Synthesising 2D Video from 3D Motion Data for Machine Learning Applications.

To increase the utility of legacy, gold-standard, three-dimensional (3D) motion capture datasets for computer vision-based machine learning applications, this study proposed and validated a method to synthesise two-dimensional (2D) video image frames from historic 3D motion data. We applied the video-based human pose estimation model OpenPose to real (in situ) and synthesised 2D videos and compared anatomical landmark keypoint outputs, with trivial observed differences (2.11−3.49 mm). We further demonstrated the utility of the method in a downstream machine learning use-case in which we trained and then tested the validity of an artificial neural network (ANN) to estimate ground reaction forces (GRFs) using synthesised and real 2D videos. Training an ANN to estimate GRFs using eight OpenPose keypoints derived from synthesised 2D videos resulted in accurate waveform GRF estimations (r > 0.9; nRMSE < 14%). When compared with using the smaller number of real videos only, accuracy was improved by adding the synthetic views and enlarging the dataset. The results highlight the utility of the developed approach to enlarge small 2D video datasets, or to create 2D video images to accompany 3D motion capture datasets to make them accessible for machine learning applications.

Google DeepMind and healthcare in an age of algorithms.

Data-driven tools and techniques, particularly machine learning methods that underpin artificial intelligence, offer promise in improving healthcare systems and services. One of the companies aspiring to pioneer these advances is DeepMind Technologies Limited, a wholly-owned subsidiary of the Google conglomerate, Alphabet Inc. In 2016, DeepMind announced its first major health project: a collaboration with the Royal Free London NHS Foundation Trust, to assist in the management of acute kidney injury. Initially received with great enthusiasm, the collaboration has suffered from a lack of clarity and openness, with issues of privacy and power emerging as potent challenges as the project has unfolded. Taking the DeepMind-Royal Free case study as its pivot, this article draws a number of lessons on the transfer of population-derived datasets to large private prospectors, identifying critical questions for policy-makers, industry and individuals as healthcare moves into an algorithmic age.

Dynamics of stomatal water relations following leaf excision.

We examined the stomatal response to leaf excision in an evergreen woody shrub, Photinia x fraseri, using a novel combination of gas exchange, traditional water relations and modelling. Plants were kept outdoors in mild winter conditions (average daily temperature range: -1 to 12 degrees C) before being transferred to a glasshouse (temperature range: 20-30 degrees C) and allowed to acclimate for different periods before experiments. 'Glasshouse plants' were acclimated for at least 9 d, and 'outdoor plants' were acclimated for fewer than 3 d before laboratory gas exchange experiments. The transient stomatal opening response to leaf excision was roughly twice as long in outdoor plants as in glasshouse plants. To elucidate the reason for this difference, we inferred variables of stomatal water relations (epidermal and guard cell turgor pressures and guard cell osmotic pressure: Pe, Pg and pi g, respectively) from stomatal conductance (gs) and bulk leaf water potential (psi l), using a hydromechanical model of gs. psi l was calculated from cumulative post-excision transpirational water loss using empirical relationships between psi l and relative water content obtained on similar leaves. Inferred Pg and Pe both declined immediately after leaf excision. Inferred pi g also declined after a lag period. The kinetics of pi g adjustment after the lag were similar in outdoors and glasshouse plants, but the lag period was much longer in outdoor plants. This suggests that the longer transient opening response in outdoor plants resulted from slower induction, not slower execution, of guard cell osmoregulation. We discuss the implications of our results for the mechanism of short-term stomatal responses to hydraulic perturbations, for dynamic modelling of gs and for leaf water status regulation.