A robust soft sensor to monitor 1,3-propanediol fermentation process by Clostridium butyricum based on artificial neural network

With the aggravation of environmental pollution and energy crisis, the sustainable microbial fermentation process of converting glycerol to 1,3-propanediol (1,3-PDO) has become an attractive alternative. However, the difficulty in the online measurement of glycerol and 1,3-PDO creates a barrier to the fermentation process and then leads to the residual glycerol and therefore, its wastage. Thus, in the present study, the four-input artificial neural network (ANN) model was developed successfully to predict the concentration of glycerol, 1,3-PDO, and biomass with high accuracy. Moreover, an ANN model combined with a kinetic model was also successfully developed to simulate the fed-batch fermentation process accurately. Hence, a soft sensor from the ANN model based on NaOH-related parameters has been successfully developed which cannot only be applied in software to solve the difficulty of glycerol and 1,3-PDO online measurement during the industrialization process, but also offer insight and reference for similar fermentation processes.     

人工神经网络在发酵工业中的应用

人工神经网络技术具有很强的非线性映射能力,用于系统的非线性建模,具有无可比拟的优势,广泛应用于发酵过程中培养基的优化和系统建模与控制方面,本主要介绍了人工神经网络的基本原理与使用方法,以及BP神经网络在非线性函数逼近的优点,详细介绍了其在发酵培养基优化,连续搅拌反应器神经网络估计,分批发酵及补料分批发酵过程建模与控制优化中的应用实例。     

生态系统响应气候变化脆弱性的人工神经网络模型评价

生态系统的脆弱性评价对于生态系统的管理具有重要作用。在分析生态系统脆弱性特征和影响因素的基础上 ,构建了针对森林和草地生态系统的脆弱性评价指标体系 ,涵盖了生态系统的结构、功能和生境 3个方面 ,评价指标分别是物种多样性、群落覆盖度、NPP、建群种年生长量、地表干燥度以及土壤有机碳等。评价系统将生态系统的脆弱性划分为轻微脆弱、中度脆弱、重度脆弱以及系统崩溃 4级。作为案例研究 ,构建了结构和性能优化的多层感知器 ,评价了温带落叶阔叶林生态系统的脆弱性。结果表明 ,通过人工神经网络模型评价生态系统的脆弱性是一条可行的途径     

Increasing productivity of Spirulina platensis in photobioreactors using artificial neural network modeling

Although production of microalgae in open ponds is conventionally practiced due to its economy, exposure of the algae to uncontrollable elements impedes achievement of quality and it is desirable to develop closed reactor cultivation methods for the production of high value products. Nevertheless, there are several constraints which affect growth of in closed reactors, some of which this study aims to address for the production of Spirulina. Periodic introduction of fresh medium resulted in increased trichome numbers and improved algal growth compared to growth in medium that was older than 4 weeks in 20 L polycarbonate bottles. Mixing of the cultures by bubbling air and use of draft tube reduced the damage to the growing cells and permitted increased growth. However, there was better growth in inclined cylindrical reactors mixed with bubbling air. The oxygen production rates were very similar irrespective differences in the maintained cultures densities. The uniformity in oxygen production rate suggested a tendency towards homeostasis in Spirulina cultures. The frequency of biomass harvest on the productivity of Spirulina showed that maintenance of moderate culture density between 0.16 and 0.32 g/L resulted in about 14% more productivity than maintaining the cell density between 0.16 and 0.53 g/L or 48% more than by daily harvest above 0.16 g/L. An artificial neural network based predictive model was developed, and the variables useful for predicting biomass output were identified. The model could predict the growth of Spirulina up to 3 days in advance with a coefficient of determination >0.94.     

Artificial neural network based experimental design procedure for enhancing fermentation development

Conventional experimental design techniques are available to assist in the optimization of fermentation processes, but due to the nonlinearities in the bioprocess, they are limited in their effectiveness. This problem is further complicated with recombinant systems as a result of the additional complexities of the process. This article describes a general strategy using artificial neural networks as an alternative approach to fermentation process development laboratory are presented for the neural network based procedures. (c) 1994 John Wiley & Sons, Inc.     

A general artificial neural network for the modelization of culture kinetics of different CHO strains

Animal cell cultures are characterized by very complex nonlinear behaviors, difficult to simulate by analytical modeling. Artificial Neural Networks, while being black box models, possess learning and generalizing capacities that could lead to better results. We first trained a three-layer perceptron to simulate the kinetics of five important parameters (biomass, lactate, glucose, glutamine and ammonia concentrations) for a series of CHO K1(Chinese Hamster Ovary, type K1) batch cultures. We then tried to use the same trained model to simulate the behavior of recombinant CHO TF70R. This was achieved, but necessitated to synchronize the time-scales of the two cell lines to compensate for their different specific growth rates. This revised version was published online in July 2006 with corrections to the Cover Date.     

基于人工神经网络的天然林生物量遥感估测

基于Landsat TM遥感图像, 以吉林省汪清天然林区为例, 应用B-P神经网络建立了森林生物量非线性遥感模型系统. 除采用遥感数据外, 该系统还引入了地形因子(海拔、坡度、坡向、立地类型等)作为模型自变量. 通过压缩输入数据和增强网络训练学习算法等措施, 对标准B-P神经网络进行了增强. 模型仿真结果表明：增强型B-P神经网络具有收敛速度快和自学习、自适应功能强的特点, 能最大限度地利用样本集的先验知识, 自动提取合理的模型, 模型预测结果能真实合理地反映实际情况. 针叶林、阔叶林和针阔混交林的生物量遥感模型系统仿真结果的平均相对误差分别为-1.47%、2.38%和3.56%, 平均相对误差绝对值分别为6.33%、8.46%和8.91%, 预估效果较理想. 应用该模型系统生成了研究区的森林生物量定量分布图, 其总体精度为88.04%.     

基于人工神经网络的农业病虫害预测模型及其效果检验

选取与病虫害有关的因子作为样本的输入特征,建立了农业病虫害年分类预测的Ｂ－Ｐ人工神经网络模型。该方法应用于稻瘟病的预测建模结果的拟合率为１００％,预留样本检验报率为８３％。     

Intrinsic fluorescence‐based at situ soft sensor for monitoring monoclonal antibody aggregation

Intrinsic fluorescence spectroscopy, in conjunction with partial least squares regression (PLSR), was investigated as a potential technique for online quality control and quantitative monitoring of Immunoglobulin G (IgG) aggregation that occurs following exposure to conditions that emulate those that can occur during protein downstream processing. Initially, the impact of three stress factors (temperature, pH, and protein concentration) on the degree of aggregation determined using size exclusion chromatography data, was investigated by performing a central composite designexperiment and applying a fitting response surface model. This investigation identified the influence of the factors as well as the operating regions with minimum propensity to induce protein aggregation. Spectral changes pertinent to the stressed samples were also investigated and found to corroborate the high sensitivity of the intrinsic fluorescence to conformational changes of the proteins under study. Ultimately, partial least squares regression was implemented to formulate two fluorescence‐based soft sensors for quality control—product classification—and quantitative monitoring—concentration of monomer. The resulting regression models exhibited accurate prediction ability and good potential for in situ monitoring of monoclonal antibody downstream purification processes. © 2015 American Institute of Chemical Engineers Biotechnol. Prog., 31:1423–1432, 2015     

基于人工神经网络-遗传算法的樟芝发酵培养基优化

采用优化模型对药用丝状真菌樟芝的复杂发酵过程进行建模,并获得最优发酵培养基组成.对樟芝发酵过程中的形态变化过程进行了观察,并分别采用人工神经网络(ANN)和响应面法(RSM)对樟芝发酵过程进行建模,同时采用遗传算法(GA)优化了发酵培养基组成.结果表明,ANN模型比RSM模型具有更好的实验数据拟合能力和预测能力,GA计算得到樟芝生物量理论最大值为6.2 g/L,并获得发酵最佳接种量及培养基组成:孢子浓度1.76× 105个/mL,葡萄糖29.1 g/L,蛋白胨9.4 g/L,黄豆粉2.8 g/L.在最佳培养条件下,樟芝生物量为(6.1±0.2)g/L.基于ANN-GA的优化方法可用于优化其他丝状真菌的复杂发酵过程,从而获得生物量或活性代谢产物.     

基于TM影像、森林资源清查数据和人工神经网络的森林碳空间分布模拟

森林是陆地生态系统中最大的碳库,在全球碳平衡和减缓全球气候变化方面发挥着不可替代的作用。当前主要利用森林资源清查数据和优势树种材积源-生物量的关系进行碳储量估算,在此基础上有效结合遥感影像数据将会更好的满足相关部门对国家和区域森林碳储量计算的需求。利用临安市2004年森林资源清查的930个样地数据和同年度Landsat TM影像数据,提取6个波段灰度值以及与碳储量相关性相对较大的3个波段组合,结合人工神经网络对研究区森林碳储量及其分布进行有效模拟。结果显示,用误差反向传播算法训练神经网络较好的重建了森林碳密度空间分布和变化,森林碳地上部分模拟结果与样地实测值之间的一致性好,全区域模拟结果森林碳平均值为0.98Mg(10.89Mg/hm²),总体森林碳密度模拟结果低于样地平均值约13%,进一步验证了人工神经网络在对大范围森林碳估算与模拟上具有较好的效果,为区域森林碳储量的估测研究提供有效的方法支持。     

人工神经网络与相容性生物量模型预测单木地上生物量的比较

森林生物量是林业生产经营和森林资源监测的重要指标,为探索高效低偏的单木生物量估测方法,引入人工神经网络.本研究采用黑龙江省东折棱河林场的101株长白落叶松地上生物量数据,基于不同变量(胸径、树高、冠幅)组合建立了4个聚合模型体系(AMS),采用加权回归消除模型的异方差.然后,基于最优的变量组合建立人工神经网络(ANN)...     

RESCUE: An artificial neural network tool for the NMR spectral assignment of proteins

The assignment of the ¹H spectrum of a protein or a polypeptide is the prerequisite for advanced NMR studies. We present here an assignment tool based on the artificial neural network technology, which determines the type of the amino acid from the chemical shift values observed in the ¹ H spectrum. Two artificial neural networks have been trained and extensively tested against a non-redundant subset of the BMRB chemical shift data bank [Seavey, B.R. et al. (1991) J. Biomol. NMR, 1, 217–236]. The most promising of the two accomplishes the analysis in two steps, grouping related amino acids together. It presents a mean rate of success above 80% on the test set. The second network tested separates down to the single amino acid; it presents a mean rate of success of 63%. This tool has been used to assist the manual assignment of peptides and proteins and can also be used as a block in an automated approach to assignment. The program has been called RESCUE and is made publicly available at the following URL: http://www.infobiosud.univ-montp1.fr/rescue.     

基于人工神经网络的生态环境质量遥感评价

利用ETM遥感数据提取反映生态环境的植被、土壤亮度、湿度,MODIS地表温度产品提取的热度指数、气象指数及其它地学辅助信息作为神经网络的输入,野外调查标准兴趣区的遥感本底值评分值作为网络输出,建立一个3层结构的BP神经网络生态环境遥感本底值预测模型.利用MATLAB软件对网络进行训练和研究区生态环境遥感本底值的预测输出,并将预测结果按照生态环境遥感本底值分级评分标准进行等级划分.结果表明,总体分类精度达87.8%.利用神经网络方法对生态环境遥感本底值进行预测是可行的.采用先预测再分级的方法不仅能很好地评价区域生态环境质量,而且能够和区域生态环境类型紧密的结合起来.     

A case for spiking neural network simulation based on configurable multiple-FPGA systems

Recent neuropsychological research has begun to reveal that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of neuronal systems. Simulation of the spiking neural networks in software is unable to rapidly generate output spikes in large-scale of neural network. An alternative approach, hardware implementation of such system, provides the possibility to generate independent spikes precisely and simultaneously output spike waves in real time, under the premise that spiking neural network can take full advantage of hardware inherent parallelism. We introduce a configurable FPGA-oriented hardware platform for spiking neural network simulation in this work. We aim to use this platform to combine the speed of dedicated hardware with the programmability of software so that it might allow neuroscientists to put together sophisticated computation experiments of their own model. A feed-forward hierarchy network is developed as a case study to describe the operation of biological neural systems (such as orientation selectivity of visual cortex) and computational models of such systems. This model demonstrates how a feed-forward neural network constructs the circuitry required for orientation selectivity and provides platform for reaching a deeper understanding of the primate visual system. In the future, larger scale models based on this framework can be used to replicate the actual architecture in visual cortex, leading to more detailed predictions and insights into visual perception phenomenon.     

基于模糊规则的人工神经网络模拟新疆杨蒸腾耗水

于2017年7—11月,应用热扩散探针(TDP)技术,结合同步测定的气象因子,对宁夏河东沙区新疆杨的耗水日变化特征及季节变化规律进行分析,提出了一种基于模糊规则的BP神经网络和Elman神经网络耗水模型,探究新疆杨蒸腾耗水规律并对其耗水量进行模拟。结果表明: 生长季内(7—10月)新疆杨平均液流密度为4.98 g·cm^-2·h^-1,影响蒸腾耗水的主要因素依次为太阳辐射、大气温度、饱和水汽压亏缺和相对湿度;受气象因子影响,新疆杨耗水具有明显的季节性变化规律,夏季(7—8月)单株耗水量为秋季(9—10月)的1.4倍;采用基于模糊规则的BP神经网络和Elman神经网络模型对新疆杨耗水进行模拟可以解释80%以上的变量,能够较准确地模拟新疆杨耗水情况,相对于BP神经网络,采用Elman神经网络对新疆杨耗水进行模拟,相对误差减少27.0%,均方根误差减少24.3%,纳什效率系数提高67.9%,决定系数达0.80以上。Elman神经网络的模拟效果优于BP神经网络,模型效率和拟合度更高,有效地提高了林木蒸腾耗水模拟精度,可作为河东沙区新疆杨林分蒸腾耗水估算的首选模型。     

Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network

The problem of predicting the enzymes and non-enzymes from the protein sequence information is still an open problem in bioinformatics. It is further becoming more important as the number of sequenced information grows exponentially over time. We describe a novel approach for predicting the enzymes and non-enzymes from its amino-acid sequence using artificial neural network (ANN). Using 61 sequence derived features alone we have been able to achieve 79 percent correct prediction of enzymes/non-enzymes (in the set of 660 proteins). For the complete set of 61 parameters using 5-fold cross-validated classification, ANN model reveal a superior model (accuracy = 78.79 plus or minus 6.86 percent, Q(pred) = 74.734 plus or minus 17.08 percent, sensitivity = 84.48 plus or minus 6.73 percent, specificity = 77.13 plus or minus 13.39 percent). The second module of ANN is based on PSSM matrix. Using the same 5-fold cross-validation set, this ANN model predicts enzymes/non-enzymes with more accuracy (accuracy = 80.37 plus or minus 6.59 percent, Q(pred) = 67.466 plus or minus 12.41 percent, sensitivity = 0.9070 plus or minus 3.37 percent, specificity = 74.66 plus or minus 7.17 percent).     

Software sensing for glucose concentration in industrial antibiotic fedbatch culture using fuzzy neural network

In order to control glucose concentration during fed-batch culture for antibiotic production, we applied so called “software sensor” which estimates unmeasured variable of interest from measured process variables using software. All data for analysis were collected from industrial scale cultures in a pharmaceutical company. First, we constructed an estimation model for glucose feed rate to keep glucose concentration at target value. In actual fed-batch culture, glucose concentration, was kept at relatively high and measured once a day, and the glucose feed rate until the next measurement time was determined by an expert worker based on the actual consumption rate. Fuzzy neural network (FNN) was applied to construct the estimation model. From the simulation results using this model, the average error for glucose concentration was 0.88 g/L. The FNN model was also applied for a special culture to keep glucose concentration at low level. Selecting the optimal input variables, it was possible to simulate the culture with a low glucose concentration from the data sets of relatively high glucose concentration. Next, a simulation model to estimate time course of glucose concentration during one day was constructed using the on-line measurable process variables, since glucose concentration was only measured off-line once a day. Here, the recursive fuzzy neural network (RFNN) was applied for the simulation model. As the result of the simulation, average error of RFNN model was 0.91 g/L and this model was found to be useful to supervise the fed-batch culture.