Search

With the rapid development of machine learning in the medical cloud system, cloud-assisted medical computing provides a concrete platform for remote rapid medical diagnosis services. Support vector machine (SVM), as one of the important algorithms of machine learning, has been widely used in the field of medical diagnosis for its high classification accuracy and efficiency. In some existing schemes, healthcare providers train diagnostic models with SVM algorithms and provide online diagnostic services to doctors. Doctors send the patient’s case report to the diagnostic models to obtain the results and assist in clinical diagnosis. However, case report involves patients’ privacy, and patients do not want their sensitive information to be leaked. Therefore, the protection of patient’s privacy has become an important research direction in the field of online medical diagnosis. In this paper, we propose a privacy-preserving medical diagnosis scheme based on multi-class SVMs. The scheme is based on the distributed two trapdoors public key cryptosystem (DT-PKC) and Boneh-Goh-Nissim (BGN) cryptosystem. We design a secure computing protocol to compute the core process of the SVM classification algorithm. Our scheme can deal with both linearly separable data and nonlinear data while protecting the privacy of user data and support vectors. The results show that our scheme is secure, reliable, scalable with high accuracy. [ABSTRACT FROM AUTHOR]

Compared with insulated superconducting magnet, no-insulation magnet can obtain higher magnetic field with smaller volume, but the existence of radial current complicates the transient analysis of NI magnet. In this paper, a 2-dimensional (2D) method was introduced into the thermal-electrical analysis of NI magnet, we discussed the current distribution and power generation during charging process at different working status. The result confirmed 2D method could greatly simplify the modeling process and reduce the number of meshes, which can enhance the convergence of calculation process, and speed up the analysis process. [ABSTRACT FROM AUTHOR]

The power industry is changing rapidly. One approach to accommodate a part of the change is the use of energy storage, in particular superconducting magnetic storage systems (SMES). Both solenoidal and toroidal magnets storing a few megajoules have been designed and valuated for this application. Solenoidal magnets have extensive stray fields, which are one of the serious limitations. Toroidal magnets require more conductor and are more complicated in terms of construction and insulation. The existing power systems require 100 s of megawatts of power from energy storage systems, whereas the power capacity of a single SMES installation will be quite limited. Modular SMES may provide a solution to this limitation. This article describes a 3 MJ/2 MW modular toroidal SMES using YBCO tape. The design approach is aimed at the reduction of the insulation requirement; and a slit structure of the cooling plate is designed to reduce the eddy current loss. The cooling process and losses of the magnet are analyzed. [ABSTRACT FROM AUTHOR]