Manifold alignment is very prevalent in machine learning for extracting common latent space from multiple datasets. These algorithms generally aim to achieve higher alignment accuracies by preserving the original structure while ensuring closeness between manifolds. This paper proposes a novel semi-supervised manifold alignment method that combines, in each manifold, both global and local linear reconstructions. We preserve a local structure through multiple manifold embedding methods. Moreover, we view manifold embedding methods as special forms of principal component analysis (PCA) and, thus, present a new penalty weight PCA approach to preserving a noise-free global structure. Finally, a closedform solution is presented in the manifold alignment. This method can concurrently match the pair-wise correspondence and preserve both the global and local structures of each dataset to obtain a latent lowdimensional space. The extensive experiments on manifold alignment prove that the proposed method achieves significantly better alignment results than the comparative methods.

Abstract:In this paper we proposed advanced technologies to provide tremendous support for network administrators by implementing a secure remote system administration app that runs on android smartphones to aid them administer their servers remotely when they (network administrators) are out stationed using their smartphones. The android app developed in eclipse establishes a secure connection with a remote server running a PHP application. The app was developed based on the Remote Frame Buffer (RFB) protocol. The RFB protocol, a display protocol has some security lapses including being vulnerable to Man-In-The-Middle (MITM) attack using a few tools and techniques. This research therefore incorporated a self-signed Secure Socket Layer (SSL) certificate in the android app to enable secure encrypted connections to be established between the android app and the remote server to ensure end-to-end security against attacks such as Man-In-The-Middle (MITM). The whole system was deployed based on client-server architecture with the hand-held smart devices as clients, providing real-time network access to network administrators to their remote servers. The secure RFB protocol proposed and implemented in the android app was compared with other existing software for remote system administration such as Remote Desktop (RDP), and RFB protocols using ICMP ping command. The results show that the average response time of the RDP protocol was 436ms, that of the RFB protocol was 496ms and that of the android app which is based on a proposed secure RFB protocol was 474ms.

No abstract

No abstract

No abstract