The speech auditory brainstem response (sABR) is a promising technique for assessing the function of the auditory system. This non-invasive technique has shown utility as a marker of central processing disorders, some types of learning difficulties in children, and potentially for fitting hearing aids. However, the sABR needs a long recording time to obtain a reliable signal due to the high background noise, which limits its clinical applicability. The objective of this work is to develop methods to detect the sABR in high background noise and enhance it based on a modeling approach and through experimental testing. First, sABR noise estimation based on LQ/QR decomposition is derived, and its mathematical proof is shown. Second, an autoregression model is used to estimate the single-trial sABR which is then used to test several sABR detection and enhancement methods. Third, a novel Artificial Neural Network (ANN) based detection approach is proposed and compared using modeled and recorded data to other detection methods in the literature: Optimal Linear Filter (LF), Online Estimator (OE), Mutual Information (MI) and Artificial Neural Network based on the Discrete Wavelet Transform and Approximate Entropy (ANN DA). Finally, comprehensive evaluation of several sABR enhancement methods is performed, based on the Wiener Filter (WF), Maximum-SNR Filter (Max-SNR), Adaptive Noise Cancellation (ANC) with Least-Mean-Square (LMS), Affine Projection (AP) and Recursive-Least-Square (RLS) adaptation algorithm. The results show that the developed LQ/QR decomposition estimated noise is similar to the actual noise, and the modeled data are statistically similar to the recorded data. Moreover, the proposed ANN-based detection method is more accurate and requires less processing time than other methods, and the comprehensive evaluation of enhancement methods shows that RLS has best overall performance in enhancing the sABR. Therefore, the methods developed and evaluated in this work have the potential to reduce the required recording time for the sABR, and thus make it more practical as a clinical tool.

The first objective of this research project is to carry out multi-objective optimization (MOO) for four simple chemical engineering processes to clearly demonstrate the wealth of information on a given process that can be obtained from the MOO instead of a single aggregate objective function. The four optimization case studies are the design of a PI controller, an SO2 to SO3 reactor, a distillation column and an acrolein reactor. Results that were obtained from these optimization case studies show the benefit of generating and using the Pareto domain to gain a deeper understanding of the underlying relationships between the various process variables and the different performance objectives. In addition, an acrylic acid production plant model is developed in order to propose a methodology to solve multi-objective optimization for the two-reactor system model using artificial neural networks (ANNs) as metamodels, in an effort to reduce the computational time requirement that is usually very high when first-principles models are employed to approximate the Pareto domain. Once the metamodel was trained, the Pareto domain was circumscribed using a genetic algorithm and ranked with the Net Flow method (NFM). After the MOO was carry out with the ANN surrogate model, the optimization time was reduced by a factor of 15.5.

Artificial Neural Networks are models of interacting neurons that can be used as classifiers with large data sets. They can also be used for feature extraction and for reducing the dimensionality of large data sets. Den-Dritic electrotonic models can be used to suggest more robust artificial neural network models that are amenable to data mining and feature extraction.

Short-term wind power forecasting is crucial for the efficient operation of power systems with high wind power penetration. Many forecasting approaches have been developed in the past to forecast short-term wind power. In recent years, artificial neural network-based approaches (ANNs) have been one of the most effective and popular approaches for short-term wind power forecasting because of the availability of large amounts of historical data and strong computational power. Although ANNs usually perform well for short-term wind power forecasting, further improvement can be obtained by selecting suitable input features, model parameters, and using forecasting techniques like spatial correlation and ensemble for ANNs. In this research, the effect of input features, model parameters, spatial correlation and ensemble techniques on short-term wind power forecasting performance of the ANNs models was evaluated. Pearson correlation coefficients between wind speed and other meteorological variables, together with a basic ANN model, were used to determine the impact of different input features on the forecasting performance of the ANNs. The effect of training sample resolution and training sample size on the forecasting performance was also investigated. To separately investigate the impact of the number of hidden layers and the number of hidden neurons on short-term wind power forecasting and to keep a single variable for each experiment, the same number of hidden neurons was used in each hidden layer. The ANNs with a total of 20 hidden neurons are shown to be sufficient for the nonlinear multivariate wind power forecasting problems faced in this dissertation. The ANNs with two hidden layers performed better than the one with a single hidden layer because additional hidden layer adds nonlinearity to the model. However, the ANNs with more than two hidden layers have the same or worse forecasting performance than the one with two hidden layers. ANNs with too many hidden layers and hidden neurons can overfit the training data. Spatial correlation technique was used to include meteorological variables from highly correlated neighbouring stations as input features to provide more surrounding information to the ANNs. The advantages of input features, model parameters, and spatial correlation and ensemble techniques were combined to form an ANN-based ensemble model to further enhance the forecasting performance from an individual ANN model. The simulation results show that all the available meteorological variables have different levels of impact on forecasting performance. Wind speed has the most significant impact on both short-term wind speed and wind power forecasting, whereas air temperature, barometric pressure, and air density have the smallest effects. The ANNs perform better with a higher data resolution and a significantly larger training sample size. However, one requires more computational power and a longer training time to train the model with a higher data resolution and a larger training sample size. Using the meteorological variables from highly related neighbouring stations do significantly improve the forecasting accuracy of target stations. It is shown that an ANNs-based ensemble model can further enhance the forecasting performance of an individual ANN by obtaining a large amount of surrounding meteorological information in parallel without encountering the overfitting issue faced by a single ANN model.

In spite of the most up-to-date investigation of the relevant techniques to analyze the traffic characteristics and traffic operations at a toll plaza, there has not been any note worthy explorations evaluating delay from toll transaction data and using Artificial Neural Networks (ANN) at a toll plaza. This thesis lays an emphasis on the application of ANN techniques to estimate the total vehicular delay according to the lane type at a toll plaza. This is done to avoid the laborious task of extracting data from the video recordings at a toll plaza. Based on the lane type a general methodology was developed to estimate the total vehicular delay at a toll plaza using ANN. Since there is zero delay in an Electronic Toll Collection (ETC) lane, ANN models were developed for estimating the total vehicular delay in a manual lane and automatic coin machine lane. Therefore, there are two ANN models developed in this thesis. These two ANN models were trained with three hours of data and validated with one hour of data from AM and PM peak data. The two ANN models were built with the dependent and independent variables. The dependent variables in the two models were the total vehicular delay for both the manual and automatic coin machine lane. The independent variables are those, which influence delay. A correlation analysis was performed to see if there exists any strong relationship between the dependent (outputs) and independent variables (inputs). These inputs and outputs are fed into the ANN models. The MATLABTB code was written to run the two ANN models. ANN predictions were good at estimating delay in manual lane, and delay in automatic coin machine lane.

No / In recent years, several accidents in pioneer gas processing industries led industries to put emphasis on real-time fault detection. Neural Network (NN) based fault (abnormal situation) detection technique played an important role in monitoring industrial safety. In this work, an attempt has been made to study the fault detection of Brahmanbaria gas processing plant using multi layered feed forward NN based system. NN based fault detection system is trained, validated and tested using data generated using the dynamic model. Preliminary results show that NN based method is able to detect the faults of Brahmanbaria Gas processing plant for fewer no of faults.

no / This study employs artificial neural networks (ANNs) to create a model to identify relationships between variables affecting drug nanoprecipitation using microfluidic reactors. The input variables examined were saturation levels of prednisolone, solvent and antisolvent flowrates, microreactor inlet angles and internal diameters, while particle size was the single output. ANNs software was used to analyse a set of data obtained by random selection of the variables. The developed model was then assessed using a separate set of validation data and provided good agreement with the observed results. The antisolvent flow rate was found to have the dominant role on determining final particle size.

No description available.

The generalization ability of artificial neural networks (ANN) is highly dependent on their architectures and can be critical to solving a given problem. The current best practice uses fixed architectures determined via a trial-and-error approach. This process can be both computationally and temporally cumbersome and does not guarantee that an optimal topology will even be found. Replacing the user’s role in designing topologies with methods that enable a system to manage its own growth can endow systems with adaptable learning. Constructive algorithms offer the possibility of compact architectures as an alternative to the trial-and-error approach. This class of algorithms grows a network’s topology by incrementally adding units during learning to match task complexity. However, the decision of when to add new units in constructive algorithms heavily depends on user-defined a priori hyperparameters, which can be task-specific. Contrary to having a user fine-tune hyperparameters that govern growth, the intrinsic population dynamics of an ANN could be used to self-govern the growing process. Theoretically, an ANN or each layer comprising the network can be viewed as a set of populations. From this perspective, a hidden layer can be considered the environment in which hidden units exist. In this work, we propose a novel, more self-governed growing algorithm inspired by population dynamics for determining near-optimal topologies of feedforward ANNs. This allows the inclusion of a carrying capacity, the maximum population of hidden units that can be sustained in a hidden layer. Including this constraint in combination with population dynamics provides a built-in mechanism for a dynamic growth rate. The proposed approach is used in parallel with direct performance feedback from the network to modulate the growth rate of the hidden layer, allowing the network to converge to smaller topologies based on the task's demands. More self-governed approaches reduce the number of finely-tuned hyperparameters required to decide when to grow and put more control of the network’s structure and representational capacities in the algorithms themselves, facilitating the emergence of inherent intelligent behaviour. Chapter one introduces a dynamic, more self-governed growing algorithm inspired by population dynamics. Results show that compared to using fixed rules for determining hidden layer sizes; dynamic growth leads to smaller topologies than predicted while still being capable of solving the task. In chapter two, we investigate the algorithm's inherent properties to validate the more self-governed aspect. The results depict that the model’s hyperparameters require less fine-tuning by the user and adhere more toward self-governance. Finally, in chapter three, we investigate the effects of growing hidden layers individually in a sequential fashion or simultaneously in a parallel fashion multilayer context. A modified version of the growing algorithm capable of growing parallel is proposed. Growing hidden layers in parallel resulted in comparable or higher performances than sequential approaches. The growing algorithm presented here offers more self-governed growth, which provides an effective general solution automatically tailored to the task.

Laser-induced breakdown spectroscopy (LIBS) is an advanced data analysis technique for spectral analysis based on the direct measurement of the spectrum of optical emission from a laser-induced plasma. Assignment of different atomic and ionic lines, which are signatures of a particular element, is the basis of a qualitative identification of the species present in plasma. The relative intensities of these atomic and ionic lines can be used for the quantitative determination of the corresponding elements present in different samples. Calibration curve based on absolute intensity is the statistical method of determining concentrations of elements in different samples. Since we need an exact knowledge of the sample composition to build the proper calibration curve, this method has some limitations in the case of samples of unknown composition. The current research is to investigate the usefulness of ANN for the determination of the element concentrations from spectral data. From the study it is shown that neural networks predict elemental concentrations that are at least as good as the results obtained from traditional analysis. Also by automating the analysis process, we have achieved a vast saving in the time required for the data analysis.