Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Kinematics of Big Biomedical Data to characterize temporal variability and seasonality of data repositories: Functional Data Analysis of data temporal evolution over non-parametric statistical manifolds

  • Sáez, Carlos
  • Garcia-Gomez, Juan M
[EN] Aim: The increasing availability of Big Biomedical Data is leading to large research data samples collected over long periods of time. We propose the analysis of the kinematics of data probability distributions over time towards the characterization of data temporal variability. Methods: First, we propose a kinematic model based on the estimation of a continuous data temporal trajectory, using Functional Data Analysis over the embedding of a non-parametric statistical manifold which points represent data temporal batches, the Information Geometric Temporal (IGT) plot. This model allows measuring the velocity and acceleration of data changes. Next, we propose a coordinate-free method to characterize the oriented seasonality of data based on the parallelism of lagged velocity vectors of the data trajectory throughout the IGT space, the Auto-Parallelism of Velocity Vectors (APVV) and APVVmap. Finally, we automatically explain the maximum variance components of the IGT space coordinates by means of correlating data points with known temporal factors from the domain application. Materials: Methods are evaluated on the US National Hospital Discharge Survey open dataset, consisting of 3,25M hospital discharges between 2000 and 2010. Results: Seasonal and abrupt behaviours were present on the estimated multivariate and univariate data trajectories. The kinematic analysis revealed seasonal effects and punctual increments in data celerity, the latter mainly related to abrupt changes in coding. The APVV and APVVmap revealed oriented seasonal changes on data trajectories. For most variables, their distributions tended to change to the same direction at a 12-month period, with a peak of change of directionality at mid and end of the year. Diagnosis and Procedure codes also included a 9-month periodic component. Kinematics and APVV methods were able to detect seasonal effects on extreme temporal subgrouped data, such as in Procedure code, where Fourier and autocorrelation methods were not able to. The automated explanation of IGT space coordinates was consistent with the results provided by the kinematic and seasonal analysis. Coordinates received different meanings according to the trajectory trend, seasonality and abrupt changes. Discussion: Treating data as a particle moving over time through a multidimensional probabilistic space and studying the kinematics of its trajectory has turned out to a new temporal variability methodology. Its results on the NHDS were aligned with the dataset and population descriptions found in the literature, contributing with a novel temporal variability characterization. We have demonstrated that the APVV and APVVmat are an appropriate tool for the coordinate-free and oriented analysis of trajectories or complex multivariate signals. Conclusion: The proposed methods comprise an exploratory methodology for the characterization of data temporal variability, what may be useful for a reliable reuse of Big Biomedical Data repositories acquired over long periods of time., This work was supported by UPV grant No. PAID-00-17, and projects DPI2016-80054-R and H2020-SC1-2016-CNECT No. 727560.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

EHRtemporalVariability: delineating temporal data-set shifts in electronic health records

  • Sáez Silvestre, Carlos|||0000-0003-2678-8249
  • Garcia-Gomez, Juan M
  • Gutiérrez-Sacristán, Alba
  • Kohane, Isaac
  • Avillach, Paul
[EN] Background: Temporal variability in health-care processes or protocols is intrinsic to medicine. Such variability can potentially introduce dataset shifts, a data quality issue when reusing electronic health records (EHRs) for secondary purposes. Temporal data-set shifts can present as trends, as well as abrupt or seasonal changes in the statistical distributions of data over time. The latter are particularly complicated to address in multimodal and highly coded data. These changes, if not delineated, can harm population and data-driven research, such as machine learning. Given that biomedical research repositories are increasingly being populated with large sets of historical data from EHRs, there is a need for specific software methods to help delineate temporal data-set shifts to ensure reliable data reuse. Results: EHRtemporalVariability is an open-source R package and Shiny app designed to explore and identify temporal data-set shifts. EHRtemporalVariability estimates the statistical distributions of coded and numerical data over time; projects their temporal evolution through non-parametric information geometric temporal plots; and enables the exploration of changes in variables through data temporal heat maps. We demonstrate the capability of EHRtemporalVariability to delineate data-set shifts in three impact case studies, one of which is available for reproducibility. Conclusions: EHRtemporalVariability enables the exploration and identification of data-set shifts, contributing to the broad examination and repurposing of large, longitudinal data sets. Our goal is to help ensure reliable data reuse for a wide range of biomedical data users. EHRtemporalVariability is designed for technical users who are programmatically utilizing the R package, as well as users who are not familiar with programming via the Shiny user interface., This work was supported by Universitat Politecnica de Valencia grant PAID-00-17, Generalitat Valenciana grant BEST/2018, and projects H2020-SC1-2016-CNECT No. 727560 and H2020-SC1-BHC-2018-2020 No. 825750
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Seasonal Local Models for Glucose Prediction in Type 1 Diabetes

  • Montaser, Eslam
  • Rossetti, Paolo
  • Rashid, Mudassir
  • Cinar, Ali
  • Diez, José-Luís|||0000-0002-5659-1212
  • Bondía Company, Jorge|||0000-0001-7286-3719
[EN] Linear empirical dynamic models have been widely used for blood glucose prediction and risks prevention in people with type 1 diabetes. More accurate blood glucose prediction models with longer prediction horizon (PH) are desirable to enable warnings to patients about imminent blood glucose changes with enough time to take corrective actions. In this study, a blood glucose prediction method is developed by integrating the predictions of a set of seasonal local models (each of them corresponding to different glucose profiles observed along historical data). In the modeling step, the number of sets and their corresponding glucose profiles characteristics are obtained by clustering techniques (Fuzzy C-Means). Then, Box-Jenkins methodology is used to identify a seasonal model for each set. Finally, blood glucose predictions of local models are integrated using different techniques. The proposed method is tested by using 18 60-h closed-loop experiments (including different exercise types and artificial pancreas strategies) and achieving mean absolute percentage error (MAPE) of 2.94%, 3.89%, 5.41%, 6.29% and 8.66% for 15-, 30-, 45-, 60-, and 90-min PHs, respectively., This work was supported in part by the Spanish Ministry of Economy and Competitiveness under Grants DPI2016-78831-C2-1-R, BES-2014-069253 and EEBB-I-17-12320, in part by the European Union through FEDER funds, and in part Universitat Politecnica de Valencia PAID-00-17 Program.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A neural network approach for chatter prediction in turning

  • Cherukuri, Harish
  • Schmitz, Tony L.
  • Pérez Bernabeu, Elena|||0000-0002-9221-7623
  • Sellés, M.A.|||0000-0002-0784-5757
[EN] Machining processes, including turning, are a critical capability for discrete part production. One limitation to high material removal rates and reduced cost in these processes is chatter, or unstable spindle speed-chip width combinations that exhibit self-excited vibration. In this paper, an artificial neural network (ANN) is applied to model turning stability. The analytical stability limit is used to generate a data set that trains the ANN. It is observed that the number and distribution of training points influences the ability of the ANN model to capture the smaller, more closely spaced lobes that occur at lower spindle speeds. Overall, the ANN is successful (>90% accuracy) at predicting the stability behavior after appropriate training., The authors gratefully acknowledge financial support from the UNC ROI program. Elena Perez-Bernabeu and Miguel Selles also acknowledge support from Universitat Politenica de Valencia (PAID-00-17). Additionally, some of the neural net figures and the 10-fold cross validation figures are based on the TikZ codes provided on StackExchange-TeX by various users. Harish Cherukuri would like to thank them for their valuable advice.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

An electroacoustic method for measuring airflow resistivity of porous sound-absorbing materials

  • Alba, Jesus|||0000-0002-4188-854X
  • del Rey, Romina|||0000-0001-5907-0677
  • Arenas, Jorge P.
  • Rodríguez-Vercher, Juan-Carlos
[EN] In this paper, a method for measuring the airflow resistivity of air-saturated porous sound-absorbing materials is presented. The method is based on a modification of the previous device developed by Dragonetti et al. The approach used in the present work involves a cavity and a Helmholtz resonator that are coupled through a loudspeaker so that the complete system behaves as a fourth-order symmetrical band-pass loudspeaker system. After a straightforward calibration, the airflow resistivity of a material sample is indirectly estimated from the direct measurement of the total electric impedance at the loudspeaker connection terminals. In this way, the use of microphones is not necessary, which makes its implementation very simple and inexpensive. Experimental results obtained with the present method agree well with those obtained through a standardized method as long as the values of the material's airflow resistance are not too high. (C) 2019 Elsevier Ltd. All rights reserved., The authors would like to gratefully acknowledge the support of CONICYT-FONDECYT under Grant 1171110 and to the Vicerectorate of R+i+t at Univ. Politecnica of Valencia, Grant PAID0017.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Machining Chatter Prediction Using a Data Learning Model

  • Cherukuri, Harish
  • Schmitz, Tony
  • Pérez Bernabeu, Elena|||0000-0002-9221-7623
  • Sellés, M.A.|||0000-0002-0784-5757
[EN] Machining processes, including turning, are a critical capability for discrete part production. One limitation to high material removal rates and reduced cost in these processes is chatter, or unstable spindle speed-chip width combinations that exhibit a self-excited vibration. In this paper, an artificial neural network (ANN)-a data learning model-is applied to model turning stability. The novel approach is to use a physics-based process model-the analytical stability limit-to generate a (synthetic) data set that trains the ANN. This enables the process physics to be combined with data learning in a hybrid approach. As anticipated, it is observed that the number and distribution of training points influences the ability of the ANN model to capture the smaller, more closely spaced lobes that occur at lower spindle speeds. Overall, the ANN is successful (>90% accuracy) at predicting the stability behavior after appropriate training., The authors gratefully acknowledge financial support fromtheUNCROI program. Elena Perez-Bernabeu and Miguel Selles also acknowledge support from Universitat Politecnica de Valencia (PAID-00-17). Additionally, some of the neural network and cross validation figures are based on the TikZ codes provided on StackExchange-TeX by various users. Harish Cherukuri would like to thank them for their valuable advice.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Assessing social performance of construction companies in public-works procurement: Data envelopment analysis based on the benefit of the doubt approach

  • Montalbán-Domingo, Laura|||0000-0002-9506-0350
  • García-Segura, Tatiana|||0000-0002-7059-0566
  • Sanz-Benlloch, Amalia|||0000-0001-8051-0649
  • Pellicer, Eugenio|||0000-0001-9100-0644
  • Torres-Machí, Cristina
  • Molenaar, Keith
[EN] There is an urgent need to improve the assessment of construction companies' Corporate Social Responsibility (CSR) in public-works procurement. Current procurement procedures assign a high level of subjectivity to CSR assessment and lack transparency. Existing research basically highlights the need to define weighting systems in which the importance of each social criterion is objective and based on the social weaknesses in the context of a project. In order to fulfill this gap, this research proposes a composite indicator for assessing CSR in public construction procurement. A Data Envelopment Analysis based on the Benefit of Doubt Approach (DEA-BOD) was chosen to define the weighting system based on the main social weaknesses that exist in the country where the contract is procured. The research employs simulation to assess the validity of this indicator. The results highlight that the use of national indices as a proxy for CSR indicators can be helpful in determining the level of importance of CSR in public procurement. The simulation showed that the proposed approach allows the objective comparison of CSR performance of construction companies, regardless of their size. This research assists decision-makers in properly integrating social sustainability in procurement procedures., The authors acknowledge the financial support of the Universitat Politecnica de Valencia (PAID -00-17) . The authors are grateful to the expert panel for their participation in this research.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Resilient structures in the seismic retrofitting of RC frames: A case study

  • Pallarés Rubio, Francisco Javier|||0000-0003-4298-2287
  • Pallarés Rubio, Luis|||0000-0003-2126-2387
  • Domínguez, David
[EN] It is very important to allocate valuable resources efficiently when reconstructing buildings after earthquake damage. This paper proposes the use of a simple seismic retrofitting system to make buildings more resilient than the stiffer systems such as the shear walls implemented in Chile after the earthquake in 2010. The proposal is based on the use of steel chevron-type braces in RC buildings as a dual system to improve the seismic performance of multistory buildings. A case study was carried out to compare the proposal with the shear wall solution for the typical seismic Chilean RC building from the structural and economic perspectives. The results show that it is more resilient than other stiffer seismic solutions, such as shear walls, reduces the demand, minimizes seismic damage, gives reliable earthquake protection and facilitates future upgrades and repairs while achieving the level of immediate occupancy without the costs of the shear walls system., The authors wish to thank the Universitat Politecnica de Valencia (UPV) (PAID-00-17), the Generalitat Valenciana (GVA) and the Spanish Ministry of Economy and Competitiveness (MINECO) for the grants and funds received to support this investigation: BIA2012-35186, BIA2015-70651-R, BEST/2018.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Fostering innovation through stakeholders&apos, engagement at the healthcare industry: Tapping the right key.

  • Segarra-Oña, Marival|||0000-0001-9674-9056
  • Peiró Signes, Angel|||0000-0002-1549-6972
  • Verma, Rohit
[EN] In this paper we investigate to which point each of the healthcare industry's stakeholders are influencing the final innovation outputs. We propose and test a model that puts together stakeholders' engagement, innovation objectives and innovation outputs. We analyze data from 400+ healthcare Spanish companies using Partial Least Squared modelling technique. Results show that stakeholders' engagement is crucial to orientate innovation objectives that are directly and positively related to innovation outputs. Also, results push to a higher implication of society in the co-creation and participation in innovation activities in the healthcare industry highlighting its importance as, both, triggers and the most benefited recipients. This paper uncovers the relationship among healthcare stakeholders and innovation outputs and also answers another research question-which stakeholders have a stronger relationship with innovation outputs. Implications suggest that healthcare industry managers and policy makers should build on the relationship with clients/customers/patients/final users as innovation-related information inputs as an effective way to improve their innovation outputs. (C) 2020 Elsevier B.V. All rights reserved, The authors would like to thank the Cornell Institute for Healthy Futures, CIHF, for hosting Prof Segarra-Oria and Prof Peiro-Signes. Also the Cornell SC Johnson College of Business for inviting Prof Peiro-Signes and Prof Segarra-Ofia as academic scholars and the Universitat Politecnica de Valencia for subsidising the research stage of Prof. Segarra-Ofia (PAID-00-17).