The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper we propose a hybridized approach for finding high quality artificial neural network (ANN) for calculating hourly estimates of solar irradiance. These properties are essential for performance analysis of solar based energy generation. To be more precise the hourly global horizontal irradiance (GHI), direct normal irradiance (DNI) and diffuse horizontal irradiance (DHI) are estimated based...
This paper proposes an intelligent scheme based on Bayesian artificial neural network (BNN) for fault detection and isolation (FDI) in variable speed wind turbine. The proposed scheme is based on data-driven fault detection method. The main idea is the use of a certain number of BNN classifiers to deals with different types of faults affecting the wind turbine. Different parts of the process were...
Pixel classification in land scape images has been found to be challenging. The problem becomes more challenging in forest images due to the similar spectral features of pixels situated close to each other. Geographically weighted variables have been employed to classify the two different species namely Cryptomeria japonica (Japanese Cedar or Sugi) and Chamaecyparisobtusa (Japanese Cypress or Hinoki)...
The main aim of this paper is to implement a Artificial Neural Network to recognize and predict Handwritten digits from 0 to 9. A dataset comprises 5000 samples of number digits with different strokes are taken for our work. The dataset was trained using gradient descent Back-propagation algorithm and further tested using the Feed-forward algorithm. The system performance is observed by varying regularization...
This paper proposed a method based on Zernike moments to classify the various stages of Alzheimer's Disease(AD) from structural MRIs. The proposed method is benefited from all three orthogonal directions of MRIs i.e. Axial, Sagittal and Coronal images. Three back-propagation algorithms had been used to train the neural network with seven neurons in hidden layer to reach the best accuracy. We experimented...
Artificial neural network (ANN) has been widely applied in flood forecasting and got good results. However, it can still not go beyond one or two hidden layers for the problematic non-convex optimization. This paper proposes a deep learning approach by integrating stacked autoencoders (SAE) and back propagation neural networks (BPNN) for the prediction of stream flow, which simultaneously takes advantages...
The performance of smoothness-enforced Bayesian PET image reconstruction is strongly affected by the weight on regularization. Compromises need to be made between variance and spatial resolution. In this work, we propose to use an artificial neural network (ANN) to fuse the image versions reconstructed from a maximum a posteriori (MAP) algorithm with different regularizing weights for quantitative...
Web service combination is an important task performed in different phases of the service-oriented architecture lifecycle. Measuring service quality based on the non-functional characteristics is an exceedingly difficult task. Therefore, this paper presents a Multilayer Perceptron Artificial Neural Network (MLPANN) to provide a method for measuring quality of service in a service-oriented architecture...
In high-performance military aircraft, high centrifugal forces result in sharp turns and such emergency maneuvers significantly affect the pilot's physiological condition and performance. The human centrifuge system is a dynamic flight simulator used to generate artificial G forces realistically. One of the objectives of this study is to underline the significance of system safety of human centrifuge...
Thailand has limited resources to generate the electric power. In developing countries, the electrical demand is growing continuously. Power system planning is very important issues. There are three major components of the electrical power system namely, generation, a high voltage transmission line, and a distribution system. The hourly power variables, at Bamnet Narong substation in northeastern...
Controlled charging and discharge of electric vehicles (EVs) in distributed power systems can reduce the peak demand on the grid. This paper presents an energy management strategy (EMS) using an artificial neural network to shave the domestic peak grid load by the coordinated response of distributed energy resource (DER) units including photovoltaic (PV) systems, V2G (vehicle to grid)-capable EVs,...
The paper considers the issue of effective formation of a representative sample to train a neural network of a multilayer perceptron (MLP). As it is known, the key problem of MLP training is the factor space division into the test, validation and training sets. To solve this problem, an approach based on the use of clustering and a Lipschitz constant estimate is put forward. Kohonen's self-organizing...
Deep Convolutional Neural Networks - also known as DCNN - are powerful models for different visual pattern classification problems. Many works in this field use image augmentation at the training phase to achieve better accuracy. This paper presents blocky artifact as an augmentation technique to increase the accuracy of DCNN for handwritten digit recognition, both English and Bangla digits, i.e.,...
In the article developed the structure of the automated system for house devices control using machine learning algorithms. The main element of the proposed structure is responsible for setting up automated devices parameters, according to the data from sensors in the home, based on decision making using artificial neural network.
This work describes the calculation parameters of the drying agent, which includes the speed of air circulation, its temperature and humidity. The result of the calculation is the establishment of radial-basis artificial neural network, which allows to determine any parameter of drying agent at any point, represented by the coordinates X, Y, Z, and located within the drying chambers. Also in this...
Affected by the special geographical environment and climate factors, some cities waterlogging occurred frequently, causing serious economic losses and social impacts. Because of certain topographic factors, once the heavy rain coming suddenly in the city, many of the major streets will be flooded by the water, how to better prevent the occurrence of waterlogging, or predict the depth of waterlogging...
This paper is an attempt to develop a new technology, which is an advancement of the previously published paper [1] for fault diagnosis of multilevel inverter adopting the machine learning and optimization techniques. The advanced machine-learning algorithm called the Optimized Radial Basis Neural Network (ORBNN) method is developed in which the Neural Network uses Radial Basis function as the activation...
We modeled in this paper the variation of wind speed as a renewable energy in Mediterranean Sea of Libya (North of Africa) using an artificial neural network (ANN). We developed multi-layer, feed-forward, back-propagation artificial neural networks for prediction monthly mean wind speed. The monthly mean wind speed data of 25 cities in Libya were monitored during the period of six years from 2010...
In this paper artificial neural network control technique is used for a nonlinear system. The nonlinear system for supervised control is considered in this paper is Inverted Pendulum which is well known problem for research due to it's highly nonlinear and unstable characteristics. Online ADALINE controller has been used here for control of system. ADALINE controller has the ability to adapt changes...
System identification is the process of developing a mathematical model of a system using input and output knowledge of system. Identification of nonlinear system is well known problem due to its unpredictability and complexity. The nonlinear system for identification is Inverted Pendulum in this work which is well known benchmark system in control system theory due to it's highly nonlinear and unstable...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.