Neural network training with global optimization techniques

This paper presents an approach of using Simulated Annealing and Tabu Search for the simultaneous optimization of neural network architectures and weights. The problem considered is the odor recognition in an artificial nose. Both methods have produced networks with high classification performance and low complexity. Generalization has been improved by using the backpropagation algorithm for fine tuning. The combination of simple and traditional search methods has shown to be very suitable for generating compact and efficient networks.     

Robust algorithm for arrhythmia classification in ECG using extreme learning machine

Background  

Recently, extensive studies have been carried out on arrhythmia classification algorithms using artificial intelligence pattern recognition methods such as neural network. To improve practicality, many studies have focused on learning speed and the accuracy of neural networks. However, algorithms based on neural networks still have some problems concerning practical application, such as slow learning speeds and unstable performance caused by local minima.     

Improved learning capacity and discrimination performance of neural networks in pattern recognition of biosignals]

Pattern recognition was an important goal in the early work on artificial neural networks. Without arousing dramatic speculation, the paper describes, how a "natural" method of dealing with the configuration of the input layer can considerably improve learning behaviour and classification rate of a modified multi-layered perception with backpropagation of the error learning rule. Using this method, recognition of complex patterns in electrophysiological signals can be performed more accurately, without rules or complicated heuristic procedures. The proposed technique is demonstrated using recognition of the J-point in the ECG as an example.     

Application of neural networks using the volume learning algorithm for the study of structure-activity relationship in chemical compounds

A volume learning algorithm for artificial neural networks was developed to quantitatively describe the three-dimensional structure-activity relationships using as an example N-benzylpiperidine derivatives. The new algorithm combines two types of neural networks, the Kohonen and the feed-forward artificial neural networks, which are used to analyze the input grid data generated by the comparative molecular field approach. Selection of the most informative parameters using the algorithm helped to reveal the most important spatial properties of the molecules, which affect their biological activities. Cluster regions determined using the new algorithm adequately predicted the activity of molecules from a control data set.     

Artificial neural networks and the study of evolution of prey coloration

In this paper, I investigate the use of artificial neural networks in the study of prey coloration. I briefly review the anti-predator functions of prey coloration and describe both in general terms and with help of two studies as specific examples the use of neural network models in the research on prey coloration. The first example investigates the effect of visual complexity of background on evolution of camouflage. The second example deals with the evolutionary choice of defence strategy, crypsis or aposematism. I conclude that visual information processing by predators is central in evolution of prey coloration. Therefore, the capability to process patterns as well as to imitate aspects of predator's information processing and responses to visual information makes neural networks a well-suited modelling approach for the study of prey coloration. In addition, their suitability for evolutionary simulations is an advantage when complex or dynamic interactions are modelled. Since not all behaviours of neural network models are necessarily biologically relevant, it is important to validate a neural network model with empirical data. Bringing together knowledge about neural networks with knowledge about topics of prey coloration would provide a potential way to deepen our understanding of the specific appearances of prey coloration.     

Application of Neural Networks Using the Volume Learning Algorithm for Quantitative Study of the Three-Dimensional Structure–Activity Relationships of Chemical Compounds

A volume learning algorithm for artificial neural networks was developed to quantitatively describe three-dimensional structure–activity relationships using as an example N-benzylpiperidine derivatives. The new algorithm combines two types of neural networks, the Kohonen and the feed-forward artificial neural networks, which are used to analyze the input grid data generated by the comparative molecular field approach. Selection of the most informative parameters using the algorithm helped reveal the most important spatial properties of the molecules, which affect their biological activities. Cluster regions determined using the new algorithm adequately predicted the activity of molecules from a control data set.     

半干旱区春小麦生长系统的人工神经网络模型与产量预测

以半干旱区春小麦生长系统为研究对象。探讨了作物生长系统中水分、土壤养分等生态因子的时空变化特征及春小麦产量形成机制,应用人工神经网络方法建立了半干旱区春小麦生长系统的产量随环境因子变化的神经网络模型,并与传统的CTM模型进行了比较。模拟结果表明,人工神经网络模型可适用于半干旱区春小麦生长系统产量随环境因子变化规律描述,且优于传统模型,从而为春小麦产量预测提供了新的途径,也为作物生态系统的人工调控提供了新的模式与定量依据。     

A comparative study of multilayer perceptron neural networks for the identification of rhubarb samples

Artificial neural networks have gained much attention in recent years as fast and flexible methods for quality control in traditional medicine. Near-infrared (NIR) spectroscopy has become an accepted method for the qualitative and quantitative analyses of traditional Chinese medicine since it is simple, rapid, and non-destructive. The present paper describes a method by which to discriminate official and unofficial rhubarb samples using three layer perceptron neural networks applied to NIR data. Multilayer perceptron neural networks were trained with back propagation, delta-bar-delta and quick propagation algorithms. Results obtained using these methods were all satisfactory, but the best outcomes were obtained with the delta-bar-delta algorithm.     

Using deep neural networks to evaluate object vision tasks in rats

In the last two decades rodents have been on the rise as a dominant model for visual neuroscience. This is particularly true for earlier levels of information processing, but a number of studies have suggested that also higher levels of processing such as invariant object recognition occur in rodents. Here we provide a quantitative and comprehensive assessment of this claim by comparing a wide range of rodent behavioral and neural data with convolutional deep neural networks. These networks have been shown to capture hallmark properties of information processing in primates through a succession of convolutional and fully connected layers. We find that performance on rodent object vision tasks can be captured using low to mid-level convolutional layers only, without any convincing evidence for the need of higher layers known to simulate complex object recognition in primates. Our approach also reveals surprising insights on assumptions made before, for example, that the best performing animals would be the ones using the most abstract representations–which we show to likely be incorrect. Our findings suggest a road ahead for further studies aiming at quantifying and establishing the richness of representations underlying information processing in animal models at large.     

Computational neural networks: Enhancing supervised learning algorithms via self-organization

A neural network processing scheme is proposed which utilizes a self-organizing Kohonen feature map as the front end to a feedforward classifier network. The results of a series of benchmarking studies based upon artificial statistical pattern recognition tasks indicate that the proposed architecture performs significantly better than conventional feedforward classifier networks when the decision regions are disjoint. This is attributed to the fact that the self-organization process allows internal units in the succeeding classifier network to be sensitive to a specific set of features in the input space at the outset of training.     

A new training algorithm using artificial neural networks to classify gender-specific dynamic gait patterns

The aim of this study was to present a new training algorithm using artificial neural networks called multi-objective least absolute shrinkage and selection operator (MOBJ-LASSO) applied to the classification of dynamic gait patterns. The movement pattern is identified by 20 characteristics from the three components of the ground reaction force which are used as input information for the neural networks in gender-specific gait classification. The classification performance between MOBJ-LASSO (97.4%) and multi-objective algorithm (MOBJ) (97.1%) is similar, but the MOBJ-LASSO algorithm achieved more improved results than the MOBJ because it is able to eliminate the inputs and automatically select the parameters of the neural network. Thus, it is an effective tool for data mining using neural networks. From 20 inputs used for training, MOBJ-LASSO selected the first and second peaks of the vertical force and the force peak in the antero-posterior direction as the variables that classify the gait patterns of the different genders.     

Neural networks predict response biases of female túngara frogs.

Artificial neural networks have become useful tools for probing the origins of perceptual biases in the absence of explicit information on underlying neuronal substrates. Preceding studies have shown that neural networks selected to recognize or discriminate simple patterns may possess emergent biases toward pattern size of symmetry--preferences often exhibited by real females--and have investigated how these biases shape signal evolution. We asked whether simple neural networks could evolve to respond to an actual mate recognition signal, the call of the túngara frog, Physalaemus pustulosus. We found that not only were networks capable of recognizing the call of the túngara frog, but that they made remarkably accurate quantitative predictions about how well females generalized to many novel calls, and that these predictions were stable over several architectures. The data suggest that the degree to which P. pustulosus females respond to a call may often be an incidental by-product of a sensory system selected simply for species recognition.     

人工神经网络模型及其在农业和生态学研究中的应用

对于一些复杂的农业生态系统,人们对其生态过程了解较少,且这些系统的不确定性和模糊性较大,用传统的方法难以模拟这些系统的行为,神经网络模型因为能较精确地模拟这些系统的行为,而引起生态学者们的广泛兴趣。该文着重介绍了误差逆传神经网络模型的结构、算法及其在农业和生态学中的应用研究。误差逆传神经网络模型一般采用三层神经网络模型结构,三层的神经网络模型能模拟任意复杂程度的连续函数,而且因为它的结构小而不容易产生与训练数据的过度吻合。误差逆传神经网络模型算法的主要特征是:利用当前的输入误差对权值进行调整。在生态学和农业研究中,误差逆传神经网络模型通常作为非线性函数模拟器用于预测作物产量、生物生产量、生物与环境之间的关系等。已有的研究表明:误差逆传神经网络模型的模拟精度要远远高于多元线性方程,类似于非线性方程,而在样本量足够的情况下,有一定的外推能力。但是误差逆传神经网络模型需要大量的样本量来保证所求取参数的可靠性,但这在实际研究中很难做到,因而限制了误差逆传神经网络模型的应用。近年来人们提出了强制训练停止、复合模型等多种技术来提高误差逆传神经网络模型的外推能力,也提出了Garson算法、敏感性分析以及随机化检验等技术对误差逆传神经网络模型的机理进行解释。误差逆传神经网络模型的真正优势在于模拟人们了解较少或不确定性和模糊性较大系统的行为,这些是传统模型所无法实现的,因而是对传统机理模型的重要补充。     

Two-dimensional fluorometry coupled with artificial neural networks: a novel method for on-line monitoring of complex biological processes

The use of two-dimensional scanning fluorometry as an on-line, noninvasive, in situ bioreactor monitoring technique is extended to complex bioprocesses using mixed cultures, with particular attention to biofilm systems. Using the example of spectra subtraction, it is demonstrated that established methods for fluorescence data analysis have a limited capability of utilizing overall fluorometric information. Artificial neural networks (ANNs) are introduced as a novel nonlinear and nonmechanistic technique for interpreting the highly complex fluorescence maps. It is shown that ANNs are able to infer process performance parameters in a pattern recognition approach, based on the entire fluorescence "fingerprint" of the biological system. The studies were carried out using an extractive membrane bioreactor (EMB) for the degradation of chlorinated organic compounds, operating with mixed cultures. Model pollutants em- ployed were 1,2-dichloroethane, 3-chloro-4-methylaniline, and p-toluidine.     

Growth behavior in plant cell cultures based on emissions detected by a multisensor array

The use of a multisensor array based on chemical gas sensors to monitor plant cell cultures is described. The multisensor array, also referred to as an electronic nose, consisted of 19 different metal oxide semiconductor sensors and one carbon dioxide sensor. The device was used to continuously monitor the off-gas from two plant cell suspension cultures, Morinda citrifolia and Nicotiana tabacum, cultivated under batch conditions. By analyzing the multiarray responses using two pattern recognition methods, principal component analysis and artificial neural networks, it was possible to monitor the course of the cultivations and, in turn, to predict (1) the biomass concentration in both systems and (2) the formation of the secondary metabolite, antraquinone, by M. citrifolia. The results identify the multisensor array method as a potentially useful analytical tool for monitoring plant process variables that are otherwise difficult to analyze on-line.