High-throughput Computer Method for 3D Neuronal Structure Reconstruction from the Image Stack of the Drosophila Brain and Its Applications

Drosophila melanogaster is a well-studied model organism, especially in the field of neurophysiology and neural circuits. The brain of the Drosophila is small but complex, and the image of a single neuron in the brain can be acquired using confocal microscopy. Analyzing the Drosophila brain is an ideal start to understanding the neural structure. The most fundamental task in studying the neural network of Drosophila is to reconstruct neuronal structures from image stacks. Although the fruit fly brain is small, it contains approximately 100 000 neurons. It is impossible to trace all the neurons manually. This study presents a high-throughput algorithm for reconstructing the neuronal structures from 3D image stacks collected by a laser scanning confocal microscope. The proposed method reconstructs the neuronal structure by applying the shortest path graph algorithm. The vertices in the graph are certain points on the 2D skeletons of the neuron in the slices. These points are close to the 3D centerlines of the neuron branches. The accuracy of the algorithm was verified using the DIADEM data set. This method has been adopted as part of the protocol of the FlyCircuit Database, and was successfully applied to process more than 16 000 neurons. This study also shows that further analysis based on the reconstruction results can be performed to gather more information on the neural network.     

基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆被分类

高效而精确的湿地遥感分类是大范围湿地资源动态监测与管理的必要保障。本研究使用ETM 遥感数据,借助Matlab神经网络工具箱,构建了基于BP神经网络的滨海湿地覆被分类模型,并将其应用于江苏盐城沿海湿地珍禽国家级自然保护区的核心区的自然湿地覆被分类研究中。本研究选择3、4、7、8波段作为输入层变量,单隐藏层设为10个节点,输出层变量对应待划分的8种覆被类型,构建三层式BP神经网络滨海湿地覆被分类模型。结果显示,BP分类总精度为85.91%,Kappa系数为0.8328,与最小距离法和极大似然法的分类总精度相比,分别提高了7.99%和6.08%,Kappa系数也相比提高。研究结果表明,BP神经网络分类法是一种较为有效的湿地遥感影像分类技术,能够提高分类精度。     

Efficiency of neural network-based combinatorial model predicting optimal culture conditions for maximum biomass yields in hairy root cultures

Key message

ANN-based combinatorial model is proposed and its efficiency is assessed for the prediction of optimal culture conditions to achieve maximum productivity in a bioprocess in terms of high biomass.

Abstract

A neural network approach is utilized in combination with Hidden Markov concept to assess the optimal values of different environmental factors that result in maximum biomass productivity of cultured tissues after definite culture duration. Five hidden Markov models (HMMs) were derived for five test culture conditions, i.e. pH of liquid growth medium, volume of medium per culture vessel, sucrose concentration (%w/v) in growth medium, nitrate concentration (g/l) in the medium and finally the density of initial inoculum (g fresh weight) per culture vessel and their corresponding fresh weight biomass. The artificial neural network (ANN) model was represented as the function of these five Markov models, and the overall simulation of fresh weight biomass was done with this combinatorial ANN–HMM. The empirical results of Rauwolfia serpentina hairy roots were taken as model and compared with simulated results obtained from pure ANN and ANN–HMMs. The stochastic testing and Cronbach’s α-value of pure and combinatorial model revealed more internal consistency and skewed character (0.4635) in histogram of ANN–HMM compared to pure ANN (0.3804). The simulated results for optimal conditions of maximum fresh weight production obtained from ANN–HMM and ANN model closely resemble the experimentally optimized culture conditions based on which highest fresh weight was obtained. However, only 2.99 % deviation from the experimental values could be observed in the values obtained from combinatorial model when compared to the pure ANN model (5.44 %). This comparison showed 45 % better potential of combinatorial model for the prediction of optimal culture conditions for the best growth of hairy root cultures.     

Mathematical modeling of Kluyveromyces marxianus growth in solid-state fermentation using a packed-bed bioreactor

This work investigated the growth of Kluyveromyces marxianus NRRL Y-7571 in solid-state fermentation in a medium composed of sugarcane bagasse, molasses, corn steep liquor and soybean meal within a packed-bed bioreactor. Seven experimental runs were carried out to evaluate the effects of flow rate and inlet air temperature on the following microbial rates: cell mass production, total reducing sugar and oxygen consumption, carbon dioxide and ethanol production, metabolic heat and water generation. A mathematical model based on an artificial neural network was developed to predict the above-mentioned microbial rates as a function of the fermentation time, initial total reducing sugar concentration, inlet and outlet air temperatures. The results showed that the microbial rates were temperature dependent for the range 27–50°C. The proposed model efficiently predicted the microbial rates, indicating that the neural network approach could be used to simulate the microbial growth in SSF.     

Successful Reconstruction of a Physiological Circuit with Known Connectivity from Spiking Activity Alone

Identifying the structure and dynamics of synaptic interactions between neurons is the first step to understanding neural network dynamics. The presence of synaptic connections is traditionally inferred through the use of targeted stimulation and paired recordings or by post-hoc histology. More recently, causal network inference algorithms have been proposed to deduce connectivity directly from electrophysiological signals, such as extracellularly recorded spiking activity. Usually, these algorithms have not been validated on a neurophysiological data set for which the actual circuitry is known. Recent work has shown that traditional network inference algorithms based on linear models typically fail to identify the correct coupling of a small central pattern generating circuit in the stomatogastric ganglion of the crab Cancer borealis. In this work, we show that point process models of observed spike trains can guide inference of relative connectivity estimates that match the known physiological connectivity of the central pattern generator up to a choice of threshold. We elucidate the necessary steps to derive faithful connectivity estimates from a model that incorporates the spike train nature of the data. We then apply the model to measure changes in the effective connectivity pattern in response to two pharmacological interventions, which affect both intrinsic neural dynamics and synaptic transmission. Our results provide the first successful application of a network inference algorithm to a circuit for which the actual physiological synapses between neurons are known. The point process methodology presented here generalizes well to larger networks and can describe the statistics of neural populations. In general we show that advanced statistical models allow for the characterization of effective network structure, deciphering underlying network dynamics and estimating information-processing capabilities.     

An improved genetic algorithm based fuzzy-tuned neural network

This paper presents a fuzzy-tuned neural network, which is trained by an improved genetic algorithm (GA). The fuzzy-tuned neural network consists of a neural-fuzzy network and a modified neural network. In the modified neural network, a neuron model with two activation functions is used so that the degree of freedom of the network function can be increased. The neural-fuzzy network governs some of the parameters of the neuron model. It will be shown that the performance of the proposed fuzzy-tuned neural network is better than that of the traditional neural network with a similar number of parameters. An improved GA is proposed to train the parameters of the proposed network. Sets of improved genetic operations are presented. The performance of the improved GA will be shown to be better than that of the traditional GA. Some application examples are given to illustrate the merits of the proposed neural network and the improved GA.     

A neural network approach for the prediction of in vitro culture parameters for maximum biomass yields in hairy root cultures

The present study deals with ANN based prediction of culture parameters in terms of inoculum density, pH and volume of growth medium per culture vessel and sucrose content of the growth medium for Glycyrrhiza hairy root cultures. This kind of study could be a model system in exploitation of hairy root cultures for commercial production of pharmaceutical compounds using large bioreactors. The study is aimed to evaluate the efficiency of regression neural network and back propagation neural network for the prediction of optimal culture conditions for maximum hairy root biomass yield. The training data for regression and back propagation networks were primed on the basis of function approximation, where final biomass fresh weight (f_wt) was considered as a function of culture parameters. On this basis the variables in culture conditions were described in the form of equations which are for inoculum density: y=0.02x+0.04, for pH of growth medium: y=x+2.8, for sucrose content in medium: y=9.9464x+(−9.7143) and for culture medium per culture vessel: y=10x. The fresh weight values obtained from training data were considered as target values and further compared with predicted fresh weight values. The empirical data were used as testing data and further compared with values predicted from trained networks. Standard MATLAB inbuilt generalized regression network with radial basis function radbas as transfer function in layer one and purelin in layer two and back propagation having purelin as transfer function in output layer and logsig in hidden layer were used. Although in comparative assessment both the networks were found efficient for prediction of optimal culture conditions for high biomass production, more accuracy in results was seen with regression network.     

Neural network modelling of fermentation processes. Microorganisms cultivation model

In the present paper the problem of chemostat modelling using the neural networks techniques is considered. A feedforward neural network with time delay feedback connections from and to the output neurons, which take into account the culture memory is proposed. A model of the growth of a strain Saccharomyces cerevisiae on a glucose limited medium is developed. Simulation investigations are carried out. The results are discussed.     

An annealed chaotic maximum neural network for bipartite subgraph problem

In this paper, based on maximum neural network, we propose a new parallel algorithm that can help the maximum neural network escape from local minima by including a transient chaotic neurodynamics for bipartite subgraph problem. The goal of the bipartite subgraph problem, which is an NP- complete problem, is to remove the minimum number of edges in a given graph such that the remaining graph is a bipartite graph. Lee et al. presented a parallel algorithm using the maximum neural model (winner-take-all neuron model) for this NP- complete problem. The maximum neural model always guarantees a valid solution and greatly reduces the search space without a burden on the parameter-tuning. However, the model has a tendency to converge to a local minimum easily because it is based on the steepest descent method. By adding a negative self-feedback to the maximum neural network, we proposed a new parallel algorithm that introduces richer and more flexible chaotic dynamics and can prevent the network from getting stuck at local minima. After the chaotic dynamics vanishes, the proposed algorithm is then fundamentally reined by the gradient descent dynamics and usually converges to a stable equilibrium point. The proposed algorithm has the advantages of both the maximum neural network and the chaotic neurodynamics. A large number of instances have been simulated to verify the proposed algorithm. The simulation results show that our algorithm finds the optimum or near-optimum solution for the bipartite subgraph problem superior to that of the best existing parallel algorithms.     

A neural network model with feature selection for Korean speech act classification

A speech act is a linguistic action intended by a speaker. Speech act classification is an essential part of a dialogue understanding system because the speech act of an utterance is closely tied with the user's intention in the utterance. We propose a neural network model for Korean speech act classification. In addition, we propose a method that extracts morphological features from surface utterances and selects effective ones among the morphological features. Using the feature selection method, the proposed neural network can partially increase precision and decrease training time. In the experiment, the proposed neural network showed better results than other models using comparatively high-level linguistic features. Based on the experimental result, we believe that the proposed neural network model is suitable for real field applications because it is easy to expand the neural network model into other domains. Moreover, we found that neural networks can be useful in speech act classification if we can convert surface sentences into vectors with fixed dimensions by using an effective feature selection method.     

A dynamic neural network with temporal coding and functional connectivity

A neural network model capable of altering its pattern classifying properties by program input is proposed. Here the “program input” is another source of input besides the pattern input. Unlike most neural network models, this model runs as a deterministic point process of spikes in continuous time; connections among neurons have finite delays, which are set randomly according to a normal distribution. Furthermore, this model utilizes functional connectivity which is dynamic connectivity among neurons peculiar to temporal-coding neural networks with short neuronal decay time constants. Computer simulation of the proposed network has been performed, and the results are considered in light of experimental results shown recently for correlated firings of neurons. Received: 6 December 1996 / Accepted in revised form: 15 September 1997     

The brain as a distributed intelligent processing system: an EEG study

Background

Various neuroimaging studies, both structural and functional, have provided support for the proposal that a distributed brain network is likely to be the neural basis of intelligence. The theory of Distributed Intelligent Processing Systems (DIPS), first developed in the field of Artificial Intelligence, was proposed to adequately model distributed neural intelligent processing. In addition, the neural efficiency hypothesis suggests that individuals with higher intelligence display more focused cortical activation during cognitive performance, resulting in lower total brain activation when compared with individuals who have lower intelligence. This may be understood as a property of the DIPS.

Methodology and Principal Findings

In our study, a new EEG brain mapping technique, based on the neural efficiency hypothesis and the notion of the brain as a Distributed Intelligence Processing System, was used to investigate the correlations between IQ evaluated with WAIS (Whechsler Adult Intelligence Scale) and WISC (Wechsler Intelligence Scale for Children), and the brain activity associated with visual and verbal processing, in order to test the validity of a distributed neural basis for intelligence.

Conclusion

The present results support these claims and the neural efficiency hypothesis.     

A Cognitive Neural Architecture Able to Learn and Communicate through Natural Language

Communicative interactions involve a kind of procedural knowledge that is used by the human brain for processing verbal and nonverbal inputs and for language production. Although considerable work has been done on modeling human language abilities, it has been difficult to bring them together to a comprehensive tabula rasa system compatible with current knowledge of how verbal information is processed in the brain. This work presents a cognitive system, entirely based on a large-scale neural architecture, which was developed to shed light on the procedural knowledge involved in language elaboration. The main component of this system is the central executive, which is a supervising system that coordinates the other components of the working memory. In our model, the central executive is a neural network that takes as input the neural activation states of the short-term memory and yields as output mental actions, which control the flow of information among the working memory components through neural gating mechanisms. The proposed system is capable of learning to communicate through natural language starting from tabula rasa, without any a priori knowledge of the structure of phrases, meaning of words, role of the different classes of words, only by interacting with a human through a text-based interface, using an open-ended incremental learning process. It is able to learn nouns, verbs, adjectives, pronouns and other word classes, and to use them in expressive language. The model was validated on a corpus of 1587 input sentences, based on literature on early language assessment, at the level of about 4-years old child, and produced 521 output sentences, expressing a broad range of language processing functionalities.     

Modeling of the three-dimensional structure of luffin-α and its simulated reaction with the substrate oligoribonucleotide GAGA

A fundamental problem in biochemistry and molecular biology is understanding the spatial structure of macromolecules and then analyzing their functions. In this study, the three-dimensional structure of a ribosome-inactivating protein luffin-α was predicted using a neural network method and molecular dynamics simulation. A feedforward neural network with the backpropagation learning algorithm were trained on model class of homologous proteins including trichosanthin andα-momorcharin. The distance constraints for the Cα atoms in the protein backbone were utilized to generate a folded crude conformation of luffin-α by model building and the steepest descent minimization approach. The crude conformation was refined by molecular dynamics techniques and a simulated annealing procedure. The interaction between luffin-α and its analogous substrate GAGA was also simulated to understand its action mechanism.     

Functional identification of biological neural networks using reservoir adaptation for point processes

The complexity of biological neural networks does not allow to directly relate their biophysical properties to the dynamics of their electrical activity. We present a reservoir computing approach for functionally identifying a biological neural network, i.e. for building an artificial system that is functionally equivalent to the reference biological network. Employing feed-forward and recurrent networks with fading memory, i.e. reservoirs, we propose a point process based learning algorithm to train the internal parameters of the reservoir and the connectivity between the reservoir and the memoryless readout neurons. Specifically, the model is an Echo State Network (ESN) with leaky integrator neurons, whose individual leakage time constants are also adapted. The proposed ESN algorithm learns a predictive model of stimulus-response relations in in vitro and simulated networks, i.e. it models their response dynamics. Receiver Operating Characteristic (ROC) curve analysis indicates that these ESNs can imitate the response signal of a reference biological network. Reservoir adaptation improved the performance of an ESN over readout-only training methods in many cases. This also held for adaptive feed-forward reservoirs, which had no recurrent dynamics. We demonstrate the predictive power of these ESNs on various tasks with cultured and simulated biological neural networks.     

A neural network study of precollicular saccadic averaging

Saccadic averaging is the phenomenon that two simultaneously presented retinal inputs result in a saccade with an endpoint located on an intermediate position between the two stimuli. Recordings from neurons in the deeper layers of the superior colliculus have revealed neural correlates of saccade averaging, indicating that it takes place at this level or upstream. Recently, we proposed a neural network for internal feedback in saccades. This neural network model is different from other models in that it suggests the possibility that averaging takes place in a stage upstream of the colliculus. The network consists of output units representing the neural map of the deeper layers of the superior colliculus and hidden layers imitating areas in the posterior parietal cortex. The deeper layers of the superior colliculus represent the motor error of a desired saccade, e.g. an eye movement to a visual target. In this article we show that averaging is an emergent property of the proposed network. When two retinal targets with different intensities are simultaneously presented to the network, the activity in the output layer represents a single motor error with a weighted average value. Our goal is to understand the mechanism of weighted averaging in this neural network. It appears that averaging in the model is caused by the linear dependence of the net input, received by the hidden units, on retinal error, independent of its retinal coding format. For nonnormalized retinal error inputs, also the nonlinearity between the net input and the activity of the hidden units plays a role in the averaging process. The averaging properties of the model are in agreement with physiological experiments if the hypothetical retinal error input map is normalized. The neural network predicts that if this normalization is overruled by electrical stimulation, averaging still takes place. However, in this case – as a consequence of the feedback task – the location of the resulting saccade depends on the initial eye position and the total intensity/current applied at the two locations. This could be a way to verify the neural network model. If the assumptions for the model are valid, a physiological implication of this paper is that averaging of saccades takes place upstream of the superior colliculus. Received: 22 June 1997 / Accepted in revised form: 19 February 1998     

Vision-based force measurement using neural networks for biological cell microinjection

This paper presents a vision-based force measurement method using an artificial neural network model. The proposed model is used for measuring the applied load to a spherical biological cell during micromanipulation process. The devised vision-based method is most useful when force measurement capability is required, but it is very challenging or even infeasible to use a force sensor. Artificial neural networks in conjunction with image processing techniques have been used to estimate the applied load to a cell. A bio-micromanipulation system capable of force measurement has also been established in order to collect the training data required for the proposed neural network model. The geometric characterization of zebrafish embryos membranes has been performed during the penetration of the micropipette prior to piercing. The geometric features are extracted from images using image processing techniques. These features have been used to describe the shape and quantify the deformation of the cell at different indentation depths. The neural network is trained by taking the visual data as the input and the measured corresponding force as the output. Once the neural network is trained with sufficient number of data, it can be used as a precise sensor in bio-micromanipulation setups. However, the proposed neural network model is applicable for indentation of any other spherical elastic object. The results demonstrate the capability of the proposed method. The outcomes of this study could be useful for measuring force in biological cell micromanipulation processes such as injection of the mouse oocyte/embryo.     

A neural network estimator for total biomass of filamentous fungi growing on two dimensional solid substrate

A neural network dynamic model is proposed for the on-line estimation of total biomass during filamentous fungi cultures on two dimensional solid substrate. The neural network provides an accurate and robust estimation of biomass from macroscopic measurements of the colony radius evolution. Experiments were performed on Gibberella fujikuroi growing on Petri dishes under different conditions of temperature and water activity. © Rapid Science Ltd. 1998     

Estimating biofilm reaction kinetics using hybrid mechanistic-neural network rate function model

This work describes an alternative method for estimation of reaction rate of a biofilm process without using a model equation. A first principles model of the biofilm process is integrated with artificial neural networks to derive a hybrid mechanistic-neural network rate function model (HMNNRFM), and this combined model structure is used to estimate the complex kinetics of the biofilm process as a consequence of the validation of its steady state solution. The performance of the proposed methodology is studied with the aid of the experimental data of an anaerobic fixed bed biofilm reactor. The statistical significance of the method is also analyzed by means of the coefficient of determination (R²) and model efficiency (ME). The results demonstrate the effectiveness of HMNNRFM for estimating the complex kinetics of the biofilm process involved in the treatment of industry wastewater.