A data security scheme based on EEG characteristics for body area networks.

Body area network (BAN) is a body-centered network of wireless wearable devices. As the basic technology of telemedicine service, BAN has aroused an immense interest in academia and the industry and provides a new technical method to solve the problems that exist in the field of medicine. However, guaranteeing full proof security of BAN during practical applications has become a technical issue that hinders the further development of BAN technology. In this article, we propose a data encryption method based on electroencephalogram (EEG) characteristic values and linear feedback shift register (LFSR) to solve the problem of data security in BAN. First, the characteristics of human EEG signals were extracted based on the wavelet packet transform method and as the MD5 input data to ensure its randomness. Then, an LFSR stream key generator was adopted. The 128-bit initial key obtained through the message-digest algorithm 5 (MD5) was used to generate the stream key for BAN data encryption. Finally, the effectiveness of the proposed security scheme was verified by various experimental evaluations. The experimental results showed that the correlation coefficient of data before and after encryption was very low, and it was difficult for the attacker to obtain the statistical features of the plaintext. Therefore, the EEG-based security scheme proposed in this article presents the advantages of high randomness and low computational complexity for BAN systems.

Epileptic prediction using spatiotemporal information combined with optimal features strategy on EEG.

Objective: Epilepsy is the second most common brain neurological disease after stroke, which has the characteristics of sudden and recurrence. Seizure prediction is seriously important for improving the quality of patients' lives. Methods: From the perspective of multiple dimensions including time-frequency, entropy and brain network, this paper proposed a novel approach by constructing the optimal spatiotemporal feature set to predict seizures. Based on strong independence and large information capabilities, the two-dimensional feature screening algorithm is performed to eliminate unnecessary redundant features. In order to verify the effectiveness of the optimal feature set, support vector machine (SVM) was used to classify the preictal and interictal states on both the Kaggle intracranial EEG and CHB-MIT scalp EEG dataset. Results: This model achieved an average accuracy of 98.01%, AUC of 0.96, F-Score of 98.3% and FPR of 0.0383/h on the Kaggle dataset; On the CHB-MIT dataset, the average accuracy, AUC, F-score and FPR were 95.93%, 0.92, 94.97% and 0.0473/h, respectively. Further ablation experiments have confirmed that the temporal and spatial features fusion has better performance than the individual temporal or spatial features. Conclusion: Compared to the state-of-the-art methods, our approach outperforms most of these existing techniques. The results show that our approach can effectively extract the spatiotemporal information of epileptic EEG signals to predict epileptic seizures with high performance.