Objective State-of-the-art techniques for surgical data analysis report promising results for automated skill assessment and action recognition. The contributions of many of these techniques, however, are limited to study-specific data and validation metrics, making assessment of progress across the field extremely challenging. Methods In this paper, we address two major problems for surgical data analysis: (1) lack of uniform shared datasets and benchmarks and (2) lack of consistent validation processes. We address the former by presenting the JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS), a public dataset we have created to support comparative research benchmarking. JIGSAWS contains synchronized video and kinematic data from multiple performances of robotic surgical tasks by operators of varying skill. We address the latter by presenting a well-documented evaluation methodology and reporting results for six techniques for automated segmentation and classification of time-series data on JIGSAWS. These techniques comprise four temporal approaches for joint segmentation and classification: Hidden Markov Model, Sparse HMM, Markov semi-Markov Conditional Random Field, and Skip-Chain CRF; and two feature-based ones that aim to classify fixed segments: Bag of spatiotemporal Features and Linear Dynamical Systems. Results Most methods recognize gesture activities with approximately 80% overall accuracy under both leave-one-super-trial-out and leave-one-user-out cross-validation settings. Conclusion Current methods show promising results on this shared dataset, but room for significant progress remains, particularly for consistent prediction of gesture activities across different surgeons. Significance The results reported in this paper provide the first systematic and uniform evaluation of surgical activity recognition techniques on the benchmark database.

Disease modelling has had considerable policy impact during the ongoing COVID-19 pandemic, and it is increasingly acknowledged that combining multiple models can improve the reliability of outputs. Here we report insights from ten weeks of collaborative short-term forecasting of COVID-19 in Germany and Poland (12 October–19 December 2020). The study period covers the onset of the second wave in both countries, with tightening non-pharmaceutical interventions (NPIs) and subsequently a decay (Poland) or plateau and renewed increase (Germany) in reported cases. Thirteen independent teams provided probabilistic real-time forecasts of COVID-19 cases and deaths. These were reported for lead times of one to four weeks, with evaluation focused on one- and two-week horizons, which are less affected by changing NPIs. Heterogeneity between forecasts was considerable both in terms of point predictions and forecast spread. Ensemble forecasts showed good relative performance, in particular in terms of coverage, but did not clearly dominate single-model predictions. The study was preregistered and will be followed up in future phases of the pandemic.

Abstract. Emissions of harmful substances into the atmosphere are a serious environmental concern. In order to understand and predict their effects, it is necessary to estimate the exact quantity and timing of the emissions from sensor measurements taken at different locations. There are a number of methods for solving this problem. However, these existing methods assume Gaussian additive errors, making them extremely sensitive to outlier measurements. We first show that the errors in real-world measurement data sets come from a heavy-tailed distribution, i.e., include outliers. Hence, we propose robustifying the existing inverse methods by adding a blind outlier-detection algorithm. The improved performance of our method is demonstrated on a real data set and compared to previously proposed methods. For the blind outlier detection, we first use an existing algorithm, RANSAC, and then propose a modification called TRANSAC, which provides a further performance improvement.

No abstract

No abstract