Speech emotion recognition (SER) is a challenging task due to its difficulty in finding proper representations for emotion embedding in speech. Recently, Convolutional Recurrent Neural Network (CRNN), which is combined by convolution neural network and recurrent neural network, is popular in this field and achieves state-of-art on related corpus. However, most of work on CRNN only utilizes simple spectral information, which is not capable to capture enough emotion characteristics for the SER task. In this work, we investigate two joint representation learning structures based on CRNN aiming at capturing richer emotional information from speech. Cooperating the handcrafted high-level statistic features with CRNN, a two-channel SER system (HSF-CRNN) is developed to jointly learn the emotion-related features with better discriminative property. Furthermore, considering that the time duration of speech segment significantly affects the accuracy of emotion recognition, another two-channel SER system is proposed where CRNN features extracted from different time scale of spectrogram segment are used for joint representation learning. The systems are evaluated over Atypical Affect Challenge of ComParE2018 and IEMOCAP corpus. Experimental results show that our proposed systems outperform the plain CRNN.
Backgrounds The Systemic Immune-Inflammation Index (SII), as a novel inflammatory biomarker, has not been researched for type 2 diabetes mellitus (T2DM). This study was designed to investigate the potential association between SII and T2DM. Methods This cross-sectional study focused on adults enrolled in 2011 and 2018 by National Health and Nutrition Examination Survey (NHANES). Univariate, as well as multivariate logistic regression analyses, subgroup analyses, and sensitivity analyses, were performed to determine the independent association between SII and T2DM. The relationship between ln-SII and T2DM was described by the fitted smoothing curve. Results A total of 10,321 subjects were enrolled in the study; of which 2,078 (20.1%) were diagnosed with T2DM. After full adjustment, multivariate logistic regression demonstrated that higher SII was an independent risk factor for increased T2DM (OR = 1.30; 95% CI, 1.08–1.56, p < 0.0001). There was no relevant association of age, race, physical activity, high blood pressure, and smoking status(all p < 0.05), as demonstrated by the subgroup analysis and the interaction study. In addition, the relationship between SII and T2DM is non-linear; as ln-SII increases, the potential for T2DM gradually increases. Conclusions Elevated SII levels were linked to a higher probability of developing T2DM. More large and prospective studies will be required to confirm the results of this study.
Background It must be admitted that the incidence of colorectal cancer (CRC) was on the rise all over the world, but the related treatment had not caught up. Further research on the underlying pathogenesis of CRC was conducive to improving the survival status of current CRC patients. Methods Differentially expressed genes (DEGs) screening were conducted based on “limma” and “RobustRankAggreg” package of R software. Weighted gene co-expression network analysis (WGCNA) was performed in the integrated DEGs that from The Cancer Genome Atlas (TCGA), and all samples of validation were from Gene Expression Omnlbus (GEO) dataset. Results The terms obtained in the functional annotation for primary DEGs indicated that they were associated with CRC. The MEyellow stand out whereby showed the significant correlation with clinical feature (disease), and 4 hub genes, including ABCC13, AMPD1, SCNN1B and TMIGD1, were identified in yellow module. Nine datasets from Gene Expression Omnibus database confirmed these four genes were significantly down-regulated and the survival estimates for the low-expression group of these genes were lower than for the high-expression group in Kaplan-Meier survival analysis section. MEXPRESS suggested that down-regulation of some top hub genes may be caused by hypermethylation. Receiver operating characteristic curves indicated that these genes had certain diagnostic efficacy. Moreover, tumor-infiltrating immune cells and gene set enrichment analysis for hub genes suggested that there were some associations between these genes and the pathogenesis of CRC. Conclusion This study identified modules that were significantly associated with CRC, four novel hub genes, and further analysis of these genes. This may provide a little new insights and directions into the potential pathogenesis of CRC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.