Personal data management at cloud with mobile devices confronts a number of practical challenges such as security, efficiency and usability. Many existing solutions suffer from high computation and communication costs, thus impractical to be deployed in mobile domains. Notably, high popularity of mobile social networking provides a good platform to assess social trust in a pervasive way, which can be applied to automatically manage personal data access at the cloud with sound performance and effectiveness. This paper presents the design and implementation of a personal cloud data access control system named CloudFile based on trust evaluation in mobile social networking. The CloudFile uses a Key Policy-Attribute Based Encryption (KP-ABE) scheme to control personal data access based on social trust in order to guarantee the safety of mobile cloud data storage. System performance tests show that the CloudFile is flexible for controlling data access, secure for personal data storage, and efficient to be deployed by mobile devices. Particularly, we investigate user acceptance on the CloudFile system. Based on user feedback, we conclude that the CloudFile is accepted with regard to perceived ease of use, practicality, user interface, playfulness and intuitive attitude.

No abstract

Due to the noise and multi-channel room acoustic environment, practical speech emotion recognition remains an unsolved challenge. In this paper, we first study the fractional spaced blind equalizer for speech preprocessing. The noise interference is effectively removed and more detailed emotional features are reserved. Second, the fuzzy k nearest neighbor algorithm is used to classify speech. Finally, the proposed algorithm is compared with traditional speech emotion recognition algorithms. Experimental results show that the fractionally spaced equalization is effective for practical speech emotion recognition.