Wi-Fi sensing technology based on deep learning has contributed many breakthroughs in gesture recognition tasks. However, most methods concentrate on single domain recognition with high computational complexity while rarely investigating cross-domain recognition with lightweight performance, which cannot meet the requirements of high recognition performance and low computational complexity in an actual gesture recognition system. Inspired by the few-shot learning methods, we propose WiGR, a Wi-Fi-based gesture recognition system. The key structure of WiGR is a lightweight few-shot learning network that introduces some lightweight blocks to achieve lower computational complexity. Moreover, the network can learn a transferable similarity evaluation ability from the training set and apply the learned knowledge to the new domain to address domain shift problems. In addition, we made a channel state information (CSI)-Domain Adaptation (CSIDA) data set that includes channel state information (CSI) traces with various domain factors (i.e., environment, users, and locations) and conducted extensive experiments on two data sets (CSIDA and SignFi). The evaluation results show that WiGR can reach 87.8%–94.8% cross-domain accuracy, and the parameters and the calculations are reduced by more than 50%. Extensive experiments demonstrate that WiGR can achieve excellent recognition performance using only a few samples and is thus a lightweight and practical gesture recognition system compared with state-of-the-art methods.
The RecA protein has an essential role in DNA recombination and repair which is mediated by its ability to bind ATP/ADP. SWISS-MODEL, an online automated server, was used to predict its tertiary structure of C. jejuni RecA. Four evaluation tools were used for quality assessment of the constructed model: QMEAN6, ERRAT, ANOLEA and PROCHECK. Quality assessments indicated that the model was of high quality and reliable for docking experiments. A total of forty natural products were used in docking the model by Hex 8.0.0 and ArgusLab 4.0.1 using ADP as control. Ten compounds had docking scores higher than that of ADP in ArgusLab 4.0.1 where quercetin had the highest docking score of -10.34 Kcal/mol. In Hex 8.0.0 docking, only cucurmin, taxifolin, isoquercitrin and vitexin had docking scores higher than that of ADP. These natural occurring compounds may be possible inhibitors of ATPase activity and, therefore, may be further analyzed to develop new antimicrobials targeting RecA in pathogenic bacteria.
Currently, there are various works presented in the literature regarding the activity recognition based on WiFi. We observe that existing public data sets do not have enough data. In this work, we present a data augmentation method called window slicing. By slicing the original data, we get multiple samples for one raw datum. As a result, the size of the data set can be increased. On the basis of the experiments performed on a public data set and our collected data set, we observe that the proposed method assists in improving the results. It is notable that, on the public data set, the activity recognition accuracy improves from 88.13% to 97.12%. Similarly, the recognition accuracy is also improved for the data set collected in this work. Although the proposed method is simple, it effectively enhances the recognition accuracy. It is a general channel state information (CSI) data augmentation method. In addition, the proposed method demonstrates good interpretability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.