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.

[Study on the vibrational spectra of 3,5-dimethoxybenzyl alcohol].

3,5-dimethoxybenzyl alcohol (L1 OH) is a kind of important pharmaceutical intermediate and it is also the starting material of a family of dendrimer LnOH (integer n means the layers of "branch"). A number of articles reported the structure and properties of the L1 OH. However, its molecular vibrational spectra have not been reported up to date. Study of vibrational spectra on L1 OH at the molecular level can provide new information, which is significant for the in-depth study of related molecules of drug and the dendrimer. Recent studies indicated a morphology effect on the light-harvesting functions of dendritic macromolecules. In the present report, the Raman and FTIR spectra of 3,5-dimethoxybenzyl alcohol were measured experimentally. And the density functional theory (DFT) method (B3LYP/6-311G(d,p)) were used to calculate the equilibrium geometry and vibration frequencies of L1 OH. The results showed that the calculated frequencies agree well with the experimental ones. Potential energy distribution of each frequency was worked out by normal mode analysis. Thereafter the authors got a detail assignment of the vibrational frequencies for L1 OH for the first time. Also, the results showed that the DFT is really a useful method in the study of molecular vibrational spectra.