Neural state estimation and prediction in amino acid fermentation

Summary On-line control of amino acid fermentations is complicated by uncertainties typical of biological processes and by difficulties in real-time monitoring of key process variables. Lysine is an essential amino acid in human nutrition, and also widely used in animal feed formulations. The paper discusses the construction and application of feed-forward, back-propagation neural networks as software sensors in state estimation, and multi-step ahead prediction of produced lysine and consumed sugar. Neural networks were programmed in MS Visual C++ for Windows for implementation in a PC, with a userfriendly interface for convenience and ease of operation. It is demonstrated that a well trained neural network of optimal architecture can be succesfsully used in control of amino acid production     

Neural network optimization for E. coli promoter prediction.

Methods for optimizing the prediction of Escherichia coli RNA polymerase promoter sequences by neural networks are presented. A neural network was trained on a set of 80 known promoter sequences combined with different numbers of random sequences. The conserved -10 region and -35 region of the promoter sequences and a combination of these regions were used in three independent training sets. The prediction accuracy of the resulting weight matrix was tested against a separate set of 30 known promoter sequences and 1500 random sequences. The effects of the network's topology, the extent of training, the number of random sequences in the training set and the effects of different data representations were examined and optimized. Accuracies of 100% on the promoter test set and 98.4% on the random test set were achieved with the optimal parameters.     

Neural network estimation of balance control during locomotion

Gait patterns of the elderly are often adjusted to accommodate for reduced function in the balance control system and a general reduction in skeletal muscle strength. Recent studies have demonstrated that measures related to motion of whole body center of mass (COM) can distinguish elderly individuals with balance impairment from healthy peers. Accurate COM estimation requires a multiple-segment anthropometric model, which may restrict its broad application in assessment of dynamic instability. Although temporal-distance measures and electromyography have been used in evaluation of overall gait function and determination of gait dysfunction, no studies have examined the use of gait measurements in predicting COM motion during gait. The purpose of this study was to demonstrate the effectiveness of an artificial neural network (ANN) model in mapping gait measurements onto COM motion in the frontal plane. Data from 40 subjects of varied age and balance impairment were entered into a 3-layer feed-forward model with back-propagated error correction. Bootstrap re-sampling was used to enhance the generalization accuracy of the model, using 20 re-sampling trials. The ANN model required minimal processing time (5 epochs, with 20 hidden units) and accurately mapped COM motion (R-values up to 0.89). As training proportion and number of hidden units increased, so did model accuracy. Overall, this model appears to be effective as a mapping tool for estimating balance control during locomotion. With easily obtained gait measures as input and a simple, computationally efficient architecture, the model may prove useful in clinical scenarios where electromyography equipment exists.     

Neural network prediction of 3(10)-helices in proteins

Secondary structure prediction from the primary sequence of a protein is fundamental to understanding its structure and folding properties. Although several prediction methodologies are in vogue, their performances are far from being completely satisfactory. Among these, non-linear neural networks have been shown to be relatively effective, especially for predicting beta-turns, where dominant interactions are local, arising from four sequence-contiguous residues. Most 3(10)-helices in proteins are also short, comprising of three sequence-contiguous residues and two capping residues. In order to understand the extent of local interactions in these 3(10)-helices, we have applied a neural network model with varying window size to predict 3(10)-helices in proteins. We found the prediction accuracy of 3(10)-helices (approximately 14%), as judged by the Matthew's Correlation Coefficient, to be less than that of beta-turns (approximately 20%). The optimal window size for the prediction of 3(10)-helices was about 9 residues. The significance and implications of these results in understanding the occurrence of 3(10)-helices and preferences of amino acid residues in 3(10)-helices are discussed.     

Neural network modeling for on-line estimation of nutrient dynamics in a sequentially-operated batch reactor.

In monitoring and controlling wastewater treatment processes, on-line information of nutrient dynamics is very important. However, these variables are determined with a significant time delay. Although the final effluent quality can be analyzed after this delay, it is often too late to make proper adjustments. In this paper, a neural network approach, a software sensor, was proposed to overcome this problem. Software sensor refers to a modeling approach inferring hard-to-measure process variables from other on-line measurable process variables. A bench-scale sequentially-operated batch reactor (SBR) used for advanced wastewater treatment (BOD plus nutrient removal) was employed to develop the neural network model. In order to improve the network performance, the structure of neural network was arranged in such a way of reflecting the change of operational conditions within a cycle. Real-time estimation of PO3-(4), NO-3, and NH+4 concentrations was successfully carried out with the on-line information of the SBR system only.     

Neural network prediction of biomass digestibility based on structural features

Plots of biomass digestibility are linear with the natural logarithm of enzyme loading; the slope and intercept characterize biomass reactivity. The feed-forward back-propagation neural networks were performed to predict biomass digestibility by simulating the 1-, 6-, and 72-h slopes and intercepts of glucan, xylan, and total sugar hydrolyses of 147 poplar wood model samples with a variety of lignin contents, acetyl contents, and crystallinity indices. Regression analysis of the neural network models indicates that they performed satisfactorily. Increasing the dimensionality of the neural network input matrix allowed investigation of the influence glucan and xylan enzymatic hydrolyses have on each other. Glucan hydrolysis affected the last stage of xylan digestion, and xylan hydrolysis had no influence on glucan digestibility. This study has demonstrated that neural networks have good potential for predicting biomass digestibility over a wide range of enzyme loadings, thus providing the potential to design cost-effective pretreatment and saccharification processes.     

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.     

Yeast concentration estimation and prediction with static and dynamic neural network models in batch cultures

The second fermentation is one of the most important steps in Champagne production. For this purpose, yeasts are grown on a wine based medium to adapt their metabolism to ethanol. Several models built with various static and dynamic neural network configurations were investigated. The main objective was to achieve real-time estimation and prediction of yeast concentration during growth. The model selected, based on recurrent neural networks, was first order with respect to the yeast concentration and to the volume of CO₂ released. Temperature and pH were included as model parameters as well. Yeast concentration during growth could thus be estimated with an error lower than 3% (±1.7×10⁶ yeasts/ml). From the measurement of initial yeast population and temperature, it was possible to predict the final yeast concentration (after 21 hours of growth) from the beginning of the growth, with about ±3×10⁶ yeasts/ml accuracy. So a predictive control strategy of this process could be investigated.     

Neural networks and linear programming for the satisfiability problem.

First a Linear Programming formulation is considered for the satisfiability problem, in particular for the satisfaction of a Conjunctive Normal Form in the Propositional Calculus and the Simplex algorithm for solving the optimization problem. The use of Recurrent Neural Networks is then described for choosing the best pivot positions and greatly improving the algorithm performance. The result of hard cases testing is reported and shows that the technique can be useful even if it requires a huge amount of size for the constraint array and Neural Network Data Input.     

Neural network committees for finger joint angle estimation from surface EMG signals

Background  

In virtual reality (VR) systems, the user's finger and hand positions are sensed and used to control the virtual environments. Direct biocontrol of VR environments using surface electromyography (SEMG) signals may be more synergistic and unconstraining to the user. The purpose of the present investigation was to develop a technique to predict the finger joint angle from the surface EMG measurements of the extensor muscle using neural network models.     

Picosecond and steady state, variable intensity and variable temperature emission spectroscopy of bacteriorhodopsin.

The bacteriorhodopsin emission lifetime at 77 degrees K has been obtained for different regions of the emission spectrum with single-pulse excitation. The data under all conditions yield a lifetime of 60 +/- 15 ps. Intensity effects on this lifetime have been ruled out by studying the relative emission amplitude as a function of the excitation pulse energy. We relate our lifetime to previously reported values at other temperatures by studying the relative emission quantum efficiency as a function of temperature. These variable temperature studies have indicated that an excited state with an emission maximum at 670 nm begins to contribute to the spectrum as the temperature is lowered. Within our experimental error the picosecond data seem to suggest that this new emission may arise from a minimum of the same electronic state responsible for the 77 degrees K emission at 720 nm. A correlation is noted between a 1.0-ps formation time observed in absorption by Ippen et al. (Ippen, E.P., C.V. Shank, A. Lewis, and M.A. Marcus. 1978. Subpicosecond spectroscopy of bacteriorhodopsin. Science [wash. D.C.]. 200:1279-1281 and a time extrapolated from relative quantum efficiency measurements and the 77 degrees K fluorescence lifetime that we report.     

Neural network prediction of prostate tissue composition based on magnetic resonance imaging analysis. A pilot study

OBJECTIVE: To develop a neural network model that estimates prostate histology using magnetic resonance imaging (MRI). STUDY DESIGN: Fifty-three men with lower urinary tract symptoms (average age = 63.8 +/- 8.9 years) underwent a prostate MRI (T2) and sextant biopsy of the prostate. Masson Trichome and immunohistochemical prostate-specific antigen staining of the biopsy material were used to calculate the amount of stroma and epithelium in the inner gland (central plus transition zone). MRIs were normalized to the mean intensity of the obturator internus muscle for comparative analyses. Gray scale and texture features were extracted from the inner gland in the midsection transverse MRI slice. Clinical and image variables were used in two neural networks predicting a high amount of stroma and a high amount of epithelium, respectively. RESULTS: The positive and negative predictive values of the stroma and epithelium neural networks were 95%, 69% and 65%, 92%, respectively. CONCLUSION: These data suggest that the combined use of these neural networks may predict patient response to medical therapy targeting prostatic stroma or epithelium.     

Integrated system for bioprocess monitoring and diagnosis using a local area network

Bioprocess monitoring and data analysis utilizing a local area network (LAN) is described in which an integrated computer environment provides for real-time monitoring from several remote personal computers with easy evaluation of the current process status and providing a common utilization of fermentation data. The computer network also enhances the decision-making process in the management of the production plant. Bioprocess control utilizing a LAN environment is expected to promote better utilization of fermentation data accumulated through repeated operations and to realize advanced control of fermentation processes. © Rapid Science Ltd. 1998     

Neural network on interval-censored data with application to the prediction of Alzheimer's disease

Alzheimer's disease (AD) is a progressive and polygenic disorder that affects millions of individuals each year. Given that there have been few effective treatments yet for AD, it is highly desirable to develop an accurate model to predict the full disease progression profile based on an individual's genetic characteristics for early prevention and clinical management. This work uses data composed of all four phases of the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, including 1740 individuals with 8 million genetic variants. We tackle several challenges in this data, characterized by large-scale genetic data, interval-censored outcome due to intermittent assessments, and left truncation in one study phase (ADNIGO). Specifically, we first develop a semiparametric transformation model on interval-censored and left-truncated data and estimate parameters through a sieve approach. Then we propose a computationally efficient generalized score test to identify variants associated with AD progression. Next, we implement a novel neural network on interval-censored data (NN-IC) to construct a prediction model using top variants identified from the genome-wide test. Comprehensive simulation studies show that the NN-IC outperforms several existing methods in terms of prediction accuracy. Finally, we apply the NN-IC to the full ADNI data and successfully identify subgroups with differential progression risk profiles. Data used in the preparation of this article were obtained from the ADNI database.     

On-line estimation of biomass concentration using a neural network and information about metabolic state

This paper deals with the design of a neural network-based biomass concentration estimation system. This system is enhanced by the incorporation of information about the actual metabolism of the microorganism cultivated, which is taken from an on-line knowledge-based system. Two different design approaches have been investigated using the fed-batch cultivation of bakers yeast as the model process. In the first, metabolic state (MS) data were passed as additional input to the neural network; in the second, these data were used to select a neural network suitable for the specific MS. Two neural network types—feed-forward (Levenberg-Marquardt) and cascade correlation—were applied to this system and tested, and the performances of these neural networks were compared.     

Motor learning and prediction in a variable environment

Traditional studies of motor learning and prediction have focused on how subjects perform a single task. Recent advances have been made in our understanding of motor learning and prediction by investigating the way we learn variable tasks, which change either predictably or unpredictably over time. Similarly, studies have examined how variability in our own movements affects motor learning.