A self-organizing neural network architecture for navigation using optic flow

This article describes a self-organizing neural network architecture that transforms optic flow and eye position information into representations of heading, scene depth, and moving object locations. These representations are used to navigate reactively in simulations involving obstacle avoidance and pursuit of a moving target. The network's weights are trained during an action-perception cycle in which self-generated eye and body movements produce optic flow information, thus allowing the network to tune itself without requiring explicit knowledge of sensor geometry. The confounding effect of eye movement during translation is suppressed by learning the relationship between eye movement outflow commands and the optic flow signals that they induce. The remaining optic flow field is due to only observer translation and independent motion of objects in the scene. A self-organizing feature map categorizes normalized translational flow patterns, thereby creating a map of cells that code heading directions. Heading information is then recombined with translational flow patterns in two different ways to form maps of scene depth and moving object locations. Most of the learning processes take place concurrently and evolve through unsupervised learning. Mapping the learned heading representations onto heading labels or motor commands requires additional structure. Simulations of the network verify its performance using both noise-free and noisy optic flow information.     

A neural network based artificial vision system for licence plate recognition

This paper presents a neural network based artificial vision system able to analyze the image of a car given by a camera, locate the registration plate and recognize the registration number of the car. The paper describes in detail various practical problems encountered in implementing this particular application and the solutions used to solve them. The main features of the system presented are: controlled stability-plasticity behavior, controlled reliability threshold, both off-line and on-line learning, self assessment of the output reliability and high reliability based on high level multiple feedback. The system has been designed using a modular approach. Sub-modules can be upgraded and/or substituted independently, thus making the system potentially suitable in a large variety of vision applications. The OCR engine was designed as an interchangeable plug-in module. This allows the user to choose an OCR engine which is suited to the particular application and to upgrade it easily in the future. At present, there are several versions of this OCR engine. One of them is based on a fully connected feedforward artificial neural network with sigmoidal activation functions. This network can be trained with various training algorithms such as error backpropagation. An alternative OCR engine is based on the constraint based decomposition (CBD) training architecture. The system has showed the following performances (on average) on real-world data: successful plate location and segmentation about 99%, successful character recognition about 98% and successful recognition of complete registration plates about 80%.     

基于BP神经网络的供应链突发风险评价模型

为评价供应链突发风险的影响,从供应链的组成和运作要素角度定义了5种类型的供应链突发风险,并建立了一套基于风险类型的供应链突发风险评价指标体系.在此基础上,以风险评价指标为输入,风险类型和风险等级为输出,建立了基于BP神经网络的供应链突发风险评价模型.该模型使用BP网络作为经验知识的学习机制来学习突发风险评价指标与突发风险类型及等级之间的映射关系,然后通过BP网络的知识记忆和泛化推理能力实现对供应链突发风险的自动识别和评价.提出的模型在一个供应链风险样本集上进行了验证,验证结果表明了模型的有效性.     

A method for producing recombinant baculovirus expression vectors at high frequency

A system has been developed that can generate recombinant baculovirus expression vectors at frequencies approaching 100%. This system provides a selection for recombinant viruses by using the essential gene downstream of the Autographa californica nuclear polyhedrosis virus (AcMNPV) polyhedrin expression locus. Two AcMNPV derivatives were constructed in which the expression locus and part of the downstream gene are flanked by restriction sites. The parental viruses are viable; however, restriction of the viral DNAs removes an essential piece of the viral genome. Transfer vectors carry a copy of the missing sequences downstream from the site into which foreign genes are inserted for expression; hence, recombination between a transfer vector and the restricted viral DNA can restore the integrity of the essential gene. Such recombination events also transfer any foreign gene present in the expression locus of the transfer vector to the viral genome. Recombinant viruses therefore have a selective advantage over nonrecombinant viral DNAs. Consequently, a high proportion of the viruses obtained by co-transfecting transfer vector DNA and restricted viral DNA of one of these new viruses expresses the target gene from the transfer vector. This system greatly reduces the time needed to make recombinant baculovirus expression vectors.     

A simple method for "reference range" estimation from routine laboratory data

A simplified method is presented to estimate reference ranges from hospital laboratory data. It is based on a combination of graphical estimation of relative sizes of normal and abnormal populations and the "mode-center" concept in which the mode of the total population centers on the 50% cumulative frequency of the normal population. This method can be applied to determine reference ranges even though the data source contains abnormally high and/or low values. The reference ranges obtained for BUN and calcium from in-patient and out-patient sources by this method were found to be similar to those reported for "healthy" subjects.     

A general method of analysis of frequency data for multiple classification designs.

There are many research areas for which the data can only be obtained in terms of counts or frequencies within specified categories rather than in terms of measures. The techniques of analysis of variance are not amenable to this kind of data. However, the use of "multiple contingency analysis" permits the investigator to make use of factorial designs even though his data are in the form of frequencies. The development of the method and an illustrative problem are presented. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A neural network representation of electromyography and joint dynamics in human gait

This study sought to evaluate postvention provided to two schools following student suicides. A risk index for suicidal behavior among exposed adolescents was devised. The index clearly differentiated high (n = 272) and low (n = 534) scorers on a range of outcome variables. While two-thirds of students attending postvention counselling had two or more putative risk factors for suicidal behavior, a further 231 uncounselled students had similar risk scores. Counselled students (n = 63) did not differ from matched controls (n = 63) at 8-month follow-up on a range of outcome variables. Measures to improve future postvention are discussed.     

A BP neural network based mathematical model for predicting Si content in hot metal from COREX process

The high and fluctuation property of ??Si?? content in hot metal (HM) is always a problem in COREX process. The precise prediction of ??Si?? content in HM from COREX process can provide a theoretical basis and technical reference for stabilizing and reducing the ??Si?? content in HM. A back propagation (BP) neural network was established to predict the ??Si?? content in HM from COREX process. The input parameters of the model were determined by correlation analysis, and the hysteretic heats corresponding to each parameter were determined by calculating the Deng??s relevancy. The results show that when the prediction error is ??0. 1%, the hit rate is 80%. The method of continuous updating the training samples was used to improve the prediction accuracy of the model. The prediction results show that the hit rate is 90% in absolute error range of ??0. 1%, and the prediction accuracy has been greatly improved compared with previous model. The improved model can provide a theoretical basis for judging the change of ??Si?? content in HM and subsequent operations.     

Artificial neural network control of FES in paraplegics for patient responsive ambulation

This paper describes an ART-1-based artificial neural network (ANN) adapted for controlling functional electrical stimulation (FES) to facilitate patient-responsive ambulation by paralyzed patients with spinal cord injuries. This network is to serve as a controller in an FES system developed by the first author which is presently in use by 300 patients worldwide (still without ANN control) and which was the first and the only FES system approved by the FDA. The proposed neural network discriminates above-lesion upper-trunk electromyographic (EMG) time series to activate standing and walking functions under FES and controls FES stimuli levels using response-EMG signals. For this particular application, we introduce several modifications of the binary adaptive resonance theory (ART-1) for pattern recognition and classification. First, a modified on-line learning rule is proposed. The new rule assures bidirectional modification of the stored patterns and prevents noise interference. Second, a new reset rule is proposed which prevents "exact matching" when the input is a subset of the chosen pattern. We show the applicability of a single ART-1-based structure to solving two problems, namely, 1) signal pattern recognition and classification, and 2) control. This also facilitates ambulation of paraplegics under FES, with adequate patient interaction in initial system training, retraining the network when needed, and in allowing patient's manual override in the case of error, where any manual override serves as a retraining input to the neural network. Thus, the practical control problems (arising in actual independent patient ambulation via FES) were all satisfied by a relatively simple ANN design.     

焦炉集气管压力智能控制系统

针对焦炉集气管压力这类多变量非线性系统，提出了一种基于模糊神经网络的智能协调控制方案，构成了焦炉集气管压力智能控制系统。实际应用表明，提出的控制策略有效解决了集气管压力的过程控制问题。     

神经网络在铁矿实验室安全状态评判中的应用

神经网络是一种人工智能,也是目前大数据应用的重要手段之一。尝试利用神经网络建立数学模型对铁矿实验室安全进行评判,从安全识别开始,以实验室安全状态的历史数据库作为神经网络学习样本,将实验室质量体系管理中的安全检查情况作为问题输入,经过模型的运算,得出铁矿实验室安全状态的辨识,达到与常规手段同样的目的。     

A proposed mechanism for memory and learning based upon very high frequency signals in the serotonergic neuronal system

Percutaneously placed central venous lines have become an intricate part of the medical management of the very low birth weight infant. It is critically important that health care providers involved with the placement of these catheters be familiar with the possible subtle sites for catheter misplacement. We present two case reports of inadvertent ascending lumbar vein catheterization with a percutaneously placed Silastic catheter where the saphenous vein was used for venous access. The literature is reviewed with regard to the history of use, indications, placement, and associated complications of these catheters.     

A new shunt DC active filter of power supply in a steady high magnetic field facility

A DC active power filter is an indispensable part in a high power and high stability power supply system, especially in the power supply system of the Steady High Magnetic Field Facility, which requires that the current ripple should be limited to 50 part     

钢铁企业综合技术经济指标的神经网络评价模型研究

利用BP神经网络理论建立技术经济指标评估的数学模型,采用3层神经网络,进行多因素输入建模.通过对模型的训练,使网络的实际输出值与期望输出值的误差均方值最小.经仿真计算证明,该数学模型具有较好的辨识精度.     

An improved shift-invariant artificial neural network for computerized detection of clustered microcalcifications in digital mammograms

A shift-invariant artificial neutral network (SIANN) has been applied to eliminate the false-positive detections reported by a rule-based computer aided-diagnosis (CAD) scheme developed in our laboratory. Regions of interest (ROIs) were selected around the centers of the rule-based CAD detections and analyzed by the SIANN. In our previous study, background-trend correction and pixel-value normalization were used as the preprocessing of the ROIs prior to the SIANN. A ROI is classified as a positive ROI, if the total number of microcalcifications detected in the ROI is greater than a certain number. In this study, modifications were made to improve the performance of the SIANN. First, the preprocessing is removed because the result of the background-trend correction is affected by the size of ROIs. Second, image-feature analysis is employed to the output of the SIANN in an effort to eliminate some of the false detections by the SIANN. In order to train the SIANN to detect microcalcifications and also to extract image features of microcalcifications, the zero-mean-weight constraint and training-free-zone techniques have been developed. A cross-validation training method was also applied to avoid the overtraining problem. The performance of the SIANN was evaluated by means of ROC analysis using a database of 39 mammograms for training and 50 different mammograms for testing. The analysis yielded an average area under the ROC curve (A(z)) of 0.90 for the testing set. Approximately 62% of false-positive clusters detected by the rule-based scheme were eliminated without any loss of the true-positive clusters by using the improved SIANN with image feature analysis techniques.     

Mechanisms of developmental regression in autism and the broader phenotype: A neural network modeling approach.

Loss of previously established behaviors in early childhood constitutes a markedly atypical developmental trajectory. It is found almost uniquely in autism and its cause is currently unknown (Baird et al., 2008). We present an artificial neural network model of developmental regression, exploring the hypothesis that regression is caused by overaggressive synaptic pruning and identifying the mechanisms involved. We used a novel population-modeling technique to investigate developmental deficits, in which both neurocomputational parameters and the learning environment were varied across a large number of simulated individuals. Regression was generated by the atypical setting of a single pruning-related parameter. We observed a probabilistic relationship between the atypical pruning parameter and the presence of regression, as well as variability in the onset, severity, behavioral specificity, and recovery from regression. Other neurocomputational parameters that varied across the population modulated the risk that an individual would show regression. We considered a further hypothesis that behavioral regression may index an underlying anomaly characterizing the broader autism phenotype. If this is the case, we show how the model also accounts for several additional findings: shared gene variants between autism and language impairment (Vernes et al., 2008); larger brain size in autism but only in early development (Redcay & Courchesne, 2005); and the possibility of quasi-autism, caused by extreme environmental deprivation (Rutter et al., 1999). We make a novel prediction that the earliest developmental symptoms in the emergence of autism should be sensory and motor rather than social and review empirical data offering preliminary support for this prediction. (PsycINFO Database Record (c) 2011 APA, all rights reserved)