Deep Learning plays an increasingly important role in device-free WiFi Sensing for human activity recognition (HAR). Despite its strong potential, significant challenges exist and are associated with the fact that one may require a large amount of samples for training, and the trained network cannot be easily adapted to a new environment. To address these challenges, we develop a novel scheme using Matching Network with enhanced channel state information (MatNet-eCSI) to facilitate one-shot learning HAR. We propose a CSI Correlation Feature Extraction (CCFE) method to improve and condense the activity-related information in input signals. It can also significantly reduce the computational complexity by decreasing the dimensions of input signals. We also propose novel training strategy which effectively utilizes the data set from the previously seen environments (PSE). In the least, the strategy can effectively realize human activity recognition using only one sample for each activity from the testing environment and the data set from one PSE. Numerous experiments are conducted and the results demonstrate that our proposed scheme significantly outperforms state-of-the-art HAR methods, achieving higher recognition accuracy and less training time.

No abstract

No abstract

No abstract

Human serum albumin (HSA) is extensively used in clinics to treat a variety of diseases, such as hypoproteinemia, hemorrhagic shock, serious burn injuries, cirrhotic ascites and fetal erythroblastosis. To address supply shortages and high safety risks from limited human donors, we recently developed recombinant technology to produce HSA from rice endosperm. To assess the risk potential of HSA derived from Oryza sativa (OsrHSA) before a First-in-human (FIH) trial, we compared OsrHSA and plasma-derived HSA (pHSA), evaluating the potential for an immune reaction and toxicity using human peripheral blood mononuclear cells (PBMCs). The results indicated that neither OsrHSA nor pHSA stimulated T cell proliferation at 1x and 5x dosages. We also found no significant differences in the profiles of the CD4+ and CD8+ T cell subsets between OsrHSA- and pHSA-treated cells. Furthermore, the results showed that there were no significant differences between OsrHSA and pHSA in the production of cytokines such as interferon-gamma (IFN-γ), tumor necrosis factor-alpha (TNF-α), interleukin (IL)-10 and IL-4. Our results demonstrated that OsrHSA has equivalent immunotoxicity to pHSA when using the PBMC model. Moreover, this ex vivo system could provide an alternative approach to predict potential risks in novel biopharmaceutical development.