ABSTRACT
In additive manufacturing (AM), process defects such as keyhole pores are difficult to anticipate, affecting the quality and integrity of the AM-produced materials. Hence, considerable efforts have aimed to predict these process defects by training machine learning (ML) models using passive measurements such as acoustic emissions. This work considered a dataset in which keyhole pores of a laser powder bed fusion (LPBF) experiment were identified using X-ray radiography and then registered both in space and time to acoustic measurements recorded during the LPBF experiment. Due to AM's intrinsic process controls, where a pore-forming event is relatively rare, the acoustic datasets collected during monitoring include more non-pores than pores. In other words, the dataset for ML model development is imbalanced. Moreover, this imbalanced and sparse data phenomenon remains ubiquitous across many AM monitoring schemes since training data is nontrivial to collect. Hence, we propose a machine learning approach to improve this dataset imbalance and enhance the prediction accuracy of pore-labeled data. Specifically, we investigate how data augmentation helps predict pores and non-pores better. This imbalance is improved using recent advances in data augmentation called Mixup, a weak-supervised learning method. Convolutional neural networks (CNNs) are trained on original and augmented datasets, and an appreciable increase in performance is reported when testing on five different experimental trials. When ML models are trained on original and augmented datasets, they achieve an accuracy of 95% and 99% on test datasets, respectively. We also provide information on how dataset size affects model performance. Lastly, we investigate the optimal Mixup parameters for augmentation in the context of CNN performance.
ABSTRACT
Introduction: The digitalisation of the German healthcare system enables a wide range of opportunities to utilize healthcare data. The implementation of the EHR in January 2021 was a significant step, but compared to other European countries, the implementation of the EHR in the German healthcare system is still at an early stage. The aim of this paper is to characterise the structural factors relating to the adoption of the EHR in more detail from the perspective of representatives of stakeholders working in the German healthcare system and to identify existing barriers to implementation and the need for change. Methods: Qualitative expert interviews were conducted with one representative from each of the stakeholder groups health insurance, pharmacies, healthcare research, EHR development and panel doctors. Results: The interviews with the various stakeholders revealed that the implementation process of the EHR is being delayed by a lack of a viable basis for decision-making, existing conflicts of interest and insufficient consideration of the needs of patients and service providers, among other things. Discussion: The current status of EHR implementation is due to deficiency in legal regulations as well as structural problems and the timing of the introduction. For instance, the access rights of various stakeholders to the EHR data and the procedure in the event of a technical failure of the telematics infrastructure are remain unclear. In addition, insufficient information and communication measures have not led to the desired acceptance of EHR use among patients and service providers.
