Search

Recently, deep neural network-based image compressed sensing methods have achieved impressive success in reconstruction quality. However, these methods (1) have limitations in sampling pattern and (2) usually have the disadvantage of high computational complexity. To this end, a fast multi-scale generative adversarial network (FMSGAN) is implemented in this paper. Specifically, (1) an effective multi-scale sampling structure is proposed. It contains four different kernels with varying sizes so that decompose, and sample images effectively, which is capable of capturing different levels of spatial features at multiple scales. (2) An efficient lightweight multi-scale residual structure for deep image reconstruction is proposed to balance receptive field size and computational complexity. The key idea is to apply smaller convolution kernel sizes in the multi-scale residual structure to reduce the number of operations while maintaining the receptive field. Meanwhile, the channel attention structure is employed for enriching useful information. Moreover, perceptual loss is combined with MSE loss and adversarial loss as the optimization function to recover a finer image. Numerous experiments show that our FMSGAN achieves state-of-the-art image reconstruction quality with low computational complexity.

Anaerobic digestion of waste-activated sludge (WAS) towards biogas recovery is constrained by the limited hydrolysis and inhibited acetogenesis steps that hinder subsequent energy recovery. This study employed Fe(VI)/S(IV) oxidation to enhance the WAS solubilization and coupled it with the syntrophic interaction of hydrogen-producing acetogen (HPA) and sulfate-reducing bacteria (SRB) to stimulate the successive procedure towards methane production. Results showed that the dosage ratio of HPA-SRB to WAS (H-S-W) with 1:1:50 outperformed with the highest methane production potential (11.63 ± 1.87 mL CH4/(g VSS·d). Meanwhile, the efficient and sequential process from acetogenesis to methanogenesis stimulated by HPA-SRB was evidenced by a significant decrease of 30.2% in the acetate concentration. The microbial community structure further manifested the crucial role of HPA-SRB with increased abundance of Desulfobulbus (2.07%), Syntrophomonas (1.24%) and Smithella (1.63%), which stimulated acetophilic methanogen boost with Methanobacterium dominating with 77.51% in H-S-W100. Furthermore, the positive syntrophic relationships among HPA-SRB and acetophilic methanogens towards methane production were confirmed via molecular ecological network and canonical correspondence analysis. This study highlighted the syntrophic cooperation of the mixed consortia of HPA and SRB on methane production based on Fe(VI)/S(IV) pretreatment and provided the theoretical and technical basis for the potential implementation of novel methanogenesis technology for WAS treatment.