基于BP神经网络和RBF神经网络预测老年痴呆症疾病进展的对比研究

目的:比较反向传播算法(BP)神经网络和径向基函数(RBF)神经网络预测老年痴呆症疾病进展的效果。方法:以老年痴呆症随访数据为研究对象,以性别、年龄、受教育程度、有无高血压、有无高胆固醇、有无心脏病、有无中风史、有无家族史8个指标作为输入变量,以五年随访的MMSE差值为输出变量,构建基于BP神经网络和RBF神经网络的老年痴呆症疾病进展预测模型。结果:与BP神经网络模型相比,RBF神经网络预测的结果更好,能够有效地预测老年痴呆症疾病进展。结论:神经网络模型将老年痴呆症疾病进展预测问题转化为随访数据中相关测量指标与MMSE差值的非线性问题,为复杂的老年痴呆症疾病进展预测提供了新思路。     

The use of a radial basis neural network and genetic algorithm for improving the efficiency of laccase-mediated dye decolourization

A radial basis function neural network (RBF) and genetic algorithm (GA) were applied to improve the efficiency of the oxidative decolourization of the recalcitrant dye Reactive Black 5 (RB 5) by a technical laccase (Trametes spp.) and the natural mediator acetosyringone (ACS). The decolourization of RB 5 in aqueous solution was studied with a 3(4) factorial design including different levels of laccase (2, 100, 200UL(-1)), acetosyringone (5, 50, 100μM), pH value (3, 4.5, 6) and incubation time (10, 20, 30min). The generated RBF network was mathematically evaluated by several statistical indices and revealed better results than a classical quadratic response surface (RS) model. The experimental data showed that within 10min of incubation time a complete decolourization (>90%) was achieved by using the highest amount of laccase (200UL(-1)) and acetosyringone (100μM) at pH 6. By applying the RBF-GA methodology, the efficiency of the laccase-mediated decolourization was improved by minimising the required amount of laccase and acetosyringone by 25% and 21.7% respectively. Complete decolourization (>90%) was obtained within 10min at the GA-optimised process conditions of laccase (150UL(-1)) and acetosyringone (78.3μM) at pH 5.67. These results illustrate that the RBF-GA methodology could be a powerful technique during scale-up studies.     

Optimization of a fermentation medium using neural networks and genetic algorithms

Artificial neural networks and genetic algorithms are used to model and optimize a fermentation medium for the production of the enzyme hydantoinase by Agrobacterium radiobacter. Experimental data reported in the literature were used to build two neural network models. The concentrations of four medium components served as inputs to the neural network models, and hydantoinase or cell concentration served as a single output of each model. Genetic algorithms were used to optimize the input space of the neural network models to find the optimum settings for maximum enzyme and cell production. Using this procedure, two artificial intelligence techniques have been effectively integrated to create a powerful tool for process modeling and optimization.     

神经网络提高肝细胞癌磁共振波谱诊断正确率

通过评价31磷磁共振波谱(31Phosphorus Magnetic Resonance Spectroscopy,31P-MRS)来辨别三种诊断类型:肝细胞癌,正常肝和肝硬化。运用反向传输神经网络(BP)和径向基函数神经网络(RBF)分析31P-MRS数据,分别建立神经网络模型,进行肝细胞癌的诊断分类以期提高识别率。实验结果证明,应用神经网络模型后,31P-MR波谱对活体肝细胞癌的诊断正确率从89.47%提高到97.3%,且BP更优于RBF。     

Evolutionary optimization of RBF networks

One of the main obstacles to the widespread use of artificial neural networks is the difficulty of adequately defining values for their free parameters. This article discusses how Radial Basis Function (RBF) networks can have their parameters defined by genetic algorithms. For such, it presents an overall view of the problems involved and the different approaches used to genetically optimize RBF networks. A new strategy to optimize RBF networks using genetic algorithms is proposed, which includes new representation, crossover operator and the use of a multiobjective optimization criterion. Experiments using a benchmark problem are performed and the results achieved using this model are compared to those achieved by other approaches.     

Clustering-neural network models for freeway work zone capacity estimation

Two neural network models, called clustering-RBFNN and clustering-BPNN models, are created for estimating the work zone capacity in a freeway work zone as a function of seventeen different factors through judicious integration of the subtractive clustering approach with the radial basis function (RBF) and the backpropagation (BP) neural network models. The clustering-RBFNN model has the attractive characteristics of training stability, accuracy, and quick convergence. The results of validation indicate that the work zone capacity can be estimated by clustering-neural network models in general with an error of less than 10%, even with limited data available to train the models. The clustering-RBFNN model is used to study several main factors affecting work zone capacity. The results of such parametric studies can assist work zone engineers and highway agencies to create effective traffic management plans (TMP) for work zones quantitatively and objectively.     

Culture conditions optimization of hyaluronic acid production by Streptococcus zooepidemicus based on radial basis function neural network and quantum-behaved particle swarm optimization algorithm

This study aimed to optimize the culture conditions (agitation speed, aeration rate and stirrer number) of hyaluronic acid production by Streptococcus zooepidemicus. Two optimization algorithms were used for comparison: response surface methodology (RSM) and radial basis function neural network coupling quantum-behaved particle swarm optimization algorithm (RBF-QPSO). In RBF-QPSO approach, RBF is employed to model the microbial HA production and QPSO algorithm is used to find the optimal culture conditions with the established RBF estimator as the objective function. The predicted maximum HA yield by RSM and RBF-QPSO was 5.27 and 5.62 g/l, respectively, while a maximum HA yield of 5.21 and 5.58 g/l was achieved in the validation experiments under the optimal culture conditions obtained by RSM and RBF-QPSO, respectively. It was indicated that both models provided similar quality predictions for the above three independent variables in terms of HA yield, but RBF model gives a slightly better fit to the measured data compared to RSM model. This work shows that the combination of RBF neural network with QPSO algorithm has good predictability and accuracy for bioprocess optimization and may be helpful to the other industrial bioprocesses optimization to improve productivity.     

Neural network models for earthquake magnitude prediction using multiple seismicity indicators

Neural networks are investigated for predicting the magnitude of the largest seismic event in the following month based on the analysis of eight mathematically computed parameters known as seismicity indicators. The indicators are selected based on the Gutenberg-Richter and characteristic earthquake magnitude distribution and also on the conclusions drawn by recent earthquake prediction studies. Since there is no known established mathematical or even empirical relationship between these indicators and the location and magnitude of a succeeding earthquake in a particular time window, the problem is modeled using three different neural networks: a feed-forward Levenberg-Marquardt backpropagation (LMBP) neural network, a recurrent neural network, and a radial basis function (RBF) neural network. Prediction accuracies of the models are evaluated using four different statistical measures: the probability of detection, the false alarm ratio, the frequency bias, and the true skill score or R score. The models are trained and tested using data for two seismically different regions: Southern California and the San Francisco bay region. Overall the recurrent neural network model yields the best prediction accuracies compared with LMBP and RBF networks. While at the present earthquake prediction cannot be made with a high degree of certainty this research provides a scientific approach for evaluating the short-term seismic hazard potential of a region.     

Identification of phytoplankton from flow cytometry data by using radial basis function neural networks.

We describe here the application of a type of artificial neural network, the Gaussian radial basis function (RBF) network, in the identification of a large number of phytoplankton strains from their 11-dimensional flow cytometric characteristics measured by the European Optical Plankton Analyser instrument. The effect of network parameters on optimization is examined. Optimized RBF networks recognized 34 species of marine and freshwater phytoplankton with 91. 5% success overall. The relative importance of each measured parameter in discriminating these data and the behavior of RBF networks in response to data from "novel" species (species not present in the training data) were analyzed.     

Optimization of biopharmaceutical downstream processes supported by mechanistic models and artificial neural networks

Downstream process development is a major area of importance within the field of bioengineering. During the design of such a downstream process, important decisions have to be made regarding the type of unit operations as well as their sequence and their operating conditions. Current computational approaches addressing these issues either show a high level of simplification or struggle with computational speed. Therefore, this article presents a new approach that combines detailed mechanistic models and speed‐enhancing artificial neural networks. This approach was able to simultaneously optimize a process with three different chromatographic columns toward yield with a minimum purity of 99.9%. The addition of artificial neural networks greatly accelerated this optimization. Due to high computational speed, the approach is easily extendable to include more unit operations. Therefore, it can be of great help in the acceleration of downstream process development. © 2017 American Institute of Chemical Engineers Biotechnol. Prog., 33:696–707, 2017     

Identification of Phytoplankton from Flow Cytometry Data by Using Radial Basis Function Neural Networks

We describe here the application of a type of artificial neural network, the Gaussian radial basis function (RBF) network, in the identification of a large number of phytoplankton strains from their 11-dimensional flow cytometric characteristics measured by the European Optical Plankton Analyser instrument. The effect of network parameters on optimization is examined. Optimized RBF networks recognized 34 species of marine and freshwater phytoplankton with 91.5% success overall. The relative importance of each measured parameter in discriminating these data and the behavior of RBF networks in response to data from “novel” species (species not present in the training data) were analyzed.     

Hybrid neural simulation of a fed-batch bioreactor for a nonideal recombinant fermentation

Fermentations employing genetically modified microbes under industrial conditions are difficult to monitor on line or to describe by simple, good mathematical models. So, a practically convenient approach is to combine mathematical models of some aspects with artificial neural networks of those aspects which are difficult to measure or model. Such hybrid models have been applied earlier to laboratory-scale bioreactors. In the present work, a model based on laboratory data for the synthesis of recombinant #-galactosidase was corrupted by adding imperfect mixing and noise in the feed stream to generate data mimicking a real nonideal operation. These data were used to train a recurrent Elman neural network and a hybrid neural network, and it was seen that a hybrid network provides more accurate estimates of both extra-cellular and intra-cellular variables. The benefit is enhanced by the hybrid network's superiority being more pronounced for the intra-cellular recombinant protein, #-galactosidase, which is the main product of interest.     

Optimization of the hydrolysis of lignocellulosic residues by using radial basis functions modeling and particle swarm optimization

The concentrations of glucose and total reducing sugars obtained by chemical hydrolysis of three different lignocellulosic feedstocks were maximized. Two response surface methodologies were applied to model the amount of sugars produced: (1) classical quadratic least-squares fit (QLS), and (2) artificial neural networks based on radial basis functions (RBF). The results obtained by applying RBF were more reliable and better statistical parameters were obtained. Depending on the type of biomass, different results were obtained. Improvements in fit between 35% and 55% were obtained when comparing the coefficients of determination (R²) computed for both QLS and RBF methods. Coupling the obtained RBF models with particle swarm optimization to calculate the global desirability function, allowed to perform multiple response optimization. The predicted optimal conditions were confirmed by carrying out independent experiments.     

湿地翅碱蓬生物量遥感估算模型

以黄河三角洲HJ-1A CCD遥感数据和滨海湿地翅碱蓬生物量实测数据为数据源,通过对比分析参数回归模型（单变量线性和非线性回归模型,多元线性逐步回归模型）和人工神经网络模型（BP网络、RBF网络、GRNN网络）,构建黄河三角洲湿地翅碱蓬生长初期的生物量湿重遥感估算最优模型。研究表明：基于遥感信息变量能够建立生长初期翅碱蓬生物量湿重估算模型。尽管基于RDVI、MSAVI和PC2的3个变量的多元线性回归模型的拟合效果较优,但是以SAVI、MSAVI、RVI、DVI、RDVI和PC2等7个遥感信息变量构建的BP神经网络模型的精度更高,平均相对误差为12.73%,估算效果最优,能够满足较高精度的生物量湿重估算需求。翅碱蓬生长初期生物量湿重最优估算模型的建立,为滨海地区植被生物量监测、区域翅碱蓬生物量季节动态模拟以及黄河三角洲生态系统功能评价提供技术支持与基础。     

Modeling and optimization of microbial hyaluronic acid production by Streptococcus zooepidemicus using radial basis function neural network coupling quantum‐behaved particle swarm optimization algorithm

Hyaluronic acid (HA) is a natural biopolymer with unique physiochemical and biological properties and finds a wide range of applications in biomedical and cosmetic fields. It is important to increase HA production to meet the increasing HA market demand. This work is aimed to model and optimize the amino acids addition to enhance HA production of Streptococcus zooepidemicus with radial basis function (RBF) neural network coupling quantum‐behaved particle swarm optimization (QPSO) algorithm. In the RBF‐QPSO approach, RBF neural network is used as a bioprocess modeling tool and QPSO algorithm is applied to conduct the optimization with the established RBF neural network black model as the objective function. The predicted maximum HA yield was 6.92 g/L under the following conditions: arginine 0.062 g/L, cysteine 0.036 g/L, and lysine 0.043 g/L. The optimal amino acids addition allowed HA yield increased from 5.0 g/L of the control to 6.7 g/L in the validation experiments. Moreover, the modeling and optimization capacity of the RBF‐QPSO approach was compared with that of response surface methodology (RSM). It was indicated that the RBF‐QPSO approach gave a slightly better modeling and optimization result compared with RSM. The developed RBF‐QPSO approach in this work may be helpful for the modeling and optimization of the other multivariable, nonlinear, time‐variant bioprocesses. © 2009 American Institute of Chemical Engineers Biotechnol. Prog., 2009     

Radial basis function neural networks for modeling growth rates of the basidiomycetes Physisporinus vitreus and Neolentinus lepideus

A radial basis function (RBF) neural network was developed and compared against a quadratic response surface (RS) model for predicting the specific growth rates of the biotechnologically important basidiomycetous fungi, Physisporinus vitreus and Neolentinus lepideus, under three environmental conditions: temperature (10–30 °C), water activity (0.950–9.998), and pH (4–6). Both the RBF network and polynomial RS model were mathematically evaluated against experimental data using graphical plots and several statistical indices. The evaluation showed that both models gave reasonably good predictions, but the performance of the RBF neural network was superior to that of the classical statistical method for all three data sets used (training, testing, full). Sensitivity analysis revealed that of the three experimental factors the most influential on the growth rate of P. vitreus was water activity, followed by temperature and pH to a lesser extent. In contrast, temperature in particular and then water activity were the key determinants of the development of N. lepideus. RBF neural networks could be a powerful technique for modeling fungal growth behavior under certain parameters and an alternative to time-consuming, traditional microbiological techniques.     

一种自优化RBF神经网络的叶绿素a浓度时序预测模型

藻类水华发生过程具有复杂性、非线性、时变性等特点,其准确预测一直是一个国际性难题.以天津市于桥水库为研究对象,根据2000年1月至2003年12月常规监测的水生生态数据(采样周期为10 d),提出了一种结合时序方法的可自优化RBF神经网络智能预测模型,对判断藻类水华的重要指标叶绿素a浓度进行预测.研究了训练样本量及RBF神经网络扩展速度SPREAD值的可自优化性能,以及该模型用于于桥水库叶绿素a浓度的短期变化趋势预测的可行性.结果表明,预测性能指标随SPREAD值及样本量不同发生变化,该预测模型能自动寻到最优SPREAD值,并发现至少需要约两年的训练样本量才能达到较好预测效果.当样本量为105,SPREAD值为10时,预测效果最好,精度较高,预测值与实测值的相关系数R达到0.982.该方法对水库的藻类水华预警有一定的参考价值.     

Prediction model of PSO-BP neural network on coliform amount in special food

Special food safety supervision by means of intelligent models and methods is of great significance for the health of local people and tourists. Models like BP neural network have the problems of low accuracy and poor robustness in food safety prediction. So, firstly, the principal component analysis was used to extract the key factors that influenced the amount of coliform communities, which was applied to reduce the dimension of this model as the input variable of BP neural network. Secondly, both the particle swarm optimization (PSO) and BP neural network were implemented to optimize initial weights and threshold to obtain the optimal parameter, and a model was constructed to predict the amount of coliform bacteria in Dai Special Snacks, Sa pie, based on PSO-BP neural network model. Finally, the predicted value of the model is verified. The results show that MSE is 0.0097, MAPE is 0.3198 and MAE is 0.0079, respectively. It was clear that PSO-BP model was better accuracy and robustness. That means, this model can effectively predict the amount of coliform. The research has important guiding significance for the quality and the production of Sa pie.     

Prediction of ubiquitin proteins using artificial neural networks, hidden markov model and support vector machines

Ubiquitin functions to regulate protein turnover in a cell by closely regulating the degradation of specific proteins. Such a regulatory role is very important, and thus I have analyzed the proteins that are ubiquitin-like, using an artificial neural network, support vector machines and a hidden Markov model (HMM). The methods were trained and tested on a set of 373 ubiquitin proteins and 373 non-ubiquitin proteins, obtained from Entrez protein database. The artificial neural network and support vector machine are trained and tested using both the physicochemical properties and PSSM matrices generated from PSI-BLAST, while in the HMM based method direct sequences are used for training-testing procedures. Further, the performance measures of the methods are calculated for test sequences, i.e. accuracy, specificity, sensitivity and Matthew's correlation coefficients of the methods are calculated. The highest accuracy of 90.2%, specificity of 87.04% and sensitivity of 94.08% was achieved using the support vector machine model with PSSM matrices. While accuracies of 86.82%, 83.37%, 80.18% and 72.11% were obtained for the support vector machine with physicochemical properties, neural network with PSSM matrices, neural networks with physicochemical properties, and hidden Markov model, respectively. As the accuracy for SVM model is better both using physicochemical properties and the PSSM matrices, it is concluded that kernel methods such as SVM outperforms neural networks and hidden Markov models.