In order to realize the rapid and non-destructive detection of SO_2 content in sulphur-fumigated Achyranthis Bidentatae Radix, this paper first prepared the sulphur-fumigated Achyranthis Bidentatae Radix samples with the usage amount of sulphur being 0, 2.5%, and 5% of the mass of Achyranthis Bidentatae Radix pieces. The SO_2 content in different batches of sulphur-fumigated Achyranthis Bidentatae Radix was determined using the method in Chinese Pharmacopoeia, followed by the acquisition of their hyperspectral data within both visible-near infrared(435-1 042 nm) and short-wave infrared(898-1 751 nm) regions by hyperspectral imaging. Meanwhile, the first derivative, AUTO, multiplicative scatter correction, Savitzky-Golay(SG) smoothing, and standard normal variable transformation algorithms were used to pre-process the original hyperspectral data, which were then subjected to characteristic band extraction based on competitive adaptive reweighted sampling(CARS) and the partial least square regression analysis for building a quantitative model of SO_2 content in sulphur-fumigated Achyranthis Bidentatae Radix. It was found that the accuracy of the quantitative model built depending on the visible-near infrared spectra was high, with the determination coefficient of prediction set(R■) reaching 0.900 1. The established quantitative model has enabled the rapid and non-destructive detection of SO_2 content in sulphur-fumigated Achyranthis Bidentatae Radix, which can serve as an effective supplement to the method described in Chinese Pharmacopeia.
Hyperspectral Imaging ; Least-Squares Analysis ; Plant Roots ; Sulfur

In the 21 st century, the rise of artificial intelligence(AI) marks the arrival of the intelligence era or the era of Industry 4.0. In addition to the rapid development of computer and electronic information science, machine learning, as the core intelligence of AI, provides a new methodology for the modernization of traditional Chinese medicine. The algorithms of machine learning include support vector machine(SVM), extreme learning machine(ELM), convolutional neural network(CNN), and recurrent neural network(RNN). The combination of machine learning algorithms and hyperspectral imaging analysis could be used for the identification of fake and inferior herbs, the origin of herbs and the content determination of bioactive ingredients in herbs, which has largely solved the difficulty in strictly controlling the quality of traditional Chinese medicine. The integration of high spectral imaging(HSI) and deep lear-ning will make the predicted results more reliable and suitable for analysis of great amounts of samples. This paper summarizes the application of hyperspectral imaging technology(HSI) and machine learning algorithms in the field of traditional Chinese medicine in recent years, focuses on the principles of hyperspectral imaging technology, preprocessing methods and deep learning algorithms, and gives the prospects of evolution of hyperspectral imaging technology in the field.
Algorithms ; Artificial Intelligence ; Deep Learning ; Hyperspectral Imaging ; Medicine, Chinese Traditional ; Neural Networks, Computer

OBJECTIVE: To estimate the univariate heritability of resting heart rate and common chronic disease such as hypertension, diabetes, and dyslipidemia based on extended pedigrees in Fujian Tulou area and to explore bivariate heritability to test for the genetic correlation between resting heart rate and other relative phenotypes. METHODS: The study was conducted in Tulou area of Nanjing County, Fujian Province from August 2015 to December 2017. The participants were residents with Zhang surname and their relatives from Taxia Village, Qujiang Village, and Nanou Village or residents with Chen surname and their relatives from Caoban Village, Tumei Village, and Beiling Village. The baseline survey recruited 1 563 family members from 452 extended pedigrees. The pedigree reconstruction was based on the family information registration and the genealogy booklet. Univariate and bivariate heritability was estimated using variance component models for continuous variables, and susceptibility-threshold model for binary variables. RESULTS: The pedigree reconstruction identified 1 seven-generation pedigree, 2 five-generation pedigrees, 23 four-generation pedigrees, 186 three-generation pedigrees, and 240 two-generation pedigrees. The mean age of the participants was 57.2 years and the males accounted for 39.4%. The prevalence of hypertension, diabetes, dyslipidemia in this population was 49.2%, 10.0%, and 45.2%, respectively. The univariate heritability estimation of resting heart rate, hypertension, and dyslipidemia was 0.263 (95%CI: 0.120－0.407), 0.404 (95%CI: 0.135－0.673), and 0.799 (95%CI: 0.590－1), respectively. The heritability of systolic blood pressure, diastolic blood pressure, fasting glucose, total cholesterol, triglyceride, high-density lipoprotein cholesterol, and low-density lipoprotein cholesterol was 0.379, 0.306, 0.393, 0.452, 0.568, 0.852, and 0.387, respectively. In bivariate analysis, there were phenotypic correlations between resting heart rate with hypertension, diabetes, diastolic blood pressure, fasting glucose, and triglyceride. After taking resting heart rate into account, there were strong genetic correlations between resting heart rate with fasting glucose (genetic correlation 0.485, 95%CI: 0.120－1, P<0.05) and diabetes (genetic correlation 0.795, 95%CI: 0.181－0.788, P<0.05). CONCLUSION Resting heart rate was a heritable trait and correlated with several common chronic diseases and related traits. There was strong genetic correlation between resting heart rate with fasting glucose and diabetes, suggesting that they may share common genetic risk factors.
Blood Pressure ; Chronic Disease ; Female ; Heart Rate ; Humans ; Hypertension ; Male ; Middle Aged ; Pedigree