The application of DBF neural networks for object recognition

On the basis of DBF nets proposed by Wang Shoujue, the model and properties of DBF neural network were discussed in this paper. When applied in pattern recognition, the algorithm and implement on hardware were presented respectively. We did experiments on recognition of omnidirectionally oriented rigid objects on the same level, using direction basis function neural networks, which acts by the method of covering the high dimensional geometrical distribution of the sample set in the feature space. Many animal and vehicle models (even with rather similar shapes) were recognized omnidirectionally thousands of times. For total 8800 tests, the correct recognition rate is 98.75%, the error rate and the rejection rate are 0.5% and 1.25% respectively. (C) 2003 Elsevier Inc. All rights reserved.

Discussion on the basic mathematical models of neurons - Double synaptic weight neuron in general-purpose neurocomputer, theory and application

Based on the introduction of the traditional mathematical models of neurons in general-purpose neurocomputer, a novel all-purpose mathematical model-Double synaptic weight neuron (DSWN) is presented, which can simulate all kinds of neuron architectures, including Radial-Basis-Function (RBF) and Back-propagation (BP) models, etc. At the same time, this new model is realized using hardware and implemented in the new CASSANN-II neurocomputer that can be used to form various types of neural networks with multiple mathematical models of neurons. In this paper, the flexibility of the new model has also been described in constructing neural networks and based on the theory of Biomimetic pattern recognition (BPR) and high-dimensional space covering, a recognition system of omni directionally oriented rigid objects on the horizontal surface and a face recognition system had been implemented on CASSANN-H neurocomputer. The result showed DSWN neural network has great potential in pattern recognition.

Modeling and optimization of semiconductor manufacturing process with neural networks

A neural network-based process model is proposed to optimize the semiconductor manufacturing process. Being different from some works in several research groups which developed neural network-based models to predict process quality with a set of process variables of only single manufacturing step, we applied this model to wafer fabrication parameters control and wafer lot yield optimization. The original data are collected from a wafer fabrication line, including technological parameters and wafer test results. The wafer lot yield is taken as the optimization target. Learning from historical technological records and wafer test results, the model can predict the wafer yield. To eliminate the "bad" or noisy samples from the sample set, an experimental method was used to determine the number of hidden units so that both good learning ability and prediction capability can be obtained.

A Distributed Outstar Network for Spatial Pattern Learning

The distributed outstar, a generalization of the outstar neural network for spatial pattern learning, is introduced. In the outstar, signals from a source node cause weights to learn and recall arbitrary patterns across a target field of nodes. The distributed outstar replaces the outstar source node with a source field of arbitrarily many nodes, whose activity pattern may be arbitrarily distributed or compressed. Learning proceeds according to a principle of atrophy due to disuse, whereby a path weight decreases in joint proportion to the transmitted path signal and the degree of disuse of the target node. During learning, the total signal to a target node converges toward that node's activity level. Weight changes at a node are apportioned according to the distributed pattern of converging signals. Three synaptic transmission functions, by a product rule, a capacity rule, and a threshold rule, are examined for this system. The three rules are computationally equivalent when source field activity is maximally compressed, or winner-take-all. When source field activity is distributed, catastrophic forgetting may occur. Only the threshold rule solves this problem. Analysis of spatial pattern learning by distributed codes thereby leads to the conjecture that the unit of long-term memory in such a system is an adaptive threshold, rather than the multiplicative path weight widely used in neural models.

Adaptive Neural Networks for Control of Movement Trajectories Invariant under Speed and Force Rescaling

This article describes two neural network modules that form part of an emerging theory of how adaptive control of goal-directed sensory-motor skills is achieved by humans and other animals. The Vector-Integration-To-Endpoint (VITE) model suggests how synchronous multi-joint trajectories are generated and performed at variable speeds. The Factorization-of-LEngth-and-TEnsion (FLETE) model suggests how outflow movement commands from a VITE model may be performed at variable force levels without a loss of positional accuracy. The invariance of positional control under speed and force rescaling sheds new light upon a familiar strategy of motor skill development: Skill learning begins with performance at low speed and low limb compliance and proceeds to higher speeds and compliances. The VITE model helps to explain many neural and behavioral data about trajectory formation, including data about neural coding within the posterior parietal cortex, motor cortex, and globus pallidus, and behavioral properties such as Woodworth's Law, Fitts Law, peak acceleration as a function of movement amplitude and duration, isotonic arm movement properties before and after arm-deafferentation, central error correction properties of isometric contractions, motor priming without overt action, velocity amplification during target switching, velocity profile invariance across different movement distances, changes in velocity profile asymmetry across different movement durations, staggered onset times for controlling linear trajectories with synchronous offset times, changes in the ratio of maximum to average velocity during discrete versus serial movements, and shared properties of arm and speech articulator movements. The FLETE model provides new insights into how spina-muscular circuits process variable forces without a loss of positional control. These results explicate the size principle of motor neuron recruitment, descending co-contractive compliance signals, Renshaw cells, Ia interneurons, fast automatic reactive control by ascending feedback from muscle spindles, slow adaptive predictive control via cerebellar learning using muscle spindle error signals to train adaptive movement gains, fractured somatotopy in the opponent organization of cerebellar learning, adaptive compensation for variable moment-arms, and force feedback from Golgi tendon organs. More generally, the models provide a computational rationale for the use of nonspecific control signals in volitional control, or "acts of will", and of efference copies and opponent processing in both reactive and adaptive motor control tasks.

A Spectral Network Model of Pitch Perception

A model of pitch perception, called the Spatial Pitch Network or SPINET model, is developed and analyzed. The model neurally instantiates ideas front the spectral pitch modeling literature and joins them to basic neural network signal processing designs to simulate a broader range of perceptual pitch data than previous spectral models. The components of the model arc interpreted as peripheral mechanical and neural processing stages, which arc capable of being incorporated into a larger network architecture for separating multiple sound sources in the environment. The core of the new model transforms a spectral representation of an acoustic source into a spatial distribution of pitch strengths. The SPINET model uses a weighted "harmonic sieve" whereby the strength of activation of a given pitch depends upon a weighted sum of narrow regions around the harmonics of the nominal pitch value, and higher harmonics contribute less to a pitch than lower ones. Suitably chosen harmonic weighting functions enable computer simulations of pitch perception data involving mistuned components, shifted harmonics, and various types of continuous spectra including rippled noise. It is shown how the weighting functions produce the dominance region, how they lead to octave shifts of pitch in response to ambiguous stimuli, and how they lead to a pitch region in response to the octave-spaced Shepard tone complexes and Deutsch tritones without the use of attentional mechanisms to limit pitch choices. An on-center off-surround network in the model helps to produce noise suppression, partial masking and edge pitch. Finally, it is shown how peripheral filtering and short term energy measurements produce a model pitch estimate that is sensitive to certain component phase relationships.

Artificial neural networks in modelling osmotic dehydration of foods

Artificial neural network (ANN) models for water loss (WL) and solid gain (SG) were evaluated as potential alternative to multiple linear regression (MLR) for osmotic dehydration of apple, banana and potato. The radial basis function (RBF) network with a Gaussian function was used in this study. The RBF employed the orthogonal least square learning method. When predictions of experimental data from MLR and ANN were compared, an agreement was found for ANN models than MLR models for SG than WL. The regression coefficient for determination (R2) for SG in MLR models was 0.31, and for ANN was 0.91. The R2 in MLR for WL was 0.89, whereas ANN was 0.84.Osmotic dehydration experiments found that the amount of WL and SG occurred in the following descending order: Golden Delicious apple > Cox apple > potato > banana. The effect of temperature and concentration of osmotic solution on WL and SG of the plant materials followed a descending order as: 55 > 40 > 32.2C and 70 > 60 > 50 > 40%, respectively.

Improved Process Monitoring Using Nonlinear Principal Component Models

This paper presents two new approaches for use in complete process monitoring. The firstconcerns the identification of nonlinear principal component models. This involves the application of linear
principal component analysis (PCA), prior to the identification of a modified autoassociative neural network (AAN) as the required nonlinear PCA (NLPCA) model. The benefits are that (i) the number of the reduced set of linear principal components (PCs) is smaller than the number of recorded process variables, and (ii) the set of PCs is better conditioned as redundant information is removed. The result is a new set of input data for a modified neural representation, referred to as a T2T network. The T2T NLPCA model is then used for complete process monitoring, involving fault detection, identification and isolation. The second approach introduces a new variable reconstruction algorithm, developed from the T2T NLPCA model. Variable reconstruction can enhance the findings of the contribution charts still widely used in industry by reconstructing the outputs from faulty sensors to produce more accurate fault isolation. These ideas are illustrated using recorded industrial data relating to developing cracks in an industrial glass melter process. A comparison of linear and nonlinear models, together with the combined use of contribution charts and variable reconstruction, is presented.

Genetic algorithms for local controller network construction

Local Controller Networks (LCNs) provide nonlinear control by interpolating between a set of locally valid, subcontrollers covering the operating range of the plant. Constructing such networks typically requires knowledge of valid local models. This paper describes a new genetic learning approach to the construction of LCNs directly from the dynamic equations of the plant, or from modelling data. The advantage is that a priori knowledge about valid local models is not needed. In addition to allowing simultaneous optimisation of both the controller and validation function parameters, the approach aids transparency by ensuring that each local controller acts independently of the rest at its operating point. It thus is valuable for simultaneous design of the LCNs and identification of the operating regimes of an unknown plant. Application results from a highly nonlinear pH neutralisation process and its associated neural network representation are utilised to illustrate these issues.

Application of auto-associative neural networks to transient fault detection in an IC engine

The tailpipe emissions from automotive engines have been subject to steadily reducing legislative limits. This reduction has been achieved through the addition of sub-systems to the basic four-stroke engine which thereby increases its complexity. To ensure the entire system functions correctly, each system and / or sub-systems needs to be continuously monitored for the presence of any faults or malfunctions. This is a requirement detailed within the On-Board Diagnostic (OBD) legislation. To date, a physical model approach has been adopted by me automotive industry for the monitoring requirement of OBD legislation. However, this approach has restrictions from the available knowledge base and computational load required. A neural network technique incorporating Multivariant Statistical Process Control (MSPC) has been proposed as an alternative method of building interrelationships between the measured variables and monitoring the correct operation of the engine. Building upon earlier work for steady state fault detection, this paper details the use of non-linear models based on an Auto-associate Neural Network (ANN) for fault detection under transient engine operation. The theory and use of the technique is shown in this paper with the application to the detection of air leaks within the inlet manifold system of a modern gasoline engine whilst operated on a pseudo-drive cycle. Copyright © 2007 by ASME.

Earthmoving trucks condition level prediction using neural networks

Purpose: The purpose of this paper is to present an artificial neural network (ANN) model that predicts earthmoving trucks condition level using simple predictors; the model’s performance is compared to the respective predictive accuracy of the statistical method of discriminant analysis (DA).

Design/methodology/approach: An ANN-based predictive model is developed. The condition level predictors selected are the capacity, age, kilometers travelled and maintenance level. The relevant data set was provided by two Greek construction companies and includes the characteristics of 126 earthmoving trucks.

Findings: Data processing identifies a particularly strong connection of kilometers travelled and maintenance level with the earthmoving trucks condition level. Moreover, the validation process reveals that the predictive efficiency of the proposed ANN model is very high. Similar findings emerge from the application of DA to the same data set using the same predictors.

Originality/value: Earthmoving trucks’ sound condition level prediction reduces downtime and its adverse impact on earthmoving duration and cost, while also enhancing the maintenance and replacement policies effectiveness. This research proves that a sound condition level prediction for earthmoving trucks is achievable through the utilization of easy to collect data and provides a comparative evaluation of the results of two widely applied predictive methods.

Power-Capped DVFS and Thread Allocation with ANN Models on Modern NUMA Systems

Abstract—Power capping is an essential function for efficient power budgeting and cost management on modern server systems. Contemporary server processors operate under power caps by using dynamic voltage and frequency scaling (DVFS). However, these processors are often deployed in non-uniform memory
access (NUMA) architectures, where thread allocation between cores may significantly affect performance and power consumption. This paper proposes a method which maximizes performance under power caps on NUMA systems by dynamically optimizing two knobs: DVFS and thread allocation. The method selects the optimal combination of the two knobs with models based on artificial neural network (ANN) that captures the nonlinear effect of thread allocation on performance. We implement
the proposed method as a runtime system and evaluate it with twelve multithreaded benchmarks on a real AMD Opteron based NUMA system. The evaluation results show that our method outperforms a naive technique optimizing only DVFS by up to
67.1%, under a power cap.

Predicting forest attributes In southeast Alaska using artificial neural networks

Artificial neural network (ANN) methods are used to predict forest characteristics. The data source is the Southeast Alaska (SEAK) Grid Inventory, a ground survey compiled by the USDA Forest Service at several thousand sites. The main objective of this article is to predict characteristics at unsurveyed locations between grid sites. A secondary objective is to evaluate the relative performance of different ANNs. Data from the grid sites are used to train six ANNs: multilayer perceptron, fuzzy ARTMAP, probabilistic, generalized regression, radial basis function, and learning vector quantization. A classification and regression tree method is used for comparison. Topographic variables are used to construct models: latitude and longitude coordinates, elevation, slope, and aspect. The models classify three forest characteristics: crown closure, species land cover, and tree size/structure. Models are constructed using n-fold cross-validation. Predictive accuracy is calculated using a method that accounts for the influence of misclassification as well as measuring correct classifications. The probabilistic and generalized regression networks are found to be the most accurate. The predictions of the ANN models are compared with a classification of the Tongass national forest in southeast Alaska based on the interpretation of satellite imagery and are found to be of similar accuracy.

Non-parametric bill of quantities estimation of concrete road bridges' superstructure: an artificial neural networks approach

Bridge construction responds to the need for environmentally friendly design of motorways and facilitates the passage through sensitive natural areas and the bypassing of urban areas. However, according to numerous research studies, bridge construction presents substantial budget overruns. Therefore, it is necessary early in the planning process for the decision makers to have reliable estimates of the final cost based on previously constructed projects. At the same time, the current European financial crisis reduces the available capital for investments and financial institutions are even less willing to finance transportation infrastructure. Consequently, it is even more necessary today to estimate the budget of high-cost construction projects -such as road bridges- with reasonable accuracy, in order for the state funds to be invested with lower risk and the projects to be designed with the highest possible efficiency. In this paper, a Bill-of-Quantities (BoQ) estimation tool for road bridges is developed in order to support the decisions made at the preliminary planning and design stages of highways. Specifically, a Feed-Forward Artificial Neural Network (ANN) with a hidden layer of 10 neurons is trained to predict the superstructure material quantities (concrete, pre-stressed steel and reinforcing steel) using the width of the deck, the adjusted length of span or cantilever and the type of the bridge as input variables. The training dataset includes actual data from 68 recently constructed concrete motorway bridges in Greece. According to the relevant metrics, the developed model captures very well the complex interrelations in the dataset and demonstrates strong generalisation capability. Furthermore, it outperforms the linear regression models developed for the same dataset. Therefore, the proposed cost estimation model stands as a useful and reliable tool for the construction industry as it enables planners to reach informed decisions for technical and economic planning of concrete bridge projects from their early implementation stages.

Predicting the greenhouse inside air temperature with RBF neural networks

The application of the Radial Basis Function (RBF) Neural Network (NN) to greenhouse inside air temperature modelling has been previously investigated (Ferreira et al., 2000a). In those studies, the inside air temperature is modelled as a function of the inside relative humidity and of the outside temperature and solar radiation. A second-order model structure previously selected (Cunha et al., 1996) in the context of dynamic temperature models identification, is used.