Search

Due to the complexity and non-stationarity of the voice generation system, the nonlinearity of speech signals cannot be accurately quantified. Recently, the recurrence quantification analysis method has been used for voice disorder detection. In this paper, multiscale recurrence quantification measures (MRQMs) are proposed. The signals are reconstructed in the high-dimensional phase space at the equivalent rectangular bandwidth scale. Recurrence plots (RPs) combining the characteristics of human auditory perception are drawn with an appropriate recurrence threshold. Based on the above, the nonlinear dynamic recurrence features of the speech signal are quantized from the recurrence plot of each frequency channel. Furthermore, this paper explores the recurrence quantification thresholds that are most suitable for pathological voices. Our results show that the proposed MRQMs with support vector machine (SVM), random forest (RF), Bayesian network (BN) and Local Weighted Learning (LWL) achieve an average accuracy of 99.45%, outperforming traditional features and other complex measurements. In addition, MRQMs also have the potential for multi-classification of voice disorder, achieving an accuracy of 89.05%. This study demonstrates that MRQMs can characterize the recurrence characteristic of pathological voices and effectively detect voice disorders.

This paper proposes a recognition method for extracting nonlinear characteristic parameters of pathological voices using Bark wavelet sub-band filtering. First, the speech signal was processed through 24 Bark filter banks. According to the signal obtained from each channel, the feature multi-frequency band nonlinear coefficient was extracted according to the frequency division factor, α. We used 53 normal voices and 117 pathological voices from the MEEI's pathological voice experimental database, and 14 machine learning methods were used to perform the recognition experiments. The experimental results showed that the proposed method effectively improved the recognition rate. Moreover, the proposed feature was optimal when α = 18, and the highest recognition rate was achieved when the support vector machine learning algorithm was used. [ABSTRACT FROM AUTHOR]

This paper proposes a recognition method for extracting nonlinear characteristic parameters of pathological voices using Bark wavelet sub-band filtering. First, the speech signal was processed through 24 Bark filter banks. According to the signal obtained from each channel, the feature multi-frequency band nonlinear coefficient was extracted according to the frequency division factor, . We used 53 normal voices and 117 pathological voices from the MEEI’s pathological voice experimental database, and 14 machine learning methods were used to perform the recognition experiments. The experimental results showed that the proposed method effectively improved the recognition rate. Moreover, the proposed feature was optimal when = 18, and the highest recognition rate was achieved when the support vector machine learning algorithm was used. [ABSTRACT FROM AUTHOR]

The relationship between inflammatory bowel disease and sleep disturbances is complicated and of increasing interest. We investigated the inflammatory and immunological consequences of EA in sleep-deprived colitis and found that dextran sulfate sodium (DSS)-induced colitis in sleep-fragmented (SF) mice was more severe than that in mice with normal sleep. This increase in the severity of colitis was accompanied by reduced body weight, shortened colon length, and deteriorated disease activity index. DSS with SF mice presented obvious diminished intestinal tight junction proteins (claudin-1 and occludin), elevated proinflammatory cytokines (CRP, IFN-γ, IL-6), lowered melatonin and adiponectin levels, downregulated vasoactive intestinal peptide (VIP) type 1 and 2 receptor (VPAC1, VPAC2) expression, and decreased diversity of gut bacteria. EA ameliorated colitis severity and preserved the performance of the epithelial tight junction proteins and VIP receptors, especially VPAC2. Meanwhile, the innate lymphoid cells-derived cytokines in both group 2 (IL-4, IL5, IL-9, IL-13) and group 3 (IL-22, GM-CSF) were elevated in mice colon tissue. Furthermore, dysbiosis was confirmed in the DSS group with and without SF, and EA could maintain the species diversity. Firmicutes could be restored, such as Lachnospiraceae, and Proteobacteria become rebalanced, mainly Enterobacteriaceae, after EA intervention. On the other hand, SF plays different roles in physiological and pathological conditions. In normal mice, interrupted sleep did not affect the expression of claudin-1 and occludin. But VPAC1, VPAC2, and gut microbiota diversity, including Burkholderiaceae and Rhodococcus, were opposite to mice in an inflamed state.