No abstract

No abstract

In recent years, emotional recognition based on Electrophysiological (EEG) signals has become more and more popular. But the researchers ignored the fact that peripheral physiological signals can also reflect changes in mood. We propose an Ensemble Convolutional Neural Network (ECNN) model, which is used to automatically mine the correlation between multi-channel EEG signals and peripheral physiological signals in order to improve the emotion recognition accuracy. First, we design five convolution networks and use global average pooling (GAP) layers instead of fully connected layers; and then the plurality voting strategy is adopted to establish the ensemble model; eventually this model divides emotions into four categories. Based on the simulations on DEAP dataset, the experimental results demonstrate the superiority of the ECNN compared with other methods.

As an emerging application of smart healthcare, mobile healthcare crowd sensing (MHCS) has become a research hotspot. However, how to ensure the confidentiality and integrity of data and protect the privacy of user is still a challenge for MHCS. To handle these issues, an effective and secure privacy protection scheme is indispensable. Recently, a large-scale concurrent data anonymous batch verification scheme for mobile healthcare crowd sensing was proposed by Liu et al. Unfortunately, we demonstrate that their scheme is insecure. This paper presents an improved anonymous scheme based on certificateless aggregate signature (CL-AS) for MHCS. First, considering the efficiency and the characteristics of the MHCS, the technique of aggregate signature is adopted, which can achieve batch verification and greatly save the bandwidth and computation resources. Second, anonymous communication is carried out in this scheme to realize privacy preservation. Third, based on certificateless cryptography, the proposed scheme can simplify the complicated certificate management and eliminate the key escrow problem. In addition, our scheme is provably secure against the existential forgery on adaptively chosen message attack in the Random Oracle Model assuming the computational Diffie-Hellman problem is intractable. Furthermore, security and efficiency analysis shows that our scheme is secure and efficient. INDEX TERMS Mobile healthcare crowd sensing, signature, certificateless cryptography, privacy preservation.