In this study, a twin-chamber upflow bio-electrochemical reactor packed with palm shell granular activated carbon as biocarrier and third electrode was used for sequential nitrification and denitrification of nitrogen-rich wastewater under different operating conditions. The experiments were performed at a constant pH value for the denitrification compartment. The effect of variables, namely, electric current (I) and hydraulic retention time (HRT), on the pH was considered in the nitrification chamber. The response surface methodology was used based on three levels to develop empirical models for the study on the effects of HRT and current values as independent operating variables on NH(4)(+)-N removal. The results showed that ammonium was reduced within the function of an extensive operational range of electric intensity (20-50 mA) and HRT (6-24h). The optimum condition for ammonium oxidation (90%) was determined with an I of 32 mA and HRT of 19.2h.
Electroencephalogram (EEG) is a common base signal used to monitor brain activities and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the performance of the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and κ = 0.79. Our developed model can be applied to other sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at https://github.com/SajadMo/SleepEEGNet.