Model and Data Dual-Driven Double-Point Observation Network for Ultra-Short MI EEG Classification.

Although deep networks have succeeded in various signal classification tasks, the time sequence samples used to train the deep models are usually required to reach a certain length. Especially, in brain computer interface (BCI) research, around 3.5s-long motor imagery (MI) Electroencephalography (EEG) samples are needed to obtain satisfactory classification performance. This time-span requirement of the training samples makes real-time MI BCI systems impossible to implement based on deep networks, which restricts the related researches within laboratory and makes practical application hard to accomplish. To address this issue, a double-point observation deep network (DoNet) is developed to classify ultra-short samples buried in noise. First, an analytical solution is developed theoretically to perform ultra-short signal classification based on double-point couples. Then, a signal-noise model is constructed to study the interference of noise on classification based on double-point couples. Based on which, an independent identical distribution condition is utilized to improve the classification accuracy in a data-driven manner. Combining the theoretical model and data-driven mechanism, DoNet can construct a steady data-distribution for the double-point couples of the samples with the same label. Therefore, the conditional probability of each double-point couple of a test sample can be obtained. With a voting strategy, the samples can be accurately classified by fusing these conditional probabilities. Meanwhile, the noise interference can be suppressed. DoNet has been evaluated on two public EEG datasets. Compared to most state-of-the-art methods, the 1s-long EEG signal classification accuracy has been improved by more than 3%.

Determination of the lower limits of antibiotic biodegradation and the fate of antibiotic resistant genes in activated sludge: Both nitrifying bacteria and heterotrophic bacteria matter.

Antibiotics can be biodegraded in activated sludge via co-metabolism and metabolism. In this study, we investigated the biodegradation pathways of sulfamethoxazole (SMX) and antibiotic resistant genes' (ARGs) fate in different autotrophic and heterotrophic microorganisms, by employing aerobic sludge, mixed sludge, and nitrifying sludge. A threshold concentration of SMX activating the degradation pathways in the initial stage of antibiotics degradation was found and proved in different activated sludge systems. Heterotrophic bacteria played an important role in SMX biodegradation. However, ammonia-oxidizing bacteria (AOB) had a faster metabolic rate, which was about 15 times higher than heterotrophic bacteria, contributing much to SMX removal via co-metabolism. As SMX concentration increases, the amoA gene and AOB relative abundance decreased in aerobic sludge due to the enrichment of functional heterotrophic bacteria, while it increased in nitrifying sludge. Microbial community analysis showed that functional bacteria which possess the capacity of SMX removal and antibiotic resistance were selected by SMX pressure. Potential ARGs hosts could increase their resistance to the biotoxicity of SMX and maintain system performance. These findings are of practical significance to guide antibiotic biodegradation and ARGs control in wastewater treatment plants.