In dynamic computed tomography (CT) reconstruction, the data acquisition speed limits the spatio-temporal resolution. Recently, compressed sensing theory has been instrumental in improving CT reconstruction from far few-view projections. In this paper, we present an adaptive method to train a tensor-based spatio-temporal dictionary for sparse representation of an image sequence during the reconstruction process. The correlations among atoms and across phases are considered to capture the characteristics of an object. The reconstruction problem is solved by the alternating direction method of multipliers. To recover fine or sharp structures such as edges, the nonlocal total variation is incorporated into the algorithmic framework. Preclinical examples including a sheep lung perfusion study and a dynamic mouse cardiac imaging demonstrate that the proposed approach outperforms the vectorized dictionary-based CT reconstruction in the case of few-view reconstruction.
Compared with traditional dexterous humanoid robotic hands, underactuated robotic hands have the advantages of selfadaptive grasp and easy real-time control. In this paper, the development of a novel underactuated robotic hand is presented. This hand has five fingers and through using underactuation, the selfadaptability of each finger is achieved. This underactuated humanoid robotic hand can accomplish complicated selfadaptive grasp without high demand for real-time control system. In the first place, the design of a two degree-of-freedom underactuated finger is given. Then the parameters affecting the rotary angle and grasp force of the underactuated finger are analyzed and optimized. Finally, taking one finger as a module, the entire humanoid robotic hand is designed. This robotic hand is similar to human hand on appearance and size. It has many good merits such as good selfadaptability, compactness, easy real-time control, small volume and light weight.
Federated learning, as a privacy-preserving collaborative machine learning paradigm, has been gaining more and more attention in the industry. With the huge rise in demand, there have been many federated learning platforms that allow federated participants to set up and build a federated model from scratch. However, exiting platforms are highly intrusive, complicated, and hard to integrate with built machine learning models. For many realworld businesses that already have mature serving models, existing federated learning platforms have high entry barriers and development costs. This paper presents a simple yet practical federated learning plug-in inspired by ensemble learning, dubbed WrapperFL, allowing participants to build/join a federated system with existing models at minimal costs. The WrapperFL works in a plug-and-play way by simply attaching to the input and output interfaces of an existing model, without the need of re-development, significantly reducing the overhead of manpower and resources. We verify our proposed method on diverse tasks under heterogeneous data distributions and heterogeneous models. The experimental results demonstrate that WrapperFL can be successfully applied to a wide range of applications under practical settings and improves the local model with federated learning at a low cost.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.