Novel Deep Learning Network for Gait Recognition Using Multimodal Inertial Sensors.

Some recent studies use a convolutional neural network (CNN) or long short-term memory (LSTM) to extract gait features, but the methods based on the CNN and LSTM have a high loss rate of time-series and spatial information, respectively. Since gait has obvious time-series characteristics, while CNN only collects waveform characteristics, and only uses CNN for gait recognition, this leads to a certain lack of time-series characteristics. LSTM can collect time-series characteristics, but LSTM results in performance degradation when processing long sequences. However, using CNN can compress the length of feature vectors. In this paper, a sequential convolution LSTM network for gait recognition using multimodal wearable inertial sensors is proposed, which is called SConvLSTM. Based on 1D-CNN and a bidirectional LSTM network, the method can automatically extract features from the raw acceleration and gyroscope signals without a manual feature design. 1D-CNN is first used to extract the high-dimensional features of the inertial sensor signals. While retaining the time-series features of the data, the dimension of the features is expanded, and the length of the feature vectors is compressed. Then, the bidirectional LSTM network is used to extract the time-series features of the data. The proposed method uses fixed-length data frames as the input and does not require gait cycle detection, which avoids the impact of cycle detection errors on the recognition accuracy. We performed experiments on three public benchmark datasets: UCI-HAR, HuGaDB, and WISDM. The results show that SConvLSTM performs better than most of those reporting the best performance methods, at present, on the three datasets.

Genome-wide identification of glutamate synthase gene family and expression patterns analysis in response to carbon and nitrogen treatment in Populus.

Glutamate synthase (GOGAT) is a key enzyme in glutamine synthetase (GS)/GOGAT cycle and at the hub of carbon and nitrogen metabolism, catalyzing the formation of glutamate from α-oxoglutarate and glutamine. In this study, members of GOGAT family in Populus trichocarpa were identified and analyzed by bioinformatics. The four PtGOGATs were divided into two subgroups: subgroup A (Fd-GOGAT1 and Fd-GOGAT2) and subgroup B (NADH-GOGAT1 and NADH-GOGAT2). Many important elements have been identified in the promoters of different PtGOGATs, including hormone- and light-responsive elements. Meanwhile, the transcript levels of PxGOGATs were affected by light and diurnal cycle. Quantitative real-time PCR showed PxFd-GOGATs and PxNADH-GOGATs were mainly expressed in leaves and roots in Populus × xiaohei T. S. Hwang et Liang, respectively. Under elevated CO2, PxGOGATs were suppressed in all tissues except the stem. And PxFd-GOGATs and PxNADH-GOGATs were strongly induced by nitrogen in leaves and roots, respectively. In addition, PxGOGATs were stimulated significantly in roots in response to NH4+and glutamine directly. Our results provide new insights about GOGATs in poplar and their expression patterns under exogenous substances, to lay molecular basis for studying gene function and provide a reference for exploring putative roles of GOGATs in carbon-nitrogen balance.

Identification and expression analyses of the alanine aminotransferase (AlaAT) gene family in poplar seedlings.

Alanine aminotransferase (AlaAT, E.C.2.6.1.2) catalyzes the reversible conversion of pyruvate and glutamate to alanine and α-oxoglutarate. The AlaAT gene family has been well studied in some herbaceous plants, but has not been well characterized in woody plants. In this study, we identified four alanine aminotransferase homologues in Populus trichocarpa, which could be classified into two subgroups, A and B. AlaAT3 and AlaAT4 in subgroup A encode AlaAT, while AlaAT1 and AlaAT2 in subgroup B encode glutamate:glyoxylate aminotransferase (GGAT), which catalyzes the reaction of glutamate and glyoxylate to α-oxoglutarate and glycine. Four AlaAT genes were cloned from P. simonii × P. nigra. PnAlaAT1 and PnAlaAT2 were expressed predominantly in leaves and induced by exogenous nitrogen and exhibited a diurnal fluctuation in leaves, but was inhibited in roots. PnAlaAT3 and PnAlaAT4 were mainly expressed in roots, stems and leaves, and was induced by exogenous nitrogen. The expression of PnAlaAT3 gene could be regulated by glutamine or its related metabolites in roots. Our results suggest that PnAlaAT3 gene may play an important role in nitrogen metabolism and is regulated by glutamine or its related metabolites in the roots of P. simonii × P. nigra.