Background Guidelines suggest computed tomography colonography (CTC) following incomplete optical colonoscopy (OC). Colon capsule endoscopies (CCE) have been suggested as an alternative, although completion rates have been unsatisfactory. Introduction of artificial intelligence (AI)-based localization algorithms of the camera capsules may enable identification of incomplete CCE investigations overlapping with incomplete OCs. Objective The study aims to investigate relative sensitivity of CCE compared with CTC following incomplete OC, investigate the completion rate when combining results from the incomplete OC and CCE, and develop a forward-tracking algorithm ensuring a safe completeness of combined investigations. Methods In this prospective paired study, patients with indication for CTC following incomplete OC were included for CCE and CTC. Location of CCE abortion and OC abortion were registered to identify complete combined investigations. AI-based algorithm for localization of capsules were developed reconstructing the passage of the colon. Results In 237 individuals with CTC indication; 105 were included, of which 97 underwent both a CCE and CTC. CCE was complete in 66 (68%). Including CCEs which reached most oral point of incomplete OC, 73 (75%) had complete colonic investigations; 78 (80%) had conclusive investigations. Relative sensitivity of CCE compared with CTC was 2.67 (95% confidence interval (CI) 1.76;4.04) for polyps >5 mm and 1.91 (95% CI 1.18;3.09) for polyps >9 mm. An AI-based algorithm was developed. Conclusion Sensitivity of CCE following incomplete OC was superior to CTC. Introducing and improving algorithm-based localization of capsule abortion may increase identification of overall complete investigation rates following incomplete OC. ClinicalTrials.gov identifier: NCT02826993

No abstract

Prognostic and health monitoring addresses the issue of detecting faults and monitoring the current state of a wind turbine. Details about the fault’s progression, and from there, the remaining useful lifetime, are key features in monitoring and industrial operation and maintenance planning. In order to avoid increase in operation and maintenance cost, as well as subjective human involvement, we present an online and automated monitoring framework for prediction of the remaining useful lifetime based on deep learning models. This framework includes training and re-training of predictive models with minimal oversight by the operators. Further, we explore the dependency of various models’ predictive abilities based on the input variables available, such as SCADA and secondary measurements. Especially deep learning approaches, such as neural networks, benefit greatly from the volume of data that can be extracted from modern-day turbines. This work utilizes upon the volume of data to present a case study on main bearing failures for 108 turbines. In the presented setting, predictions of the remaining useful lifetime of more than 90 days can be expected on average, outperforming the closest state-of-the-art estimate by almost a factor of two on average.

A statistical approach to abstract and predict turbine states in an online manner has been developed. Online inference is performed on temperature measurement residuals to predict the failure state Dn steps ahead of time. In this framework a case study is performed showing the ability to predict bearing failure 33 days, on average, ahead of time. The approach is based on the separability of the sufficient statistics and a hidden variable, namely the state length. The predictive probability is conditioned on the data available, as well as the state variables. It is shown that the predictive probability can be calculated by a model for the samples and a hazard function describing the probability for undergoing a state transition. This study is concerned with the prior training of the model, for which run-to-failure time series of bearing measurements are used. For the sample model prediction is conditioned on prior information and predict the next Dn samples from a feature space spanned by the prior samples. By assuming that the feature space can be described by a multivariate Gaussian distribution, the prediction is treated as a Gaussian process over the feature space.

Background and study aims  The aim of this study was to develop a machine learning-based model to classify bowel cleansing quality and to test this model in comparison to a pixel analysis model and assessments by four colon capsule endoscopy (CCE) readers. Methods  A pixel analysis and a machine learning-based model with four cleanliness classes (unacceptable, poor, fair and good) were developed to classify CCE videos. Cleansing assessments by four CCE readers in 41 videos from a previous study were compared to the results both models yielded in this pilot study. Results  The machine learning-based model classified 47 % of the videos in agreement with the averaged classification by CCE readers, as compared to 32 % by the pixel analysis model. A difference of more than one class was detected in 12 % of the videos by the machine learning-based model and in 32 % by the pixel analysis model, as the latter tended to overestimate cleansing quality. A specific analysis of unacceptable videos found that the pixel analysis model classified almost all of them as fair or good, whereas the machine learning-based model identified five out of 11 videos in agreement with at least one CCE reader as unacceptable. Conclusions  The machine learning-based model was superior to the pixel analysis in classifying bowel cleansing quality, due to a higher sensitivity to unacceptable and poor cleansing quality. The machine learning-based model can be further improved by coming to a consensus on how to classify cleanliness of a complete CCE video, by means of an expert panel.

a b s t r a c tA model-based optimisation approach is used to investigate the potential gain of wind-farm power with a cooperative control strategy between the wind turbines. Based on the Jensen wake model with the Katic wake superposition rule, the potential gain for the Nysted offshore wind farm is calculated to be 1.4 e5.4% for standard choices 0.4 ! k ! 0.25 of the wake expansion parameter. Wake model fits based on short time intervals of length 15sec T 10 min within three months of data reveal a strong wake flow variability, resulting in rather broad distributions for the wake expansion parameter. When an optimized wind-farm control strategy, derived from a fixed wake parameter, is facing this flow variability, the potential gain reduces to 0.3e0.5%. An omnipotent control strategy, which has real-time knowledge of the actual wake flow, would be able to increase the gain in wind-farm power to 4.9%.

No abstract

In large bowel investigations using endoscopic capsules and upon detection of significant findings, physicians require the location of those findings for a follow-up therapeutic colonoscopy. To cater to this need, we propose a model based on tracking feature points in consecutive frames of videos retrieved from colon capsule endoscopy investigations. By locally approximating the colon as a cylinder, we obtained both the displacement and the orientation of the capsule using geometrical assumptions and by setting priors on both physical properties of the intestine and the image sample frequency of the endoscopic capsule. Our proposed model tracks a colon capsule endoscope through the large intestine for different prior selections. A discussion on validating the findings in terms of intra and inter capsule and expert panel validation is provided. The performance of the model is evaluated based on the average difference in multiple reconstructed capsule’s paths through the large intestine. The path difference averaged over all videos was as low as 4±0.7 cm, with min and max error corresponding to 1.2 and 6.0 cm, respectively. The inter comparison addresses frame classification for the rectum, descending and sigmoid, splenic flexure, transverse, hepatic, and ascending, with an average accuracy of 86%.