Backpropagation

In this paper, a new algorithm for Automatic License Plate Localisation and Recognition (ALPR) is proposed on the basis of isotropic dilation that can be achieved using the binary image Euclidean distance transform. In a blob analysis problem, any two Region of Interest (RoIs) that is discontinuous are typically treated as separate blobs. However, the proposed algorithm combine with Connected Component Analysis (CCA) are coded to seek for RoI within a certain distance of other RoI to be treated as non-unique. This paper investigates the design and implementation of several pre-processing techniques and isotropic dilation algorithm to classify moving vehicles with different backgrounds and varying angles. A multi-layer feed-forward back-propagation Neural Network is used to train the segmented and refined characters. The results obtained can be used for implementation in the vehicle parking management system.

Levenberg-Marquardt back-propagation training method has some limitations associated with over fitting and local optimum problems. Here, we proposed a new algorithm to increase the convergence speed of Backpropagation learning to design the airfoil. The aerodynamic force coefficients corresponding to series of airfoil are stored in a database along with the airfoil coordinates. A feedforward neural network is created with aerodynamic coefficient as input to produce the airfoil coordinates as output. In the proposed algorithm, for output layer, we used the cost function having linear & nonlinear error terms then for the hidden layer, we used steepest descent cost function. Results indicate that this mixed approach greatly enhances the training of artificial neural network and may accurately predict airfoil profile.

With the rise of web-based education systems and the increased use of information systems in education institutions, the amount of data recorded on student performance and behavior has increased exponentially. Thus, bringing about a large number of contributions to the field of educational research, which in itself contributed to the further evolution off the field in the last two decades alone, with terms such as Educational Data Mining (EDM), Learning Analytics, Data-driven Education, Teaching Analytics and others being added to the literature. In this paper, we evaluate the usefulness of a model using Rough Set Theory (RST) and Backpropagation Neural Network (BPNN) in effectively predicting the students’ overall performance. The dataset used consists of 10 different attributes and one decision factor belonging to 53 students collected from a language course which administers in-person education with the aid of an online platform for assignments. RST was implemented in order to re...

7.2 Phoneme Recognition Using Time-Delay Neural Networks 395 Fig. 1. A Time-Delay Neural Network (TDNN) unit. BOG Output layer integration Hidden Layer 2 Hidden layer 1 I Input layer 15 frames 10 msec frame rate Fig. 2. The architecture of the TDNN. network, where ...

In response to the growing concern over the use of fossil fuels, renewable energy industries have been significant economic drivers in many parts of the United States. In the recent years there is a strong growth in solar power generation industries that requires prediction of solar energy to develop highly efficient stand-alone photovoltaic systems as well as hybrid power systems. In order to accomplish the goal, we propose a predictive model that is based on recurrent neural networks trained with the Levenberg-Marquardt backpropagation learning algorithm to forecast the solar radiation using the past solar radiation and solar energy. This computational intelligence modeling tool explored the impact of solar radiation and solar energy in forecasting reliable long-run solar energy. Based on the excellent experimental results including the mean squared error analysis, error autocorrelation function analysis, regression analysis, and time series response, it demonstrated that the prop...

ANN Backpropagation adalah metode dengan algoritma pembelajaran untuk memperkecil tingkat error dengan cara menyesuaikan bobotnya berdasarkan perbedaan output dan target yang diinginkan. Pada percobaan kali ini fungsi aktivasi yang dipakai adalah fungsi bipolar sigmoid yang dimana fungsi ini memiliki rentang -1 sampai dengan 1. Program ini melakukan algoritma pelatihan metode ANN BP dalam tiga tahap, yaitu, melatih pola input yang diberikan, kemudian membandingkan output dengan pola target yang telah diinput sebelumnya, dan yang ketiga adalah mengambil nilai error yang didapat dari perbandingan tadi untuk diambil rata-rata errornya dan kemudian data error tadi menjadi nilai acuan untuk penyesuain bobot-bobot yang menjadi struktur dalam ANN BP.
Pada program ini, terdapat dua pendulum, yaitu pendulum target dan pendulum pengikut. Pada pergerakan pendulum target didasarkan dari sinyal sinusoidal murni. Dan pendulum pengikut didasarkan pergerakanya berdasarkan persamaan gerak dari bandul dan persamaan itu terdapat parameter karakteristik nyatanya. Seperti gravitasi, massa dan panjang tali (l). Perubahan dari masing-masing parameter nyata ini sangat berpengaruh dari pergerakan pendulum pengikut dan hal ini telah dibuktikan pada bab hasil percobaan sebelumnya.

Technological intelligence is a highly sought after commodity even in traffic-based systems. These intelligent systems do not only help in traffic monitoring but also in commuter safety, law enforcement and commercial applications. In this paper, a license plate localization and recognition system for vehicles in Malaysia is proposed. This system is developed based on digital images and can be easily

The authors propose a general fuzzy classification scheme with learning ability using an adaptive network. System parameters, such as the membership functions defined for each feature and the parameterized t-norms used to combine conjunctive conditions, are calibrated with backpropagation. To explain this approach, the concept of adaptive networks is introduced and a supervised learning procedure based on a gradient descent algorithm is derived to update the parameters in an adaptive network. The proposed architecture is applied to two problems: two-spiral classification and Iris categorization. From the experimental results, it is concluded that the adaptively adjusted classifier performs well on an Iris classification problem. The results are discussed from the viewpoint of feature selection

... Olatoyosi Olude Department of Systems Science & Industrial Engineering ... In order to improve the stock market performance, Quah & Srinivasan [31] proposed a stock selection system using ANN to select stocks that are top–performers and to avoid selecting under–performers. ...

The objective of this paper is to develop the hybrid neural network models for bankruptcy prediction. The proposed hybrid neural network models are (1) a MDA-assisted neural network, (2) an ID3-assisted neural network, and (3) a SOFM(self organizing feature map)-assisted neural network. Both the MDA-assisted neural network and the 11)3-assisted neural network are the neural network models operating with the input variables selected by the MDA method and 1133 respectively. The SOFM-assisted neural network combines a backpropagation model (supervised learning) with a SOFM model (unsupervised learning). The performance of the hybrid neural network model is evaluated using MDA and ID3 as a benchmark. Empirical results using Korean bankruptcy data show that hybrid neural network models are very promising neural network models for bankruptcy prediction in terms of predictive accuracy and adaptability.

Cuenca 2 Programa para el manejo del agua y el suelo (PROMAS), Universidad de Cuenca Resumen La aplicación de modelos matemáticos en el manejo de cuencas hidrográficas tiene requerimientos exigentes de información y en su mayoría no han sido desarrollados para ser aplicados en regiones de montaña. Por esta razón es necesario buscar e implementar modelos que no tengan estos requerimientos y que permitan establecer relaciones entre los datos de entrada y los de salida en una cuenca hidrográfica. Técnicas informáticas de inteligencia artificial permiten establecer relaciones entre los datos de entrada y los de salida en una cuenca hidrográfica. El proyecto busca evaluar diferentes modelos de Redes Neuronales Artificiales (RNA) con el fin de seleccionar uno e implementarlo, con esto se pretende obtener la posibilidad de manipular cada una de las conexiones del modelo de la red neuronal para buscar una convergencia rápida y la minimización del margen de error. Una vez que el modelo sea c...

In the dynamic global economy, the accuracy in forecasting the foreign currency exchange (Forex) rates or at least predicting the trend correctly is of crucial importance for any future investment. The use of computational intelligence based techniques for forecasting has ...

This study and research aimed is to classify and predict the credit card default customers payment by means of contemporary approach of artificial neural network (ANN) known as deep neural network. This paper explains the dataset which signifies Taiwan credit card defaults in 2005 and their previous payment histories taken from popular machine learning dataset resource known as UCI. The paper enlightens each and every concept and step require to build, train, validate and test a deep neural network model for classification task that has never been discussed before. Moreover, we tried to elaborate the relevant and important concepts associated with deep neural network model that must be kept in mind during model building. This paper mainly tries to classify the default payment customer with more than 82% accuracy. For this purpose, various deep neural network techniques with different libraries are used to attain maximum accuracy and we have tried to build a best possible model which can be used for future prediction. This study proves deep neural network is the only one that can accurately estimate the real probability of default. So, by using this network model, which is more complex, sophisticated and most widely used than a simple neural network and logistic regression model, the classification simulation shall have a better performance and accuracy.

An approach using a convolutional neural network (CNN) is proposed for real-time gender classification based on facial images. The proposed CNN architecture exhibits a much reduced design complexity when compared with other CNN solutions applied in pattern recognition. The number of processing layers in the CNN is reduced to only four by fusing the convolutional and subsampling layers. Unlike in conventional CNNs, we replace the convolution operation with cross-correlation, hence reducing the computational load. The network is trained using a second-order backpropagation learning algorithm with annealed global learning rates. Performance evaluation of the proposed CNN solution is conducted on two publicly available face databases of SUMS and AT&T. We achieve classification accuracies of 98.75% and 99.38% on the SUMS and AT&T databases, respectively. The neural network is able to process and classify a 32 × 32 pixel face image in less than 0.27 ms, which corresponds to a very high throughput of over 3700 images per second. Training converges within less than 20 epochs. These results correspond to a superior classification performance, verifying that the proposed CNN is an effective real-time solution for gender recognition.