Basis Of Artificial Neural Network Research Articles

Using artificial neural networks to predict potential complications during trauma patients' hospitalization period.

Complications during treatment of seriously injured trauma patients cause an increase in mortality rates, and increased treatment costs, including bed occupancy. Current methods treat those at risk, and include numbers of false positives. By finding a method to predict those at risk of the three most common recorded Trauma Registry complications, considerable savings in mortality and treatment costs could arise. Artificial Neural Networks (ANN) work well with classification problems using feed-forward/back propagation methodology. Using the National Trauma Data Bank (V6.2) data files, Tiberius Software created the ANN models. Best models were identified by their Gini co-efficient, ability to predict the complication outcome selected, and their Root Mean Squared Error (RMSE) scores. The model ensemble for the three major complications recorded in the registry were determined, variables ranked and model accuracy recorded. The basic ANN is fairly accurate for those likely to contract Acute Respiratory Disease Syndrome (ARDS) though with a high rate of false positives. The ANN ability to predict Ventilator Associated Pneumonia (VAP) is less effective, though better at producing fewer false positives. Predicting Urinary Tract Infections (UTI) cases is not good enough using these input variables. Both VAP and UTI relate to those aged over 55 years, while ARDS related more to those under 16 years. The models need improving.

Retrieval snow depth by artificial neural network methodology from integrated AMSR-E and in-situ data—A case study in Qinghai-Tibet Plateau

On the basis of artificial neural network (ANN) model, this paper presents an algorithm for inversing snow depth with use of AMSR-E (Advanced Microwave Scanning Radiometer-Earth Observing System (EOS)) dataset, i.e., brightness temperature at 18.7 and 36.5GHz in Qinghai-Tibet Plateau during the snow season of 2002–2003. In order to overcome the overfitting problem in ANN modeling, this methodology adopts a Bayesian regularization approach. The experiments are performed to compare the results obtained from the ANN-based algorithm with those obtained from other existing algorithms, i.e., Chang algorithm, spectral polarization difference (SPD) algorithm, and temperature gradient (TG) algorithm. The experimental results show that the presented algorithm has the highest accuracy in estimating snow depth. In addition, the effects of the noises in datasets on model fitting can be decreased due to adopting the Bayesian regularization approach.

Modeling of Moment of Friction under Increasing Load Using Artificial Neural Networks

Preliminary results of testing of influence of load and rotational speed on moment of friction are presented in this paper. Tests were carried out under increasing load and within the range of rotational speed of 500 – 1500 rpm. The analysis of results was elaborated and model of moment of friction was developed on the basis of artificial neural network (ANN). Different kind of networks and various training algorithms were applied in order to obtain the best quality of the developed models.

Analyses of the temperature and pH effects on the complexation of magnesium and calcium in human blood plasma: an approach using artificial neural networks

The temperature and pH effects on the equilibrium of a blood plasma model have been studied on the basis of artificial neural networks. The proposed blood plasma was modeled considering two important metals, calcium and magnesium, and six ligands, namely, alanate, carbonate, citrate, glycinate, histidinate and succinate. A large data set has been used to simulate different concentrations of magnesium and calcium as a function of temperature and pH and these data were used for training the neural network. The proposed model allowed different types of analyses, such as the effects of pH on calcium and magnesium concentrations, the competition between calcium and magnesium for ligands and the effects of temperature on calcium and magnesium concentrations. The model developed was also used to predict how the variation of calcium concentration can affect magnesium concentrations. A comparison of neural network predictions against experimental data produced errors of about 3%. Moreover, in agreement with experimental measurements (Wang et al. in Arch. Pathol. 126:947-950, 2002; Heining et al. in Scand. J. Clin. Lab. Invest. 43:709-714, 1983), the artificial neural network predicted that calcium and magnesium concentrations decrease when pH increases. Similarly, the magnesium concentrations are less sensitive than calcium concentrations to pH changes. It is also found that both calcium and magnesium concentrations decrease when the temperature increases. Finally, the theoretical model also predicted that an increase of calcium concentrations will lead to an increase of magnesium concentration almost at the same rate. These results suggest that artificial neural networks can be efficiently applied as a complementary tool for studying metal ion complexation, with especial attention to the blood plasma analysis.

The virtual manufacturing model of the worsted yarn based on artificial neural networks and grey theory

Grey incidence analysis has been primarily studied in order to efficiently select the input variables of artificial neural networks (ANNs). The analysis of the processed data indicates that the weightiness sequence of all the variables influencing on the yarn quality and spinning performance could be ranked according to the grey incidence matrix. The comparison of the performance of ANNs model using grey superior analysis (GS), subjective and empirical approach (SE), and multi-linear regress method (MLR) shows that the model using the input variables selected by GS is superior to that by SE and MLR. At the same time, the virtual manufacturing model (VMM) of the worsted yarn has been used to simulate the spinning on the basis of ANNs and GS. In addition, through adjusting the first superior factors in the VMM, the yarn quality could be controlled and obviously improved.

Boosted ARTMAP: Modifications to fuzzy ARTMAP motivated by boosting theory

In this paper, several modifications to the Fuzzy ARTMAP neural network architecture are proposed for conducting classification in complex, possibly noisy, environments. The goal of these modifications is to improve upon the generalization performance of Fuzzy ART-based neural networks, such as Fuzzy ARTMAP, in these situations. One of the major difficulties of employing Fuzzy ARTMAP on such learning problems involves over-fitting of the training data. Structural risk minimization is a machine-learning framework that addresses the issue of over-fitting by providing a backbone for analysis as well as an impetus for the design of better learning algorithms. The theory of structural risk minimization reveals a trade-off between training error and classifier complexity in reducing generalization error, which will be exploited in the learning algorithms proposed in this paper. Boosted ART extends Fuzzy ART by allowing the spatial extent of each cluster formed to be adjusted independently. Boosted ARTMAP generalizes upon Fuzzy ARTMAP by allowing non-zero training error in an effort to reduce the hypothesis complexity and hence improve overall generalization performance. Although Boosted ARTMAP is strictly speaking not a boosting algorithm, the changes it encompasses were motivated by the goals that one strives to achieve when employing boosting. Boosted ARTMAP is an on-line learner, it does not require excessive parameter tuning to operate, and it reduces precisely to Fuzzy ARTMAP for particular parameter values. Another architecture described in this paper is Structural Boosted ARTMAP, which uses both Boosted ART and Boosted ARTMAP to perform structural risk minimization learning. Structural Boosted ARTMAP will allow comparison of the capabilities of off-line versus on-line learning as well as empirical risk minimization versus structural risk minimization using Fuzzy ARTMAP-based neural network architectures. Both empirical and theoretical results are presented to enhance the understanding of these architectures.

A classifier based on the artificial neural network approach for cardiologic auscultation in pediatrics

This research work was aimed at developing a reliable screening device for diagnosis of heart murmurs in pediatrics. This is a significant problem in pediatric cardiology because of the high rate of incidence of heart murmurs in this population (reportedly 77-95%), of which only a small fraction arises from congenital heart disease. The screening devices currently available (e.g. chest X-ray, electrocardiogram, etc.) suffer from poor sensitivity and specificity in detecting congenital heart disease. Thus, patients with heart murmurs today are frequently assessed by consultation as well with advanced imaging techniques. The most prominent among these is echocardiography. However, echocardiography is expensive and is usually only available in healthcare centers in major cities. Thus, for patients being evaluated with a heart murmur, developing a more accurate screening device is vital to efforts in reducing health care costs. The data set was collected from incoming pediatrics at the cardiology clinic of The Children's Hospital (Denver, Colorado), on whom echocardiography had been performed to identify congenital heart disease. Recordings of approximately 10-15s duration were made at 44,100Hz and the average record length was approximately 60,000 points. The best three cycles with respect to signal quality sounds were extracted from the original recording. The resulting data comprised 241 examples, of which 88 were examples of innocent murmurs and 153 were examples of pathological murmurs. The selected phonocardiograms were subject to the digital signal processing (DSP) technique of fast Fourier transform (FFT) to extract the energy spectrum in frequency domain. The spectral range was 0-300Hz at a resolution of 1Hz. The processed signals were used to develop statistical classifiers and a classifier based on our in-house artificial neural network (ANN) software. For the latter, we also tried enhancements to the basic ANN scheme. These included a method for setting the decision-threshold and a scheme for consensus-based decision by a committee of experts. Of the different classifiers tested, the ANN-based classifier performed the best. With this classifier, we were able to achieve classification accuracy of 83% sensitivity and 90% specificity in discriminating between innocent and pathological heart murmurs. For the problem of discrimination between innocent murmurs and murmurs of the ventricular septal defect (VSD), the accuracy was higher, with sensitivity of 90% and specificity of 93%. An ANN-based approach for detection and identification of congenital heart disease in pediatrics from heart murmurs can result in an accurate screening device. Considering that only a simple feature set was used for classification, the results are very encouraging and point out the need for further development using improved feature set with more potent diagnostic variables.

Effect of temperature on short term load forecasting using an integrated ANN

An integrated Artificial Neural Network (ANN) approach to Short-Term Load Forecasting (STLF) is proposed in this paper. Four modules consisting of the Basic ANN, Peak and Valley ANN, Averager and Forecaster and Adaptive Combiner form the integrated method for load forecasting. The Basic ANN uses the historical data of load and temperature to predict the next 24 h load, while the Peak and Valley ANN uses the past peak and valley data of load and temperatures, respectively. The Averager captures the average variation of the load from the previous load behaviour, while the adaptive combiner uses the weighted combination of outputs from the Basic ANN and the Forecaster, to forecast the final load. The regression based and time series methods are conceptually incorporated into the ANN to obtain an integrated load forecasting approach.

Application of artificial neural networks in the design of controlled release drug delivery systems

Controlled release drug delivery systems offer great advantages over the conventional dosage forms. However, there are great challenges to efficiently develop controlled release drug delivery systems due to the complexity of these delivery systems. Traditional statistic response surface methodology (RSM) is one of the techniques that has been employed to develop and formulate controlled release dosage forms. However, there are some limitations to the RSM technique. Hence, another technique called artificial neural networks (ANN) has recently gained wide popularity in the development of controlled release dosage forms. In this review, the basic ANN structure, the development of the ANN model and an explanation of how to use ANN to design and develop controlled release drug delivery systems are discussed. In addition, the applications of ANN in the design and development of controlled release dosage forms are also summarized in this review.

Development and Application of Back-Propagation-Based Artificial Neural Network Models in Solving Engineering

Artificial Neural Networks (ANNs) are computer software programs that mimic the human brain's ability to classify patterns or to make forecasts or decisions based on past experience. The development of this research area can be attributed to two factors, sufficient computer power to begin practical ANN-based research in the late 1970s and the development of back-propagation in 1986 that enabled ANN models to solve everyday business, scientific, and industrial problems. Since then, significant applications have been implemented in several fields of study, and many useful intelligent applications and systems have been developed. The objective of this paper is to generate awareness and to encourage applications development using artificial intelligence-based systems. Therefore, this paper provides basic ANN concepts, outlines steps used for ANN model development, and lists examples of engineering applications based on the use of the back-propagation paradigm conducted in Oman. The paper is intended to provide guidelines and necessary references and resources for novice individuals interested in conducting research in engineering or other fields of study using back-propagation artificial neural networks.

New Hybrid Neural Network Model for Prediction of Phase Equilibrium in a Two-Phase Extraction System

A novel approach to modeling prediction of phase equilibrium is presented. The method, evolutionary polymorphic neural network (EPNN), is developed by the authors on the basis of artificial neural networks and evolutionary computing. The system poly(ethylene glycol) (PEG)/potassium phosphate/water at pH = 7 was selected to demonstrate the performance of the model. The results were favorable as compared to a traditional neural network modeling approach and the experimental data set. Seven distinct data sets of varying PEG molecular weights were used in this work. Of the seven, five were used for training, while the remaining two were employed as the test cases. Following the training, a networked symbolic equation system evolved, which, in addition to reproducing the data, can also be used to improve understanding of the phase diagram mechanism through the discovered parameters.

PERFORMANCE OF HYBRID REAL CODED GENETIC ALGORITHMS

This paper presents a new robust, two -phase hybrid optimization algorithm to solve non-linear constrained optimization problems. The proposed algorithm is very much useful when addressing heavily constrained optimization problem in terms of solution accuracy and computation time. It can out perform conventional genetic algorithms (CGAs) is the sense that Hybrid GAs makes it possible to improve both the quality of the solution and reduce the computing expenses. The proposed hybrid scheme is developed in such a way that a simple real coded GA is acting as a base level search, which makes a quick decision to direct the search towards the optimal region, and local search method is next employed to do fine tuning. The phase - 1 uses real coded genetic algorithm, while optimization by direct search and systematic reduction of the size of search region method is employed in the phase - 2. Thirteen test problems were taken from the literature have been simulated and results obtained were compared. The results clearly demonstrate that the proposed hybrid real coded genetic algorithm not only improve the reliability but also make the algorithm more efficient in terms of number of function evaluations to reach the global optimum point. Thus the usefulness and effectiveness of this algorithm is placed in a sharper focus.

Microwave Radiometer for Cloud Carthography: A 22‐channel ground‐based microwave radiometer for atmospheric research

A 22‐channel Microwave Radiometer for Cloud Carthography (MICCY) for the profiling of tropospheric temperature, humidity, and cloud liquid water has been developed. The radiometer has 10 channels along the high‐frequency wing of the 22.235 GHz water vapor line, 10 channels along the low‐frequency side of the 60 GHz oxygen complex, and 2 channels at 90 GHz. Two features make the radiometer a unique tool for the observation of small‐scale structures related to cloud processes: (1) Atmospheric brightness temperatures are measured simultaneously at all channels with an integration time of 1 s. (2) A Cassegrain system including a 90 cm off‐axis parabolic mirror leads to a spatial resolution better than 1° full width at half maximum for all frequencies. The necessity of these features for cloud observations is demonstrated. Algorithms for the retrieval of integrated water vapor, integrated cloud liquid water, and the profiles of temperature and humidity were developed on the basis of artificial neural networks. Measurement examples, including comparisons with radiosondes, demonstrate the systems capabilities for high‐resolution atmospheric monitoring.

A stroke-based neuro-fuzzy system for handwritten chinese character recognition

In this article, a stroke-based neuro-fuzzy system for off-line recognition of handwritten Chinese characters is proposed. The system consists of three main components: stroke extraction, feature extraction, and recognition. Stroke extraction applies a run-length-based method to extract strokes from the image of a given character. Various fuzzy features of the extracted strokes, including slope, length, location, and cross relation, are obtained by the feature extraction module. An ART-based neural network, using a two-stage training algorithm, is used to recognize characters. This system extracts strokes in only two passes, and is free from the presence of spurious and thick strokes. The neural model used provides a fast convergence rate. Nodes are allowed to be shared to reduce the size of the resulting network. Features need not be classified in advance by the user. Furthermore, the architecture of the network is self-constructed without the intervention of the user. Experiments have shown that this system is effective.

Effect of patient histoy data on the prediction of breast cancer from mammographic findings with artificial neural networks

The authors evaluated the contribution of medical history data to the prediction of breast cancer with artificial neural network (ANN) models based on mammographic findings. Three ANNs were developed: The first used 10 Breast Imaging Reporting and Data System (BI-RADS) variables; the second, the BI-RADS variables plus patient age; the third, the BI-RADS variables, patient age, and seven other history variables, for a total of 18 inputs. Performance of the ANNs and the original radiologist's impression were evaluated with five metrics: receiver operating characteristic area index (Az); specificity at given sensitivities of 100%, 98%, and 95%; and positive predictive value. All three ANNs consistently outperformed the radiologist's impression over all five performance metrics. The patient-age variable was particularly valuable. Adding the age variable to the basic ANN model, which used only the BI-RADS findings, significantly improved Az (P = .028). In fact, replacing all history data with just the age variable resulted in virtually no changes for Az or specificity at 98% sensitivity (P = .324 and P = .410, respectively). Patient age was an important variable for the prediction of breast cancer from mammographic findings with the ANNs. For this data set, all history data could be replaced with age alone.

MART: a multichannel ART-based neural network

This paper describes MART, an ART-based neural network for adaptive classification of multichannel signal patterns without prior supervised learning. Like other ART-based classifiers, MART is especially suitable for situations in which not even the number of pattern categories to be distinguished is known a priori; its novelty lies in its truly multichannel orientation, especially its ability to quantify and take into account during pattern classification the different changing reliability of the individual signal channels. The extent to which this ability can reduce the creation of spurious or duplicate categories (a major problem for ART-based classifiers of noisy signals) is illustrated by evaluation of its performance in classifying QRS complexes in two-channel ECG traces which were taken from the MIT-BIH database and contaminated with noise.

PREDICTION OF PEAK HORIZONTAL ACCELERATION USING AN ARTIFICIAL NEURAL NETWORK MODEL

In this study, a model on the basis of artificial neural networks is developed to predict the peak horizontal acceleration. The neural network model provides an objective analysis method which requires neither specifying predictive functional forms nor the independence of the inside variables. The Joyner and Boore data set (DSSA, Vol. 71, pp. 2011-2038, 1981), was used for analysis. For comparison, one-and two-step regression procedures were also applied to the same data set. Various fitness criteria have been considered. Finally, the proposed procedure showed an agreeable capability for the required prediction of ground motion parameters.

A neural network based technique for short-term forecasting of anomalous load periods

The paper illustrates a part of the research activity conducted by the authors in the field of electric short term load forecasting (STLF) based on artificial neural network (ANN) architectures. Previous experiences with basic ANN architectures have shown that, even though these architectures provide results comparable with those obtained by human operators for most normal days, they evidence some accuracy deficiencies when applied to "anomalous" load conditions occurring during holidays and long weekends. For these periods a specific procedure based upon a combined (unsupervised/supervised) approach has been proposed. The unsupervised stage provides a preventive classification of the historical load data by means of a Kohonen's self-organizing map (SOM). The supervised stage, performing the proper forecasting activity, is obtained by using a multi-layer perceptron with a backpropagation learning algorithm similar to the ones mentioned above. The unconventional use of information deriving from the classification stage permits the proposed procedure to obtain a relevant enhancement of the forecast accuracy for anomalous load situations.