Application of Bayesian regularized BP neural network model for analysis of aquatic ecological data—A case study of chlorophyll-a prediction in Nanzui water area of Dongting Lake

Bayesian regularized BP neural network（BRBPNN） technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS i1.0 software, the BRBPNN model was established between chlorophyll-α and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.000？8426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll- α declined in the order of alga amount 〉 secchi disc depth（SD） 〉 electrical conductivity （EC）. Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-α concentration, total phosphorus（TP） and total nitrogen（TN） were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data（chlorophyll-α prediction） and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.

Bayesian Network Model of Product Information Diffusion and Reasoning of Influence

Information diffusion on social media has become a key strategy in people’s daily interactions. This paper studies consumers’ participation in the product information diffusion, and analyzes the complexity of information diffusion which is affected by many factors. Prior investigations of information diffusion have primarily focused on the composition of diffusion networks with independent factors and the intricacy of the process has not been completely evaluated. The majority of prior investigations have focused on strategies and the moving forces in social media processes and the determination of influential seed nodes, with few evaluations conducted about the factors affecting consumers’ choices in information diffusion. In this study, a Bayesian network model of product information diffusion was created to examine the links between factors and consumer deportment. It revealed how those factors had an impact on each other and on consumer deportment choice. The innovation of the thesis is reflected in the exploration and analysis of the specific communication path of product information diffusion, which provides a better marketing idea and practical method for the development of mobile e-commerce. The research findings can help identify the quantitative relationships between the factors affecting the process of product information diffusion and user behavior.

Building Bayesian Network(BN)-Based System Reliability Model by Dual Genetic Algorithm(DGA)

A system reliability model based on Bayesian network(BN)is built via an evolutionary strategy called dual genetic algorithm(DGA).BN is a probabilistic approach to analyze relationships between stochastic events.In contrast with traditional methods where BN model is built by professionals,DGA is proposed for the automatic analysis of historical data and construction of BN for the estimation of system reliability.The whole solution space of BN structures is searched by DGA and a more accurate BN model is obtained.Efficacy of the proposed method is shown by some literature examples.

Predicting the nephrotoxicity of Chinese herbal medicines based on a Bayesian network model

Objective:Based on a Bayesian network model(BNM),we constructed and evaluated a predictive model of Chinese herbal medicines(CHMs)nephrotoxicity,explored its influencing factors,and provided a reference for the prevention and control of nephrotoxicity.Methods:We searched for CHMs with nephrotoxicity through academic journals and academic works,screened non-nephrotoxic CHMs,and then tested the correlation between nephrotoxic and non-nephrotoxic CHMs and their four properties,five flavours,and channel tropism.The screened variables were used to construct the Bayesian network model(BNM),predict important factors affecting the nephrotoxicity of Chinese herbal medicines(CHMs),draw the receiver operating characteristic(ROC)curve of the model,and calculate the area under the curve(AUC)to evaluate the forecasting effect of the model.Results:Medicinal property theory(four properties and five flavours)are important factors affecting the nephrotoxicity of CHMs.Nephrotoxic and non-nephrotoxic CHMs are related to their four propertiesand five flavours(P<0.05).BNM showed that sweetness and flatness wereimportant protective factors for nephrotoxicity of CHMs;the prediction accuracy was 77.92%,the AUC result of the model ROC curve was 0.661(95%CI:0.620-0.701),and the best sensitivity(0.736)and specificity(0.571)were obtained at 0.65.Discussion:Modern mathematical statistics and modeling methods have certain reference significance and application value for the prediction of CHMs nephrotoxicity and toxicology research.

Ontology Mapping Based on Bayesian Network

Ontology mapping is a key interoperability enabler for the semantic web. In this paper,a new ontology mapping approach called ontology mapping based on Bayesian network( OM-BN) is proposed. OM-BN combines the models of ontology and Bayesian Network,and applies the method of Multi-strategy to computing similarity. In OM-BN,the characteristics of ontology,such as tree structure and semantic inclusion relations among concepts,are used during the process of translation from ontology to ontology Bayesian network( OBN). Then the method of Multi-strategy is used to create similarity table( ST) for each concept-node in OBN. Finally,the iterative process of mapping reasoning is used to deduce new mappings from STs,repeatedly.

Hierarchy Bayesian model based services awareness of high-speed optical access networks

As the speed of optical access networks soars with ever increasing multiple services, the service-supporting ability of optical access networks suffers greatly from the shortage of service awareness. Aiming to solve this problem, a hierarchy Bayesian model based services awareness mechanism is proposed for high-speed optical access networks. This approach builds a so-called hierarchy Bayesian model, according to the structure of typical optical access networks. Moreover, the proposed scheme is able to conduct simple services awareness operation in each optical network unit(ONU) and to perform complex services awareness from the whole view of system in optical line terminal(OLT). Simulation results show that the proposed scheme is able to achieve better quality of services(Qo S), in terms of packet loss rate and time delay.

An Information Fusion Model of Innovation Alliances Based on the Bayesian Network

To solve the problem of information fusion from multiple sources in innovation alliances, an information fusion model based on the Bayesian network is presented. The multi-source information fusion process of innovation alliances was classified into three layers, namely, the information perception layer, the feature clustering layer,and the decision fusion layer. The agencies in the alliance were defined as sensors through which information is perceived and obtained, and the features were clustered. Finally, various types of information were fused by the innovation alliance based on the fusion algorithm to achieve complete and comprehensive information. The model was applied to a study on economic information prediction, where the accuracy of the fusion results was higher than that from a single source and the errors obtained were also smaller with the MPE less than 3%, which demonstrates the proposed fusion method is more effective and reasonable. This study provides a reasonable basis for decision-making of innovation alliances.

Improving herdsmen’s well-being through scenario planning:A case study in Xilinhot City,Inner Mongolia Autonomous Region

Grassland ecosystems support well-being with food,shelter,income,and culture of herdsmen.While the associa-tion between ecosystem services and human well-being has been widely studied,such association is understudied in grassland ecosystems.This study aims to fill this gap through a case study of Xilinhot City,Inner Mongolia Autonomous Region,China.We examined the association between grassland provisioning services and herds-men’s well-being between 1985 and 2015 through participatory observations,interviews,surveys,and Bayesian belief network modeling.Considering the uncertainties of weather and sheep prices,we developed four scenarios to examine the future well-being of herdsmen.Our results show that the most important factor for herdsmen’s well-being was income,which is highly sensitive to the market price of sheep and precipitation.Considering the uncertainties of sheep prices and precipitation,scenario analysis revealed a divergence between income and well-being.While herdsmen’s income is most likely to increase with low precipitation and increased sheep prices,their well-being is most likely to improve with abundant precipitation and increased sheep prices.Based on our find-ings,we argue that developing alternative income sources(e.g.,tourism),reducing dependence on government subsidies through commercial insurance,and branding lamb with grassland ecosystem to alleviate the impact of price fluctuations would help improve herdsmen’s well-being in all scenarios.

Evaluation and prediction of engineering construction suitability in the Chinae-Mongoliae-Russia economic corridor

It is proposed to build a high-speed railway through the China‒Mongolia‒Russia economic corridor(CMREC)which runs from Beijing to Moscow via Mongolia.However,the frozen ground in this corridor has great impacts on the infrastructure stability,especially under the background of climate warming and permafrost degradation.Based on the Bayesian Network Model(BNM),this study evaluates the suitability for engineering construction in the CMREC,by using 21 factors in five aspects of terrain,climate,ecology,soil,and frozen-ground thermal stability.The results showed that the corridor of Mongolia's Gobi and Inner Mongolia in China is suitable for engineering construction,and the corridor in Amur,Russia near the northern part of Northeast China is also suitable due to cold and stable permafrost overlaying by a thin active layer.However,the corridor near Petropavlovsk in Kazakhstan and Omsk in Russia is not suitable for engineering construction because of low freezing index and ecological vulnerability.Furthermore,the sensitivity analysis of influence factors indicates that the thermal stability of frozen ground has the greatest impact on the suitability of engineering construction.These conclusions can provide a reference basis for the future engineering planning,construction and risk assessment.