Subjects: Engineering and technical science >> Biomedical Engineering submitted time 2024-04-29
Abstract： The limited training samples pose a significant obstacle to the practical application of brain-computer interface based on error-related potentials (ErrPs), affecting their recognition accuracy. To enhance ErrP recognition under such constraints, we propose a transfer discriminant subspace analysis (TDSA) algorithm that leverages a data alignment strategy. This algorithm extracts a shared discriminant subspace from electroencephalogram samples of both source and target subjects, capturing inter-class differences. By applying temporal alignment within this subspace, it effectively reinforces common features across subjects. We evaluate six different data alignment transfer learning strategies using two publicly available datasets. The results demonstrate that the TDSA algorithm achieves a 6.07% improvement in balanced accuracy for dataset 1 compared to the suboptimal Euclidean alignment method and a 7.88% improvement over non-transfer learning methods. Remarkably, with only 60~100 target subject data samples for training, the TDSA algorithm approaches the classification performance of traditional strategies that require 210~350 samples. This provides a new perspective for facilitating the data alignment of ErrPs.
Peer Review Status:
Awaiting Review
Subjects: Biology >> Botany >> Applied botany submitted time 2022-08-05 Cooperative journals: 《广西植物》
Abstract： In order to explore the photosynthetic physiological adaptation mechanism of karst plant, Li-6400XT portable photosynthesis system were used to detect the leaf photosythetic parameters of eight karst adaptable plants in Pingguo City, Guangxi, including net photosynthetic rate (Pn), stomatal conductivity (Gs), intercellular CO2 concentration (Ci), transpiration rate (Tr), water use efficiency (WUE) and stomatal limitation value (Ls). Statistical methods, such as Pearson correlation analysis, principal component analysis (PCA), and permutational multivariate analysis of variance (PERMANOVA) were used in this study. The results showed the six photosynthetic parameters had different variation within and between species, and all the intraspecific variations were greater than the interspecific. Change of Gs and Tr mainly originated from interspecific variation (46.72% - 49.76%), while that of Pn 、Ci 、WUE and Ls mainly from intraspecific variation (48.66% - 64.50%). At the life form level, the intraspecific variations of Pn、Gs and Tr of evergreen plants were less than those of deciduous plants, but the intraspecific variation of Ci、WUE and Ls of evergreen plants was higher. Interspecific variations of all the parameters of deciduous plants were greater than those of evergreen plants. Gs variation was the greatest both at the intraspecific and the interspecific level, followed by Tr and Pn, while Ls and WUE, and Ci variation were the least. There were significant positive correlations among Pn、Gs and Tr (P<0.01). Ls was significantly positively correlated with WUE (P<0.05), but negatively with Gs and Ci (P<0.05). The correlations among these photosynthetic parameters are basically consistent with the global scale, which reflects the diverse trade-off strategies of plants to environment resources. The results also verified the leaf economics spectrum (LES) of karst plant. Evergreen plants were located at the slow investment-return end of the LES with high values of Ls, WUE and low values of Gs、Tr、Ci and Pn. On the contrary, deciduous plants were located at the quick investment-return end of the LES with low value of WUE and high value of Pn and Tr. The results reflect karst plant adapt to changing environment with different adaptation strategies by trade-offs or co-ordinations among traits, and provide scientific basis for selecting adaptive tree species and accelerating the succession process of vegetation restoration in the karst area.
Hits
Hits
Downloads
Comment