Constructing a query-able radial basis function artificial neural network

Artificial neural networks will be more widely accepted as standard engineering tools if their reasoning process can be made less opaque. This paper describes NetQuery, an explanation mechanism that extracts meaningful explanations from trained Radial Basis Function (RBF) networks. RBF networks are well suited for explanation generation because they contain a set of locally tuned units. Standard RBF networks are modified to identify dependencies between the inputs, to be sparsely connected, and to have an easily interpretable output layer. Given these modifications, the network architecture can be used to extract "Why?" and "Why not?" explanations from the network in terms of excitatory and inhibitory in-puts and their linear relationships, greatly simplified by a run-time pruning algorithm. These query results are validated by creating an expert system based on the explanations. NetQuery is also able to inform a user about a possible change in category for a given pattern by responding to a "How can I...?" query. This kind of query is extremely useful when analyzing the quality of a pattern set.     

Genome-enabled prediction of genetic values using radial basis function neural networks

The availability of high density panels of molecular markers has prompted the adoption of genomic selection (GS) methods in animal and plant breeding. In GS, parametric, semi-parametric and non-parametric regressions models are used for predicting quantitative traits. This article shows how to use neural networks with radial basis functions (RBFs) for prediction with dense molecular markers. We illustrate the use of the linear Bayesian LASSO regression model and of two non-linear regression models, reproducing kernel Hilbert spaces (RKHS) regression and radial basis function neural networks (RBFNN) on simulated data and real maize lines genotyped with 55,000 markers and evaluated for several trait-environment combinations. The empirical results of this study indicated that the three models showed similar overall prediction accuracy, with a slight and consistent superiority of RKHS and RBFNN over the additive Bayesian LASSO model. Results from the simulated data indicate that RKHS and RBFNN models captured epistatic effects; however, adding non-signal (redundant) predictors (interaction between markers) can adversely affect the predictive accuracy of the non-linear regression models.     

A short-term temperature forecaster based on a novel radial basis functions neural network

Many applications dealing with electric load forecasting in buildings require temperature prediction. A new method for short-term temperature forecasting based on a Radial Basis Functions Neural Network, initialized by a Regression Tree, is presented. In this method, each terminal node of the tree contributes one hidden unit to the RBF network. The forecaster uses the current coded hour and the temperature as inputs, and predicts the next hour temperature. The results demonstrate this predictor can be used for load forecasting.     

Towards a better understanding of the genetic and physiological basis for nitrogen use efficiency in maize

To enhance our understanding of the genetic basis of nitrogen use efficiency in maize (Zea mays), we have developed a quantitative genetic approach by associating metabolic functions and agronomic traits to DNA markers. In this study, leaves of vegetative recombinant inbred lines of maize, already assessed for their agronomic performance, were analyzed for physiological traits such as nitrate content, nitrate reductase (NR), and glutamine synthetase (GS) activities. A significant genotypic variation was found for these traits and a positive correlation was observed between nitrate content, GS activity and yield, and its components. NR activity, on the other hand, was negatively correlated. These results suggest that increased productivity in maize genotypes was due to their ability to accumulate nitrate in their leaves during vegetative growth and to efficiently remobilize this stored nitrogen during grain filling. Quantitative trait loci (QTL) for various agronomic and physiological traits were searched for and located on the genetic map of maize. Coincidences of QTL for yield and its components with genes encoding cytosolic GS and the corresponding enzyme activity were detected. In particular, it appears that the GS locus on chromosome 5 is a good candidate gene that can, at least partially, explain variations in yield or kernel weight. Because at this locus coincidences of QTLs for grain yield, GS, NR activity, and nitrate content were also observed, we hypothesize that leaf nitrate accumulation and the reactions catalyzed by NR and GS are coregulated and represent key elements controlling nitrogen use efficiency in maize.     

Enhanced radial basis function neural network for tomato plant disease leaf image segmentation

Primary crop losses in agriculture are due to leaf diseases, which farmers cannot identify early. If the diseases are not detected early and correctly, then the farmer will have to undergo huge losses. Therefore, in the field of agriculture, the detection of leaf diseases in tomato crops plays a vital role. Recent advances in computer vision and deep learning techniques have made disease prediction easy in agriculture. Tomato crop front side leaf images are considered for research due to their high exposure to diseases. The image segmentation process assumes a significant role in identifying disease affected areas on tomato leaf images. Therefore, this paper develops an efficient tomato crop leaf disease segmentation model using an enhanced radial basis function neural network (ERBFNN). The proposed ERBFNN is enhanced using the modified sunflower optimization (MSFO) algorithm. Initially, the noise present in the images is removed by a Gaussian filter followed by CLAHE (contrast-limited adaptive histogram equalization) based on contrast enhancement and un-sharp masking. Then, color features are extracted from each leaf image and given to the segmentation stage to segment the disease portion of the input image. The performance of the proposed ERBFNN approach is estimated using different metrics such as accuracy, Jaccard coefficient (JC), Dice's coefficient (DC), precision, recall, F-Measure, sensitivity, specificity, and mean intersection over union (MIoU) and are compared with existing state-of-the-art methods of radial basis function (RBF), fuzzy c-means (FCM), and region growing (RG). The experimental results show that the proposed ERBFNN segmentation model outperformed with an accuracy of 98.92% compared to existing state-of-the-art methods like RBFNN, FCM, and RG, as well as previous research work.     

Hierarchical genetic algorithm for near optimal feedforward neural network design

In this paper, we propose a genetic algorithm based design procedure for a multi layer feed forward neural network. A hierarchical genetic algorithm is used to evolve both the neural networks topology and weighting parameters. Compared with traditional genetic algorithm based designs for neural networks, the hierarchical approach addresses several deficiencies, including a feasibility check highlighted in literature. A multi objective cost function is used herein to optimize the performance and topology of the evolved neural network simultaneously. In the prediction of Mackey Glass chaotic time series, the networks designed by the proposed approach prove to be competitive, or even superior, to traditional learning algorithms for the multi layer Perceptron networks and radial basis function networks. Based upon the chosen cost function, a linear weight combination decision making approach has been applied to derive an approximated Pareto optimal solution set. Therefore, designing a set of neural networks can be considered as solving a two objective optimization problem.     

Shape identification of electrocardiographic ST segment based on radial basis function neural network

The types of myocardial ischemia can be revealed by electrocardiographic (ECG) ST segment.Effective measurement and electrocardiographic analysis of ST as well as calculation of displacement and shape change of ST segment can help doctors diagnose coronary heart disease and myocardial ischemia,especially for asymptomatic myocardial ischemia.Therefore,it is a very important subject in clinical practice to measure and classify the ECG ST segment.In this paper,we introduce a computerized automatic identification method of the electrocardiographic ST segment shape with radial basis function neural network based on adaptive fuzzy system,which has a better effect than other methods.It helps to analyze the reason of the ST segment change and confirm the position of myocardial ischemia,and is useful for doctor diagnosis.     

Shape identification of electrocardiographic ST segment based on radial basis function neural network

The types of myocardial ischemia can be revealed by electrocardiographic (ECG) ST segment. Effective measurement and electrocardiographic analysis of ST as well as calculation of displacement and shape change of ST segment can help doctors diagnose coronary heart disease and myocardial ischemia, especially for asymptomatic myocardial ischemia. Therefore, it is a very important subject in clinical practice to measure and classify the ECG ST segment. In this paper, we introduce a computerized automatic identification method of the electrocardiographic ST segment shape with radial basis function neural network based on adaptive fuzzy system, which has a better effect than other methods. It helps to analyze the reason of the ST segment change and confirm the position of myocardial ischemia, and is useful for doctor diagnosis. Translated from Acta Biophysica Sinica, 2005, 21(6): 443–448 [译自: 生物物理学报]     

The physiological basis for genetic variation in water use efficiency and carbon isotope composition in Arabidopsis thaliana

Ecologists and physiologists have documented extensive variation in water use efficiency (WUE) in Arabidopsis thaliana, as well as association of WUE with climatic variation. Here, we demonstrate correlations of whole-plant transpiration efficiency and carbon isotope composition (δ¹³C) among life history classes of A. thaliana. We also use a whole-plant cuvette to examine patterns of co-variation in component traits of WUE and δ¹³C. We find that stomatal conductance (g _s) explains more variation in WUE than does A. Overall, there was a strong genetic correlation between A and g _s, consistent with selection acting on the ratio of these traits. At a more detailed level, genetic variation in A was due to underlying variation in both maximal rate of carboxylation (V _cmax) and maximum electron transport rate (Jmax). We also found strong effects of leaf anatomy, where lines with lower WUE had higher leaf water content (LWC) and specific leaf area (SLA), suggesting a role for mesophyll conductance (g _m) in variation of WUE. We hypothesize that this is due to an effect through g _m, and test this hypothesis using the abi4 mutant. We show that mutants of ABI4 have higher SLA, LWC, and g _m than wild-type, consistent with variation in leaf anatomy causing variation in g _m and δ¹³C. These functional data also add further support to the central, integrative role of ABI4 in simultaneously altering ABA sensitivity, sugar signaling, and CO₂ assimilation. Together our results highlight the need for a more holistic approach in functional studies, both for more accurate annotation of gene function and to understand co-limitations to plant growth and productivity.     

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.     

The superior fault tolerance of artificial neural network training with a fault/noise injectionbased genetic algorithm

Artificial neural networks (ANNs) are powerful computational tools that are designed to replicate the human brain and adopted to solve a variety of problems in many different fields. Fault tolerance (FT), an important property of ANNs, ensures their reliability when significant portions of a network are lost. In this paper, a fault/noise injection-based (FIB) genetic algorithm (GA) is proposed to construct fault-tolerant ANNs. The FT performance of an FIB-GA was compared with that of a common genetic algorithm, the back-propagation algorithm, and the modification of weights algorithm. The FIB-GA showed a slower fitting speed when solving the exclusive OR (XOR) problem and the overlapping classification problem, but it significantly reduced the errors in cases of single or multiple faults in ANN weights or nodes. Further analysis revealed that the fit weights showed no correlation with the fitting errors in the ANNs constructed with the FIB-GA, suggesting a relatively even distribution of the various fitting parameters. In contrast, the output weights in the training of ANNs implemented with the use the other three algorithms demonstrated a positive correlation with the errors. Our findings therefore indicate that a combination of the fault/noise injection-based method and a GA is capable of introducing FT to ANNs and imply that the distributed ANNs demonstrate superior FT performance.     

Optimum DNA curvature using a hybrid approach involving an artificial neural network and genetic algorithm

In the present paper, a hybrid technique involving artificial neural network (ANN) and genetic algorithm (GA) has been proposed for performing modeling and optimization of complex biological systems. In this approach, first an ANN approximates (models) the nonlinear relationship(s) existing between its input and output example data sets. Next, the GA, which is a stochastic optimization technique, searches the input space of the ANN with a view to optimize the ANN output. The efficacy of this formalism has been tested by conducting a case study involving optimization of DNA curvature characterized in terms of the RL value. Using the ANN-GA methodology, a number of sequences possessing high RL values have been obtained and analyzed to verify the existence of features known to be responsible for the occurrence of curvature. A couple of sequences have also been tested experimentally. The experimental results validate qualitatively and also near-quantitatively, the solutions obtained using the hybrid formalism. The ANN-GA technique is a useful tool to obtain, ahead of experimentation, sequences that yield high RL values. The methodology is a general one and can be suitably employed for optimizing any other biological feature.     

Quantifying and analyzing the network basis of genetic complexity

Genotype-to-phenotype maps exhibit complexity. This genetic complexity is mentioned frequently in the literature, but a consistent and quantitative definition is lacking. Here, we derive such a definition and investigate its consequences for model genetic systems. The definition equates genetic complexity with a surplus of genotypic diversity over phenotypic diversity. Applying this definition to ensembles of Boolean network models, we found that the in-degree distribution and the number of periodic attractors produced determine the relative complexity of different topology classes. We found evidence that networks that are difficult to control, or that exhibit a hierarchical structure, are genetically complex. We analyzed the complexity of the cell cycle network of Sacchoromyces cerevisiae and pinpointed genes and interactions that are most important for its high genetic complexity. The rigorous definition of genetic complexity is a tool for unraveling the structure and properties of genotype-to-phenotype maps by enabling the quantitative comparison of the relative complexities of different genetic systems. The definition also allows the identification of specific network elements and subnetworks that have the greatest effects on genetic complexity. Moreover, it suggests ways to engineer biological systems with desired genetic properties.     

Near infrared spectroscopy coupled with radial basis function neural network for at-line monitoring of Lactococcus lactis subsp. fermentation

In our previous work, partial least squares (PLSs) were employed to develop the near infrared spectroscopy (NIRs) models for at-line (fast off-line) monitoring key parameters of Lactococcus lactis subsp. fermentation. In this study, radial basis function neural network (RBFNN) as a non-linear modeling method was investigated to develop NIRs models instead of PLS. A method named moving window radial basis function neural network (MWRBFNN) was applied to select the characteristic wavelength variables by using the degree approximation (Da) as criterion. Next, the RBFNN models with selected wavelength variables were optimized by selecting a suitable constant spread. Finally, the effective spectra pretreatment methods were selected by comparing the robustness of the optimum RBFNN models developed with pretreated spectra. The results demonstrated that the robustness of the optimal RBFNN models were better than the PLS models for at-line monitoring of glucose and pH of L. lactis subsp. fermentation.     

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     

The challenge of improving nitrogen use efficiency in crop plants: towards a more central role for genetic variability and quantitative genetics within integrated approaches

In this review, recent developments and future prospects of obtaining a better understanding of the regulation of nitrogen use efficiency in the main crop species cultivated in the world are presented. In these crops, an increased knowledge of the regulatory mechanisms controlling plant nitrogen economy is vital for improving nitrogen use efficiency and for reducing excessive input of fertilizers, while maintaining an acceptable yield. Using plants grown under agronomic conditions at low and high nitrogen fertilization regimes, it is now possible to develop whole-plant physiological studies combined with gene, protein, and metabolite profiling to build up a comprehensive picture depicting the different steps of nitrogen uptake, assimilation, and recycling to the final deposition in the seed. A critical overview is provided on how understanding of the physiological and molecular controls of N assimilation under varying environmental conditions in crops has been improved through the use of combined approaches, mainly based on whole-plant physiology, quantitative genetics, and forward and reverse genetics approaches. Current knowledge and prospects for future agronomic development and application for breeding crops adapted to lower fertilizer input are explored, taking into account the world economic and environmental constraints in the next century.     

The thermodynamic basis for the use of lipophilic efficiency (LipE) in enthalpic optimizations

Approaches to improve the efficiency of molecular optimizations have received great attention and numerous efficiency metrics have been introduced to assist in this effort. Optimization of properties is equally important to optimization of potency and therefore these metrics contain potency versus property calculations. Widespread use of a metric does not guarantee its accuracy and a further understanding of which, if any, metric increases the probability of success was sought. An analysis of LE, LELP and LipE based on theoretical and experimental data was performed demonstrating that LipE most strongly correlates with compound quality as defined by enthalpy-driven binding. The basis for the prioritization of LipE over other metrics in enthalpic optimizations is described.     

Real-time interactive isosurfacing: a new method for improving marching isosurfacing algorithm output and efficiency

Efficient rendering of a changing volumetric data-set is central to the development of effective medical simulations that incorporate haptic feedback. A new method referred to as real-time interactive isosurfacing (RTII) is described in this paper. RTII is an algorithm that can be applied to output from Marching Cubes-like algorithms to improve performance for real-time applications. The approach minimises processing by re-evaluating the isosurface around changing sub-volumes resulting from user interactions. It includes innovations that significantly reduce mesh complexity and improve mesh quality as triangles are created from the Marching Tetrahedra isosurfacing algorithm. Rendering efficiency is further improved over other marching isosurfacing algorithm outputs by maintaining an indexed triangle representation of the mesh. The effectiveness of RTII is discussed within the context of an endoscopic sinus surgery simulation currently being developed by the authors.     

A neural network algorithm for the multiple traveling salesmen problem

We developed an efficient neural network algorithm for solving the Multiple Traveling Salesmen Problem (MTSP). A new transformation of the N-city M-salesmen MTSP to the standard Traveling Salesmen Problem (TSP) is introduced. The transformed problem is represented by an expanded version of Hopfield-Tank's neuromorphic city-position map with (N + M-1)-cities and a single fictitious salesmen. The dynamic model associated with the problem is based on the Basic Differential Multiplier Method (BDMM) [26] which evaluates Lagrange multipliers simultaneously with the problem's state variables. The algorithm was successfully tested on many problems with up to 30 cities and five salesmen. In all test cases, the algorithm always converged to valid solutions. The great advantage of this kind of algorithm is that it can provide solutions to complex decision making problems directly by solving a system of ordinary differential equations. No learning steps, logical if statements or adjusting of parameters are required during the computation. The algorithm can therefore be implemented in hardware to solve complex constraint satisfaction problems such as the MTSP at the speed of analog silicon VLSI devices or possibly future optical neural computers.