Representing time has been considered a general problem for artificial intelligence research for many years. More recently, the question of representing time has become increasingly important in representing human decision making process through connectionist expert systems. Because most human behaviors unfold over time, any attempt to represent expert performance, without considering its temporal nature, can often lead to incorrect results. A temporal feedforward neural network model that can be applied to a number of neural network application areas, including connectionist expert systems, has been introduced. The neural network model has a multi-layer structure, i.e. the number of layers is not limited. Also, the model has the flexibility of defining output nodes in any layer. This is especially important for connectionist expert system applications. A temporal backpropagation algorithm which supports the model has been developed. The model along with the temporal backpropagation algorithm makes it extremely practical to define any artificial neural network application. Also, an approach that can be followed to decrease the memory space used by weight matrix has been introduced. The algorithm was tested using a medical connectionist expert system to show how best we describe not only the disease but also the entire course of the disease. The system, first, was trained using a pattern that was encoded from the expert system knowledge base rules. Following then, series of experiments were carried out using the temporal model and the temporal backpropagation algorithm. The first series of experiments was done to determine if the training process worked as predicted. In the second series of experiments, the weight matrix in the trained system was defined as a function of time intervals before presenting the system with the learned patterns. The result of the two experiments indicate that both approaches produce correct results. The only difference between the two results was that compressing the weight matrix required more training epochs to produce correct results. To get a measure of the correctness of the results, an error measure which is the value of the error squared was summed over all patterns to get a total sum of squares.

<p>In this study, Artificial Neural Network (ANN) is used to check the integrity of the Global Positioning Recommended Minimum (GPRMC) sentences. The GPRMC sentences are the most common sentences transmitted by the Global Positioning System (GPS) devices. This sentence contains nearly every thing a GPS application needs. The data integrity is compared on the basis of the classification accuracy and the minimum error obtained using the ANN. The ANN requires data to be presented in a certain format supported by the learning process of the network. Therefore a certain amount of data processing is needed before training patterns are presented to the network. The data pre processing is done by the design and development of different algorithms in C# using Visual Studio.Net 2003. This study uses the BackPropagation (BP) feed forward multilayer ANN algorithm with the learning rate and the momentum as its parameters. The results are analyzed based on different ANN architectures, classification accuracy, Sum of Square Error (SSE), variables sensitivity analysis and training graph. The best obtained ANN architecture shows a good performance with the selection classification of 96.79 % and the selection sum of square error 0.2022. This study uses the ANN tool Trajan 6.0 Demonstrator.</p>

El problema del desbalance de las clases aparece cuando existen muchos más elementos de una o algunas clases, que de la otra u otras clases (dos o múltiples clases). Esta desproporción en el tamaño de las diferentes clases en un mismo conjunto de datos, puede ocasionar una disminución en la efectividad del clasificación sobre las clases menos representadas. En el caso específico de las redes neuronales artificiales, el desbalance de las clases ocasiona lentitud en la convergencia de las clases minoritarias, lo que se traduce en una pobre capacidad de generalización del clasificador. En este trabajo se estudia y trata el problema del desbalance de las clases en el ámbito de las redes neuronales artificiales. Para ello se entrena la red con el algoritmo back-propagation con procesamiento por grupos desde tres enfoques distintos: (a) Incluyendo funciones de coste al proceso de entrenamiento, (b) aplicando redes neuronales modulares (descomposición del problema), y (c) reduciendo la región de solapamiento de las clases menos representadas. En síntesis, este trabajo presenta un estudio empírico comparativo de los efectos y posibles tratamientos del problema del desbalance de las clases sobre tres modelos de red neuronal artificial.

In this study, Artificial Neural Network (ANN) is used to check the integrity of the Global Positioning Recommended Minimum (GPRMC) sentences. The GPRMC sentences are the most common sentences transmitted by the Global Positioning System (GPS) devices. This sentence contains nearly every thing a GPS application needs. The data integrity is compared on the basis of the classification accuracy and the minimum error obtained using the ANN. The ANN requires data to be presented in a certain format supported by the learning process of the network. Therefore a certain amount of data processing is needed before training patterns are presented to the network. The data pre processing is done by the design and development of different algorithms in C# using Visual Studio.Net 2003. This study uses the BackPropagation (BP) feed forward multilayer ANN algorithm with the learning rate and the momentum as its parameters. The results are analyzed based on different ANN architectures, classification accuracy, Sum of Square Error (SSE), variables sensitivity analysis and training graph. The best obtained ANN architecture shows a good performance with the selection classification of 96.79 % and the selection sum of square error 0.2022. This study uses the ANN tool Trajan 6.0 Demonstrator.

The two-stage data mining technique for classifications in tourism recommendation system is necessary to connect user perception, decision criteria and decision purpose. In existed literature, hybrid data mining method combining Decision Tree and K-nearest neighbour approaches (DTKNN) were proposed. It has a high precision rate of approximately 80% in K-nearest Neighbour (KNN) but a much lower rate in the first stage using Decision Tree (Fu & Tu, 2011). It included two potential improvements on two-stage technique. To improve the first stage of DTKNN in precision rate and the efficiency, the amount of questions is decreased when users search for the desired recommendation on the system. In this paper, the researcher investigates the way to improve the first stage of DTKNN for full questionnaires and also determines the suitability of dynamic questionnaire based on its precision rate in future tourism recommendation system. Firstly, this study compared and chose the highest precision rate among Decision Tree, Multi-staged Binary Tree and Back Propagation of Error Neural Network (BPNN). The chosen method is then combined with KNN to propose a new methodology. Secondly, the study compared and deter¬mined the suitability of dynamic questionnaires for all three classification methods by decreasing the number of attributes. The suitable dynamic questionnaire is based on the least amount of attributes used with an appropriate precision rate. Tourism recommendation system is selected as the target to apply and analyse the usefulness of the algorithm as tourism selection is a two-stage example. Tourism selection is to determine expected goal and experience before going on a tour at the first stage and to choose the tour that best matches stage one. The result indicates that Multi-staged Bi¬nary Tree has the highest precision rate of 74.167% comparing to Decision Tree with 73.33% then BPNN with 65.47% for full questionnaire. This new approach will improve the effectiveness of the system by improving the precision rate of first stage under the current DTKNN method. For dynamic questionnaire, the result has shown that Decision Tree is the most suitable method given that it resulted in the least difference of 1.33% in precision rate comparing to full questionnaire, as opposed to 1.48% for BPNN and 4% for Multi-staged Binary Tree. Thus, dynamic questionnaire will also improve the efficiency by decreasing the amount of questions which users are required to fill in when searching for the desired recommendation on the system. It provides users with the option to not answer some questions. It also increases the practicality of non-dynamic questionnaire and, therefore, affects the ultimate precision rate.

Mémoire (M.Eng.)-- Université du Québec à Chicoutimi, 1992. / Résumé disponible sur Internet. CaQCU Bibliogr.: f. 142-150. Document électronique également accessible en format PDF. CaQCU

Orientador: Anna Diva Plasencia Lotufo / Banca: Maria do Carmo Gomes da Silveira / Banca: Gelson da. Cruz Junior / Resumo: A previsão de carga, considerada essencial no planejamento da operação energética e nos estudos de ampliação e reforços da rede básica, assume importância estratégica na extensão comercial, valorizando os processos de armazenamento desses dados e da extração de conhecimentos através de técnicas computacionais. Nos últimos anos, diversos trabalhos foram publicados sobre sistemas de previsão de cargas (demanda) elétricas. Nos horizontes de curto, médio e longo prazo, os modelos neurais, estão entre os mais explorados. O objetivo deste trabalho é apresentar um sistema previsor de cargas elétricas de forma simples e eficiente através de sistemas baseados em redes neurais artificiais com treinamento realizado pelo algoritmo back-propagation. Para isto, optou-se pelo desenvolvimento de um software utilizando os paradigmas de programação orientada a objetos para criar um modelo neural de fácil manipulação, e que de certa forma, consiga corrigir o problema dos mínimos locais. Em geral, o sistema desenvolvido é capaz de atribuir os parâmetros da rede neural de forma automática através de processos exaustivos. Os resultados apresentados foram comparados utilizando outros trabalhos em que também se usaram-se os dados da mesma companhia elétrica. Este trabalho apresentou um ganho de desempenho bem satisfatório em relação a outros trabalhos encontrados na literatura para a mesma classe de problemas / Abstract: Load Forecasting is essential in planning and operation of power systems, in enlarging and reinforcing the basic network, is also very important commercially, valorizing the filing process of these data and extracting knowledge by computational techniques. Lately, several works have been published about electrical load forecasting. Short term, medium term and long term horizons are equally studied. The objective of this work is to present an electrical load forecasting system, which is simple and efficient and based on artificial neural networks whose training is with the back-propagation algorithm. Therefore, a software is developed using the paradigms of the object oriented programming technique to create a neural model which is ease to manipulate, and able to correct the local minimum problem. This system attributes the neural parameters automatically by exhaustive procedures. Results are compared with other works that have used the same data and this work presents a satisfactory performance when compared with those and others found in the literature / Mestre

This thesis compares forward neural networks with algorithms using game theory on basis of board game Blokus. The theoretical introduction part describes the characteristics of neural networks and work with them. There is also outlined algorithm of game theory. The second part deals about the implementation of players based on the outlined principles  and shortly descriptions GUI of application. In conclusion, the differences between the players  are evaluated on the charts created on the performed tests.

Employee selection research identifies and makes use of associations between individual differences, such as those measured by psychological testing, and individual differences in job performance. Artificial neural networks are computer simulations of biological nerve systems that can be used to model unspecified relationships between sets of numbers. Thirty-five neural networks were trained to estimate normalized annual revenue produced by telephone sales agents based on personality and biographic predictors using concurrent validation data (N=1085). Accuracy of the neural estimates was compared to OLS regression and a proprietary nonlinear model used by the participating company to select agents.

Targeting heavier freights and transporting passengers with higher speeds became the strategic railway development during the past decades significantly increasing interests on railway networks. Among different components of a railway network, bridges constitute a major portion imposing considerable construction and maintenance costs. On the other hand, heavier axle loads and higher trains speeds may cause resonance occurrence on bridges; which consequently limits operational train speed and lines. Therefore, satisfaction of new expectations requires conducting a large number of dynamic assessments/analyses on bridges, especially on existing ones. Evidently, such assessments need detailed information, expert engineers and consuming considerable computational costs. In order to save the computational efforts and decreasing required amount of expertise in preliminary evaluation of dynamic responses, predictive models using artificial neural network (ANN) are proposed in this study. In this regard, a previously developed closed-form solution method (based on solving a series of moving force) was adopted to calculate the dynamic responses (maximum deck deflection and maximum vertical deck acceleration) of randomly generated bridges. Basic variables in generation of random bridges were extracted both from literature and geometrical properties of existing bridges in Sweden. Different ANN architectures including number of inputs and neurons were considered to train the most accurate and computationally cost-effective mode. Then, the most efficient model was selected by comparing their performance using absolute error (ERR), Root Mean Square Error (RMSE) and coefficient of determination (R2). The obtained results revealed that the ANN model can acceptably predict the dynamic responses. The proposed model presents Err of about 11.1% and 9.9% for prediction of maximum acceleration and maximum deflection, respectively. Furthermore, its R2 for maximum acceleration and maximum deflection predictions equal to 0.982 and 0.998, respectively. And its RMSE is 0.309 and 1.51E-04 for predicting the maximum acceleration and maximum deflection prediction, respectively. Finally, sensitivity analyses were conducted to evaluate the importance of each input variable on the outcomes. It was noted that the span length of the bridge and speed of the train are the most influential parameters.