Comparisons of forecasting for hepatitis in Guangxi Province, China by using three neural networks models.
Ontology highlight
ABSTRACT:
SUBMITTER: Gan R
PROVIDER: S-EPMC5103820 | biostudies-literature | 2016
REPOSITORIES: biostudies-literature
Publications
Comparisons of forecasting for hepatitis in Guangxi Province, China by using three neural networks models.
Gan Ruijing R Chen Ni N Huang Daizheng D
PeerJ 20161108
This study compares and evaluates the prediction of hepatitis in Guangxi Province, China by using back propagation neural networks based genetic algorithm (BPNN-GA), generalized regression neural networks (GRNN), and wavelet neural networks (WNN). In order to compare the results of forecasting, the data obtained from 2004 to 2013 and 2014 were used as modeling and forecasting samples, respectively. The results show that when the small data set of hepatitis has seasonal fluctuation, the predictio ...[more]
Similar Datasets
Project description:In this paper we investigate the utility of one-dimensional convolutional neural network (CNN) models in epidemiological forecasting. Deep learning models, in particular variants of recurrent neural networks (RNNs) have been studied for ILI (Influenza-Like Illness) forecasting, and have achieved a higher forecasting skill compared to conventional models such as ARIMA. In this study, we adapt two neural networks that employ one-dimensional temporal convolutional layers as a primary building block-temporal convolutional networks and simple neural attentive meta-learners-for epidemiological forecasting. We then test them with influenza data from the US collected over 2010-2019. We find that epidemiological forecasting with CNNs is feasible, and their forecasting skill is comparable to, and at times, superior to, plain RNNs. Thus CNNs and RNNs bring the power of nonlinear transformations to purely data-driven epidemiological models, a capability that heretofore has been limited to more elaborate mechanistic/compartmental disease models.
| S-EPMC8270135 | biostudies-literature
Project description:In this article we forecast daily closing price series of Bitcoin, Litecoin and Ethereum cryptocurrencies, using data on prices and volumes of prior days. Cryptocurrencies price behaviour is still largely unexplored, presenting new opportunities for researchers and economists to highlight similarities and differences with standard financial prices. We compared our results with various benchmarks: one recent work on Bitcoin prices forecasting that follows different approaches, a well-known paper that uses Intel, National Bank shares and Microsoft daily NASDAQ closing prices spanning a 3-year interval and another, more recent paper which gives quantitative results on stock market index predictions. We followed different approaches in parallel, implementing both statistical techniques and machine learning algorithms: the Simple Linear Regression (SLR) model for uni-variate series forecast using only closing prices, and the Multiple Linear Regression (MLR) model for multivariate series using both price and volume data. We used two artificial neural networks as well: Multilayer Perceptron (MLP) and Long short-term memory (LSTM). While the entire time series resulted to be indistinguishable from a random walk, the partitioning of datasets into shorter sequences, representing different price "regimes", allows to obtain precise forecast as evaluated in terms of Mean Absolute Percentage Error(MAPE) and relative Root Mean Square Error (relativeRMSE). In this case the best results are obtained using more than one previous price, thus confirming the existence of time regimes different from random walks. Our models perform well also in terms of time complexity, and provide overall results better than those obtained in the benchmark studies, improving the state-of-the-art.
| S-EPMC7924725 | biostudies-literature
Project description:BackgroundGuangxi is the province most seriously affected by rabies virus (RABV) in China. Those most affected by RABV each year are people in rural areas, where dogs are the main cause of human infection with the virus.MethodsIn this study, we established a rabies vaccination demonstration program that included eradication, core, and peripheral areas. This program was implemented for 9 years and comprised three stages: 12 counties in the first stage (2008-2010), 21 counties in the second stage (2011-2013), and then extending to all counties of Guangxi Province in the third stage (2014-2016). The program included a dog vaccination campaign, surveillance of clinically healthy dogs who may be potential RABV carriers, monitoring anti-RABV antibody titers in vaccinated dogs, and compiling and reporting statistics of human rabies cases.ResultsThe target effectiveness was achieved in the eradication, core, and peripheral areas in all three stages. The vaccination demonstration program successfully promoted RABV vaccination of domestic dogs throughout Guangxi Province by drawing upon the experience gained at key points. Compared with a vaccination coverage rate of 39.42-46.85% in Guangxi Province overall during 2003-2007, this rate gradually increased to 48.98-52.67% in 2008-2010, 60.24-69.67% in 2011-2013, and 70.09-71.53% in 2014-2016, thereby meeting World Health Organization requirements. The total cases of human rabies in the province decreased from 602 in 2004 to 41 cases in 2017.ConclusionsThe present pilot vaccination program obviously increased the rabies vaccination and seroconversion rates, and effectively reduced the spread of rabies from dogs to humans as well as the number of human rabies cases, thus successfully controlling rabies in Guangxi.
| S-EPMC6086044 | biostudies-literature
Project description:BackgroundHuman rabies cases in the Guangxi province of China decreased from 839 in 1982 to 24 in 1995, but subsequently underwent a sharp increase, and has since maintained a high level.Methodology/principal findings3,040 brain samples from normal dogs and cats were collected from 14 districts of Guangxi and assessed by RT-PCR. The brain samples showed an average rabies virus (RV) positivity rate of 3.26%, but reached 4.71% for the period Apr 2002 to Dec 2003. A total of 30 isolates were obtained from normal dogs and 28 isolates from rabid animals by the mouse inoculation test (MIT). Six representative group I and II RV isolates showed an LD50 of 10-5.35/ml to 10-6.19/ml. The reactivity of monoclonal antibodies (MAbs) to group I and II RV isolates from the Guangxi major epidemic showed that eight anti-G MAbs showed strong reactivity with isolates of group I and II with titers of ?10,000; however, the MAbs 9-6, 13-3 and 12-14 showed lower reactivity. Phylogenetic analysis based on the G gene demonstrated that the Guangxi RV isolates have similar topologies with strong bootstrap values and are closely bonded. Alignment of deduced amino acids revealed that the mature G protein has four substitutions A96S, L132F, N436S, and A447I specific to group I, and 13 substitutions T90M, Y168C, S204G, T249I, P253S, S289T, V332I, Q382H, V427I, L474P, R463K Q486H, and T487N specific to group II, coinciding with the phylogenetic analysis of the isolates.ConclusionsRe-emergence of human rabies has mainly occurred in rural areas of Guangxi since 1996. The human rabies incidence rate increased is related with RV positive rate of normal dogs. The Guangxi isolates tested showed a similar pathogenicity and antigenicity. The results of phylogenetic analysis coincide with that of alignment of deduced amino acids.
| S-EPMC4183421 | biostudies-literature
Project description:Guangxi, a province in southwestern China, has the second highest reported number of HIV/AIDS cases in China. This study aimed to develop an accurate and effective model to describe the tendency of HIV and to predict its incidence in Guangxi. HIV incidence data of Guangxi from 2005 to 2016 were obtained from the database of the Chinese Center for Disease Control and Prevention. Long short-term memory (LSTM) neural network models, autoregressive integrated moving average (ARIMA) models, generalised regression neural network (GRNN) models and exponential smoothing (ES) were used to fit the incidence data. Data from 2015 and 2016 were used to validate the most suitable models. The model performances were evaluated by evaluating metrics, including mean square error (MSE), root mean square error, mean absolute error and mean absolute percentage error. The LSTM model had the lowest MSE when the N value (time step) was 12. The most appropriate ARIMA models for incidence in 2015 and 2016 were ARIMA (1, 1, 2) (0, 1, 2)12 and ARIMA (2, 1, 0) (1, 1, 2)12, respectively. The accuracy of GRNN and ES models in forecasting HIV incidence in Guangxi was relatively poor. Four performance metrics of the LSTM model were all lower than the ARIMA, GRNN and ES models. The LSTM model was more effective than other time-series models and is important for the monitoring and control of local HIV epidemics.
| S-EPMC6518582 | biostudies-literature
Project description:Shih-Pin Huang, Yahui Zhao, I-Shiung Chen, and Kwang-Tsao Shao (2017) Microphysogobio zhangi n. sp., a new cyprinid species is described from Guangxi Province, China. Morphological and molecular evidence based on mitochondrial DNA Cytochrome b (Cyt b) sequence were used for comparing this new species and other related species. The phylogenetic tree topology revealed that this new species is closely related to M. elongatus and M. fukiensis. We also observed the existence of a peculiar trans-river gene ow in the Pearl River and the Yangtze River populations, and speculated that it was caused by an ancient arti cial canal, the Lingqu Canal, which forming a pathway directly connecting these two rivers.
| S-EPMC6517699 | biostudies-literature
Project description:Porcine deltacoronavirus (PDCoV) has been detected sporadically in China since its first description in 2012. In our study, 62 faecal and intestinal samples from pigs with diarrhoea were collected in Guangxi Province, China, during 2017 and 2018. Twelve samples (19.4%, 12/62) were positive for PDCoV. Five complete genomes of PDCoV were then determined, and sequence alignment revealed that the five strains had discontinuous deletions at 400-401 aa in non-structural protein 2 (NSP2) and 758-760 aa in non-structural protein 3 (NSP3) compared with the respective proteins in the HKU15-44 strain. Notably, the CHN-GX81-2018 strain contained two insertions in the S gene and 3'-UTR. Multiple sequence alignment and phylogenetic analysis showed that four strains shared 98.2%-98.4% nucleotide identity with CHN-AH-2004 and were classified into a new cluster of China lineage strains, whereas the CHN-GX81-2018 strain shared 98.7% nucleotide identity with Vietnam/Binh21/2015 and belonged to the Vietnam/Laos/Thailand lineage. Recombination analyses revealed that four strains were the result of recombination between CHN-HB-2014 and Vietnam/Binh21/2015 strains. This study demonstrated the co-existence of multiple lineages of PDCoV in China, and our findings will aid the reorganization and evolution of the virus.
| S-EPMC7738719 | biostudies-literature
Project description:In recent years, entrepreneurship has been gaining more prominence as a potential tool for solving poverty in developing countries. This paper mainly examines the relationship between farmer entrepreneurship and rural poverty alleviation in China by assessing the contribution of farm entrepreneurs towards overcoming poverty. Data were collected from 309 employees of farmer entrepreneurships in Guangxi Province through survey questionnaires. Structural equation modeling was used to conduct an analysis of the effects of three identified capabilities of farm entrepreneurs-economic, educational and knowledge, and socio-cultural capabilities-on attitude towards farmer entrepreneurship growth and the qualitative growth of farmer entrepreneurship and how these in turn affect rural poverty, using AMOS 21. The findings show that socio-cultural capability has the greatest influence on farmer entrepreneurship growth (β = 0.50, p<0.001). The qualitative growth of farmer entrepreneurship also more significantly impacts rural poverty (β = 0.69, p<0.001) than attitude towards farmer entrepreneurship growth. This study suggests that policy makers in China should involve more rural farmers in the targeted poverty alleviation strategies of the government by equipping rural farmers with entrepreneurial skills. This can serve as a sustainable, bottom-up approach to alleviating rural poverty in remote areas of the country. The study also extends the literature on the farmer entrepreneurship-rural poverty alleviation nexus in China, and this can serve as a lesson for other developing countries in the fight against rural poverty.
| S-EPMC5875809 | biostudies-literature
Project description:BackgroundHuman brucellosis has become a severe public health problem in China's Guangxi Province, and there has been higher prevalence of brucellosis in this region after 2010. Both multiple locus variable-number tandem repeat analysis (MLVA) and multilocus sequence typing (MLST) assay schedules were used to genotype isolates and determine relationships among isolates.ResultsA total of 40 isolates of Brucella were obtained from humans, pigs, and dogs from 1961 to 2016. There were at least three species of Brucella detected in Guangxi Province, Brucella melitensis, Brucella suis, and Brucella canis, with 16, 17, and 7 isolates, respectively. Of which B. suis biovar 3 was the predominant species resulting in pig brucellosis in the area examined before 2000s. Moreover, B. melitensis biovar 3 was found to be mainly responsible for human brucellosis during 2012-2016. All B. melitensis isolates in this study belonged to East Mediterranean lineage. MLVA-11 genotype 116 was the dominant genotype and represented 81.2% of the isolates. MLVA cluster analysis showed there to be 44% (7/16) brucellosis cases caused by B. melitensis with a profile of outbreak epidemic from 2012 to 2016. However, nearly 83.3% (20/24) of brucellosis cases resulting from both B. suis and B. canis showed no epidemiological links or sporadic characteristics. MLVA-16 analysis confirmed extensive genotype-sharing events between B. melitensis isolates from Guangxi and other northern provinces within China. These data revealed that there are potential epidemiology links among these strains. B. suis strains of this study showed a unique genetic lineage at the global level and may have existed historically in this area. However, present B. canis isolates were closely related to previously reported isolates in Korea, where they may have originated. MLST typing showed that the population structure of Brucella strains had changed considerably in this province; ST17 and ST21, two previously predominant populations appeared to have been replaced by recently emerging ST8 group.ConclusionsOur investigation data have inspired the hypothesis that Guangxi Province had been subject to an imported human brucellosis epidemic. Our data suggest that strains found in Northern regions of China are the principal source of infections in recent cases of human brucellosis in Guangxi Province. Comparative genomic analysis from more strains is necessary to confirm this hypothesis. This work will facilitate better understanding of the epidemiology and improve the effectiveness of control and prevention of brucellosis in this region.
| S-EPMC6916230 | biostudies-literature
Project description:BackgroundRabies is a severe epidemic in Guangxi province, China, with hundreds of deaths occurring each year. In the past six decades, rabies has emerged three times in Guangxi, and the province has reported the largest number of rabies cases in China. The domestic dog is the principal vector for rabies, and 95% of human cases are associated with transmission from dogs.ResultsTo understand the genetic relationship between street rabies virus (RABV) from Guangxi, genetic diversity analysis was performed using RABV isolates collected between 1999 and 2012. The N gene of 42 RABV isolates, and the P and M genes, as well as fragments of the 3' terminus (L1-680) and the polymerase activity module of the L gene (Lpam) of 36 RABV isolates were sequenced. In addition, whole genome sequencing was performed for 5 RABV isolates. There was evidence of topological discrepancy in the phylogenetic trees based on different genes of the RABV isolates. Amino acid variation of the deduced N protein exhibited different patterns to those obtained from the P and M proteins reported here, and the previously reported G protein (Tang H. et al., PLoS Negl Trop Dis, 8(10): e3114, 2014), and L1-680 and Lpam. These RABV isolates were divided into three main branches against fixed strains.ConclusionRABV is prevalent in Guangxi province and strains collected over the last two decades belong mainly to three groups (I, II, III). These RABV isolates reveal genetic diversity. Individual RABV genes from Guangxi exhibit different evolutionary characteristics. The results will have benefits for continuing comprehensive rabies surveillance, prevention and control in China.
| S-EPMC6006964 | biostudies-literature