Automatic epileptic seizure detection based on EEG using a moth-flame optimization of one-dimensional convolutional neural networks.

Introduction: Frequent epileptic seizures can cause irreversible damage to the brains of patients. A potential therapeutic approach is to detect epileptic seizures early and provide artificial intervention to the patient. Currently, extracting electroencephalogram (EEG) features to detect epileptic seizures often requires tedious methods or the repeated adjustment of neural network hyperparameters, which can be time- consuming and demanding for researchers. Methods: This study proposes an automatic detection model for an EEG based on moth-flame optimization (MFO) optimized one-dimensional convolutional neural networks (1D-CNN). First, according to the characteristics and need for early epileptic seizure detection, a data augmentation method for dividing an EEG into small samples is proposed. Second, the hyperparameters are tuned based on MFO and trained for an EEG. Finally, the softmax classifier is used to output EEG classification from a small-sample and single channel. Results: The proposed model is evaluated with the Bonn EEG dataset, which verifies the feasibility of EEG classification problems that involve up to five classes, including healthy, preictal, and ictal EEG from various brain regions and individuals. Discussion: Compared with existing advanced optimization algorithms, such as particle swarm optimization, genetic algorithm, and grey wolf optimizer, the superiority of the proposed model is further verified. The proposed model can be implemented into an automatic epileptic seizure detection system to detect seizures in clinical applications.

QQ-PAC core-shell structured quorum quenching beads for potential membrane antifouling properties.

Quorum quenching (QQ) has been proven to be an effective method to reduce MBR membrane biological contamination. In this paper, a novel and efficient QQ-PAC core-shell beads were prepared for mitigating the membrane contamination. The bead was composed of two parts: QQ bacteria embedded in the core and PAC in the shell. The microstructure of the bead was observed by scanning electron microscopy (SEM) and the functional groups were revealed by Fourier transform infrared spectroscopy (FTIR). Meanwhile, the mechanical strength, swelling property, penetration property and QQ activity of the core bead, the core shell-without PAC bead and the core shell-with PAC bead were compared. The core shell-with PAC structure improved the adsorption capacity under good mass transfer conditions. Besides, the combined effect of QQ bacteria and PAC enhanced the QQ effect and alleviated the process of MBR membrane biological contamination consequently. Therefore, the QQ-PAC core-shell beads have a potential possibility in MBR membrane fouling control as the immobilization technology of QQ bacteria.

Control of indigenous quorum quenching bacteria on membrane biofouling in a short-period MBR.

In this paper, the immobilized quorum quenching (QQ) bacteria - microbial bag was added to a short-period membrane bioreactor (MBR) and its antifouling ability and mechanism were studied by monitoring the changes in transmembrane pressure (TMP), along with the production of N-acyl-homoserine lactones (AHLs), extracellular polymeric substance (EPS) and soluble microbial products (SMP). The QQ bacteria showed efficient mitigation of TMP increase in different membrane fouling stages. In the control MBR group, the TMP reached 43 kPa on the 4th day, while in the experimental group, TMP of QQ-MBR was only 18 kPa at the same time. The detection result of EPS and SMP content of protein and polysaccharide in MBRs showed that QQ bacteria had significant inhibitory effects on EPS and SMP. Also, the QQ bacterial exhibited excellent AHLs degradation rate in MBR reaction tank.

Membrane layers intensifying quorum quenching alginate cores and its potential for membrane biofouling control.

Quorum quenching (QQ) has been proved to be an efficient method to mitigate biofouling in membrane bioreactors (MBRs). In this paper, in order to enhance practicability of QQ microcapsules, we prepared three types microcapsules with same alginate cores (SAs). The microcapsules with polyacrylonitrile (PAN) layer showed excellent performance in preventing cell leakage from the microcapsules, increasing service life and improving mechanical strength. And confocal laser scanning microscopy images demonstrated that there were very little dead bacteria in the microcapsules with both chitosan and PAN layer than microcapsules with only PAN layer because chitosan layer can protect bacteria entrapped in cores from the hurt caused by poisonous PAN solution. At the same time, the microcapsules with PAN layer presented more efficient anti-biofouling ability in the physical washing test. At last, the bacterial microcapsules coated with both chitosan and PAN layer showed an obvious biofouling mitigation during the MBRs operation.