Personalized Human Activity Recognition Based on Integrated Wearable Sensor and Transfer Learning.

Human activity recognition (HAR) based on the wearable device has attracted more attention from researchers with sensor technology development in recent years. However, personalized HAR requires high accuracy of recognition, while maintaining the model's generalization capability is a major challenge in this field. This paper designed a compact wireless wearable sensor node, which combines an air pressure sensor and inertial measurement unit (IMU) to provide multi-modal information for HAR model training. To solve personalized recognition of user activities, we propose a new transfer learning algorithm, which is a joint probability domain adaptive method with improved pseudo-labels (IPL-JPDA). This method adds the improved pseudo-label strategy to the JPDA algorithm to avoid cumulative errors due to inaccurate initial pseudo-labels. In order to verify our equipment and method, we use the newly designed sensor node to collect seven daily activities of 7 subjects. Nine different HAR models are trained by traditional machine learning and transfer learning methods. The experimental results show that the multi-modal data improve the accuracy of the HAR system. The IPL-JPDA algorithm proposed in this paper has the best performance among five HAR models, and the average recognition accuracy of different subjects is 93.2%.

Synthesis and biological activities of novel isoxazoline-linked pseudodisaccharide derivatives.

A series of novel isoxazoline linked pseudodisaccharide derivatives were regiospecifically synthesized by 1,3-dipolar cycloaddition of α-allyl-C-glycopyranosides and sugar-derived nitrile oxides with good yields. The structures of the compounds were characterized by NMR spectroscopy and MS spectrometry and confirmed by the X-ray crystallographic analysis of compound ((5S)-3-(2,3-O-isopropylidene-5-deoxy-d-lyxofuranose-4-yl)isoxazoline-5-yl) methyl α- C-D-galactopyranoside. Their biological activities against glycosidases (α-amylase, α-glucosidase, and ß-glucosidase) and HIV-RT, and antitumor activity were preliminarily evaluated. Some of them exhibited potent inhibitory activity to HIV-RT.

Synthesis of C-Pseudonucleosides Bearing Thiazolidin-4-one as a Novel Potential Immunostimulating Agent.

Several novel C-pseudonucleosides bearing thiazolidin-4-one were synthesized by one-pot three-component condensation using unprotected sugar aldehyde at room temperature, and their effects on T cells, B cells, the cytokine secretion of IL-2, IL-4, and IFN-γ, T cell-associated molecules (CD3, CD4, CD8), and B cell-associated molecules (CD19) were first evaluated. The experimental data demonstrated that such thiazolidin-4-one C-pseudonucleosides hold potential as immunostimulating agents.