Search results for "Data-driven"
showing 10 items of 59 documents
Towards a validated definition of the clinical transition to secondary progressive multiple sclerosis: A study from the Italian MS Register.
2022
Background: Definitions for reliable identification of transition from relapsing-remitting multiple sclerosis (MS) to secondary progressive (SP)MS in clinical cohorts are not available. Objectives: To compare diagnostic performances of two different data-driven SPMS definitions. Methods: Data-driven SPMS definitions based on a version of Lorscheider’s algorithm (DDA) and on the EXPAND trial inclusion criteria were compared, using the neurologist’s definition (ND) as gold standard, in terms of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), Akaike information criterion (AIC) and area under the curve (AUC). Results: A cohort of 10,240 MS patients wi…
(Pre)occupations: A data-driven model of jobs and its consequences for categorization and evaluation
2018
Abstract We present a data-driven model of stereotypes about occupations (total N = 3919). Across two classification systems and national contexts (U.S.; Germany), we show remarkable convergence in the stereotype dimensions spontaneously employed to make sense of occupational groups (agency; progressiveness). Further studies show that these dimensions reflect presumed characteristics of job holders and not just describe their occupational role (Study 2), and that proximity of occupations on the emerging stereotype model increased superordinate categorization (Study 3) and contagious transfer of (positive and negative) valence from one occupation to another (Study 4). Together these studies …
Transition to secondary progression in relapsing-onset multiple sclerosis: Definitions and risk factors
2021
Background: No uniform criteria for a sensitive identification of the transition from relapsing–remitting multiple sclerosis (MS) to secondary-progressive multiple sclerosis (SPMS) are available. Objective: To compare risk factors of SPMS using two definitions: one based on the neurologist judgment (ND) and an objective data-driven algorithm (DDA). Methods: Relapsing-onset MS patients ( n = 19,318) were extracted from the Italian MS Registry. Risk factors for SPMS and for reaching irreversible Expanded Disability Status Scale (EDSS) 6.0, after SP transition, were estimated using multivariable Cox regression models. Results: SPMS identified by the DDA ( n = 2343, 12.1%) were older, more disa…
Flexible Data Driven Inventory Management with Interactive Multiobjective Lot Size Optimization
2021
We study data-driven decision support and formalise a path from data to decision making. We focus on lot sizing in inventory management with stochastic demand and propose an interactive multi-objective optimisation approach. We forecast demand with a Bayesian model, which is based on sales data. After identifying relevant objectives relying on the demand model, we formulate an optimisation problem to determine lot sizes for multiple future time periods. Our approach combines different interactive multi-objective optimisation methods for finding the best balance among the objectives. For that, a decision maker with substance knowledge directs the solution process with one’s preference inform…
On Dealing with Uncertainties from Kriging Models in Offline Data-Driven Evolutionary Multiobjective Optimization
2019
Many works on surrogate-assisted evolutionary multiobjective optimization have been devoted to problems where function evaluations are time-consuming (e.g., based on simulations). In many real-life optimization problems, mathematical or simulation models are not always available and, instead, we only have data from experiments, measurements or sensors. In such cases, optimization is to be performed on surrogate models built on the data available. The main challenge there is to fit an accurate surrogate model and to obtain meaningful solutions. We apply Kriging as a surrogate model and utilize corresponding uncertainty information in different ways during the optimization process. We discuss…
INTERPRETING LARGE SCALE NATIONAL LEVEL ASSESSMENT DATA IN MATHEMATICS BY USING RASCH ANALYSIS
2020
Latvia is undergoing a nation-wide curriculum reform in general education, with an aim to help students to develop 21st century skills. In order to successfully implement reform, not only teacher performance in the classroom is important, but also the transformation of the school culture is of high priority. One of the key dimensions that is characteristic for a school as learning organization culture is whether it has data-driven culture and is using data on continuous basis to improve student achievement. Large scale national level assessment data is used for many different purposes, however, this data only rarely is recognised as useful data source for planning actions to improve student…
Restrictions on data-driven political micro-targeting in Germany
2017
The revitalisation of canvassing in recent elections is strongly related to campaigns´ growing possibilities for analysing voter data to gain knowledge about their constituents, identifying their most likely voters and serving up personalised messages through individual conversations. The research literature about political micro-targeting hardly ever focusses on campaigns in parliamentary democracies with strict data protection laws. Based on in-depth expert interviews we introduce a framework of constraints in strategic political communication and reveal several restrictions on the macro, meso and micro levels which hinder the implementation of sophisticated data strategies in Germany. We…
A Data-Driven Architecture for Personalized QoE Management in 5G Wireless Networks
2017
With the emergence of a variety of new wireless network types, business types, and QoS in a more autonomic, diverse, and interactive manner, it is envisioned that a new era of personalized services has arrived, which emphasizes users' requirements and service experiences. As a result, users' QoE will become one of the key features in 5G/future networks. In this article, we first review the state of the art of QoE research from several perspectives, including definition, influencing factors, assessment methods, QoE models, and control methods. Then a data-driven architecture for enhancing personalized QoE is proposed for 5G networks. Under this architecture, we specifically propose a two-ste…
Autonomous Robotic Sensing for Simultaneous Geometric and Volumetric Inspection of Free-Form Parts
2022
Robotic sensing is used in many sectors to improve the inspection of large and/or complex parts, enhancing data acquisition speed, part coverage and inspection reliability. Several automated or semi-automated solutions have been proposed to enable the automated deployment of specific types of sensors. The trajectory to be followed by a robotic manipulator is typically obtained through the offline programmed tool paths for the inspection of a part. This method is acceptable for a part with known geometry in a well-structured and controlled environment. The part undergoing assessment needs to be precisely registered with respect to the robot reference system. It implies the need for a setup p…
TSVD as a Statistical Estimator in the Latent Semantic Analysis Paradigm
2015
The aim of this paper is to present a new point of view that makes it possible to give a statistical interpretation of the traditional latent semantic analysis (LSA) paradigm based on the truncated singular value decomposition (TSVD) technique. We show how the TSVD can be interpreted as a statistical estimator derived from the LSA co-occurrence relationship matrix by mapping probability distributions on Riemanian manifolds. Besides, the quality of the estimator model can be expressed by introducing a figure of merit arising from the Solomonoff approach. This figure of merit takes into account both the adherence to the sample data and the simplicity of the model. In our model, the simplicity…