Search

Language Technology is an essential component of many Cyber-Physical Systems (CPSs) because specialized linguistic knowledge is indispensable to prevent fatal errors. We present the case of automatic identification of implant terms. The need of an automatic identification of implant terms spurs from safety reasons because patients who have an implant may or may be not submitted to Magnetic Resonance Imaging (MRI). Normally, MRI scans are safe. However, in some cases an MRI scan may not be recommended. It is important to know if a patient has an implant, because MRI scanning is incompatible with some implants. At present, the process of ascertain whether a patient could be at risk is lengthy, manual, and based on the specialized knowledge of medical staff. We argue that this process can be sped up, streamlined and become safer by sieving through patients’ medical records. In this paper, we explore how to discover implant terms in electronic medical records (EMRs) written in Swedish with an unsupervised approach. To this aim we use BERT, a state-of-the-art deep learning algorithm based on pre-trained word embeddings. We observe that BERT discovers a solid proportion of terms that are indicative of implants.

There are fundamental limits on how much potentially available intermittent renewable energy can be consumed at a regional level in real time since generation and demand do not match on short time horizons, e.g. hour, day. Grid interconnectors allow real time wind and solar energy exchange between the over- and under-supplied areas. We assess the techno-economic feasibility of global interconnected power grid across continents, based on HVDC technology, to maximize the use of potentially available variable renewables. The analysis framework is based on a dynamic transmission and generation optimal expansion model with the objective to minimize capital and operational expenditures. Results highlight that in scenarios up to 2050, a construction of multiple high capacity transmission links between continents can be economically justified. The total system cost over the simulation period is reduced if the global grid is deployed compared to a case where each region tries to solve the energy transition in isolation.

This paper analyzes the station-internal phase-to-ground fault in bipolar HVDC transmission systems. An overvoltage problem due to the existence of the bipolar cells in the modular multilevel converter (MMC) arms closer to the grounding pole are presented. Consequently, a new hybrid arm MMC is proposed to overcome the overvoltage problem while providing the benefits of: a lower number of cells, fewer switching devices and lower conduction losses. Guidelines are developed and confirmed by simulation results to determine the required number of cells to block the DC side fault.

This paper introduces a new method for automatic quantification of subcutaneous, visceral and non-visceral internal fat from MR-images acquired using the two point Dixon technique in the abdominal region. The method includes (1) a three dimensional phase unwrapping to provide water and fat images, (2) an image intensity inhomogeneity correction, and (3) a morphon based registration and segmentation of the tissue. This is followed by an integration of the corrected fat images within the different fat compartments that avoids the partial volume effects associated with traditional fat segmentation methods. The method was tested on 18 subjects before and after a period of fast-food hyper-alimentation showing high stability and performance in all analysis steps.

Two- and three-dimensional isotropic and anisotropic spatial filters for adaptive fMRI data analysis are compared in terms of activation detection sensitivity and specificity. Evaluations using both real and artificial data are presented. It is shown that three-dimensional anisotropic filters provide superior activation detection performance.