RESUMO
Wearable sensors provide a more effective means of activity monitoring and management by recording patients' daily activity data for assessing their daily function and rehabilitation progress, as well as providing a convenient and practical solution for human activity recognition (HAR). However, during the motor rehabilitation of stroke patients, sensors provide vast amounts of high-dimensional data that are large and complex. To enhance the accuracy of activity monitoring and identification, as well as address the limitations of real-time processing, data visualization, and tracking in conventional monitoring approaches, it is essential to perform valid data processing and analysis. This paper combines deep learning models to explore the potential relationships and patterns between data to build an intelligent post-stroke rehabilitation system. This paper proposes a novel framework aimed at accurately recognizing activities performed by stroke patients. Our approach leverages a data fusion mechanism based on multiple sensors to construct a fusion tensor and employs a bidirectional long and short-term memory (BiLSTM) network enhanced with an attention mechanism. This network effectively captures temporal patterns and long-term dependencies within the data, resulting in improved performance for wearable sensor-based activity classification. Furthermore, we introduce an enhanced loss function to optimize the learning process. To assess the performance of the proposed model algorithm, two benchmark datasets were employed. These datasets served as the basis for evaluating and comparing the baseline method as well as other proposed methods. The experimental results clearly demonstrated that the proposed model outperformed the compared methods, indicating its superior performance in activity recognition.
RESUMO
Anabarilius duoyiheensis is a native and rare fish in Yunnan. In this study, the complete mitochondrial genome of A. duoyiheensis was sequenced and published for a total of 16,614 bp, including 13 protein-coding genes, 22 transfer RNAs, two ribosomal RNAs, and one control region. The phylogenetic analysis based on the complete mitochondrial genome showed that A. duoyiheensis belongs to the clade of the genus Anabarilius and was sister to the clade of Hemiculter. This study also contributes to the genus phylogeny of Anabarilius and other members of the family Xenocyprididae.
RESUMO
In this study, the whole mitochondrial genome of Silurus grahami was reported to be 16,518 bp in length, including 13 protein-coding genes, two ribosomal RNAs, 22 transfer RNAs, and one control region. The phylogenetic analysis based on 13 protein-coding genes showed that S. grahami was sister to clade of S. meridionalis and S. lanzhouensis. A total of 81 bases differences were identified in COI barcoding region, which could be used for species identification in catfish.
RESUMO
Sexual dimorphism is widespread in fish species. The red-tail catfish (Mystus wyckioides) is a commercially important catfish in the lower reaches of the Lancang River and the Mekong basin, and it shows a growth advantage in males. Here, RNA-seq was for the first time used to explore the gene expression difference between the sexes in the hypothalamus and pituitary of red-tail catfish, respectively. In the hypothalamus, 5732 and 271 unigenes have significantly higher and lower expressions, respectively, in males compared with females. KEGG analysis showed that 212 DEGs were annotated to 216 signaling pathways, and enrichment analysis suggested different levels of cAMP and glutamatergic synapse signaling between male and female hypothalami and some of the DEGs appear involved in gonad development and growth. In the pituitary, we found only 19 differentially expressed unigenes, which were annotated to 32 signaling pathways, most of which play important roles in gonad development.
