Occupational stress can cause health problems, productivity loss or absenteeism. Resilience interventions that help employees positively adapt to adversity can help prevent the negative consequences of occupational stress. Due to advances in sensor technology and smartphone applications, relatively unobtrusive self-monitoring of resilience-related outcomes is possible. With models that can recognize intra-individual changes in these outcomes and relate them to causal factors within the employee's context, an automated resilience intervention that gives personalized, just-in-time feedback can be developed. This paper presents the conceptual framework and methods behind the WearMe project, which aims to develop such models. A cyclical conceptual framework based on existing theories of stress and resilience is presented as the basis for the WearMe project. The operationalization of the concepts and the daily measurement cycle are described, including the use of wearable sensor technology (e.g., sleep tracking and heart rate variability measurements) and Ecological Momentary Assessment (mobile app). Analyses target the development of within-subject (n=1) and between-subjects models and include repeated measures correlation, multilevel modelling, time series analysis and Bayesian network statistics. Future work will focus on further developing these models and eventually explore the effectiveness of the envisioned personalized resilience system.
DOCUMENT
Estimating the remaining useful life (RUL) of an asset lies at the heart of prognostics and health management (PHM) of many operations-critical industries such as aviation. Mod- ern methods of RUL estimation adopt techniques from deep learning (DL). However, most of these contemporary tech- niques deliver only single-point estimates for the RUL without reporting on the confidence of the prediction. This practice usually provides overly confident predictions that can have severe consequences in operational disruptions or even safety. To address this issue, we propose a technique for uncertainty quantification (UQ) based on Bayesian deep learning (BDL). The hyperparameters of the framework are tuned using a novel bi-objective Bayesian optimization method with objectives the predictive performance and predictive uncertainty. The method also integrates the data pre-processing steps into the hyperparameter optimization (HPO) stage, models the RUL as a Weibull distribution, and returns the survival curves of the monitored assets to allow informed decision-making. We vali- date this method on the widely used C-MAPSS dataset against a single-objective HPO baseline that aggregates the two ob- jectives through the harmonic mean (HM). We demonstrate the existence of trade-offs between the predictive performance and the predictive uncertainty and observe that the bi-objective HPO returns a larger number of hyperparameter configurations compared to the single-objective baseline. Furthermore, we see that with the proposed approach, it is possible to configure models for RUL estimation that exhibit better or comparable performance to the single-objective baseline when validated on the test sets.
DOCUMENT
Fingermarks are highly relevant in criminal investigations for individualization purposes. In some cases, the question in court changes from ‘Who is the source of the fingermarks?’ to ‘How did the fingermark end up on the surface?’. In this paper, we explore evaluation of fingermarks given activity level propositions by using Bayesian networks. The variables that provide information on activity level questions for fingermarks are identified and their current state of knowledge with regards to fingermarks is discussed. We identified the variables transfer, persistency, recovery, background fingermarks, location of the fingermarks, direction of the fingermarks, the area of friction ridge skin that left the mark and pressure distortions as variables that may provide information on how a fingermark ended up on a surface. Using three case examples, we show how Bayesian networks can be used for the evaluation of fingermarks given activity level propositions.
DOCUMENT
