No abstract

Deep neural networks have recently succeeded in digital halftoning using vanilla convolutional layers with high parallelism. However, existing deep methods fail to generate halftones with a satisfying blue-noise property and require complex training schemes. In this paper, we propose a halftoning method based on multi-agent deep reinforcement learning, called HALFTONERS, which learns a shared policy to generate high-quality halftone images. Specifically, we view the decision of each binary pixel value as an action of a virtual agent, whose policy is trained by a low-variance policy gradient. Moreover, the blue-noise property is achieved by a novel anisotropy suppressing loss function. Experiments show that our halftoning method produces high-quality halftones while staying relatively fast.

BackgroundGastric cancer remains a major cause of mortality and morbidity worldwide. In recent years, gene-based therapeutic strategies were confirmed promising in cancer inhibition and attracted great attention. RNA interference (RNAi) is a powerful tool for gene therapy and has been widely employed to aid in treatment for various diseases, especially cancers. However, effective delivery of small interfering RNA (siRNA) to target cells in vivo remains a challenge for that it is prone to degradation and only lasts a few days in rapidly dividing cells.MethodsDue to its biocompatibility and well-established safety profile, collagen represents a favourable matrix for in-site drug delivery. In the study, collagen hydrogel was used as carriers to test the feasibility of localized and sustained delivery of Id1-targeted siRNA for in vivo gastric cancer inhibition. To enhance the siRNA delivery, cationic polyethylenimine (PEI) was further emplored for scallold modification. The efficacy of siRNA delivery and cancer inhibition were evaluated with multimodality of mehods in vitro and in vivo.ResultsOur results showed that addition of polyethylenimine (PEI) to collagen can facilitate entry of Id1-siRNA into target cells, prolong the silencing effect, and further inhibit tumor growth both in vitro and in vivo.ConclusionThis collagen-based delivery system may facilitate the pathogenesis elucidation and design of effective therapies against gastric cancer.

14In order to clarify how cadmium (Cd) chemical forms in planta relate to the genotype difference 15 in Cd accumulation of spinach (Spinacia oleracea L.), two low-Cd and two high-Cd cultivars 16 were compared under a hydroponic experiment with two concentrations of Cd (1 or 5 mg Cd L -1 ). 17The concentrations of phosphorus in the hydroponic system were also adjusted to two levels tested cultivars and the effect had superiority over the cultivar alternation under higher Cd stress. 24Cadmium in the NaCl-extractable fraction of the plant tissues showed the greatest relationship to

Median filtering (MF) is frequently applied to conceal the traces of forgery and therefore can provide indirect forensic evidence of tampering when investigating composite images. The existing MF forensic methods, however, ignore how JPEG compression affects median filtered images, resulting in heavy performance degradation when detecting filtered images stored in the JPEG format. In this paper, we propose a new robust MF forensic method based on a modified convolutional neural network (CNN). First, relying on the analysis of the influence on median filtered images caused by JPEG compression, we effectively suppress the interference using image deblocking. Second, the fingerprints left by MF are highlighted via filtered residual fusion. These two functions are fulfilled with a deblocking layer and a fused filtered residual (FFR) layer. Finally, the output of the FFR layer becomes input when extracting multiple features for further classification using a tailor-made CNN. The extensive experimental results show that the proposed method outperforms the state-of-the-art methods in both JPEG compressed and small-sized MF image detection. INDEX TERMS Median filtering, convolutional neural networks, robust forensics, JPEG compression, image deblocking.