern Based Processes

    Authors: Noa Ruschin Rimini, Irad Ben-Gal and Oded Maimon
    Affiliation: Department of Industrial Engineering, Tel-Aviv University, Tel-Aviv, Israel
    Primary area of focus / application: Process
    Keywords: Quality-control , Patterns , Data-Rich , Anomaly detection
    Submitted at 22-Jun-2011 08:31 by Irad Ben-Gal
    6-Sep-2011 11:25 Fractal Geometry Statistical Process Control for Pattern Based Processes
    We suggest a new statistical process control (SPC) approach for data-rich environments. The proposed approach is based on the theory of fractal geometry. In particular, we develop a monitoring scheme which is based on fractal representation of the monitored data at each stage, to account for online changes in monitored processes. There are several intuitive reasons why we use fractals for SPC applications. Fractals are naturally tuned to represent a large number of data patterns with complex dependence structures. They are known for their ability to visually represent data-complex and data-massive environments. Moreover, their construction does not require a-priori assumptions regarding the dependencies within the patterns or the data distribution. The proposed fractal SPC enables a dynamic inspection of non-linear and state-dependent processes with a discrete and finite state space. It is aimed for both univariate and multivariate data. The SPC is accomplished by applying a suggested Iterated Function System (IFS) to represent a process as a fractal, and exploiting an important attribute of the fractal, the fractal dimension as a monitoring statistic. We show how data patterns can be transformed into representing fractals in a manner that preserves their reference ("in-control") correlations and dependencies. The fractal statistics can be then used for anomaly detection, pattern analysis and root cause analysis. Numerical examples and comparisons to conventional SPC methods are given.
  • Health Outsourcing in Italy: the relationship between ASLs (local health authorities) and private operators

    Authors: R. Falotico, P. Mariani, G. Data
    Affiliation: Bicocca Applied Statistics Center (B-ASC), Università degli Studi Milano Bicocca
    Primary area of focus / application: Business
    Keywords: Outsourcing , local health authorities , pharmaceutical industry , Health customer satisfaction
    Submitted at 22-Jun-2011 14:53 by Rosa Falotico
    5-Sep-2011 16:57 Health Outsourcing in Italy: the relationship between ASLs (local health authorities) and private operators
    Outsourcing has shown itself worldwide to be a powerful instrument for development while also providing an important competitive advantage for both private and public companies. The budgetary constraints imposed by the Italian government on its health industry are enhancing the urgency to outsource to face costs. While partnerships between public and private health operators have rapidly developed elsewhere, Italy has been slower.
    Our study deals with the relationship between ASLs (the Italian local health authorities) and private operators outsourcing in Italy.
    We took a sample of 44 pharmaceutical companies (with a yearly turnover of about € 6 billion) and 34 ASL (with about 12 million users) to find out the areas in which they used outsourcing, the amount and the frequency of such investment, their satisfaction and, therefore, their future intentions. We analyzed the answers in search for possible relationships between location, size, frequency of use and other features to uncover a possible convergence between public and private interest in outsourcing.
    We analyzed the customer satisfaction derived from partnership between public and private operators using some important feature like number and qualification of contacts, companies dimension, different typologies of activities and more.
    The results suggest that public operators are more satisfied than private ones by the outsourcing activities taken. Nevertheless, pharmaceutical companies intend to invest in the future partnership more than the ASLs.
  • An Application of a Measurement System Analysis

    Authors: Misbah Ahmed
    Affiliation: Statistical Sciences Europe, GlaxoSmithKline (UK-Ware)
    Primary area of focus / application: Six Sigma
    Keywords: MSA , Measurement , System , Analysis , Variance , analytical , Variability
    Submitted at 22-Jun-2011 16:29 by Misbah Ahmed
    5-Sep-2011 16:40 An Application of a Measurement System Analysis

    Measurement System Analyses are widely used within the Pharmaceutical arena particularly to determine the magnitude of variability within an analytical method. The purpose of this poster is to outline and propose a possible approach to the design and analysis of such MSAs. With limited resourcing and money and time constraints, we advocate approaches based on a nested staggered design. We will discuss how testing for heterogeneity can be carried out with the use of the mixed procedure within SAS 9.2. This example will also illustrate the use of Bayesian methodology to determine the total variability and create tolerance intervals for the analytical method. Finally, this example will propose a suggestion to quantifying variability in the presence of fixed and random effects.
  • Accelerated Development and Improved Process Operations Using Advanced Multivariate Latent Variable Modeling

    Authors: Salvador Garcia-Munoz
    Affiliation: Pfizer Inc.
    Primary area of focus / application: Process
    Keywords: Multivariate Analysis , Quality by Design , Optimization , Pharmaceuticals
    Submitted at 22-Jun-2011 16:30 by Salvador Garcia-Munoz
    6-Sep-2011 11:15 Accelerated Development and Improved Process Operations Using Advanced Multivariate Latent Variable Modeling
    This talk will focus on the use of advanced multivariate latent variable models to aid the accelerated development of the product and the process, as well as the incorporation of these models into a process improvement cycle at the manufacturing scale. Multivariate data analysis (MVDA) has been extensively applied in the pharmaceutical sector to analyze spectral data and build calibration models to replace laboratory analysis (chemometrics); this is perhaps the most typical use of MVDA in pharma. There are however other areas of opportunity where the application of MVDA along with optimization techniques allow the hybrid integration of data derived empirical models with deterministic models driven from fundamental knowledge about the system. Industrial cases and applications will be shown on the advantages and opportunity areas.
  • Multivariate Process Capability Indices—A New Principal Component Analysis Approach

    Authors: Ingrid Tano and Kerstin Vännman
    Affiliation: University West and Luleå University of Technology, Sweden
    Primary area of focus / application: Process
    Keywords: Process Capability Index , Multivariate Process Capability Index , Principal Component Analys , Cp , Cpk , test
    Submitted at 23-Jun-2011 09:58 by Ingrid Tano
    6-Sep-2011 15:45 Multivariate Process Capability Indices—A New Principal Component Analysis Approach
    Often the quality of a process is determined by several correlated quality characteristics. In such cases the quality characteristic should be treated as a vector and a number of different multivariate process capability indices (MPCI:s) have been developed for such a situation. One of the existing MPCIs described in the literature is based on principal component analysis (PCA). The idea behind this MPCI is to do a PCA and consider only the first few principle components that explain the main part of the variability. Then one of the well-known univariate process capability indices is applied to each selected principle component and thereafter the univariate process capability indices for the selected principle components are combined to one MPCI. In order define this MPCI the tolerance region for the quality characteristic vector is transformed to a separate specification interval for each principal component. Recently it was shown that this transformation of the tolerance region into separate specification intervals is done in an improper way. And it is far from obvious how to obtain the individual specification limits for each selected principal component when the transformation is properly made. This problem gets complicated for 2 principal components and even worse for more than 2 principal components. We propose a new method based on PCA that circumvent these difficulties for the case when the tolerance region is a hyper-rectangular. This method first transforms the original data in a suitable way. Then PCA is done on the transformed data and it is shown that only the first principal component is needed to deem a process as capable or not at a stated significance level. Hence, a multivariate situation is transferred into a univariate situation and well-known theory for univariate process capability indices can be used to draw conclusions about the process capability. The properties of this method are investigated through a simulation study.