RESUMO
The key to the analysis of electroencephalogram (EEG) signals lies in the extraction of effective features from the raw EEG signals, which can then be utilized to augment the classification accuracy of motor imagery (MI) applications in brain-computer interface (BCI). It can be argued that the utilization of features from multiple domains can be a more effective approach to feature extraction for MI pattern classification, as it can provide a more comprehensive set of information that the traditional single feature extraction method may not be able to capture. In this paper, a multi-feature fusion algorithm based on uniform manifold approximate and projection (UMAP) is proposed for motor imagery EEG signals. The brain functional network and common spatial pattern (CSP) are initially extracted as features. Subsequently, UMAP is utilized to fuse the extracted multi-domain features to generate low-dimensional features with improved discriminative capability. Finally, the k-nearest neighbor (KNN) classifier is applied in a lower dimensional space. The proposed method is evaluated using left-right hand EEG signals, and achieved the average accuracy of over 92%. The results indicate that, compared with single-domain-based feature extraction methods, multi-feature fusion EEG signal classification based on the UMAP algorithm yields superior classification and visualization performance. Feature extraction and fusion based on UMAP algorithm of left-right hand motor imagery.
RESUMO
Cervical cancer remains the second-most prevalent female malignancy around the world, leading to a great majority of cancer-related mortality that occurs mainly in developing countries. Developing an effective and low-cost vaccine against human papillomavirus (HPV) infection, especially in medically underfunded areas, is urgent. Compared with vaccines based on HPV L1 viruslike particles (VLPs) in the market, recombinant HPV L1 pentamer expressed in Escherichia coli represents a promising and potentially cost-effective vaccine for preventing HPV infection. Hybrid particles comprising a polymer core and lipid shell have shown great potential compared to conventional aluminum salts adjuvant and is urgently needed for HPV L1 pentamer vaccines. It is well-reported that particle sizes are crucial in regulating immune responses. Nevertheless, reports on the relationship between the particulate size and the resultant immune response have been in conflict, and there is no answer to how the size of particles regulates specific immune response for HPV L1 pentamer-based candidate vaccines. Here, we fabricated HPV 16 L1 pentamer-loaded poly(d,l-lactide- co-glycolide) (PLGA)/lecithin hybrid particles with uniform sizes (0.3, 1, and 3 µm) and investigated the particle size effects on antigen release, activation of lymphocytes, dendritic cells (DCs) activation and maturation, follicular helper CD4+ T (TFH) cells differentiation, and release of pro-inflammatory cytokines and chemokines. Compared with the other particle sizes, 1 µm particles induced more powerful antibody protection and yielded more persistent antibody responses, as well as more heightened anamnestic responses upon repeat vaccination. The superior immune responses might be attributed to sustainable antigen release and robust antigen uptake and transport and then further promoted a series of cascade reactions, including enhanced DCs maturation, increased lymphocytes activation, and augmented TFH cells differentiation in draining lymph nodes (DLNs). Here, a powerful and economical platform for HPV vaccine and a comprehensive understanding of particle size effect on immune responses for HPV L1 pentamer-based candidate vaccines are provided.