Automatic seizure detection has been often treated as a classification problem that aims at determining the label of electroencephalogram (EEG) signals by computer science, as the EEG monitoring is a helpful adjunct to the diagnosis of epilepsy. In most existing work, the traditional signal energy of the EEG has been applied for classification, since the energy pattern of epileptic seizures differs from that of non-seizures. Although they are effective, the accuracy either heavily depends on additional information besides energy or is limited by the shortcoming of energy-based features. To address this issue, the proposed approach achieves the classification based on the instantaneous energy of the EEG signals instead. The proposed approach first measures the instantaneous energy related to changes in the EEG signals. Then, energy behavior over time is characterized by instantaneous energy-based features from different aspects. Finally, the classification is carried out on the features to produce output labels. By processing instantaneous energy, the information of energy evolution is involved. As such, the accuracy is improved without bringing in extra information besides energy, or complicated transformation. In multi-class problems, the proposed approach has obtained promising results for identifying the ictal EEG, which indicates the tremendous potential of the proposed approach for epileptic seizure detection. INDEX TERMSSeizure identification, electroencephalogram (EEG) signal, instantaneous energy, energy behavior.

With the development of pervasive sensing and machine learning technologies, automated epileptic seizure detection based on electroencephalogram (EEG) signals has provided tremendous support for the lives of epileptic patients. Discrete wavelet transform (DWT) is an effective method for time-frequency analysis of EEG and has been used for seizure detection in daily healthcare monitoring systems. However, the shift variance, the lack of directionality and the substantial aliasing, limit the effects of DWT in some applications. Dual-tree discrete wavelet transform (DTDWT) can overcome those drawbacks but may increase information redundancy. For classification tasks with small dataset sizes, such redundancy can greatly reduce learning efficiency and model performance. In this work, we proposed a novel redundancy removed DTDWT (RR-DTDWT) framework for automated seizure detection. Energy and modified multi-scale entropy (MMSE) features in a dual tree wavelet domain were extracted to construct a complete picture of mental states. To the best of our knowledge, this is the first study to employ MMSE as an indicator of epileptic seizures. Moreover, a compact EEG representation can be obtained after removing useless information redundancy (redundancy between wavelet trees, adjacent channels and entropy scales) by a general auto-weighted feature selection framework via global redundancy minimization (AGRM). Through validation on Bonn and CHB-MIT databases, the proposed RR-DTDWT method can achieve better performance than previous studies.

Ionic liquids (ILs) attract more and more interests in improving drug transport across membrane, including transdermal, nasal, and oral delivery. However, some drawbacks of ILs impede the application in oral drug delivery, such as rapid precipitation of poorly soluble drugs in stomach. This study aimed to employ enteric mesoporous silica nanoparticles (MSNs) to load ILs to overcome the shortcomings faced in oral administration.The choline sorbate ILs (SCILs) were synthesized by choline bicarbonate and sorbic acid and then adsorbed in mesopores of MSNs after dissolving cyclosporin A (CyA). MSNs loading SCILs and CyA were coated by Eudragit ® L100 to form enteric nanoparticles.The in vitro release study showed that the CyA and SCILs released only 10% for 2 h in simulated gastric fluids but more than 90% in simulated intestinal fluid. In addition, SCILs and CyA were able to release from MSNs synchronously. After oral administration, enteric MSNs loading SCILs were capable of improving oral absorption of CyA significantly and the oral bioavailability of CyA was similar with that of oral Neoral ® . In addition, the oral absorption of enteric MSNs was higher than that of nonenteric MSNs, which showed that enteric coating was necessary to ILs in oral delivery. These findings revealed great potential of translation of ILs to be enteric nanoparticles for facilitating oral absorption of CyA. It is predictable this delivery system is promising to be a platform for delivering poorly water-soluble drugs and even biologics orally.

No abstract